From: Junyang Shao Date: Thu, 31 Jul 2025 23:45:09 +0000 (+0000) Subject: [dev.simd] cmd/compile, simd: change Shift*AndFillUpperFrom to Shift*Concat X-Git-Tag: go1.26rc1~147^2~153 X-Git-Url: http://www.git.cypherpunks.su/?a=commitdiff_plain;h=2c25f3e846;p=gostls13.git [dev.simd] cmd/compile, simd: change Shift*AndFillUpperFrom to Shift*Concat This CL is generated by CL 692216. Change-Id: Ib7530142bcce2a23f90d48866271994c57561955 Reviewed-on: https://go-review.googlesource.com/c/go/+/692215 Reviewed-by: David Chase LUCI-TryBot-Result: Go LUCI --- diff --git a/src/cmd/compile/internal/ssa/_gen/simdAMD64.rules b/src/cmd/compile/internal/ssa/_gen/simdAMD64.rules index e5e3fb0d50..38b602f35b 100644 --- a/src/cmd/compile/internal/ssa/_gen/simdAMD64.rules +++ b/src/cmd/compile/internal/ssa/_gen/simdAMD64.rules @@ -1401,42 +1401,42 @@ (ShiftAllLeftUint64x2 ...) => (VPSLLQ128 ...) (ShiftAllLeftUint64x4 ...) => (VPSLLQ256 ...) (ShiftAllLeftUint64x8 ...) => (VPSLLQ512 ...) -(ShiftAllLeftAndFillUpperFromInt16x8 ...) => (VPSHLDW128 ...) -(ShiftAllLeftAndFillUpperFromInt16x16 ...) => (VPSHLDW256 ...) -(ShiftAllLeftAndFillUpperFromInt16x32 ...) => (VPSHLDW512 ...) -(ShiftAllLeftAndFillUpperFromInt32x4 ...) => (VPSHLDD128 ...) -(ShiftAllLeftAndFillUpperFromInt32x8 ...) => (VPSHLDD256 ...) -(ShiftAllLeftAndFillUpperFromInt32x16 ...) => (VPSHLDD512 ...) -(ShiftAllLeftAndFillUpperFromInt64x2 ...) => (VPSHLDQ128 ...) -(ShiftAllLeftAndFillUpperFromInt64x4 ...) => (VPSHLDQ256 ...) -(ShiftAllLeftAndFillUpperFromInt64x8 ...) => (VPSHLDQ512 ...) -(ShiftAllLeftAndFillUpperFromUint16x8 ...) => (VPSHLDW128 ...) -(ShiftAllLeftAndFillUpperFromUint16x16 ...) => (VPSHLDW256 ...) -(ShiftAllLeftAndFillUpperFromUint16x32 ...) => (VPSHLDW512 ...) -(ShiftAllLeftAndFillUpperFromUint32x4 ...) => (VPSHLDD128 ...) -(ShiftAllLeftAndFillUpperFromUint32x8 ...) => (VPSHLDD256 ...) -(ShiftAllLeftAndFillUpperFromUint32x16 ...) => (VPSHLDD512 ...) -(ShiftAllLeftAndFillUpperFromUint64x2 ...) => (VPSHLDQ128 ...) -(ShiftAllLeftAndFillUpperFromUint64x4 ...) => (VPSHLDQ256 ...) -(ShiftAllLeftAndFillUpperFromUint64x8 ...) => (VPSHLDQ512 ...) -(ShiftAllLeftAndFillUpperFromMaskedInt16x8 [a] x y mask) => (VPSHLDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedInt16x16 [a] x y mask) => (VPSHLDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedInt16x32 [a] x y mask) => (VPSHLDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedInt32x4 [a] x y mask) => (VPSHLDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedInt32x8 [a] x y mask) => (VPSHLDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedInt32x16 [a] x y mask) => (VPSHLDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedInt64x2 [a] x y mask) => (VPSHLDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedInt64x4 [a] x y mask) => (VPSHLDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedInt64x8 [a] x y mask) => (VPSHLDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedUint16x8 [a] x y mask) => (VPSHLDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedUint16x16 [a] x y mask) => (VPSHLDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedUint16x32 [a] x y mask) => (VPSHLDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedUint32x4 [a] x y mask) => (VPSHLDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedUint32x8 [a] x y mask) => (VPSHLDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedUint32x16 [a] x y mask) => (VPSHLDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedUint64x2 [a] x y mask) => (VPSHLDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedUint64x4 [a] x y mask) => (VPSHLDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) -(ShiftAllLeftAndFillUpperFromMaskedUint64x8 [a] x y mask) => (VPSHLDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) +(ShiftAllLeftConcatInt16x8 ...) => (VPSHLDW128 ...) +(ShiftAllLeftConcatInt16x16 ...) => (VPSHLDW256 ...) +(ShiftAllLeftConcatInt16x32 ...) => (VPSHLDW512 ...) +(ShiftAllLeftConcatInt32x4 ...) => (VPSHLDD128 ...) +(ShiftAllLeftConcatInt32x8 ...) => (VPSHLDD256 ...) +(ShiftAllLeftConcatInt32x16 ...) => (VPSHLDD512 ...) +(ShiftAllLeftConcatInt64x2 ...) => (VPSHLDQ128 ...) +(ShiftAllLeftConcatInt64x4 ...) => (VPSHLDQ256 ...) +(ShiftAllLeftConcatInt64x8 ...) => (VPSHLDQ512 ...) +(ShiftAllLeftConcatUint16x8 ...) => (VPSHLDW128 ...) +(ShiftAllLeftConcatUint16x16 ...) => (VPSHLDW256 ...) +(ShiftAllLeftConcatUint16x32 ...) => (VPSHLDW512 ...) +(ShiftAllLeftConcatUint32x4 ...) => (VPSHLDD128 ...) +(ShiftAllLeftConcatUint32x8 ...) => (VPSHLDD256 ...) +(ShiftAllLeftConcatUint32x16 ...) => (VPSHLDD512 ...) +(ShiftAllLeftConcatUint64x2 ...) => (VPSHLDQ128 ...) +(ShiftAllLeftConcatUint64x4 ...) => (VPSHLDQ256 ...) +(ShiftAllLeftConcatUint64x8 ...) => (VPSHLDQ512 ...) +(ShiftAllLeftConcatMaskedInt16x8 [a] x y mask) => (VPSHLDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) +(ShiftAllLeftConcatMaskedInt16x16 [a] x y mask) => (VPSHLDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) +(ShiftAllLeftConcatMaskedInt16x32 [a] x y mask) => (VPSHLDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) +(ShiftAllLeftConcatMaskedInt32x4 [a] x y mask) => (VPSHLDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) +(ShiftAllLeftConcatMaskedInt32x8 [a] x y mask) => (VPSHLDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) +(ShiftAllLeftConcatMaskedInt32x16 [a] x y mask) => (VPSHLDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) +(ShiftAllLeftConcatMaskedInt64x2 [a] x y mask) => (VPSHLDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) +(ShiftAllLeftConcatMaskedInt64x4 [a] x y mask) => (VPSHLDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) +(ShiftAllLeftConcatMaskedInt64x8 [a] x y mask) => (VPSHLDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) +(ShiftAllLeftConcatMaskedUint16x8 [a] x y mask) => (VPSHLDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) +(ShiftAllLeftConcatMaskedUint16x16 [a] x y mask) => (VPSHLDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) +(ShiftAllLeftConcatMaskedUint16x32 [a] x y mask) => (VPSHLDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) +(ShiftAllLeftConcatMaskedUint32x4 [a] x y mask) => (VPSHLDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) +(ShiftAllLeftConcatMaskedUint32x8 [a] x y mask) => (VPSHLDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) +(ShiftAllLeftConcatMaskedUint32x16 [a] x y mask) => (VPSHLDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) +(ShiftAllLeftConcatMaskedUint64x2 [a] x y mask) => (VPSHLDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) +(ShiftAllLeftConcatMaskedUint64x4 [a] x y mask) => (VPSHLDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) +(ShiftAllLeftConcatMaskedUint64x8 [a] x y mask) => (VPSHLDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) (ShiftAllLeftMaskedInt16x8 x y mask) => (VPSLLWMasked128 x y (VPMOVVec16x8ToM mask)) (ShiftAllLeftMaskedInt16x16 x y mask) => (VPSLLWMasked256 x y (VPMOVVec16x16ToM mask)) (ShiftAllLeftMaskedInt16x32 x y mask) => (VPSLLWMasked512 x y (VPMOVVec16x32ToM mask)) @@ -1473,42 +1473,42 @@ (ShiftAllRightUint64x2 ...) => (VPSRLQ128 ...) (ShiftAllRightUint64x4 ...) => (VPSRLQ256 ...) (ShiftAllRightUint64x8 ...) => (VPSRLQ512 ...) -(ShiftAllRightAndFillUpperFromInt16x8 ...) => (VPSHRDW128 ...) -(ShiftAllRightAndFillUpperFromInt16x16 ...) => (VPSHRDW256 ...) -(ShiftAllRightAndFillUpperFromInt16x32 ...) => (VPSHRDW512 ...) -(ShiftAllRightAndFillUpperFromInt32x4 ...) => (VPSHRDD128 ...) -(ShiftAllRightAndFillUpperFromInt32x8 ...) => (VPSHRDD256 ...) -(ShiftAllRightAndFillUpperFromInt32x16 ...) => (VPSHRDD512 ...) -(ShiftAllRightAndFillUpperFromInt64x2 ...) => (VPSHRDQ128 ...) -(ShiftAllRightAndFillUpperFromInt64x4 ...) => (VPSHRDQ256 ...) -(ShiftAllRightAndFillUpperFromInt64x8 ...) => (VPSHRDQ512 ...) -(ShiftAllRightAndFillUpperFromUint16x8 ...) => (VPSHRDW128 ...) -(ShiftAllRightAndFillUpperFromUint16x16 ...) => (VPSHRDW256 ...) -(ShiftAllRightAndFillUpperFromUint16x32 ...) => (VPSHRDW512 ...) -(ShiftAllRightAndFillUpperFromUint32x4 ...) => (VPSHRDD128 ...) -(ShiftAllRightAndFillUpperFromUint32x8 ...) => (VPSHRDD256 ...) -(ShiftAllRightAndFillUpperFromUint32x16 ...) => (VPSHRDD512 ...) -(ShiftAllRightAndFillUpperFromUint64x2 ...) => (VPSHRDQ128 ...) -(ShiftAllRightAndFillUpperFromUint64x4 ...) => (VPSHRDQ256 ...) -(ShiftAllRightAndFillUpperFromUint64x8 ...) => (VPSHRDQ512 ...) -(ShiftAllRightAndFillUpperFromMaskedInt16x8 [a] x y mask) => (VPSHRDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedInt16x16 [a] x y mask) => (VPSHRDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedInt16x32 [a] x y mask) => (VPSHRDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedInt32x4 [a] x y mask) => (VPSHRDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedInt32x8 [a] x y mask) => (VPSHRDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedInt32x16 [a] x y mask) => (VPSHRDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedInt64x2 [a] x y mask) => (VPSHRDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedInt64x4 [a] x y mask) => (VPSHRDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedInt64x8 [a] x y mask) => (VPSHRDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedUint16x8 [a] x y mask) => (VPSHRDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedUint16x16 [a] x y mask) => (VPSHRDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedUint16x32 [a] x y mask) => (VPSHRDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedUint32x4 [a] x y mask) => (VPSHRDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedUint32x8 [a] x y mask) => (VPSHRDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedUint32x16 [a] x y mask) => (VPSHRDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedUint64x2 [a] x y mask) => (VPSHRDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedUint64x4 [a] x y mask) => (VPSHRDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) -(ShiftAllRightAndFillUpperFromMaskedUint64x8 [a] x y mask) => (VPSHRDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) +(ShiftAllRightConcatInt16x8 ...) => (VPSHRDW128 ...) +(ShiftAllRightConcatInt16x16 ...) => (VPSHRDW256 ...) +(ShiftAllRightConcatInt16x32 ...) => (VPSHRDW512 ...) +(ShiftAllRightConcatInt32x4 ...) => (VPSHRDD128 ...) +(ShiftAllRightConcatInt32x8 ...) => (VPSHRDD256 ...) +(ShiftAllRightConcatInt32x16 ...) => (VPSHRDD512 ...) +(ShiftAllRightConcatInt64x2 ...) => (VPSHRDQ128 ...) +(ShiftAllRightConcatInt64x4 ...) => (VPSHRDQ256 ...) +(ShiftAllRightConcatInt64x8 ...) => (VPSHRDQ512 ...) +(ShiftAllRightConcatUint16x8 ...) => (VPSHRDW128 ...) +(ShiftAllRightConcatUint16x16 ...) => (VPSHRDW256 ...) +(ShiftAllRightConcatUint16x32 ...) => (VPSHRDW512 ...) +(ShiftAllRightConcatUint32x4 ...) => (VPSHRDD128 ...) +(ShiftAllRightConcatUint32x8 ...) => (VPSHRDD256 ...) +(ShiftAllRightConcatUint32x16 ...) => (VPSHRDD512 ...) +(ShiftAllRightConcatUint64x2 ...) => (VPSHRDQ128 ...) +(ShiftAllRightConcatUint64x4 ...) => (VPSHRDQ256 ...) +(ShiftAllRightConcatUint64x8 ...) => (VPSHRDQ512 ...) +(ShiftAllRightConcatMaskedInt16x8 [a] x y mask) => (VPSHRDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) +(ShiftAllRightConcatMaskedInt16x16 [a] x y mask) => (VPSHRDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) +(ShiftAllRightConcatMaskedInt16x32 [a] x y mask) => (VPSHRDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) +(ShiftAllRightConcatMaskedInt32x4 [a] x y mask) => (VPSHRDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) +(ShiftAllRightConcatMaskedInt32x8 [a] x y mask) => (VPSHRDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) +(ShiftAllRightConcatMaskedInt32x16 [a] x y mask) => (VPSHRDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) +(ShiftAllRightConcatMaskedInt64x2 [a] x y mask) => (VPSHRDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) +(ShiftAllRightConcatMaskedInt64x4 [a] x y mask) => (VPSHRDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) +(ShiftAllRightConcatMaskedInt64x8 [a] x y mask) => (VPSHRDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) +(ShiftAllRightConcatMaskedUint16x8 [a] x y mask) => (VPSHRDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) +(ShiftAllRightConcatMaskedUint16x16 [a] x y mask) => (VPSHRDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) +(ShiftAllRightConcatMaskedUint16x32 [a] x y mask) => (VPSHRDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) +(ShiftAllRightConcatMaskedUint32x4 [a] x y mask) => (VPSHRDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) +(ShiftAllRightConcatMaskedUint32x8 [a] x y mask) => (VPSHRDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) +(ShiftAllRightConcatMaskedUint32x16 [a] x y mask) => (VPSHRDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) +(ShiftAllRightConcatMaskedUint64x2 [a] x y mask) => (VPSHRDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) +(ShiftAllRightConcatMaskedUint64x4 [a] x y mask) => (VPSHRDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) +(ShiftAllRightConcatMaskedUint64x8 [a] x y mask) => (VPSHRDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) (ShiftAllRightMaskedInt16x8 x y mask) => (VPSRAWMasked128 x y (VPMOVVec16x8ToM mask)) (ShiftAllRightMaskedInt16x16 x y mask) => (VPSRAWMasked256 x y (VPMOVVec16x16ToM mask)) (ShiftAllRightMaskedInt16x32 x y mask) => (VPSRAWMasked512 x y (VPMOVVec16x32ToM mask)) @@ -1545,42 +1545,42 @@ (ShiftLeftUint64x2 ...) => (VPSLLVQ128 ...) (ShiftLeftUint64x4 ...) => (VPSLLVQ256 ...) (ShiftLeftUint64x8 ...) => (VPSLLVQ512 ...) -(ShiftLeftAndFillUpperFromInt16x8 ...) => (VPSHLDVW128 ...) -(ShiftLeftAndFillUpperFromInt16x16 ...) => (VPSHLDVW256 ...) -(ShiftLeftAndFillUpperFromInt16x32 ...) => (VPSHLDVW512 ...) -(ShiftLeftAndFillUpperFromInt32x4 ...) => (VPSHLDVD128 ...) -(ShiftLeftAndFillUpperFromInt32x8 ...) => (VPSHLDVD256 ...) -(ShiftLeftAndFillUpperFromInt32x16 ...) => (VPSHLDVD512 ...) -(ShiftLeftAndFillUpperFromInt64x2 ...) => (VPSHLDVQ128 ...) -(ShiftLeftAndFillUpperFromInt64x4 ...) => (VPSHLDVQ256 ...) -(ShiftLeftAndFillUpperFromInt64x8 ...) => (VPSHLDVQ512 ...) -(ShiftLeftAndFillUpperFromUint16x8 ...) => (VPSHLDVW128 ...) -(ShiftLeftAndFillUpperFromUint16x16 ...) => (VPSHLDVW256 ...) -(ShiftLeftAndFillUpperFromUint16x32 ...) => (VPSHLDVW512 ...) -(ShiftLeftAndFillUpperFromUint32x4 ...) => (VPSHLDVD128 ...) -(ShiftLeftAndFillUpperFromUint32x8 ...) => (VPSHLDVD256 ...) -(ShiftLeftAndFillUpperFromUint32x16 ...) => (VPSHLDVD512 ...) -(ShiftLeftAndFillUpperFromUint64x2 ...) => (VPSHLDVQ128 ...) -(ShiftLeftAndFillUpperFromUint64x4 ...) => (VPSHLDVQ256 ...) -(ShiftLeftAndFillUpperFromUint64x8 ...) => (VPSHLDVQ512 ...) -(ShiftLeftAndFillUpperFromMaskedInt16x8 x y z mask) => (VPSHLDVWMasked128 x y z (VPMOVVec16x8ToM mask)) -(ShiftLeftAndFillUpperFromMaskedInt16x16 x y z mask) => (VPSHLDVWMasked256 x y z (VPMOVVec16x16ToM mask)) -(ShiftLeftAndFillUpperFromMaskedInt16x32 x y z mask) => (VPSHLDVWMasked512 x y z (VPMOVVec16x32ToM mask)) -(ShiftLeftAndFillUpperFromMaskedInt32x4 x y z mask) => (VPSHLDVDMasked128 x y z (VPMOVVec32x4ToM mask)) -(ShiftLeftAndFillUpperFromMaskedInt32x8 x y z mask) => (VPSHLDVDMasked256 x y z (VPMOVVec32x8ToM mask)) -(ShiftLeftAndFillUpperFromMaskedInt32x16 x y z mask) => (VPSHLDVDMasked512 x y z (VPMOVVec32x16ToM mask)) -(ShiftLeftAndFillUpperFromMaskedInt64x2 x y z mask) => (VPSHLDVQMasked128 x y z (VPMOVVec64x2ToM mask)) -(ShiftLeftAndFillUpperFromMaskedInt64x4 x y z mask) => (VPSHLDVQMasked256 x y z (VPMOVVec64x4ToM mask)) -(ShiftLeftAndFillUpperFromMaskedInt64x8 x y z mask) => (VPSHLDVQMasked512 x y z (VPMOVVec64x8ToM mask)) -(ShiftLeftAndFillUpperFromMaskedUint16x8 x y z mask) => (VPSHLDVWMasked128 x y z (VPMOVVec16x8ToM mask)) -(ShiftLeftAndFillUpperFromMaskedUint16x16 x y z mask) => (VPSHLDVWMasked256 x y z (VPMOVVec16x16ToM mask)) -(ShiftLeftAndFillUpperFromMaskedUint16x32 x y z mask) => (VPSHLDVWMasked512 x y z (VPMOVVec16x32ToM mask)) -(ShiftLeftAndFillUpperFromMaskedUint32x4 x y z mask) => (VPSHLDVDMasked128 x y z (VPMOVVec32x4ToM mask)) -(ShiftLeftAndFillUpperFromMaskedUint32x8 x y z mask) => (VPSHLDVDMasked256 x y z (VPMOVVec32x8ToM mask)) -(ShiftLeftAndFillUpperFromMaskedUint32x16 x y z mask) => (VPSHLDVDMasked512 x y z (VPMOVVec32x16ToM mask)) -(ShiftLeftAndFillUpperFromMaskedUint64x2 x y z mask) => (VPSHLDVQMasked128 x y z (VPMOVVec64x2ToM mask)) -(ShiftLeftAndFillUpperFromMaskedUint64x4 x y z mask) => (VPSHLDVQMasked256 x y z (VPMOVVec64x4ToM mask)) -(ShiftLeftAndFillUpperFromMaskedUint64x8 x y z mask) => (VPSHLDVQMasked512 x y z (VPMOVVec64x8ToM mask)) +(ShiftLeftConcatInt16x8 ...) => (VPSHLDVW128 ...) +(ShiftLeftConcatInt16x16 ...) => (VPSHLDVW256 ...) +(ShiftLeftConcatInt16x32 ...) => (VPSHLDVW512 ...) +(ShiftLeftConcatInt32x4 ...) => (VPSHLDVD128 ...) +(ShiftLeftConcatInt32x8 ...) => (VPSHLDVD256 ...) +(ShiftLeftConcatInt32x16 ...) => (VPSHLDVD512 ...) +(ShiftLeftConcatInt64x2 ...) => (VPSHLDVQ128 ...) +(ShiftLeftConcatInt64x4 ...) => (VPSHLDVQ256 ...) +(ShiftLeftConcatInt64x8 ...) => (VPSHLDVQ512 ...) +(ShiftLeftConcatUint16x8 ...) => (VPSHLDVW128 ...) +(ShiftLeftConcatUint16x16 ...) => (VPSHLDVW256 ...) +(ShiftLeftConcatUint16x32 ...) => (VPSHLDVW512 ...) +(ShiftLeftConcatUint32x4 ...) => (VPSHLDVD128 ...) +(ShiftLeftConcatUint32x8 ...) => (VPSHLDVD256 ...) +(ShiftLeftConcatUint32x16 ...) => (VPSHLDVD512 ...) +(ShiftLeftConcatUint64x2 ...) => (VPSHLDVQ128 ...) +(ShiftLeftConcatUint64x4 ...) => (VPSHLDVQ256 ...) +(ShiftLeftConcatUint64x8 ...) => (VPSHLDVQ512 ...) +(ShiftLeftConcatMaskedInt16x8 x y z mask) => (VPSHLDVWMasked128 x y z (VPMOVVec16x8ToM mask)) +(ShiftLeftConcatMaskedInt16x16 x y z mask) => (VPSHLDVWMasked256 x y z (VPMOVVec16x16ToM mask)) +(ShiftLeftConcatMaskedInt16x32 x y z mask) => (VPSHLDVWMasked512 x y z (VPMOVVec16x32ToM mask)) +(ShiftLeftConcatMaskedInt32x4 x y z mask) => (VPSHLDVDMasked128 x y z (VPMOVVec32x4ToM mask)) +(ShiftLeftConcatMaskedInt32x8 x y z mask) => (VPSHLDVDMasked256 x y z (VPMOVVec32x8ToM mask)) +(ShiftLeftConcatMaskedInt32x16 x y z mask) => (VPSHLDVDMasked512 x y z (VPMOVVec32x16ToM mask)) +(ShiftLeftConcatMaskedInt64x2 x y z mask) => (VPSHLDVQMasked128 x y z (VPMOVVec64x2ToM mask)) +(ShiftLeftConcatMaskedInt64x4 x y z mask) => (VPSHLDVQMasked256 x y z (VPMOVVec64x4ToM mask)) +(ShiftLeftConcatMaskedInt64x8 x y z mask) => (VPSHLDVQMasked512 x y z (VPMOVVec64x8ToM mask)) +(ShiftLeftConcatMaskedUint16x8 x y z mask) => (VPSHLDVWMasked128 x y z (VPMOVVec16x8ToM mask)) +(ShiftLeftConcatMaskedUint16x16 x y z mask) => (VPSHLDVWMasked256 x y z (VPMOVVec16x16ToM mask)) +(ShiftLeftConcatMaskedUint16x32 x y z mask) => (VPSHLDVWMasked512 x y z (VPMOVVec16x32ToM mask)) +(ShiftLeftConcatMaskedUint32x4 x y z mask) => (VPSHLDVDMasked128 x y z (VPMOVVec32x4ToM mask)) +(ShiftLeftConcatMaskedUint32x8 x y z mask) => (VPSHLDVDMasked256 x y z (VPMOVVec32x8ToM mask)) +(ShiftLeftConcatMaskedUint32x16 x y z mask) => (VPSHLDVDMasked512 x y z (VPMOVVec32x16ToM mask)) +(ShiftLeftConcatMaskedUint64x2 x y z mask) => (VPSHLDVQMasked128 x y z (VPMOVVec64x2ToM mask)) +(ShiftLeftConcatMaskedUint64x4 x y z mask) => (VPSHLDVQMasked256 x y z (VPMOVVec64x4ToM mask)) +(ShiftLeftConcatMaskedUint64x8 x y z mask) => (VPSHLDVQMasked512 x y z (VPMOVVec64x8ToM mask)) (ShiftLeftMaskedInt16x8 x y mask) => (VPSLLVWMasked128 x y (VPMOVVec16x8ToM mask)) (ShiftLeftMaskedInt16x16 x y mask) => (VPSLLVWMasked256 x y (VPMOVVec16x16ToM mask)) (ShiftLeftMaskedInt16x32 x y mask) => (VPSLLVWMasked512 x y (VPMOVVec16x32ToM mask)) @@ -1617,42 +1617,42 @@ (ShiftRightUint64x2 ...) => (VPSRLVQ128 ...) (ShiftRightUint64x4 ...) => (VPSRLVQ256 ...) (ShiftRightUint64x8 ...) => (VPSRLVQ512 ...) -(ShiftRightAndFillUpperFromInt16x8 ...) => (VPSHRDVW128 ...) -(ShiftRightAndFillUpperFromInt16x16 ...) => (VPSHRDVW256 ...) -(ShiftRightAndFillUpperFromInt16x32 ...) => (VPSHRDVW512 ...) -(ShiftRightAndFillUpperFromInt32x4 ...) => (VPSHRDVD128 ...) -(ShiftRightAndFillUpperFromInt32x8 ...) => (VPSHRDVD256 ...) -(ShiftRightAndFillUpperFromInt32x16 ...) => (VPSHRDVD512 ...) -(ShiftRightAndFillUpperFromInt64x2 ...) => (VPSHRDVQ128 ...) -(ShiftRightAndFillUpperFromInt64x4 ...) => (VPSHRDVQ256 ...) -(ShiftRightAndFillUpperFromInt64x8 ...) => (VPSHRDVQ512 ...) -(ShiftRightAndFillUpperFromUint16x8 ...) => (VPSHRDVW128 ...) -(ShiftRightAndFillUpperFromUint16x16 ...) => (VPSHRDVW256 ...) -(ShiftRightAndFillUpperFromUint16x32 ...) => (VPSHRDVW512 ...) -(ShiftRightAndFillUpperFromUint32x4 ...) => (VPSHRDVD128 ...) -(ShiftRightAndFillUpperFromUint32x8 ...) => (VPSHRDVD256 ...) -(ShiftRightAndFillUpperFromUint32x16 ...) => (VPSHRDVD512 ...) -(ShiftRightAndFillUpperFromUint64x2 ...) => (VPSHRDVQ128 ...) -(ShiftRightAndFillUpperFromUint64x4 ...) => (VPSHRDVQ256 ...) -(ShiftRightAndFillUpperFromUint64x8 ...) => (VPSHRDVQ512 ...) -(ShiftRightAndFillUpperFromMaskedInt16x8 x y z mask) => (VPSHRDVWMasked128 x y z (VPMOVVec16x8ToM mask)) -(ShiftRightAndFillUpperFromMaskedInt16x16 x y z mask) => (VPSHRDVWMasked256 x y z (VPMOVVec16x16ToM mask)) -(ShiftRightAndFillUpperFromMaskedInt16x32 x y z mask) => (VPSHRDVWMasked512 x y z (VPMOVVec16x32ToM mask)) -(ShiftRightAndFillUpperFromMaskedInt32x4 x y z mask) => (VPSHRDVDMasked128 x y z (VPMOVVec32x4ToM mask)) -(ShiftRightAndFillUpperFromMaskedInt32x8 x y z mask) => (VPSHRDVDMasked256 x y z (VPMOVVec32x8ToM mask)) -(ShiftRightAndFillUpperFromMaskedInt32x16 x y z mask) => (VPSHRDVDMasked512 x y z (VPMOVVec32x16ToM mask)) -(ShiftRightAndFillUpperFromMaskedInt64x2 x y z mask) => (VPSHRDVQMasked128 x y z (VPMOVVec64x2ToM mask)) -(ShiftRightAndFillUpperFromMaskedInt64x4 x y z mask) => (VPSHRDVQMasked256 x y z (VPMOVVec64x4ToM mask)) -(ShiftRightAndFillUpperFromMaskedInt64x8 x y z mask) => (VPSHRDVQMasked512 x y z (VPMOVVec64x8ToM mask)) -(ShiftRightAndFillUpperFromMaskedUint16x8 x y z mask) => (VPSHRDVWMasked128 x y z (VPMOVVec16x8ToM mask)) -(ShiftRightAndFillUpperFromMaskedUint16x16 x y z mask) => (VPSHRDVWMasked256 x y z (VPMOVVec16x16ToM mask)) -(ShiftRightAndFillUpperFromMaskedUint16x32 x y z mask) => (VPSHRDVWMasked512 x y z (VPMOVVec16x32ToM mask)) -(ShiftRightAndFillUpperFromMaskedUint32x4 x y z mask) => (VPSHRDVDMasked128 x y z (VPMOVVec32x4ToM mask)) -(ShiftRightAndFillUpperFromMaskedUint32x8 x y z mask) => (VPSHRDVDMasked256 x y z (VPMOVVec32x8ToM mask)) -(ShiftRightAndFillUpperFromMaskedUint32x16 x y z mask) => (VPSHRDVDMasked512 x y z (VPMOVVec32x16ToM mask)) -(ShiftRightAndFillUpperFromMaskedUint64x2 x y z mask) => (VPSHRDVQMasked128 x y z (VPMOVVec64x2ToM mask)) -(ShiftRightAndFillUpperFromMaskedUint64x4 x y z mask) => (VPSHRDVQMasked256 x y z (VPMOVVec64x4ToM mask)) -(ShiftRightAndFillUpperFromMaskedUint64x8 x y z mask) => (VPSHRDVQMasked512 x y z (VPMOVVec64x8ToM mask)) +(ShiftRightConcatInt16x8 ...) => (VPSHRDVW128 ...) +(ShiftRightConcatInt16x16 ...) => (VPSHRDVW256 ...) +(ShiftRightConcatInt16x32 ...) => (VPSHRDVW512 ...) +(ShiftRightConcatInt32x4 ...) => (VPSHRDVD128 ...) +(ShiftRightConcatInt32x8 ...) => (VPSHRDVD256 ...) +(ShiftRightConcatInt32x16 ...) => (VPSHRDVD512 ...) +(ShiftRightConcatInt64x2 ...) => (VPSHRDVQ128 ...) +(ShiftRightConcatInt64x4 ...) => (VPSHRDVQ256 ...) +(ShiftRightConcatInt64x8 ...) => (VPSHRDVQ512 ...) +(ShiftRightConcatUint16x8 ...) => (VPSHRDVW128 ...) +(ShiftRightConcatUint16x16 ...) => (VPSHRDVW256 ...) +(ShiftRightConcatUint16x32 ...) => (VPSHRDVW512 ...) +(ShiftRightConcatUint32x4 ...) => (VPSHRDVD128 ...) +(ShiftRightConcatUint32x8 ...) => (VPSHRDVD256 ...) +(ShiftRightConcatUint32x16 ...) => (VPSHRDVD512 ...) +(ShiftRightConcatUint64x2 ...) => (VPSHRDVQ128 ...) +(ShiftRightConcatUint64x4 ...) => (VPSHRDVQ256 ...) +(ShiftRightConcatUint64x8 ...) => (VPSHRDVQ512 ...) +(ShiftRightConcatMaskedInt16x8 x y z mask) => (VPSHRDVWMasked128 x y z (VPMOVVec16x8ToM mask)) +(ShiftRightConcatMaskedInt16x16 x y z mask) => (VPSHRDVWMasked256 x y z (VPMOVVec16x16ToM mask)) +(ShiftRightConcatMaskedInt16x32 x y z mask) => (VPSHRDVWMasked512 x y z (VPMOVVec16x32ToM mask)) +(ShiftRightConcatMaskedInt32x4 x y z mask) => (VPSHRDVDMasked128 x y z (VPMOVVec32x4ToM mask)) +(ShiftRightConcatMaskedInt32x8 x y z mask) => (VPSHRDVDMasked256 x y z (VPMOVVec32x8ToM mask)) +(ShiftRightConcatMaskedInt32x16 x y z mask) => (VPSHRDVDMasked512 x y z (VPMOVVec32x16ToM mask)) +(ShiftRightConcatMaskedInt64x2 x y z mask) => (VPSHRDVQMasked128 x y z (VPMOVVec64x2ToM mask)) +(ShiftRightConcatMaskedInt64x4 x y z mask) => (VPSHRDVQMasked256 x y z (VPMOVVec64x4ToM mask)) +(ShiftRightConcatMaskedInt64x8 x y z mask) => (VPSHRDVQMasked512 x y z (VPMOVVec64x8ToM mask)) +(ShiftRightConcatMaskedUint16x8 x y z mask) => (VPSHRDVWMasked128 x y z (VPMOVVec16x8ToM mask)) +(ShiftRightConcatMaskedUint16x16 x y z mask) => (VPSHRDVWMasked256 x y z (VPMOVVec16x16ToM mask)) +(ShiftRightConcatMaskedUint16x32 x y z mask) => (VPSHRDVWMasked512 x y z (VPMOVVec16x32ToM mask)) +(ShiftRightConcatMaskedUint32x4 x y z mask) => (VPSHRDVDMasked128 x y z (VPMOVVec32x4ToM mask)) +(ShiftRightConcatMaskedUint32x8 x y z mask) => (VPSHRDVDMasked256 x y z (VPMOVVec32x8ToM mask)) +(ShiftRightConcatMaskedUint32x16 x y z mask) => (VPSHRDVDMasked512 x y z (VPMOVVec32x16ToM mask)) +(ShiftRightConcatMaskedUint64x2 x y z mask) => (VPSHRDVQMasked128 x y z (VPMOVVec64x2ToM mask)) +(ShiftRightConcatMaskedUint64x4 x y z mask) => (VPSHRDVQMasked256 x y z (VPMOVVec64x4ToM mask)) +(ShiftRightConcatMaskedUint64x8 x y z mask) => (VPSHRDVQMasked512 x y z (VPMOVVec64x8ToM mask)) (ShiftRightMaskedInt16x8 x y mask) => (VPSRAVWMasked128 x y (VPMOVVec16x8ToM mask)) (ShiftRightMaskedInt16x16 x y mask) => (VPSRAVWMasked256 x y (VPMOVVec16x16ToM mask)) (ShiftRightMaskedInt16x32 x y mask) => (VPSRAVWMasked512 x y (VPMOVVec16x32ToM mask)) diff --git a/src/cmd/compile/internal/ssa/_gen/simdgenericOps.go b/src/cmd/compile/internal/ssa/_gen/simdgenericOps.go index f1c1246d24..d681620bc3 100644 --- a/src/cmd/compile/internal/ssa/_gen/simdgenericOps.go +++ b/src/cmd/compile/internal/ssa/_gen/simdgenericOps.go @@ -1278,42 +1278,42 @@ func simdGenericOps() []opData { {name: "ShiftAllRightUint64x2", argLength: 2, commutative: false}, {name: "ShiftAllRightUint64x4", argLength: 2, commutative: false}, {name: "ShiftAllRightUint64x8", argLength: 2, commutative: false}, - {name: "ShiftLeftAndFillUpperFromInt16x8", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromInt16x16", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromInt16x32", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromInt32x4", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromInt32x8", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromInt32x16", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromInt64x2", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromInt64x4", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromInt64x8", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedInt16x8", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedInt16x16", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedInt16x32", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedInt32x4", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedInt32x8", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedInt32x16", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedInt64x2", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedInt64x4", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedInt64x8", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedUint16x8", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedUint16x16", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedUint16x32", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedUint32x4", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedUint32x8", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedUint32x16", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedUint64x2", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedUint64x4", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromMaskedUint64x8", argLength: 4, commutative: false}, - {name: "ShiftLeftAndFillUpperFromUint16x8", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromUint16x16", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromUint16x32", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromUint32x4", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromUint32x8", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromUint32x16", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromUint64x2", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromUint64x4", argLength: 3, commutative: false}, - {name: "ShiftLeftAndFillUpperFromUint64x8", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatInt16x8", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatInt16x16", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatInt16x32", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatInt32x4", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatInt32x8", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatInt32x16", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatInt64x2", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatInt64x4", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatInt64x8", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatMaskedInt16x8", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedInt16x16", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedInt16x32", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedInt32x4", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedInt32x8", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedInt32x16", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedInt64x2", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedInt64x4", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedInt64x8", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedUint16x8", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedUint16x16", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedUint16x32", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedUint32x4", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedUint32x8", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedUint32x16", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedUint64x2", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedUint64x4", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatMaskedUint64x8", argLength: 4, commutative: false}, + {name: "ShiftLeftConcatUint16x8", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatUint16x16", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatUint16x32", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatUint32x4", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatUint32x8", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatUint32x16", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatUint64x2", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatUint64x4", argLength: 3, commutative: false}, + {name: "ShiftLeftConcatUint64x8", argLength: 3, commutative: false}, {name: "ShiftLeftInt16x8", argLength: 2, commutative: false}, {name: "ShiftLeftInt16x16", argLength: 2, commutative: false}, {name: "ShiftLeftInt16x32", argLength: 2, commutative: false}, @@ -1350,42 +1350,42 @@ func simdGenericOps() []opData { {name: "ShiftLeftUint64x2", argLength: 2, commutative: false}, {name: "ShiftLeftUint64x4", argLength: 2, commutative: false}, {name: "ShiftLeftUint64x8", argLength: 2, commutative: false}, - {name: "ShiftRightAndFillUpperFromInt16x8", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromInt16x16", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromInt16x32", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromInt32x4", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromInt32x8", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromInt32x16", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromInt64x2", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromInt64x4", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromInt64x8", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedInt16x8", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedInt16x16", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedInt16x32", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedInt32x4", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedInt32x8", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedInt32x16", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedInt64x2", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedInt64x4", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedInt64x8", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedUint16x8", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedUint16x16", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedUint16x32", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedUint32x4", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedUint32x8", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedUint32x16", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedUint64x2", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedUint64x4", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromMaskedUint64x8", argLength: 4, commutative: false}, - {name: "ShiftRightAndFillUpperFromUint16x8", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromUint16x16", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromUint16x32", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromUint32x4", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromUint32x8", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromUint32x16", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromUint64x2", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromUint64x4", argLength: 3, commutative: false}, - {name: "ShiftRightAndFillUpperFromUint64x8", argLength: 3, commutative: false}, + {name: "ShiftRightConcatInt16x8", argLength: 3, commutative: false}, + {name: "ShiftRightConcatInt16x16", argLength: 3, commutative: false}, + {name: "ShiftRightConcatInt16x32", argLength: 3, commutative: false}, + {name: "ShiftRightConcatInt32x4", argLength: 3, commutative: false}, + {name: "ShiftRightConcatInt32x8", argLength: 3, commutative: false}, + {name: "ShiftRightConcatInt32x16", argLength: 3, commutative: false}, + {name: "ShiftRightConcatInt64x2", argLength: 3, commutative: false}, + {name: "ShiftRightConcatInt64x4", argLength: 3, commutative: false}, + {name: "ShiftRightConcatInt64x8", argLength: 3, commutative: false}, + {name: "ShiftRightConcatMaskedInt16x8", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedInt16x16", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedInt16x32", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedInt32x4", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedInt32x8", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedInt32x16", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedInt64x2", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedInt64x4", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedInt64x8", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedUint16x8", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedUint16x16", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedUint16x32", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedUint32x4", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedUint32x8", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedUint32x16", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedUint64x2", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedUint64x4", argLength: 4, commutative: false}, + {name: "ShiftRightConcatMaskedUint64x8", argLength: 4, commutative: false}, + {name: "ShiftRightConcatUint16x8", argLength: 3, commutative: false}, + {name: "ShiftRightConcatUint16x16", argLength: 3, commutative: false}, + {name: "ShiftRightConcatUint16x32", argLength: 3, commutative: false}, + {name: "ShiftRightConcatUint32x4", argLength: 3, commutative: false}, + {name: "ShiftRightConcatUint32x8", argLength: 3, commutative: false}, + {name: "ShiftRightConcatUint32x16", argLength: 3, commutative: false}, + {name: "ShiftRightConcatUint64x2", argLength: 3, commutative: false}, + {name: "ShiftRightConcatUint64x4", argLength: 3, commutative: false}, + {name: "ShiftRightConcatUint64x8", argLength: 3, commutative: false}, {name: "ShiftRightInt16x8", argLength: 2, commutative: false}, {name: "ShiftRightInt16x16", argLength: 2, commutative: false}, {name: "ShiftRightInt16x32", argLength: 2, commutative: false}, @@ -1722,78 +1722,78 @@ func simdGenericOps() []opData { {name: "SetElemUint16x8", argLength: 2, commutative: false, aux: "Int8"}, {name: "SetElemUint32x4", argLength: 2, commutative: false, aux: "Int8"}, {name: "SetElemUint64x2", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromInt16x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromInt16x16", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromInt16x32", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromInt32x4", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromInt32x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromInt32x16", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromInt64x2", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromInt64x4", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromInt64x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedInt16x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedInt16x16", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedInt16x32", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedInt32x4", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedInt32x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedInt32x16", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedInt64x2", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedInt64x4", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedInt64x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedUint16x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedUint16x16", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedUint16x32", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedUint32x4", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedUint32x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedUint32x16", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedUint64x2", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedUint64x4", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromMaskedUint64x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromUint16x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromUint16x16", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromUint16x32", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromUint32x4", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromUint32x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromUint32x16", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromUint64x2", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromUint64x4", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllLeftAndFillUpperFromUint64x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromInt16x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromInt16x16", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromInt16x32", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromInt32x4", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromInt32x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromInt32x16", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromInt64x2", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromInt64x4", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromInt64x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedInt16x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedInt16x16", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedInt16x32", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedInt32x4", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedInt32x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedInt32x16", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedInt64x2", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedInt64x4", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedInt64x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedUint16x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedUint16x16", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedUint16x32", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedUint32x4", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedUint32x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedUint32x16", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedUint64x2", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedUint64x4", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromMaskedUint64x8", argLength: 3, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromUint16x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromUint16x16", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromUint16x32", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromUint32x4", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromUint32x8", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromUint32x16", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromUint64x2", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromUint64x4", argLength: 2, commutative: false, aux: "Int8"}, - {name: "ShiftAllRightAndFillUpperFromUint64x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatInt16x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatInt16x16", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatInt16x32", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatInt32x4", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatInt32x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatInt32x16", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatInt64x2", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatInt64x4", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatInt64x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedInt16x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedInt16x16", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedInt16x32", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedInt32x4", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedInt32x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedInt32x16", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedInt64x2", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedInt64x4", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedInt64x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedUint16x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedUint16x16", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedUint16x32", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedUint32x4", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedUint32x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedUint32x16", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedUint64x2", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedUint64x4", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatMaskedUint64x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatUint16x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatUint16x16", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatUint16x32", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatUint32x4", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatUint32x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatUint32x16", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatUint64x2", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatUint64x4", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllLeftConcatUint64x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatInt16x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatInt16x16", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatInt16x32", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatInt32x4", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatInt32x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatInt32x16", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatInt64x2", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatInt64x4", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatInt64x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedInt16x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedInt16x16", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedInt16x32", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedInt32x4", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedInt32x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedInt32x16", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedInt64x2", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedInt64x4", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedInt64x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedUint16x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedUint16x16", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedUint16x32", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedUint32x4", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedUint32x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedUint32x16", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedUint64x2", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedUint64x4", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatMaskedUint64x8", argLength: 3, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatUint16x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatUint16x16", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatUint16x32", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatUint32x4", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatUint32x8", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatUint32x16", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatUint64x2", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatUint64x4", argLength: 2, commutative: false, aux: "Int8"}, + {name: "ShiftAllRightConcatUint64x8", argLength: 2, commutative: false, aux: "Int8"}, {name: "TruncWithPrecisionFloat32x4", argLength: 1, commutative: false, aux: "Int8"}, {name: "TruncWithPrecisionFloat32x8", argLength: 1, commutative: false, aux: "Int8"}, {name: "TruncWithPrecisionFloat32x16", argLength: 1, commutative: false, aux: "Int8"}, diff --git a/src/cmd/compile/internal/ssa/opGen.go b/src/cmd/compile/internal/ssa/opGen.go index ed0203b639..de4477bc91 100644 --- a/src/cmd/compile/internal/ssa/opGen.go +++ b/src/cmd/compile/internal/ssa/opGen.go @@ -5764,42 +5764,42 @@ const ( OpShiftAllRightUint64x2 OpShiftAllRightUint64x4 OpShiftAllRightUint64x8 - OpShiftLeftAndFillUpperFromInt16x8 - OpShiftLeftAndFillUpperFromInt16x16 - OpShiftLeftAndFillUpperFromInt16x32 - OpShiftLeftAndFillUpperFromInt32x4 - OpShiftLeftAndFillUpperFromInt32x8 - OpShiftLeftAndFillUpperFromInt32x16 - OpShiftLeftAndFillUpperFromInt64x2 - OpShiftLeftAndFillUpperFromInt64x4 - OpShiftLeftAndFillUpperFromInt64x8 - OpShiftLeftAndFillUpperFromMaskedInt16x8 - OpShiftLeftAndFillUpperFromMaskedInt16x16 - OpShiftLeftAndFillUpperFromMaskedInt16x32 - OpShiftLeftAndFillUpperFromMaskedInt32x4 - OpShiftLeftAndFillUpperFromMaskedInt32x8 - OpShiftLeftAndFillUpperFromMaskedInt32x16 - OpShiftLeftAndFillUpperFromMaskedInt64x2 - OpShiftLeftAndFillUpperFromMaskedInt64x4 - OpShiftLeftAndFillUpperFromMaskedInt64x8 - OpShiftLeftAndFillUpperFromMaskedUint16x8 - OpShiftLeftAndFillUpperFromMaskedUint16x16 - OpShiftLeftAndFillUpperFromMaskedUint16x32 - OpShiftLeftAndFillUpperFromMaskedUint32x4 - OpShiftLeftAndFillUpperFromMaskedUint32x8 - OpShiftLeftAndFillUpperFromMaskedUint32x16 - OpShiftLeftAndFillUpperFromMaskedUint64x2 - OpShiftLeftAndFillUpperFromMaskedUint64x4 - OpShiftLeftAndFillUpperFromMaskedUint64x8 - OpShiftLeftAndFillUpperFromUint16x8 - OpShiftLeftAndFillUpperFromUint16x16 - OpShiftLeftAndFillUpperFromUint16x32 - OpShiftLeftAndFillUpperFromUint32x4 - OpShiftLeftAndFillUpperFromUint32x8 - OpShiftLeftAndFillUpperFromUint32x16 - OpShiftLeftAndFillUpperFromUint64x2 - OpShiftLeftAndFillUpperFromUint64x4 - OpShiftLeftAndFillUpperFromUint64x8 + OpShiftLeftConcatInt16x8 + OpShiftLeftConcatInt16x16 + OpShiftLeftConcatInt16x32 + OpShiftLeftConcatInt32x4 + OpShiftLeftConcatInt32x8 + OpShiftLeftConcatInt32x16 + OpShiftLeftConcatInt64x2 + OpShiftLeftConcatInt64x4 + OpShiftLeftConcatInt64x8 + OpShiftLeftConcatMaskedInt16x8 + OpShiftLeftConcatMaskedInt16x16 + OpShiftLeftConcatMaskedInt16x32 + OpShiftLeftConcatMaskedInt32x4 + OpShiftLeftConcatMaskedInt32x8 + OpShiftLeftConcatMaskedInt32x16 + OpShiftLeftConcatMaskedInt64x2 + OpShiftLeftConcatMaskedInt64x4 + OpShiftLeftConcatMaskedInt64x8 + OpShiftLeftConcatMaskedUint16x8 + OpShiftLeftConcatMaskedUint16x16 + OpShiftLeftConcatMaskedUint16x32 + OpShiftLeftConcatMaskedUint32x4 + OpShiftLeftConcatMaskedUint32x8 + OpShiftLeftConcatMaskedUint32x16 + OpShiftLeftConcatMaskedUint64x2 + OpShiftLeftConcatMaskedUint64x4 + OpShiftLeftConcatMaskedUint64x8 + OpShiftLeftConcatUint16x8 + OpShiftLeftConcatUint16x16 + OpShiftLeftConcatUint16x32 + OpShiftLeftConcatUint32x4 + OpShiftLeftConcatUint32x8 + OpShiftLeftConcatUint32x16 + OpShiftLeftConcatUint64x2 + OpShiftLeftConcatUint64x4 + OpShiftLeftConcatUint64x8 OpShiftLeftInt16x8 OpShiftLeftInt16x16 OpShiftLeftInt16x32 @@ -5836,42 +5836,42 @@ const ( OpShiftLeftUint64x2 OpShiftLeftUint64x4 OpShiftLeftUint64x8 - OpShiftRightAndFillUpperFromInt16x8 - OpShiftRightAndFillUpperFromInt16x16 - OpShiftRightAndFillUpperFromInt16x32 - OpShiftRightAndFillUpperFromInt32x4 - OpShiftRightAndFillUpperFromInt32x8 - OpShiftRightAndFillUpperFromInt32x16 - OpShiftRightAndFillUpperFromInt64x2 - OpShiftRightAndFillUpperFromInt64x4 - OpShiftRightAndFillUpperFromInt64x8 - OpShiftRightAndFillUpperFromMaskedInt16x8 - OpShiftRightAndFillUpperFromMaskedInt16x16 - OpShiftRightAndFillUpperFromMaskedInt16x32 - OpShiftRightAndFillUpperFromMaskedInt32x4 - OpShiftRightAndFillUpperFromMaskedInt32x8 - OpShiftRightAndFillUpperFromMaskedInt32x16 - OpShiftRightAndFillUpperFromMaskedInt64x2 - OpShiftRightAndFillUpperFromMaskedInt64x4 - OpShiftRightAndFillUpperFromMaskedInt64x8 - OpShiftRightAndFillUpperFromMaskedUint16x8 - OpShiftRightAndFillUpperFromMaskedUint16x16 - OpShiftRightAndFillUpperFromMaskedUint16x32 - OpShiftRightAndFillUpperFromMaskedUint32x4 - OpShiftRightAndFillUpperFromMaskedUint32x8 - OpShiftRightAndFillUpperFromMaskedUint32x16 - OpShiftRightAndFillUpperFromMaskedUint64x2 - OpShiftRightAndFillUpperFromMaskedUint64x4 - OpShiftRightAndFillUpperFromMaskedUint64x8 - OpShiftRightAndFillUpperFromUint16x8 - OpShiftRightAndFillUpperFromUint16x16 - OpShiftRightAndFillUpperFromUint16x32 - OpShiftRightAndFillUpperFromUint32x4 - OpShiftRightAndFillUpperFromUint32x8 - OpShiftRightAndFillUpperFromUint32x16 - OpShiftRightAndFillUpperFromUint64x2 - OpShiftRightAndFillUpperFromUint64x4 - OpShiftRightAndFillUpperFromUint64x8 + OpShiftRightConcatInt16x8 + OpShiftRightConcatInt16x16 + OpShiftRightConcatInt16x32 + OpShiftRightConcatInt32x4 + OpShiftRightConcatInt32x8 + OpShiftRightConcatInt32x16 + OpShiftRightConcatInt64x2 + OpShiftRightConcatInt64x4 + OpShiftRightConcatInt64x8 + OpShiftRightConcatMaskedInt16x8 + OpShiftRightConcatMaskedInt16x16 + OpShiftRightConcatMaskedInt16x32 + OpShiftRightConcatMaskedInt32x4 + OpShiftRightConcatMaskedInt32x8 + OpShiftRightConcatMaskedInt32x16 + OpShiftRightConcatMaskedInt64x2 + OpShiftRightConcatMaskedInt64x4 + OpShiftRightConcatMaskedInt64x8 + OpShiftRightConcatMaskedUint16x8 + OpShiftRightConcatMaskedUint16x16 + OpShiftRightConcatMaskedUint16x32 + OpShiftRightConcatMaskedUint32x4 + OpShiftRightConcatMaskedUint32x8 + OpShiftRightConcatMaskedUint32x16 + OpShiftRightConcatMaskedUint64x2 + OpShiftRightConcatMaskedUint64x4 + OpShiftRightConcatMaskedUint64x8 + OpShiftRightConcatUint16x8 + OpShiftRightConcatUint16x16 + OpShiftRightConcatUint16x32 + OpShiftRightConcatUint32x4 + OpShiftRightConcatUint32x8 + OpShiftRightConcatUint32x16 + OpShiftRightConcatUint64x2 + OpShiftRightConcatUint64x4 + OpShiftRightConcatUint64x8 OpShiftRightInt16x8 OpShiftRightInt16x16 OpShiftRightInt16x32 @@ -6208,78 +6208,78 @@ const ( OpSetElemUint16x8 OpSetElemUint32x4 OpSetElemUint64x2 - OpShiftAllLeftAndFillUpperFromInt16x8 - OpShiftAllLeftAndFillUpperFromInt16x16 - OpShiftAllLeftAndFillUpperFromInt16x32 - OpShiftAllLeftAndFillUpperFromInt32x4 - OpShiftAllLeftAndFillUpperFromInt32x8 - OpShiftAllLeftAndFillUpperFromInt32x16 - OpShiftAllLeftAndFillUpperFromInt64x2 - OpShiftAllLeftAndFillUpperFromInt64x4 - OpShiftAllLeftAndFillUpperFromInt64x8 - OpShiftAllLeftAndFillUpperFromMaskedInt16x8 - OpShiftAllLeftAndFillUpperFromMaskedInt16x16 - OpShiftAllLeftAndFillUpperFromMaskedInt16x32 - OpShiftAllLeftAndFillUpperFromMaskedInt32x4 - OpShiftAllLeftAndFillUpperFromMaskedInt32x8 - OpShiftAllLeftAndFillUpperFromMaskedInt32x16 - OpShiftAllLeftAndFillUpperFromMaskedInt64x2 - OpShiftAllLeftAndFillUpperFromMaskedInt64x4 - OpShiftAllLeftAndFillUpperFromMaskedInt64x8 - OpShiftAllLeftAndFillUpperFromMaskedUint16x8 - OpShiftAllLeftAndFillUpperFromMaskedUint16x16 - OpShiftAllLeftAndFillUpperFromMaskedUint16x32 - OpShiftAllLeftAndFillUpperFromMaskedUint32x4 - OpShiftAllLeftAndFillUpperFromMaskedUint32x8 - OpShiftAllLeftAndFillUpperFromMaskedUint32x16 - OpShiftAllLeftAndFillUpperFromMaskedUint64x2 - OpShiftAllLeftAndFillUpperFromMaskedUint64x4 - OpShiftAllLeftAndFillUpperFromMaskedUint64x8 - OpShiftAllLeftAndFillUpperFromUint16x8 - OpShiftAllLeftAndFillUpperFromUint16x16 - OpShiftAllLeftAndFillUpperFromUint16x32 - OpShiftAllLeftAndFillUpperFromUint32x4 - OpShiftAllLeftAndFillUpperFromUint32x8 - OpShiftAllLeftAndFillUpperFromUint32x16 - OpShiftAllLeftAndFillUpperFromUint64x2 - OpShiftAllLeftAndFillUpperFromUint64x4 - OpShiftAllLeftAndFillUpperFromUint64x8 - OpShiftAllRightAndFillUpperFromInt16x8 - OpShiftAllRightAndFillUpperFromInt16x16 - OpShiftAllRightAndFillUpperFromInt16x32 - OpShiftAllRightAndFillUpperFromInt32x4 - OpShiftAllRightAndFillUpperFromInt32x8 - OpShiftAllRightAndFillUpperFromInt32x16 - OpShiftAllRightAndFillUpperFromInt64x2 - OpShiftAllRightAndFillUpperFromInt64x4 - OpShiftAllRightAndFillUpperFromInt64x8 - OpShiftAllRightAndFillUpperFromMaskedInt16x8 - OpShiftAllRightAndFillUpperFromMaskedInt16x16 - OpShiftAllRightAndFillUpperFromMaskedInt16x32 - OpShiftAllRightAndFillUpperFromMaskedInt32x4 - OpShiftAllRightAndFillUpperFromMaskedInt32x8 - OpShiftAllRightAndFillUpperFromMaskedInt32x16 - OpShiftAllRightAndFillUpperFromMaskedInt64x2 - OpShiftAllRightAndFillUpperFromMaskedInt64x4 - OpShiftAllRightAndFillUpperFromMaskedInt64x8 - OpShiftAllRightAndFillUpperFromMaskedUint16x8 - OpShiftAllRightAndFillUpperFromMaskedUint16x16 - OpShiftAllRightAndFillUpperFromMaskedUint16x32 - OpShiftAllRightAndFillUpperFromMaskedUint32x4 - OpShiftAllRightAndFillUpperFromMaskedUint32x8 - OpShiftAllRightAndFillUpperFromMaskedUint32x16 - OpShiftAllRightAndFillUpperFromMaskedUint64x2 - OpShiftAllRightAndFillUpperFromMaskedUint64x4 - OpShiftAllRightAndFillUpperFromMaskedUint64x8 - OpShiftAllRightAndFillUpperFromUint16x8 - OpShiftAllRightAndFillUpperFromUint16x16 - OpShiftAllRightAndFillUpperFromUint16x32 - OpShiftAllRightAndFillUpperFromUint32x4 - OpShiftAllRightAndFillUpperFromUint32x8 - OpShiftAllRightAndFillUpperFromUint32x16 - OpShiftAllRightAndFillUpperFromUint64x2 - OpShiftAllRightAndFillUpperFromUint64x4 - OpShiftAllRightAndFillUpperFromUint64x8 + OpShiftAllLeftConcatInt16x8 + OpShiftAllLeftConcatInt16x16 + OpShiftAllLeftConcatInt16x32 + OpShiftAllLeftConcatInt32x4 + OpShiftAllLeftConcatInt32x8 + OpShiftAllLeftConcatInt32x16 + OpShiftAllLeftConcatInt64x2 + OpShiftAllLeftConcatInt64x4 + OpShiftAllLeftConcatInt64x8 + OpShiftAllLeftConcatMaskedInt16x8 + OpShiftAllLeftConcatMaskedInt16x16 + OpShiftAllLeftConcatMaskedInt16x32 + OpShiftAllLeftConcatMaskedInt32x4 + OpShiftAllLeftConcatMaskedInt32x8 + OpShiftAllLeftConcatMaskedInt32x16 + OpShiftAllLeftConcatMaskedInt64x2 + OpShiftAllLeftConcatMaskedInt64x4 + OpShiftAllLeftConcatMaskedInt64x8 + OpShiftAllLeftConcatMaskedUint16x8 + OpShiftAllLeftConcatMaskedUint16x16 + OpShiftAllLeftConcatMaskedUint16x32 + OpShiftAllLeftConcatMaskedUint32x4 + OpShiftAllLeftConcatMaskedUint32x8 + OpShiftAllLeftConcatMaskedUint32x16 + OpShiftAllLeftConcatMaskedUint64x2 + OpShiftAllLeftConcatMaskedUint64x4 + OpShiftAllLeftConcatMaskedUint64x8 + OpShiftAllLeftConcatUint16x8 + OpShiftAllLeftConcatUint16x16 + OpShiftAllLeftConcatUint16x32 + OpShiftAllLeftConcatUint32x4 + OpShiftAllLeftConcatUint32x8 + OpShiftAllLeftConcatUint32x16 + OpShiftAllLeftConcatUint64x2 + OpShiftAllLeftConcatUint64x4 + OpShiftAllLeftConcatUint64x8 + OpShiftAllRightConcatInt16x8 + OpShiftAllRightConcatInt16x16 + OpShiftAllRightConcatInt16x32 + OpShiftAllRightConcatInt32x4 + OpShiftAllRightConcatInt32x8 + OpShiftAllRightConcatInt32x16 + OpShiftAllRightConcatInt64x2 + OpShiftAllRightConcatInt64x4 + OpShiftAllRightConcatInt64x8 + OpShiftAllRightConcatMaskedInt16x8 + OpShiftAllRightConcatMaskedInt16x16 + OpShiftAllRightConcatMaskedInt16x32 + OpShiftAllRightConcatMaskedInt32x4 + OpShiftAllRightConcatMaskedInt32x8 + OpShiftAllRightConcatMaskedInt32x16 + OpShiftAllRightConcatMaskedInt64x2 + OpShiftAllRightConcatMaskedInt64x4 + OpShiftAllRightConcatMaskedInt64x8 + OpShiftAllRightConcatMaskedUint16x8 + OpShiftAllRightConcatMaskedUint16x16 + OpShiftAllRightConcatMaskedUint16x32 + OpShiftAllRightConcatMaskedUint32x4 + OpShiftAllRightConcatMaskedUint32x8 + OpShiftAllRightConcatMaskedUint32x16 + OpShiftAllRightConcatMaskedUint64x2 + OpShiftAllRightConcatMaskedUint64x4 + OpShiftAllRightConcatMaskedUint64x8 + OpShiftAllRightConcatUint16x8 + OpShiftAllRightConcatUint16x16 + OpShiftAllRightConcatUint16x32 + OpShiftAllRightConcatUint32x4 + OpShiftAllRightConcatUint32x8 + OpShiftAllRightConcatUint32x16 + OpShiftAllRightConcatUint64x2 + OpShiftAllRightConcatUint64x4 + OpShiftAllRightConcatUint64x8 OpTruncWithPrecisionFloat32x4 OpTruncWithPrecisionFloat32x8 OpTruncWithPrecisionFloat32x16 @@ -68518,182 +68518,182 @@ var opcodeTable = [...]opInfo{ generic: true, }, { - name: "ShiftLeftAndFillUpperFromInt16x8", + name: "ShiftLeftConcatInt16x8", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromInt16x16", + name: "ShiftLeftConcatInt16x16", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromInt16x32", + name: "ShiftLeftConcatInt16x32", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromInt32x4", + name: "ShiftLeftConcatInt32x4", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromInt32x8", + name: "ShiftLeftConcatInt32x8", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromInt32x16", + name: "ShiftLeftConcatInt32x16", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromInt64x2", + name: "ShiftLeftConcatInt64x2", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromInt64x4", + name: "ShiftLeftConcatInt64x4", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromInt64x8", + name: "ShiftLeftConcatInt64x8", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedInt16x8", + name: "ShiftLeftConcatMaskedInt16x8", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedInt16x16", + name: "ShiftLeftConcatMaskedInt16x16", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedInt16x32", + name: "ShiftLeftConcatMaskedInt16x32", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedInt32x4", + name: "ShiftLeftConcatMaskedInt32x4", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedInt32x8", + name: "ShiftLeftConcatMaskedInt32x8", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedInt32x16", + name: "ShiftLeftConcatMaskedInt32x16", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedInt64x2", + name: "ShiftLeftConcatMaskedInt64x2", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedInt64x4", + name: "ShiftLeftConcatMaskedInt64x4", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedInt64x8", + name: "ShiftLeftConcatMaskedInt64x8", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedUint16x8", + name: "ShiftLeftConcatMaskedUint16x8", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedUint16x16", + name: "ShiftLeftConcatMaskedUint16x16", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedUint16x32", + name: "ShiftLeftConcatMaskedUint16x32", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedUint32x4", + name: "ShiftLeftConcatMaskedUint32x4", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedUint32x8", + name: "ShiftLeftConcatMaskedUint32x8", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedUint32x16", + name: "ShiftLeftConcatMaskedUint32x16", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedUint64x2", + name: "ShiftLeftConcatMaskedUint64x2", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedUint64x4", + name: "ShiftLeftConcatMaskedUint64x4", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromMaskedUint64x8", + name: "ShiftLeftConcatMaskedUint64x8", argLen: 4, generic: true, }, { - name: "ShiftLeftAndFillUpperFromUint16x8", + name: "ShiftLeftConcatUint16x8", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromUint16x16", + name: "ShiftLeftConcatUint16x16", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromUint16x32", + name: "ShiftLeftConcatUint16x32", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromUint32x4", + name: "ShiftLeftConcatUint32x4", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromUint32x8", + name: "ShiftLeftConcatUint32x8", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromUint32x16", + name: "ShiftLeftConcatUint32x16", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromUint64x2", + name: "ShiftLeftConcatUint64x2", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromUint64x4", + name: "ShiftLeftConcatUint64x4", argLen: 3, generic: true, }, { - name: "ShiftLeftAndFillUpperFromUint64x8", + name: "ShiftLeftConcatUint64x8", argLen: 3, generic: true, }, @@ -68878,182 +68878,182 @@ var opcodeTable = [...]opInfo{ generic: true, }, { - name: "ShiftRightAndFillUpperFromInt16x8", + name: "ShiftRightConcatInt16x8", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromInt16x16", + name: "ShiftRightConcatInt16x16", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromInt16x32", + name: "ShiftRightConcatInt16x32", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromInt32x4", + name: "ShiftRightConcatInt32x4", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromInt32x8", + name: "ShiftRightConcatInt32x8", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromInt32x16", + name: "ShiftRightConcatInt32x16", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromInt64x2", + name: "ShiftRightConcatInt64x2", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromInt64x4", + name: "ShiftRightConcatInt64x4", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromInt64x8", + name: "ShiftRightConcatInt64x8", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedInt16x8", + name: "ShiftRightConcatMaskedInt16x8", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedInt16x16", + name: "ShiftRightConcatMaskedInt16x16", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedInt16x32", + name: "ShiftRightConcatMaskedInt16x32", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedInt32x4", + name: "ShiftRightConcatMaskedInt32x4", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedInt32x8", + name: "ShiftRightConcatMaskedInt32x8", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedInt32x16", + name: "ShiftRightConcatMaskedInt32x16", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedInt64x2", + name: "ShiftRightConcatMaskedInt64x2", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedInt64x4", + name: "ShiftRightConcatMaskedInt64x4", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedInt64x8", + name: "ShiftRightConcatMaskedInt64x8", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedUint16x8", + name: "ShiftRightConcatMaskedUint16x8", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedUint16x16", + name: "ShiftRightConcatMaskedUint16x16", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedUint16x32", + name: "ShiftRightConcatMaskedUint16x32", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedUint32x4", + name: "ShiftRightConcatMaskedUint32x4", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedUint32x8", + name: "ShiftRightConcatMaskedUint32x8", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedUint32x16", + name: "ShiftRightConcatMaskedUint32x16", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedUint64x2", + name: "ShiftRightConcatMaskedUint64x2", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedUint64x4", + name: "ShiftRightConcatMaskedUint64x4", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromMaskedUint64x8", + name: "ShiftRightConcatMaskedUint64x8", argLen: 4, generic: true, }, { - name: "ShiftRightAndFillUpperFromUint16x8", + name: "ShiftRightConcatUint16x8", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromUint16x16", + name: "ShiftRightConcatUint16x16", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromUint16x32", + name: "ShiftRightConcatUint16x32", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromUint32x4", + name: "ShiftRightConcatUint32x4", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromUint32x8", + name: "ShiftRightConcatUint32x8", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromUint32x16", + name: "ShiftRightConcatUint32x16", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromUint64x2", + name: "ShiftRightConcatUint64x2", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromUint64x4", + name: "ShiftRightConcatUint64x4", argLen: 3, generic: true, }, { - name: "ShiftRightAndFillUpperFromUint64x8", + name: "ShiftRightConcatUint64x8", argLen: 3, generic: true, }, @@ -70950,433 +70950,433 @@ var opcodeTable = [...]opInfo{ generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromInt16x8", + name: "ShiftAllLeftConcatInt16x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromInt16x16", + name: "ShiftAllLeftConcatInt16x16", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromInt16x32", + name: "ShiftAllLeftConcatInt16x32", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromInt32x4", + name: "ShiftAllLeftConcatInt32x4", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromInt32x8", + name: "ShiftAllLeftConcatInt32x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromInt32x16", + name: "ShiftAllLeftConcatInt32x16", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromInt64x2", + name: "ShiftAllLeftConcatInt64x2", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromInt64x4", + name: "ShiftAllLeftConcatInt64x4", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromInt64x8", + name: "ShiftAllLeftConcatInt64x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedInt16x8", + name: "ShiftAllLeftConcatMaskedInt16x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedInt16x16", + name: "ShiftAllLeftConcatMaskedInt16x16", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedInt16x32", + name: "ShiftAllLeftConcatMaskedInt16x32", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedInt32x4", + name: "ShiftAllLeftConcatMaskedInt32x4", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedInt32x8", + name: "ShiftAllLeftConcatMaskedInt32x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedInt32x16", + name: "ShiftAllLeftConcatMaskedInt32x16", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedInt64x2", + name: "ShiftAllLeftConcatMaskedInt64x2", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedInt64x4", + name: "ShiftAllLeftConcatMaskedInt64x4", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedInt64x8", + name: "ShiftAllLeftConcatMaskedInt64x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedUint16x8", + name: "ShiftAllLeftConcatMaskedUint16x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedUint16x16", + name: "ShiftAllLeftConcatMaskedUint16x16", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedUint16x32", + name: "ShiftAllLeftConcatMaskedUint16x32", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedUint32x4", + name: "ShiftAllLeftConcatMaskedUint32x4", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedUint32x8", + name: "ShiftAllLeftConcatMaskedUint32x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedUint32x16", + name: "ShiftAllLeftConcatMaskedUint32x16", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedUint64x2", + name: "ShiftAllLeftConcatMaskedUint64x2", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedUint64x4", + name: "ShiftAllLeftConcatMaskedUint64x4", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromMaskedUint64x8", + name: "ShiftAllLeftConcatMaskedUint64x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromUint16x8", + name: "ShiftAllLeftConcatUint16x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromUint16x16", + name: "ShiftAllLeftConcatUint16x16", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromUint16x32", + name: "ShiftAllLeftConcatUint16x32", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromUint32x4", + name: "ShiftAllLeftConcatUint32x4", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromUint32x8", + name: "ShiftAllLeftConcatUint32x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromUint32x16", + name: "ShiftAllLeftConcatUint32x16", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromUint64x2", + name: "ShiftAllLeftConcatUint64x2", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromUint64x4", + name: "ShiftAllLeftConcatUint64x4", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllLeftAndFillUpperFromUint64x8", + name: "ShiftAllLeftConcatUint64x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromInt16x8", + name: "ShiftAllRightConcatInt16x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromInt16x16", + name: "ShiftAllRightConcatInt16x16", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromInt16x32", + name: "ShiftAllRightConcatInt16x32", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromInt32x4", + name: "ShiftAllRightConcatInt32x4", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromInt32x8", + name: "ShiftAllRightConcatInt32x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromInt32x16", + name: "ShiftAllRightConcatInt32x16", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromInt64x2", + name: "ShiftAllRightConcatInt64x2", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromInt64x4", + name: "ShiftAllRightConcatInt64x4", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromInt64x8", + name: "ShiftAllRightConcatInt64x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedInt16x8", + name: "ShiftAllRightConcatMaskedInt16x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedInt16x16", + name: "ShiftAllRightConcatMaskedInt16x16", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedInt16x32", + name: "ShiftAllRightConcatMaskedInt16x32", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedInt32x4", + name: "ShiftAllRightConcatMaskedInt32x4", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedInt32x8", + name: "ShiftAllRightConcatMaskedInt32x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedInt32x16", + name: "ShiftAllRightConcatMaskedInt32x16", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedInt64x2", + name: "ShiftAllRightConcatMaskedInt64x2", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedInt64x4", + name: "ShiftAllRightConcatMaskedInt64x4", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedInt64x8", + name: "ShiftAllRightConcatMaskedInt64x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedUint16x8", + name: "ShiftAllRightConcatMaskedUint16x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedUint16x16", + name: "ShiftAllRightConcatMaskedUint16x16", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedUint16x32", + name: "ShiftAllRightConcatMaskedUint16x32", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedUint32x4", + name: "ShiftAllRightConcatMaskedUint32x4", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedUint32x8", + name: "ShiftAllRightConcatMaskedUint32x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedUint32x16", + name: "ShiftAllRightConcatMaskedUint32x16", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedUint64x2", + name: "ShiftAllRightConcatMaskedUint64x2", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedUint64x4", + name: "ShiftAllRightConcatMaskedUint64x4", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromMaskedUint64x8", + name: "ShiftAllRightConcatMaskedUint64x8", auxType: auxInt8, argLen: 3, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromUint16x8", + name: "ShiftAllRightConcatUint16x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromUint16x16", + name: "ShiftAllRightConcatUint16x16", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromUint16x32", + name: "ShiftAllRightConcatUint16x32", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromUint32x4", + name: "ShiftAllRightConcatUint32x4", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromUint32x8", + name: "ShiftAllRightConcatUint32x8", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromUint32x16", + name: "ShiftAllRightConcatUint32x16", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromUint64x2", + name: "ShiftAllRightConcatUint64x2", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromUint64x4", + name: "ShiftAllRightConcatUint64x4", auxType: auxInt8, argLen: 2, generic: true, }, { - name: "ShiftAllRightAndFillUpperFromUint64x8", + name: "ShiftAllRightConcatUint64x8", auxType: auxInt8, argLen: 2, generic: true, diff --git a/src/cmd/compile/internal/ssa/rewriteAMD64.go b/src/cmd/compile/internal/ssa/rewriteAMD64.go index 986f256887..e9a2fd70e4 100644 --- a/src/cmd/compile/internal/ssa/rewriteAMD64.go +++ b/src/cmd/compile/internal/ssa/rewriteAMD64.go @@ -4443,94 +4443,94 @@ func rewriteValueAMD64(v *Value) bool { case OpSetElemUint8x16: v.Op = OpAMD64VPINSRB128 return true - case OpShiftAllLeftAndFillUpperFromInt16x16: + case OpShiftAllLeftConcatInt16x16: v.Op = OpAMD64VPSHLDW256 return true - case OpShiftAllLeftAndFillUpperFromInt16x32: + case OpShiftAllLeftConcatInt16x32: v.Op = OpAMD64VPSHLDW512 return true - case OpShiftAllLeftAndFillUpperFromInt16x8: + case OpShiftAllLeftConcatInt16x8: v.Op = OpAMD64VPSHLDW128 return true - case OpShiftAllLeftAndFillUpperFromInt32x16: + case OpShiftAllLeftConcatInt32x16: v.Op = OpAMD64VPSHLDD512 return true - case OpShiftAllLeftAndFillUpperFromInt32x4: + case OpShiftAllLeftConcatInt32x4: v.Op = OpAMD64VPSHLDD128 return true - case OpShiftAllLeftAndFillUpperFromInt32x8: + case OpShiftAllLeftConcatInt32x8: v.Op = OpAMD64VPSHLDD256 return true - case OpShiftAllLeftAndFillUpperFromInt64x2: + case OpShiftAllLeftConcatInt64x2: v.Op = OpAMD64VPSHLDQ128 return true - case OpShiftAllLeftAndFillUpperFromInt64x4: + case OpShiftAllLeftConcatInt64x4: v.Op = OpAMD64VPSHLDQ256 return true - case OpShiftAllLeftAndFillUpperFromInt64x8: + case OpShiftAllLeftConcatInt64x8: v.Op = OpAMD64VPSHLDQ512 return true - case OpShiftAllLeftAndFillUpperFromMaskedInt16x16: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt16x16(v) - case OpShiftAllLeftAndFillUpperFromMaskedInt16x32: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt16x32(v) - case OpShiftAllLeftAndFillUpperFromMaskedInt16x8: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt16x8(v) - case OpShiftAllLeftAndFillUpperFromMaskedInt32x16: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt32x16(v) - case OpShiftAllLeftAndFillUpperFromMaskedInt32x4: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt32x4(v) - case OpShiftAllLeftAndFillUpperFromMaskedInt32x8: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt32x8(v) - case OpShiftAllLeftAndFillUpperFromMaskedInt64x2: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt64x2(v) - case OpShiftAllLeftAndFillUpperFromMaskedInt64x4: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt64x4(v) - case OpShiftAllLeftAndFillUpperFromMaskedInt64x8: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt64x8(v) - case OpShiftAllLeftAndFillUpperFromMaskedUint16x16: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint16x16(v) - case OpShiftAllLeftAndFillUpperFromMaskedUint16x32: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint16x32(v) - case OpShiftAllLeftAndFillUpperFromMaskedUint16x8: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint16x8(v) - case OpShiftAllLeftAndFillUpperFromMaskedUint32x16: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint32x16(v) - case OpShiftAllLeftAndFillUpperFromMaskedUint32x4: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint32x4(v) - case OpShiftAllLeftAndFillUpperFromMaskedUint32x8: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint32x8(v) - case OpShiftAllLeftAndFillUpperFromMaskedUint64x2: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint64x2(v) - case OpShiftAllLeftAndFillUpperFromMaskedUint64x4: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint64x4(v) - case OpShiftAllLeftAndFillUpperFromMaskedUint64x8: - return rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint64x8(v) - case OpShiftAllLeftAndFillUpperFromUint16x16: + case OpShiftAllLeftConcatMaskedInt16x16: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt16x16(v) + case OpShiftAllLeftConcatMaskedInt16x32: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt16x32(v) + case OpShiftAllLeftConcatMaskedInt16x8: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt16x8(v) + case OpShiftAllLeftConcatMaskedInt32x16: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt32x16(v) + case OpShiftAllLeftConcatMaskedInt32x4: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt32x4(v) + case OpShiftAllLeftConcatMaskedInt32x8: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt32x8(v) + case OpShiftAllLeftConcatMaskedInt64x2: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt64x2(v) + case OpShiftAllLeftConcatMaskedInt64x4: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt64x4(v) + case OpShiftAllLeftConcatMaskedInt64x8: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt64x8(v) + case OpShiftAllLeftConcatMaskedUint16x16: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint16x16(v) + case OpShiftAllLeftConcatMaskedUint16x32: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint16x32(v) + case OpShiftAllLeftConcatMaskedUint16x8: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint16x8(v) + case OpShiftAllLeftConcatMaskedUint32x16: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint32x16(v) + case OpShiftAllLeftConcatMaskedUint32x4: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint32x4(v) + case OpShiftAllLeftConcatMaskedUint32x8: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint32x8(v) + case OpShiftAllLeftConcatMaskedUint64x2: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint64x2(v) + case OpShiftAllLeftConcatMaskedUint64x4: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint64x4(v) + case OpShiftAllLeftConcatMaskedUint64x8: + return rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint64x8(v) + case OpShiftAllLeftConcatUint16x16: v.Op = OpAMD64VPSHLDW256 return true - case OpShiftAllLeftAndFillUpperFromUint16x32: + case OpShiftAllLeftConcatUint16x32: v.Op = OpAMD64VPSHLDW512 return true - case OpShiftAllLeftAndFillUpperFromUint16x8: + case OpShiftAllLeftConcatUint16x8: v.Op = OpAMD64VPSHLDW128 return true - case OpShiftAllLeftAndFillUpperFromUint32x16: + case OpShiftAllLeftConcatUint32x16: v.Op = OpAMD64VPSHLDD512 return true - case OpShiftAllLeftAndFillUpperFromUint32x4: + case OpShiftAllLeftConcatUint32x4: v.Op = OpAMD64VPSHLDD128 return true - case OpShiftAllLeftAndFillUpperFromUint32x8: + case OpShiftAllLeftConcatUint32x8: v.Op = OpAMD64VPSHLDD256 return true - case OpShiftAllLeftAndFillUpperFromUint64x2: + case OpShiftAllLeftConcatUint64x2: v.Op = OpAMD64VPSHLDQ128 return true - case OpShiftAllLeftAndFillUpperFromUint64x4: + case OpShiftAllLeftConcatUint64x4: v.Op = OpAMD64VPSHLDQ256 return true - case OpShiftAllLeftAndFillUpperFromUint64x8: + case OpShiftAllLeftConcatUint64x8: v.Op = OpAMD64VPSHLDQ512 return true case OpShiftAllLeftInt16x16: @@ -4623,94 +4623,94 @@ func rewriteValueAMD64(v *Value) bool { case OpShiftAllLeftUint64x8: v.Op = OpAMD64VPSLLQ512 return true - case OpShiftAllRightAndFillUpperFromInt16x16: + case OpShiftAllRightConcatInt16x16: v.Op = OpAMD64VPSHRDW256 return true - case OpShiftAllRightAndFillUpperFromInt16x32: + case OpShiftAllRightConcatInt16x32: v.Op = OpAMD64VPSHRDW512 return true - case OpShiftAllRightAndFillUpperFromInt16x8: + case OpShiftAllRightConcatInt16x8: v.Op = OpAMD64VPSHRDW128 return true - case OpShiftAllRightAndFillUpperFromInt32x16: + case OpShiftAllRightConcatInt32x16: v.Op = OpAMD64VPSHRDD512 return true - case OpShiftAllRightAndFillUpperFromInt32x4: + case OpShiftAllRightConcatInt32x4: v.Op = OpAMD64VPSHRDD128 return true - case OpShiftAllRightAndFillUpperFromInt32x8: + case OpShiftAllRightConcatInt32x8: v.Op = OpAMD64VPSHRDD256 return true - case OpShiftAllRightAndFillUpperFromInt64x2: + case OpShiftAllRightConcatInt64x2: v.Op = OpAMD64VPSHRDQ128 return true - case OpShiftAllRightAndFillUpperFromInt64x4: + case OpShiftAllRightConcatInt64x4: v.Op = OpAMD64VPSHRDQ256 return true - case OpShiftAllRightAndFillUpperFromInt64x8: + case OpShiftAllRightConcatInt64x8: v.Op = OpAMD64VPSHRDQ512 return true - case OpShiftAllRightAndFillUpperFromMaskedInt16x16: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt16x16(v) - case OpShiftAllRightAndFillUpperFromMaskedInt16x32: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt16x32(v) - case OpShiftAllRightAndFillUpperFromMaskedInt16x8: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt16x8(v) - case OpShiftAllRightAndFillUpperFromMaskedInt32x16: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt32x16(v) - case OpShiftAllRightAndFillUpperFromMaskedInt32x4: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt32x4(v) - case OpShiftAllRightAndFillUpperFromMaskedInt32x8: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt32x8(v) - case OpShiftAllRightAndFillUpperFromMaskedInt64x2: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt64x2(v) - case OpShiftAllRightAndFillUpperFromMaskedInt64x4: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt64x4(v) - case OpShiftAllRightAndFillUpperFromMaskedInt64x8: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt64x8(v) - case OpShiftAllRightAndFillUpperFromMaskedUint16x16: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint16x16(v) - case OpShiftAllRightAndFillUpperFromMaskedUint16x32: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint16x32(v) - case OpShiftAllRightAndFillUpperFromMaskedUint16x8: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint16x8(v) - case OpShiftAllRightAndFillUpperFromMaskedUint32x16: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint32x16(v) - case OpShiftAllRightAndFillUpperFromMaskedUint32x4: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint32x4(v) - case OpShiftAllRightAndFillUpperFromMaskedUint32x8: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint32x8(v) - case OpShiftAllRightAndFillUpperFromMaskedUint64x2: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint64x2(v) - case OpShiftAllRightAndFillUpperFromMaskedUint64x4: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint64x4(v) - case OpShiftAllRightAndFillUpperFromMaskedUint64x8: - return rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint64x8(v) - case OpShiftAllRightAndFillUpperFromUint16x16: + case OpShiftAllRightConcatMaskedInt16x16: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedInt16x16(v) + case OpShiftAllRightConcatMaskedInt16x32: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedInt16x32(v) + case OpShiftAllRightConcatMaskedInt16x8: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedInt16x8(v) + case OpShiftAllRightConcatMaskedInt32x16: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedInt32x16(v) + case OpShiftAllRightConcatMaskedInt32x4: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedInt32x4(v) + case OpShiftAllRightConcatMaskedInt32x8: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedInt32x8(v) + case OpShiftAllRightConcatMaskedInt64x2: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedInt64x2(v) + case OpShiftAllRightConcatMaskedInt64x4: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedInt64x4(v) + case OpShiftAllRightConcatMaskedInt64x8: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedInt64x8(v) + case OpShiftAllRightConcatMaskedUint16x16: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedUint16x16(v) + case OpShiftAllRightConcatMaskedUint16x32: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedUint16x32(v) + case OpShiftAllRightConcatMaskedUint16x8: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedUint16x8(v) + case OpShiftAllRightConcatMaskedUint32x16: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedUint32x16(v) + case OpShiftAllRightConcatMaskedUint32x4: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedUint32x4(v) + case OpShiftAllRightConcatMaskedUint32x8: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedUint32x8(v) + case OpShiftAllRightConcatMaskedUint64x2: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedUint64x2(v) + case OpShiftAllRightConcatMaskedUint64x4: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedUint64x4(v) + case OpShiftAllRightConcatMaskedUint64x8: + return rewriteValueAMD64_OpShiftAllRightConcatMaskedUint64x8(v) + case OpShiftAllRightConcatUint16x16: v.Op = OpAMD64VPSHRDW256 return true - case OpShiftAllRightAndFillUpperFromUint16x32: + case OpShiftAllRightConcatUint16x32: v.Op = OpAMD64VPSHRDW512 return true - case OpShiftAllRightAndFillUpperFromUint16x8: + case OpShiftAllRightConcatUint16x8: v.Op = OpAMD64VPSHRDW128 return true - case OpShiftAllRightAndFillUpperFromUint32x16: + case OpShiftAllRightConcatUint32x16: v.Op = OpAMD64VPSHRDD512 return true - case OpShiftAllRightAndFillUpperFromUint32x4: + case OpShiftAllRightConcatUint32x4: v.Op = OpAMD64VPSHRDD128 return true - case OpShiftAllRightAndFillUpperFromUint32x8: + case OpShiftAllRightConcatUint32x8: v.Op = OpAMD64VPSHRDD256 return true - case OpShiftAllRightAndFillUpperFromUint64x2: + case OpShiftAllRightConcatUint64x2: v.Op = OpAMD64VPSHRDQ128 return true - case OpShiftAllRightAndFillUpperFromUint64x4: + case OpShiftAllRightConcatUint64x4: v.Op = OpAMD64VPSHRDQ256 return true - case OpShiftAllRightAndFillUpperFromUint64x8: + case OpShiftAllRightConcatUint64x8: v.Op = OpAMD64VPSHRDQ512 return true case OpShiftAllRightInt16x16: @@ -4803,94 +4803,94 @@ func rewriteValueAMD64(v *Value) bool { case OpShiftAllRightUint64x8: v.Op = OpAMD64VPSRLQ512 return true - case OpShiftLeftAndFillUpperFromInt16x16: + case OpShiftLeftConcatInt16x16: v.Op = OpAMD64VPSHLDVW256 return true - case OpShiftLeftAndFillUpperFromInt16x32: + case OpShiftLeftConcatInt16x32: v.Op = OpAMD64VPSHLDVW512 return true - case OpShiftLeftAndFillUpperFromInt16x8: + case OpShiftLeftConcatInt16x8: v.Op = OpAMD64VPSHLDVW128 return true - case OpShiftLeftAndFillUpperFromInt32x16: + case OpShiftLeftConcatInt32x16: v.Op = OpAMD64VPSHLDVD512 return true - case OpShiftLeftAndFillUpperFromInt32x4: + case OpShiftLeftConcatInt32x4: v.Op = OpAMD64VPSHLDVD128 return true - case OpShiftLeftAndFillUpperFromInt32x8: + case OpShiftLeftConcatInt32x8: v.Op = OpAMD64VPSHLDVD256 return true - case OpShiftLeftAndFillUpperFromInt64x2: + case OpShiftLeftConcatInt64x2: v.Op = OpAMD64VPSHLDVQ128 return true - case OpShiftLeftAndFillUpperFromInt64x4: + case OpShiftLeftConcatInt64x4: v.Op = OpAMD64VPSHLDVQ256 return true - case OpShiftLeftAndFillUpperFromInt64x8: + case OpShiftLeftConcatInt64x8: v.Op = OpAMD64VPSHLDVQ512 return true - case OpShiftLeftAndFillUpperFromMaskedInt16x16: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt16x16(v) - case OpShiftLeftAndFillUpperFromMaskedInt16x32: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt16x32(v) - case OpShiftLeftAndFillUpperFromMaskedInt16x8: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt16x8(v) - case OpShiftLeftAndFillUpperFromMaskedInt32x16: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt32x16(v) - case OpShiftLeftAndFillUpperFromMaskedInt32x4: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt32x4(v) - case OpShiftLeftAndFillUpperFromMaskedInt32x8: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt32x8(v) - case OpShiftLeftAndFillUpperFromMaskedInt64x2: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt64x2(v) - case OpShiftLeftAndFillUpperFromMaskedInt64x4: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt64x4(v) - case OpShiftLeftAndFillUpperFromMaskedInt64x8: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt64x8(v) - case OpShiftLeftAndFillUpperFromMaskedUint16x16: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint16x16(v) - case OpShiftLeftAndFillUpperFromMaskedUint16x32: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint16x32(v) - case OpShiftLeftAndFillUpperFromMaskedUint16x8: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint16x8(v) - case OpShiftLeftAndFillUpperFromMaskedUint32x16: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint32x16(v) - case OpShiftLeftAndFillUpperFromMaskedUint32x4: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint32x4(v) - case OpShiftLeftAndFillUpperFromMaskedUint32x8: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint32x8(v) - case OpShiftLeftAndFillUpperFromMaskedUint64x2: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint64x2(v) - case OpShiftLeftAndFillUpperFromMaskedUint64x4: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint64x4(v) - case OpShiftLeftAndFillUpperFromMaskedUint64x8: - return rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint64x8(v) - case OpShiftLeftAndFillUpperFromUint16x16: + case OpShiftLeftConcatMaskedInt16x16: + return rewriteValueAMD64_OpShiftLeftConcatMaskedInt16x16(v) + case OpShiftLeftConcatMaskedInt16x32: + return rewriteValueAMD64_OpShiftLeftConcatMaskedInt16x32(v) + case OpShiftLeftConcatMaskedInt16x8: + return rewriteValueAMD64_OpShiftLeftConcatMaskedInt16x8(v) + case OpShiftLeftConcatMaskedInt32x16: + return rewriteValueAMD64_OpShiftLeftConcatMaskedInt32x16(v) + case OpShiftLeftConcatMaskedInt32x4: + return rewriteValueAMD64_OpShiftLeftConcatMaskedInt32x4(v) + case OpShiftLeftConcatMaskedInt32x8: + return rewriteValueAMD64_OpShiftLeftConcatMaskedInt32x8(v) + case OpShiftLeftConcatMaskedInt64x2: + return rewriteValueAMD64_OpShiftLeftConcatMaskedInt64x2(v) + case OpShiftLeftConcatMaskedInt64x4: + return rewriteValueAMD64_OpShiftLeftConcatMaskedInt64x4(v) + case OpShiftLeftConcatMaskedInt64x8: + return rewriteValueAMD64_OpShiftLeftConcatMaskedInt64x8(v) + case OpShiftLeftConcatMaskedUint16x16: + return rewriteValueAMD64_OpShiftLeftConcatMaskedUint16x16(v) + case OpShiftLeftConcatMaskedUint16x32: + return rewriteValueAMD64_OpShiftLeftConcatMaskedUint16x32(v) + case OpShiftLeftConcatMaskedUint16x8: + return rewriteValueAMD64_OpShiftLeftConcatMaskedUint16x8(v) + case OpShiftLeftConcatMaskedUint32x16: + return rewriteValueAMD64_OpShiftLeftConcatMaskedUint32x16(v) + case OpShiftLeftConcatMaskedUint32x4: + return rewriteValueAMD64_OpShiftLeftConcatMaskedUint32x4(v) + case OpShiftLeftConcatMaskedUint32x8: + return rewriteValueAMD64_OpShiftLeftConcatMaskedUint32x8(v) + case OpShiftLeftConcatMaskedUint64x2: + return rewriteValueAMD64_OpShiftLeftConcatMaskedUint64x2(v) + case OpShiftLeftConcatMaskedUint64x4: + return rewriteValueAMD64_OpShiftLeftConcatMaskedUint64x4(v) + case OpShiftLeftConcatMaskedUint64x8: + return rewriteValueAMD64_OpShiftLeftConcatMaskedUint64x8(v) + case OpShiftLeftConcatUint16x16: v.Op = OpAMD64VPSHLDVW256 return true - case OpShiftLeftAndFillUpperFromUint16x32: + case OpShiftLeftConcatUint16x32: v.Op = OpAMD64VPSHLDVW512 return true - case OpShiftLeftAndFillUpperFromUint16x8: + case OpShiftLeftConcatUint16x8: v.Op = OpAMD64VPSHLDVW128 return true - case OpShiftLeftAndFillUpperFromUint32x16: + case OpShiftLeftConcatUint32x16: v.Op = OpAMD64VPSHLDVD512 return true - case OpShiftLeftAndFillUpperFromUint32x4: + case OpShiftLeftConcatUint32x4: v.Op = OpAMD64VPSHLDVD128 return true - case OpShiftLeftAndFillUpperFromUint32x8: + case OpShiftLeftConcatUint32x8: v.Op = OpAMD64VPSHLDVD256 return true - case OpShiftLeftAndFillUpperFromUint64x2: + case OpShiftLeftConcatUint64x2: v.Op = OpAMD64VPSHLDVQ128 return true - case OpShiftLeftAndFillUpperFromUint64x4: + case OpShiftLeftConcatUint64x4: v.Op = OpAMD64VPSHLDVQ256 return true - case OpShiftLeftAndFillUpperFromUint64x8: + case OpShiftLeftConcatUint64x8: v.Op = OpAMD64VPSHLDVQ512 return true case OpShiftLeftInt16x16: @@ -4983,94 +4983,94 @@ func rewriteValueAMD64(v *Value) bool { case OpShiftLeftUint64x8: v.Op = OpAMD64VPSLLVQ512 return true - case OpShiftRightAndFillUpperFromInt16x16: + case OpShiftRightConcatInt16x16: v.Op = OpAMD64VPSHRDVW256 return true - case OpShiftRightAndFillUpperFromInt16x32: + case OpShiftRightConcatInt16x32: v.Op = OpAMD64VPSHRDVW512 return true - case OpShiftRightAndFillUpperFromInt16x8: + case OpShiftRightConcatInt16x8: v.Op = OpAMD64VPSHRDVW128 return true - case OpShiftRightAndFillUpperFromInt32x16: + case OpShiftRightConcatInt32x16: v.Op = OpAMD64VPSHRDVD512 return true - case OpShiftRightAndFillUpperFromInt32x4: + case OpShiftRightConcatInt32x4: v.Op = OpAMD64VPSHRDVD128 return true - case OpShiftRightAndFillUpperFromInt32x8: + case OpShiftRightConcatInt32x8: v.Op = OpAMD64VPSHRDVD256 return true - case OpShiftRightAndFillUpperFromInt64x2: + case OpShiftRightConcatInt64x2: v.Op = OpAMD64VPSHRDVQ128 return true - case OpShiftRightAndFillUpperFromInt64x4: + case OpShiftRightConcatInt64x4: v.Op = OpAMD64VPSHRDVQ256 return true - case OpShiftRightAndFillUpperFromInt64x8: + case OpShiftRightConcatInt64x8: v.Op = OpAMD64VPSHRDVQ512 return true - case OpShiftRightAndFillUpperFromMaskedInt16x16: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt16x16(v) - case OpShiftRightAndFillUpperFromMaskedInt16x32: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt16x32(v) - case OpShiftRightAndFillUpperFromMaskedInt16x8: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt16x8(v) - case OpShiftRightAndFillUpperFromMaskedInt32x16: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt32x16(v) - case OpShiftRightAndFillUpperFromMaskedInt32x4: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt32x4(v) - case OpShiftRightAndFillUpperFromMaskedInt32x8: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt32x8(v) - case OpShiftRightAndFillUpperFromMaskedInt64x2: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt64x2(v) - case OpShiftRightAndFillUpperFromMaskedInt64x4: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt64x4(v) - case OpShiftRightAndFillUpperFromMaskedInt64x8: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt64x8(v) - case OpShiftRightAndFillUpperFromMaskedUint16x16: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint16x16(v) - case OpShiftRightAndFillUpperFromMaskedUint16x32: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint16x32(v) - case OpShiftRightAndFillUpperFromMaskedUint16x8: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint16x8(v) - case OpShiftRightAndFillUpperFromMaskedUint32x16: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint32x16(v) - case OpShiftRightAndFillUpperFromMaskedUint32x4: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint32x4(v) - case OpShiftRightAndFillUpperFromMaskedUint32x8: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint32x8(v) - case OpShiftRightAndFillUpperFromMaskedUint64x2: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint64x2(v) - case OpShiftRightAndFillUpperFromMaskedUint64x4: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint64x4(v) - case OpShiftRightAndFillUpperFromMaskedUint64x8: - return rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint64x8(v) - case OpShiftRightAndFillUpperFromUint16x16: + case OpShiftRightConcatMaskedInt16x16: + return rewriteValueAMD64_OpShiftRightConcatMaskedInt16x16(v) + case OpShiftRightConcatMaskedInt16x32: + return rewriteValueAMD64_OpShiftRightConcatMaskedInt16x32(v) + case OpShiftRightConcatMaskedInt16x8: + return rewriteValueAMD64_OpShiftRightConcatMaskedInt16x8(v) + case OpShiftRightConcatMaskedInt32x16: + return rewriteValueAMD64_OpShiftRightConcatMaskedInt32x16(v) + case OpShiftRightConcatMaskedInt32x4: + return rewriteValueAMD64_OpShiftRightConcatMaskedInt32x4(v) + case OpShiftRightConcatMaskedInt32x8: + return rewriteValueAMD64_OpShiftRightConcatMaskedInt32x8(v) + case OpShiftRightConcatMaskedInt64x2: + return rewriteValueAMD64_OpShiftRightConcatMaskedInt64x2(v) + case OpShiftRightConcatMaskedInt64x4: + return rewriteValueAMD64_OpShiftRightConcatMaskedInt64x4(v) + case OpShiftRightConcatMaskedInt64x8: + return rewriteValueAMD64_OpShiftRightConcatMaskedInt64x8(v) + case OpShiftRightConcatMaskedUint16x16: + return rewriteValueAMD64_OpShiftRightConcatMaskedUint16x16(v) + case OpShiftRightConcatMaskedUint16x32: + return rewriteValueAMD64_OpShiftRightConcatMaskedUint16x32(v) + case OpShiftRightConcatMaskedUint16x8: + return rewriteValueAMD64_OpShiftRightConcatMaskedUint16x8(v) + case OpShiftRightConcatMaskedUint32x16: + return rewriteValueAMD64_OpShiftRightConcatMaskedUint32x16(v) + case OpShiftRightConcatMaskedUint32x4: + return rewriteValueAMD64_OpShiftRightConcatMaskedUint32x4(v) + case OpShiftRightConcatMaskedUint32x8: + return rewriteValueAMD64_OpShiftRightConcatMaskedUint32x8(v) + case OpShiftRightConcatMaskedUint64x2: + return rewriteValueAMD64_OpShiftRightConcatMaskedUint64x2(v) + case OpShiftRightConcatMaskedUint64x4: + return rewriteValueAMD64_OpShiftRightConcatMaskedUint64x4(v) + case OpShiftRightConcatMaskedUint64x8: + return rewriteValueAMD64_OpShiftRightConcatMaskedUint64x8(v) + case OpShiftRightConcatUint16x16: v.Op = OpAMD64VPSHRDVW256 return true - case OpShiftRightAndFillUpperFromUint16x32: + case OpShiftRightConcatUint16x32: v.Op = OpAMD64VPSHRDVW512 return true - case OpShiftRightAndFillUpperFromUint16x8: + case OpShiftRightConcatUint16x8: v.Op = OpAMD64VPSHRDVW128 return true - case OpShiftRightAndFillUpperFromUint32x16: + case OpShiftRightConcatUint32x16: v.Op = OpAMD64VPSHRDVD512 return true - case OpShiftRightAndFillUpperFromUint32x4: + case OpShiftRightConcatUint32x4: v.Op = OpAMD64VPSHRDVD128 return true - case OpShiftRightAndFillUpperFromUint32x8: + case OpShiftRightConcatUint32x8: v.Op = OpAMD64VPSHRDVD256 return true - case OpShiftRightAndFillUpperFromUint64x2: + case OpShiftRightConcatUint64x2: v.Op = OpAMD64VPSHRDVQ128 return true - case OpShiftRightAndFillUpperFromUint64x4: + case OpShiftRightConcatUint64x4: v.Op = OpAMD64VPSHRDVQ256 return true - case OpShiftRightAndFillUpperFromUint64x8: + case OpShiftRightConcatUint64x8: v.Op = OpAMD64VPSHRDVQ512 return true case OpShiftRightInt16x16: @@ -50752,12 +50752,12 @@ func rewriteValueAMD64_OpSelectN(v *Value) bool { } return false } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt16x16(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt16x16(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedInt16x16 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedInt16x16 [a] x y mask) // result: (VPSHLDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50772,12 +50772,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt16x16(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt16x32(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt16x32(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedInt16x32 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedInt16x32 [a] x y mask) // result: (VPSHLDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50792,12 +50792,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt16x32(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt16x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt16x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedInt16x8 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedInt16x8 [a] x y mask) // result: (VPSHLDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50812,12 +50812,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt16x8(v *Value) boo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt32x16(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt32x16(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedInt32x16 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedInt32x16 [a] x y mask) // result: (VPSHLDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50832,12 +50832,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt32x16(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt32x4(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt32x4(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedInt32x4 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedInt32x4 [a] x y mask) // result: (VPSHLDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50852,12 +50852,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt32x4(v *Value) boo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt32x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt32x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedInt32x8 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedInt32x8 [a] x y mask) // result: (VPSHLDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50872,12 +50872,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt32x8(v *Value) boo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt64x2(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt64x2(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedInt64x2 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedInt64x2 [a] x y mask) // result: (VPSHLDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50892,12 +50892,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt64x2(v *Value) boo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt64x4(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt64x4(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedInt64x4 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedInt64x4 [a] x y mask) // result: (VPSHLDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50912,12 +50912,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt64x4(v *Value) boo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt64x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedInt64x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedInt64x8 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedInt64x8 [a] x y mask) // result: (VPSHLDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50932,12 +50932,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedInt64x8(v *Value) boo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint16x16(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint16x16(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedUint16x16 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedUint16x16 [a] x y mask) // result: (VPSHLDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50952,12 +50952,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint16x16(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint16x32(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint16x32(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedUint16x32 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedUint16x32 [a] x y mask) // result: (VPSHLDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50972,12 +50972,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint16x32(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint16x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint16x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedUint16x8 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedUint16x8 [a] x y mask) // result: (VPSHLDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -50992,12 +50992,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint16x8(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint32x16(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint32x16(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedUint32x16 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedUint32x16 [a] x y mask) // result: (VPSHLDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51012,12 +51012,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint32x16(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint32x4(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint32x4(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedUint32x4 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedUint32x4 [a] x y mask) // result: (VPSHLDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51032,12 +51032,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint32x4(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint32x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint32x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedUint32x8 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedUint32x8 [a] x y mask) // result: (VPSHLDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51052,12 +51052,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint32x8(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint64x2(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint64x2(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedUint64x2 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedUint64x2 [a] x y mask) // result: (VPSHLDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51072,12 +51072,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint64x2(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint64x4(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint64x4(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedUint64x4 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedUint64x4 [a] x y mask) // result: (VPSHLDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51092,12 +51092,12 @@ func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint64x4(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllLeftAndFillUpperFromMaskedUint64x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllLeftConcatMaskedUint64x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllLeftAndFillUpperFromMaskedUint64x8 [a] x y mask) + // match: (ShiftAllLeftConcatMaskedUint64x8 [a] x y mask) // result: (VPSHLDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51436,12 +51436,12 @@ func rewriteValueAMD64_OpShiftAllLeftMaskedUint64x8(v *Value) bool { return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt16x16(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedInt16x16(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedInt16x16 [a] x y mask) + // match: (ShiftAllRightConcatMaskedInt16x16 [a] x y mask) // result: (VPSHRDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51456,12 +51456,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt16x16(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt16x32(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedInt16x32(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedInt16x32 [a] x y mask) + // match: (ShiftAllRightConcatMaskedInt16x32 [a] x y mask) // result: (VPSHRDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51476,12 +51476,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt16x32(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt16x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedInt16x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedInt16x8 [a] x y mask) + // match: (ShiftAllRightConcatMaskedInt16x8 [a] x y mask) // result: (VPSHRDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51496,12 +51496,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt16x8(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt32x16(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedInt32x16(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedInt32x16 [a] x y mask) + // match: (ShiftAllRightConcatMaskedInt32x16 [a] x y mask) // result: (VPSHRDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51516,12 +51516,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt32x16(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt32x4(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedInt32x4(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedInt32x4 [a] x y mask) + // match: (ShiftAllRightConcatMaskedInt32x4 [a] x y mask) // result: (VPSHRDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51536,12 +51536,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt32x4(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt32x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedInt32x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedInt32x8 [a] x y mask) + // match: (ShiftAllRightConcatMaskedInt32x8 [a] x y mask) // result: (VPSHRDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51556,12 +51556,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt32x8(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt64x2(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedInt64x2(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedInt64x2 [a] x y mask) + // match: (ShiftAllRightConcatMaskedInt64x2 [a] x y mask) // result: (VPSHRDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51576,12 +51576,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt64x2(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt64x4(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedInt64x4(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedInt64x4 [a] x y mask) + // match: (ShiftAllRightConcatMaskedInt64x4 [a] x y mask) // result: (VPSHRDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51596,12 +51596,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt64x4(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt64x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedInt64x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedInt64x8 [a] x y mask) + // match: (ShiftAllRightConcatMaskedInt64x8 [a] x y mask) // result: (VPSHRDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51616,12 +51616,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedInt64x8(v *Value) bo return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint16x16(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedUint16x16(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedUint16x16 [a] x y mask) + // match: (ShiftAllRightConcatMaskedUint16x16 [a] x y mask) // result: (VPSHRDWMasked256 [a] x y (VPMOVVec16x16ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51636,12 +51636,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint16x16(v *Value) return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint16x32(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedUint16x32(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedUint16x32 [a] x y mask) + // match: (ShiftAllRightConcatMaskedUint16x32 [a] x y mask) // result: (VPSHRDWMasked512 [a] x y (VPMOVVec16x32ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51656,12 +51656,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint16x32(v *Value) return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint16x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedUint16x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedUint16x8 [a] x y mask) + // match: (ShiftAllRightConcatMaskedUint16x8 [a] x y mask) // result: (VPSHRDWMasked128 [a] x y (VPMOVVec16x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51676,12 +51676,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint16x8(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint32x16(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedUint32x16(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedUint32x16 [a] x y mask) + // match: (ShiftAllRightConcatMaskedUint32x16 [a] x y mask) // result: (VPSHRDDMasked512 [a] x y (VPMOVVec32x16ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51696,12 +51696,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint32x16(v *Value) return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint32x4(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedUint32x4(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedUint32x4 [a] x y mask) + // match: (ShiftAllRightConcatMaskedUint32x4 [a] x y mask) // result: (VPSHRDDMasked128 [a] x y (VPMOVVec32x4ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51716,12 +51716,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint32x4(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint32x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedUint32x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedUint32x8 [a] x y mask) + // match: (ShiftAllRightConcatMaskedUint32x8 [a] x y mask) // result: (VPSHRDDMasked256 [a] x y (VPMOVVec32x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51736,12 +51736,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint32x8(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint64x2(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedUint64x2(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedUint64x2 [a] x y mask) + // match: (ShiftAllRightConcatMaskedUint64x2 [a] x y mask) // result: (VPSHRDQMasked128 [a] x y (VPMOVVec64x2ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51756,12 +51756,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint64x2(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint64x4(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedUint64x4(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedUint64x4 [a] x y mask) + // match: (ShiftAllRightConcatMaskedUint64x4 [a] x y mask) // result: (VPSHRDQMasked256 [a] x y (VPMOVVec64x4ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -51776,12 +51776,12 @@ func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint64x4(v *Value) b return true } } -func rewriteValueAMD64_OpShiftAllRightAndFillUpperFromMaskedUint64x8(v *Value) bool { +func rewriteValueAMD64_OpShiftAllRightConcatMaskedUint64x8(v *Value) bool { v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftAllRightAndFillUpperFromMaskedUint64x8 [a] x y mask) + // match: (ShiftAllRightConcatMaskedUint64x8 [a] x y mask) // result: (VPSHRDQMasked512 [a] x y (VPMOVVec64x8ToM mask)) for { a := auxIntToInt8(v.AuxInt) @@ -52120,13 +52120,13 @@ func rewriteValueAMD64_OpShiftAllRightMaskedUint64x8(v *Value) bool { return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt16x16(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedInt16x16(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedInt16x16 x y z mask) + // match: (ShiftLeftConcatMaskedInt16x16 x y z mask) // result: (VPSHLDVWMasked256 x y z (VPMOVVec16x16ToM mask)) for { x := v_0 @@ -52140,13 +52140,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt16x16(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt16x32(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedInt16x32(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedInt16x32 x y z mask) + // match: (ShiftLeftConcatMaskedInt16x32 x y z mask) // result: (VPSHLDVWMasked512 x y z (VPMOVVec16x32ToM mask)) for { x := v_0 @@ -52160,13 +52160,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt16x32(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt16x8(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedInt16x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedInt16x8 x y z mask) + // match: (ShiftLeftConcatMaskedInt16x8 x y z mask) // result: (VPSHLDVWMasked128 x y z (VPMOVVec16x8ToM mask)) for { x := v_0 @@ -52180,13 +52180,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt16x8(v *Value) bool { return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt32x16(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedInt32x16(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedInt32x16 x y z mask) + // match: (ShiftLeftConcatMaskedInt32x16 x y z mask) // result: (VPSHLDVDMasked512 x y z (VPMOVVec32x16ToM mask)) for { x := v_0 @@ -52200,13 +52200,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt32x16(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt32x4(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedInt32x4(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedInt32x4 x y z mask) + // match: (ShiftLeftConcatMaskedInt32x4 x y z mask) // result: (VPSHLDVDMasked128 x y z (VPMOVVec32x4ToM mask)) for { x := v_0 @@ -52220,13 +52220,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt32x4(v *Value) bool { return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt32x8(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedInt32x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedInt32x8 x y z mask) + // match: (ShiftLeftConcatMaskedInt32x8 x y z mask) // result: (VPSHLDVDMasked256 x y z (VPMOVVec32x8ToM mask)) for { x := v_0 @@ -52240,13 +52240,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt32x8(v *Value) bool { return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt64x2(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedInt64x2(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedInt64x2 x y z mask) + // match: (ShiftLeftConcatMaskedInt64x2 x y z mask) // result: (VPSHLDVQMasked128 x y z (VPMOVVec64x2ToM mask)) for { x := v_0 @@ -52260,13 +52260,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt64x2(v *Value) bool { return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt64x4(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedInt64x4(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedInt64x4 x y z mask) + // match: (ShiftLeftConcatMaskedInt64x4 x y z mask) // result: (VPSHLDVQMasked256 x y z (VPMOVVec64x4ToM mask)) for { x := v_0 @@ -52280,13 +52280,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt64x4(v *Value) bool { return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt64x8(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedInt64x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedInt64x8 x y z mask) + // match: (ShiftLeftConcatMaskedInt64x8 x y z mask) // result: (VPSHLDVQMasked512 x y z (VPMOVVec64x8ToM mask)) for { x := v_0 @@ -52300,13 +52300,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedInt64x8(v *Value) bool { return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint16x16(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedUint16x16(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedUint16x16 x y z mask) + // match: (ShiftLeftConcatMaskedUint16x16 x y z mask) // result: (VPSHLDVWMasked256 x y z (VPMOVVec16x16ToM mask)) for { x := v_0 @@ -52320,13 +52320,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint16x16(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint16x32(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedUint16x32(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedUint16x32 x y z mask) + // match: (ShiftLeftConcatMaskedUint16x32 x y z mask) // result: (VPSHLDVWMasked512 x y z (VPMOVVec16x32ToM mask)) for { x := v_0 @@ -52340,13 +52340,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint16x32(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint16x8(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedUint16x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedUint16x8 x y z mask) + // match: (ShiftLeftConcatMaskedUint16x8 x y z mask) // result: (VPSHLDVWMasked128 x y z (VPMOVVec16x8ToM mask)) for { x := v_0 @@ -52360,13 +52360,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint16x8(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint32x16(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedUint32x16(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedUint32x16 x y z mask) + // match: (ShiftLeftConcatMaskedUint32x16 x y z mask) // result: (VPSHLDVDMasked512 x y z (VPMOVVec32x16ToM mask)) for { x := v_0 @@ -52380,13 +52380,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint32x16(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint32x4(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedUint32x4(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedUint32x4 x y z mask) + // match: (ShiftLeftConcatMaskedUint32x4 x y z mask) // result: (VPSHLDVDMasked128 x y z (VPMOVVec32x4ToM mask)) for { x := v_0 @@ -52400,13 +52400,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint32x4(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint32x8(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedUint32x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedUint32x8 x y z mask) + // match: (ShiftLeftConcatMaskedUint32x8 x y z mask) // result: (VPSHLDVDMasked256 x y z (VPMOVVec32x8ToM mask)) for { x := v_0 @@ -52420,13 +52420,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint32x8(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint64x2(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedUint64x2(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedUint64x2 x y z mask) + // match: (ShiftLeftConcatMaskedUint64x2 x y z mask) // result: (VPSHLDVQMasked128 x y z (VPMOVVec64x2ToM mask)) for { x := v_0 @@ -52440,13 +52440,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint64x2(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint64x4(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedUint64x4(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedUint64x4 x y z mask) + // match: (ShiftLeftConcatMaskedUint64x4 x y z mask) // result: (VPSHLDVQMasked256 x y z (VPMOVVec64x4ToM mask)) for { x := v_0 @@ -52460,13 +52460,13 @@ func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint64x4(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftLeftAndFillUpperFromMaskedUint64x8(v *Value) bool { +func rewriteValueAMD64_OpShiftLeftConcatMaskedUint64x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftLeftAndFillUpperFromMaskedUint64x8 x y z mask) + // match: (ShiftLeftConcatMaskedUint64x8 x y z mask) // result: (VPSHLDVQMasked512 x y z (VPMOVVec64x8ToM mask)) for { x := v_0 @@ -52804,13 +52804,13 @@ func rewriteValueAMD64_OpShiftLeftMaskedUint64x8(v *Value) bool { return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt16x16(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedInt16x16(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedInt16x16 x y z mask) + // match: (ShiftRightConcatMaskedInt16x16 x y z mask) // result: (VPSHRDVWMasked256 x y z (VPMOVVec16x16ToM mask)) for { x := v_0 @@ -52824,13 +52824,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt16x16(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt16x32(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedInt16x32(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedInt16x32 x y z mask) + // match: (ShiftRightConcatMaskedInt16x32 x y z mask) // result: (VPSHRDVWMasked512 x y z (VPMOVVec16x32ToM mask)) for { x := v_0 @@ -52844,13 +52844,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt16x32(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt16x8(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedInt16x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedInt16x8 x y z mask) + // match: (ShiftRightConcatMaskedInt16x8 x y z mask) // result: (VPSHRDVWMasked128 x y z (VPMOVVec16x8ToM mask)) for { x := v_0 @@ -52864,13 +52864,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt16x8(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt32x16(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedInt32x16(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedInt32x16 x y z mask) + // match: (ShiftRightConcatMaskedInt32x16 x y z mask) // result: (VPSHRDVDMasked512 x y z (VPMOVVec32x16ToM mask)) for { x := v_0 @@ -52884,13 +52884,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt32x16(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt32x4(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedInt32x4(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedInt32x4 x y z mask) + // match: (ShiftRightConcatMaskedInt32x4 x y z mask) // result: (VPSHRDVDMasked128 x y z (VPMOVVec32x4ToM mask)) for { x := v_0 @@ -52904,13 +52904,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt32x4(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt32x8(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedInt32x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedInt32x8 x y z mask) + // match: (ShiftRightConcatMaskedInt32x8 x y z mask) // result: (VPSHRDVDMasked256 x y z (VPMOVVec32x8ToM mask)) for { x := v_0 @@ -52924,13 +52924,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt32x8(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt64x2(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedInt64x2(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedInt64x2 x y z mask) + // match: (ShiftRightConcatMaskedInt64x2 x y z mask) // result: (VPSHRDVQMasked128 x y z (VPMOVVec64x2ToM mask)) for { x := v_0 @@ -52944,13 +52944,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt64x2(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt64x4(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedInt64x4(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedInt64x4 x y z mask) + // match: (ShiftRightConcatMaskedInt64x4 x y z mask) // result: (VPSHRDVQMasked256 x y z (VPMOVVec64x4ToM mask)) for { x := v_0 @@ -52964,13 +52964,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt64x4(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt64x8(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedInt64x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedInt64x8 x y z mask) + // match: (ShiftRightConcatMaskedInt64x8 x y z mask) // result: (VPSHRDVQMasked512 x y z (VPMOVVec64x8ToM mask)) for { x := v_0 @@ -52984,13 +52984,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedInt64x8(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint16x16(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedUint16x16(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedUint16x16 x y z mask) + // match: (ShiftRightConcatMaskedUint16x16 x y z mask) // result: (VPSHRDVWMasked256 x y z (VPMOVVec16x16ToM mask)) for { x := v_0 @@ -53004,13 +53004,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint16x16(v *Value) boo return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint16x32(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedUint16x32(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedUint16x32 x y z mask) + // match: (ShiftRightConcatMaskedUint16x32 x y z mask) // result: (VPSHRDVWMasked512 x y z (VPMOVVec16x32ToM mask)) for { x := v_0 @@ -53024,13 +53024,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint16x32(v *Value) boo return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint16x8(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedUint16x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedUint16x8 x y z mask) + // match: (ShiftRightConcatMaskedUint16x8 x y z mask) // result: (VPSHRDVWMasked128 x y z (VPMOVVec16x8ToM mask)) for { x := v_0 @@ -53044,13 +53044,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint16x8(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint32x16(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedUint32x16(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedUint32x16 x y z mask) + // match: (ShiftRightConcatMaskedUint32x16 x y z mask) // result: (VPSHRDVDMasked512 x y z (VPMOVVec32x16ToM mask)) for { x := v_0 @@ -53064,13 +53064,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint32x16(v *Value) boo return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint32x4(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedUint32x4(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedUint32x4 x y z mask) + // match: (ShiftRightConcatMaskedUint32x4 x y z mask) // result: (VPSHRDVDMasked128 x y z (VPMOVVec32x4ToM mask)) for { x := v_0 @@ -53084,13 +53084,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint32x4(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint32x8(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedUint32x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedUint32x8 x y z mask) + // match: (ShiftRightConcatMaskedUint32x8 x y z mask) // result: (VPSHRDVDMasked256 x y z (VPMOVVec32x8ToM mask)) for { x := v_0 @@ -53104,13 +53104,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint32x8(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint64x2(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedUint64x2(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedUint64x2 x y z mask) + // match: (ShiftRightConcatMaskedUint64x2 x y z mask) // result: (VPSHRDVQMasked128 x y z (VPMOVVec64x2ToM mask)) for { x := v_0 @@ -53124,13 +53124,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint64x2(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint64x4(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedUint64x4(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedUint64x4 x y z mask) + // match: (ShiftRightConcatMaskedUint64x4 x y z mask) // result: (VPSHRDVQMasked256 x y z (VPMOVVec64x4ToM mask)) for { x := v_0 @@ -53144,13 +53144,13 @@ func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint64x4(v *Value) bool return true } } -func rewriteValueAMD64_OpShiftRightAndFillUpperFromMaskedUint64x8(v *Value) bool { +func rewriteValueAMD64_OpShiftRightConcatMaskedUint64x8(v *Value) bool { v_3 := v.Args[3] v_2 := v.Args[2] v_1 := v.Args[1] v_0 := v.Args[0] b := v.Block - // match: (ShiftRightAndFillUpperFromMaskedUint64x8 x y z mask) + // match: (ShiftRightConcatMaskedUint64x8 x y z mask) // result: (VPSHRDVQMasked512 x y z (VPMOVVec64x8ToM mask)) for { x := v_0 diff --git a/src/cmd/compile/internal/ssagen/simdintrinsics.go b/src/cmd/compile/internal/ssagen/simdintrinsics.go index a30144cbd1..d6c5b889ed 100644 --- a/src/cmd/compile/internal/ssagen/simdintrinsics.go +++ b/src/cmd/compile/internal/ssagen/simdintrinsics.go @@ -1412,42 +1412,42 @@ func simdIntrinsics(addF func(pkg, fn string, b intrinsicBuilder, archFamilies . addF(simdPackage, "Uint64x2.ShiftAllLeft", opLen2(ssa.OpShiftAllLeftUint64x2, types.TypeVec128), sys.AMD64) addF(simdPackage, "Uint64x4.ShiftAllLeft", opLen2(ssa.OpShiftAllLeftUint64x4, types.TypeVec256), sys.AMD64) addF(simdPackage, "Uint64x8.ShiftAllLeft", opLen2(ssa.OpShiftAllLeftUint64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int16x8.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromInt16x8, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int16x16.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromInt16x16, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int16x32.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromInt16x32, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int32x4.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromInt32x4, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int32x8.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromInt32x8, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int32x16.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromInt32x16, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int64x2.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromInt64x2, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int64x4.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromInt64x4, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int64x8.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromInt64x8, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint16x8.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromUint16x8, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint16x16.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromUint16x16, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint16x32.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromUint16x32, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint32x4.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromUint32x4, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint32x8.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromUint32x8, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint32x16.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromUint32x16, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint64x2.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromUint64x2, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint64x4.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromUint64x4, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint64x8.ShiftAllLeftAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllLeftAndFillUpperFromUint64x8, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int16x8.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedInt16x8, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int16x16.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedInt16x16, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int16x32.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedInt16x32, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int32x4.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedInt32x4, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int32x8.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedInt32x8, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int32x16.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedInt32x16, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int64x2.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedInt64x2, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int64x4.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedInt64x4, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int64x8.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedInt64x8, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint16x8.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedUint16x8, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint16x16.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedUint16x16, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint16x32.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedUint16x32, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint32x4.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedUint32x4, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint32x8.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedUint32x8, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint32x16.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedUint32x16, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint64x2.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedUint64x2, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint64x4.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedUint64x4, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint64x8.ShiftAllLeftAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllLeftAndFillUpperFromMaskedUint64x8, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int16x8.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatInt16x8, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int16x16.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatInt16x16, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int16x32.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatInt16x32, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int32x4.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatInt32x4, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int32x8.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatInt32x8, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int32x16.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatInt32x16, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int64x2.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatInt64x2, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int64x4.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatInt64x4, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int64x8.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatInt64x8, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint16x8.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatUint16x8, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint16x16.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatUint16x16, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint16x32.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatUint16x32, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint32x4.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatUint32x4, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint32x8.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatUint32x8, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint32x16.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatUint32x16, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint64x2.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatUint64x2, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint64x4.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatUint64x4, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint64x8.ShiftAllLeftConcat", opLen2Imm8(ssa.OpShiftAllLeftConcatUint64x8, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int16x8.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedInt16x8, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int16x16.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedInt16x16, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int16x32.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedInt16x32, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int32x4.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedInt32x4, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int32x8.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedInt32x8, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int32x16.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedInt32x16, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int64x2.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedInt64x2, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int64x4.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedInt64x4, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int64x8.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedInt64x8, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint16x8.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedUint16x8, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint16x16.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedUint16x16, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint16x32.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedUint16x32, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint32x4.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedUint32x4, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint32x8.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedUint32x8, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint32x16.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedUint32x16, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint64x2.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedUint64x2, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint64x4.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedUint64x4, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint64x8.ShiftAllLeftConcatMasked", opLen3Imm8(ssa.OpShiftAllLeftConcatMaskedUint64x8, types.TypeVec512, 0), sys.AMD64) addF(simdPackage, "Int16x8.ShiftAllLeftMasked", opLen3(ssa.OpShiftAllLeftMaskedInt16x8, types.TypeVec128), sys.AMD64) addF(simdPackage, "Int16x16.ShiftAllLeftMasked", opLen3(ssa.OpShiftAllLeftMaskedInt16x16, types.TypeVec256), sys.AMD64) addF(simdPackage, "Int16x32.ShiftAllLeftMasked", opLen3(ssa.OpShiftAllLeftMaskedInt16x32, types.TypeVec512), sys.AMD64) @@ -1484,42 +1484,42 @@ func simdIntrinsics(addF func(pkg, fn string, b intrinsicBuilder, archFamilies . addF(simdPackage, "Uint64x2.ShiftAllRight", opLen2(ssa.OpShiftAllRightUint64x2, types.TypeVec128), sys.AMD64) addF(simdPackage, "Uint64x4.ShiftAllRight", opLen2(ssa.OpShiftAllRightUint64x4, types.TypeVec256), sys.AMD64) addF(simdPackage, "Uint64x8.ShiftAllRight", opLen2(ssa.OpShiftAllRightUint64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int16x8.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromInt16x8, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int16x16.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromInt16x16, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int16x32.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromInt16x32, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int32x4.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromInt32x4, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int32x8.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromInt32x8, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int32x16.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromInt32x16, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int64x2.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromInt64x2, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int64x4.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromInt64x4, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int64x8.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromInt64x8, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint16x8.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromUint16x8, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint16x16.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromUint16x16, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint16x32.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromUint16x32, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint32x4.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromUint32x4, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint32x8.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromUint32x8, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint32x16.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromUint32x16, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint64x2.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromUint64x2, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint64x4.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromUint64x4, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint64x8.ShiftAllRightAndFillUpperFrom", opLen2Imm8(ssa.OpShiftAllRightAndFillUpperFromUint64x8, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int16x8.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedInt16x8, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int16x16.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedInt16x16, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int16x32.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedInt16x32, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int32x4.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedInt32x4, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int32x8.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedInt32x8, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int32x16.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedInt32x16, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Int64x2.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedInt64x2, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Int64x4.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedInt64x4, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Int64x8.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedInt64x8, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint16x8.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedUint16x8, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint16x16.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedUint16x16, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint16x32.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedUint16x32, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint32x4.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedUint32x4, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint32x8.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedUint32x8, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint32x16.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedUint32x16, types.TypeVec512, 0), sys.AMD64) - addF(simdPackage, "Uint64x2.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedUint64x2, types.TypeVec128, 0), sys.AMD64) - addF(simdPackage, "Uint64x4.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedUint64x4, types.TypeVec256, 0), sys.AMD64) - addF(simdPackage, "Uint64x8.ShiftAllRightAndFillUpperFromMasked", opLen3Imm8(ssa.OpShiftAllRightAndFillUpperFromMaskedUint64x8, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int16x8.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatInt16x8, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int16x16.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatInt16x16, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int16x32.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatInt16x32, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int32x4.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatInt32x4, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int32x8.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatInt32x8, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int32x16.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatInt32x16, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int64x2.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatInt64x2, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int64x4.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatInt64x4, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int64x8.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatInt64x8, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint16x8.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatUint16x8, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint16x16.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatUint16x16, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint16x32.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatUint16x32, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint32x4.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatUint32x4, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint32x8.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatUint32x8, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint32x16.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatUint32x16, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint64x2.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatUint64x2, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint64x4.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatUint64x4, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint64x8.ShiftAllRightConcat", opLen2Imm8(ssa.OpShiftAllRightConcatUint64x8, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int16x8.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedInt16x8, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int16x16.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedInt16x16, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int16x32.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedInt16x32, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int32x4.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedInt32x4, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int32x8.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedInt32x8, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int32x16.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedInt32x16, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Int64x2.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedInt64x2, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Int64x4.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedInt64x4, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Int64x8.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedInt64x8, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint16x8.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedUint16x8, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint16x16.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedUint16x16, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint16x32.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedUint16x32, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint32x4.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedUint32x4, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint32x8.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedUint32x8, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint32x16.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedUint32x16, types.TypeVec512, 0), sys.AMD64) + addF(simdPackage, "Uint64x2.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedUint64x2, types.TypeVec128, 0), sys.AMD64) + addF(simdPackage, "Uint64x4.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedUint64x4, types.TypeVec256, 0), sys.AMD64) + addF(simdPackage, "Uint64x8.ShiftAllRightConcatMasked", opLen3Imm8(ssa.OpShiftAllRightConcatMaskedUint64x8, types.TypeVec512, 0), sys.AMD64) addF(simdPackage, "Int16x8.ShiftAllRightMasked", opLen3(ssa.OpShiftAllRightMaskedInt16x8, types.TypeVec128), sys.AMD64) addF(simdPackage, "Int16x16.ShiftAllRightMasked", opLen3(ssa.OpShiftAllRightMaskedInt16x16, types.TypeVec256), sys.AMD64) addF(simdPackage, "Int16x32.ShiftAllRightMasked", opLen3(ssa.OpShiftAllRightMaskedInt16x32, types.TypeVec512), sys.AMD64) @@ -1556,42 +1556,42 @@ func simdIntrinsics(addF func(pkg, fn string, b intrinsicBuilder, archFamilies . addF(simdPackage, "Uint64x2.ShiftLeft", opLen2(ssa.OpShiftLeftUint64x2, types.TypeVec128), sys.AMD64) addF(simdPackage, "Uint64x4.ShiftLeft", opLen2(ssa.OpShiftLeftUint64x4, types.TypeVec256), sys.AMD64) addF(simdPackage, "Uint64x8.ShiftLeft", opLen2(ssa.OpShiftLeftUint64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int16x8.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromInt16x8, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int16x16.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromInt16x16, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int16x32.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromInt16x32, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int32x4.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromInt32x4, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int32x8.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromInt32x8, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int32x16.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromInt32x16, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int64x2.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromInt64x2, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int64x4.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromInt64x4, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int64x8.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromInt64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint16x8.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromUint16x8, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint16x16.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromUint16x16, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint16x32.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromUint16x32, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint32x4.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromUint32x4, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint32x8.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromUint32x8, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint32x16.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromUint32x16, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint64x2.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromUint64x2, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint64x4.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromUint64x4, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint64x8.ShiftLeftAndFillUpperFrom", opLen3(ssa.OpShiftLeftAndFillUpperFromUint64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int16x8.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedInt16x8, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int16x16.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedInt16x16, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int16x32.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedInt16x32, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int32x4.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedInt32x4, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int32x8.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedInt32x8, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int32x16.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedInt32x16, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int64x2.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedInt64x2, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int64x4.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedInt64x4, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int64x8.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedInt64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint16x8.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedUint16x8, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint16x16.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedUint16x16, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint16x32.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedUint16x32, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint32x4.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedUint32x4, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint32x8.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedUint32x8, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint32x16.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedUint32x16, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint64x2.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedUint64x2, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint64x4.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedUint64x4, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint64x8.ShiftLeftAndFillUpperFromMasked", opLen4(ssa.OpShiftLeftAndFillUpperFromMaskedUint64x8, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int16x8.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatInt16x8, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int16x16.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatInt16x16, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int16x32.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatInt16x32, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int32x4.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatInt32x4, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int32x8.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatInt32x8, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int32x16.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatInt32x16, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int64x2.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatInt64x2, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int64x4.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatInt64x4, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int64x8.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatInt64x8, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint16x8.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatUint16x8, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint16x16.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatUint16x16, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint16x32.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatUint16x32, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint32x4.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatUint32x4, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint32x8.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatUint32x8, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint32x16.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatUint32x16, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint64x2.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatUint64x2, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint64x4.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatUint64x4, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint64x8.ShiftLeftConcat", opLen3(ssa.OpShiftLeftConcatUint64x8, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int16x8.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedInt16x8, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int16x16.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedInt16x16, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int16x32.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedInt16x32, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int32x4.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedInt32x4, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int32x8.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedInt32x8, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int32x16.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedInt32x16, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int64x2.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedInt64x2, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int64x4.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedInt64x4, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int64x8.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedInt64x8, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint16x8.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedUint16x8, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint16x16.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedUint16x16, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint16x32.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedUint16x32, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint32x4.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedUint32x4, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint32x8.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedUint32x8, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint32x16.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedUint32x16, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint64x2.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedUint64x2, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint64x4.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedUint64x4, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint64x8.ShiftLeftConcatMasked", opLen4(ssa.OpShiftLeftConcatMaskedUint64x8, types.TypeVec512), sys.AMD64) addF(simdPackage, "Int16x8.ShiftLeftMasked", opLen3(ssa.OpShiftLeftMaskedInt16x8, types.TypeVec128), sys.AMD64) addF(simdPackage, "Int16x16.ShiftLeftMasked", opLen3(ssa.OpShiftLeftMaskedInt16x16, types.TypeVec256), sys.AMD64) addF(simdPackage, "Int16x32.ShiftLeftMasked", opLen3(ssa.OpShiftLeftMaskedInt16x32, types.TypeVec512), sys.AMD64) @@ -1628,42 +1628,42 @@ func simdIntrinsics(addF func(pkg, fn string, b intrinsicBuilder, archFamilies . addF(simdPackage, "Uint64x2.ShiftRight", opLen2(ssa.OpShiftRightUint64x2, types.TypeVec128), sys.AMD64) addF(simdPackage, "Uint64x4.ShiftRight", opLen2(ssa.OpShiftRightUint64x4, types.TypeVec256), sys.AMD64) addF(simdPackage, "Uint64x8.ShiftRight", opLen2(ssa.OpShiftRightUint64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int16x8.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromInt16x8, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int16x16.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromInt16x16, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int16x32.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromInt16x32, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int32x4.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromInt32x4, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int32x8.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromInt32x8, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int32x16.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromInt32x16, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int64x2.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromInt64x2, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int64x4.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromInt64x4, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int64x8.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromInt64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint16x8.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromUint16x8, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint16x16.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromUint16x16, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint16x32.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromUint16x32, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint32x4.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromUint32x4, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint32x8.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromUint32x8, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint32x16.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromUint32x16, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint64x2.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromUint64x2, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint64x4.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromUint64x4, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint64x8.ShiftRightAndFillUpperFrom", opLen3(ssa.OpShiftRightAndFillUpperFromUint64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int16x8.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedInt16x8, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int16x16.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedInt16x16, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int16x32.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedInt16x32, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int32x4.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedInt32x4, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int32x8.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedInt32x8, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int32x16.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedInt32x16, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Int64x2.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedInt64x2, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Int64x4.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedInt64x4, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Int64x8.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedInt64x8, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint16x8.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedUint16x8, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint16x16.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedUint16x16, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint16x32.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedUint16x32, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint32x4.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedUint32x4, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint32x8.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedUint32x8, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint32x16.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedUint32x16, types.TypeVec512), sys.AMD64) - addF(simdPackage, "Uint64x2.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedUint64x2, types.TypeVec128), sys.AMD64) - addF(simdPackage, "Uint64x4.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedUint64x4, types.TypeVec256), sys.AMD64) - addF(simdPackage, "Uint64x8.ShiftRightAndFillUpperFromMasked", opLen4(ssa.OpShiftRightAndFillUpperFromMaskedUint64x8, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int16x8.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatInt16x8, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int16x16.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatInt16x16, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int16x32.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatInt16x32, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int32x4.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatInt32x4, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int32x8.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatInt32x8, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int32x16.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatInt32x16, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int64x2.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatInt64x2, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int64x4.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatInt64x4, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int64x8.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatInt64x8, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint16x8.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatUint16x8, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint16x16.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatUint16x16, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint16x32.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatUint16x32, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint32x4.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatUint32x4, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint32x8.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatUint32x8, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint32x16.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatUint32x16, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint64x2.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatUint64x2, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint64x4.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatUint64x4, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint64x8.ShiftRightConcat", opLen3(ssa.OpShiftRightConcatUint64x8, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int16x8.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedInt16x8, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int16x16.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedInt16x16, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int16x32.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedInt16x32, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int32x4.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedInt32x4, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int32x8.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedInt32x8, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int32x16.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedInt32x16, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Int64x2.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedInt64x2, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Int64x4.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedInt64x4, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Int64x8.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedInt64x8, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint16x8.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedUint16x8, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint16x16.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedUint16x16, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint16x32.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedUint16x32, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint32x4.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedUint32x4, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint32x8.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedUint32x8, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint32x16.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedUint32x16, types.TypeVec512), sys.AMD64) + addF(simdPackage, "Uint64x2.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedUint64x2, types.TypeVec128), sys.AMD64) + addF(simdPackage, "Uint64x4.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedUint64x4, types.TypeVec256), sys.AMD64) + addF(simdPackage, "Uint64x8.ShiftRightConcatMasked", opLen4(ssa.OpShiftRightConcatMaskedUint64x8, types.TypeVec512), sys.AMD64) addF(simdPackage, "Int16x8.ShiftRightMasked", opLen3(ssa.OpShiftRightMaskedInt16x8, types.TypeVec128), sys.AMD64) addF(simdPackage, "Int16x16.ShiftRightMasked", opLen3(ssa.OpShiftRightMaskedInt16x16, types.TypeVec256), sys.AMD64) addF(simdPackage, "Int16x32.ShiftRightMasked", opLen3(ssa.OpShiftRightMaskedInt16x32, types.TypeVec512), sys.AMD64) diff --git a/src/simd/ops_amd64.go b/src/simd/ops_amd64.go index 8d94136090..f88410af43 100644 --- a/src/simd/ops_amd64.go +++ b/src/simd/ops_amd64.go @@ -9259,155 +9259,155 @@ func (x Uint64x4) ShiftAllLeft(y uint64) Uint64x4 // Asm: VPSLLQ, CPU Feature: AVX512F func (x Uint64x8) ShiftAllLeft(y uint64) Uint64x8 -/* ShiftAllLeftAndFillUpperFrom */ +/* ShiftAllLeftConcat */ -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Int16x8) ShiftAllLeftAndFillUpperFrom(shift uint8, y Int16x8) Int16x8 +func (x Int16x8) ShiftAllLeftConcat(shift uint8, y Int16x8) Int16x8 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Int16x16) ShiftAllLeftAndFillUpperFrom(shift uint8, y Int16x16) Int16x16 +func (x Int16x16) ShiftAllLeftConcat(shift uint8, y Int16x16) Int16x16 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Int16x32) ShiftAllLeftAndFillUpperFrom(shift uint8, y Int16x32) Int16x32 +func (x Int16x32) ShiftAllLeftConcat(shift uint8, y Int16x32) Int16x32 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Int32x4) ShiftAllLeftAndFillUpperFrom(shift uint8, y Int32x4) Int32x4 +func (x Int32x4) ShiftAllLeftConcat(shift uint8, y Int32x4) Int32x4 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Int32x8) ShiftAllLeftAndFillUpperFrom(shift uint8, y Int32x8) Int32x8 +func (x Int32x8) ShiftAllLeftConcat(shift uint8, y Int32x8) Int32x8 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Int32x16) ShiftAllLeftAndFillUpperFrom(shift uint8, y Int32x16) Int32x16 +func (x Int32x16) ShiftAllLeftConcat(shift uint8, y Int32x16) Int32x16 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Int64x2) ShiftAllLeftAndFillUpperFrom(shift uint8, y Int64x2) Int64x2 +func (x Int64x2) ShiftAllLeftConcat(shift uint8, y Int64x2) Int64x2 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Int64x4) ShiftAllLeftAndFillUpperFrom(shift uint8, y Int64x4) Int64x4 +func (x Int64x4) ShiftAllLeftConcat(shift uint8, y Int64x4) Int64x4 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Int64x8) ShiftAllLeftAndFillUpperFrom(shift uint8, y Int64x8) Int64x8 +func (x Int64x8) ShiftAllLeftConcat(shift uint8, y Int64x8) Int64x8 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Uint16x8) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint16x8) Uint16x8 +func (x Uint16x8) ShiftAllLeftConcat(shift uint8, y Uint16x8) Uint16x8 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Uint16x16) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint16x16) Uint16x16 +func (x Uint16x16) ShiftAllLeftConcat(shift uint8, y Uint16x16) Uint16x16 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Uint16x32) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint16x32) Uint16x32 +func (x Uint16x32) ShiftAllLeftConcat(shift uint8, y Uint16x32) Uint16x32 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Uint32x4) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint32x4) Uint32x4 +func (x Uint32x4) ShiftAllLeftConcat(shift uint8, y Uint32x4) Uint32x4 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Uint32x8) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint32x8) Uint32x8 +func (x Uint32x8) ShiftAllLeftConcat(shift uint8, y Uint32x8) Uint32x8 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Uint32x16) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint32x16) Uint32x16 +func (x Uint32x16) ShiftAllLeftConcat(shift uint8, y Uint32x16) Uint32x16 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x2) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint64x2) Uint64x2 +func (x Uint64x2) ShiftAllLeftConcat(shift uint8, y Uint64x2) Uint64x2 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x4) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint64x4) Uint64x4 +func (x Uint64x4) ShiftAllLeftConcat(shift uint8, y Uint64x4) Uint64x4 -// ShiftAllLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcat shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x8) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint64x8) Uint64x8 +func (x Uint64x8) ShiftAllLeftConcat(shift uint8, y Uint64x8) Uint64x8 -/* ShiftAllLeftAndFillUpperFromMasked */ +/* ShiftAllLeftConcatMasked */ -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9415,9 +9415,9 @@ func (x Uint64x8) ShiftAllLeftAndFillUpperFrom(shift uint8, y Uint64x8) Uint64x8 // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Int16x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int16x8, mask Mask16x8) Int16x8 +func (x Int16x8) ShiftAllLeftConcatMasked(shift uint8, y Int16x8, mask Mask16x8) Int16x8 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9425,9 +9425,9 @@ func (x Int16x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int16x8, mask // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Int16x16) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int16x16, mask Mask16x16) Int16x16 +func (x Int16x16) ShiftAllLeftConcatMasked(shift uint8, y Int16x16, mask Mask16x16) Int16x16 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9435,9 +9435,9 @@ func (x Int16x16) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int16x16, ma // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Int16x32) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int16x32, mask Mask16x32) Int16x32 +func (x Int16x32) ShiftAllLeftConcatMasked(shift uint8, y Int16x32, mask Mask16x32) Int16x32 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9445,9 +9445,9 @@ func (x Int16x32) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int16x32, ma // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Int32x4) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int32x4, mask Mask32x4) Int32x4 +func (x Int32x4) ShiftAllLeftConcatMasked(shift uint8, y Int32x4, mask Mask32x4) Int32x4 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9455,9 +9455,9 @@ func (x Int32x4) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int32x4, mask // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Int32x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int32x8, mask Mask32x8) Int32x8 +func (x Int32x8) ShiftAllLeftConcatMasked(shift uint8, y Int32x8, mask Mask32x8) Int32x8 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9465,9 +9465,9 @@ func (x Int32x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int32x8, mask // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Int32x16) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int32x16, mask Mask32x16) Int32x16 +func (x Int32x16) ShiftAllLeftConcatMasked(shift uint8, y Int32x16, mask Mask32x16) Int32x16 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9475,9 +9475,9 @@ func (x Int32x16) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int32x16, ma // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Int64x2) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int64x2, mask Mask64x2) Int64x2 +func (x Int64x2) ShiftAllLeftConcatMasked(shift uint8, y Int64x2, mask Mask64x2) Int64x2 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9485,9 +9485,9 @@ func (x Int64x2) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int64x2, mask // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Int64x4) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int64x4, mask Mask64x4) Int64x4 +func (x Int64x4) ShiftAllLeftConcatMasked(shift uint8, y Int64x4, mask Mask64x4) Int64x4 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9495,9 +9495,9 @@ func (x Int64x4) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int64x4, mask // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Int64x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int64x8, mask Mask64x8) Int64x8 +func (x Int64x8) ShiftAllLeftConcatMasked(shift uint8, y Int64x8, mask Mask64x8) Int64x8 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9505,9 +9505,9 @@ func (x Int64x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Int64x8, mask // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Uint16x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint16x8, mask Mask16x8) Uint16x8 +func (x Uint16x8) ShiftAllLeftConcatMasked(shift uint8, y Uint16x8, mask Mask16x8) Uint16x8 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9515,9 +9515,9 @@ func (x Uint16x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint16x8, ma // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Uint16x16) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint16x16, mask Mask16x16) Uint16x16 +func (x Uint16x16) ShiftAllLeftConcatMasked(shift uint8, y Uint16x16, mask Mask16x16) Uint16x16 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9525,9 +9525,9 @@ func (x Uint16x16) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint16x16, // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDW, CPU Feature: AVX512VBMI2 -func (x Uint16x32) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint16x32, mask Mask16x32) Uint16x32 +func (x Uint16x32) ShiftAllLeftConcatMasked(shift uint8, y Uint16x32, mask Mask16x32) Uint16x32 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9535,9 +9535,9 @@ func (x Uint16x32) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint16x32, // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Uint32x4) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint32x4, mask Mask32x4) Uint32x4 +func (x Uint32x4) ShiftAllLeftConcatMasked(shift uint8, y Uint32x4, mask Mask32x4) Uint32x4 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9545,9 +9545,9 @@ func (x Uint32x4) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint32x4, ma // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Uint32x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint32x8, mask Mask32x8) Uint32x8 +func (x Uint32x8) ShiftAllLeftConcatMasked(shift uint8, y Uint32x8, mask Mask32x8) Uint32x8 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9555,9 +9555,9 @@ func (x Uint32x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint32x8, ma // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDD, CPU Feature: AVX512VBMI2 -func (x Uint32x16) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint32x16, mask Mask32x16) Uint32x16 +func (x Uint32x16) ShiftAllLeftConcatMasked(shift uint8, y Uint32x16, mask Mask32x16) Uint32x16 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9565,9 +9565,9 @@ func (x Uint32x16) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint32x16, // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x2) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint64x2, mask Mask64x2) Uint64x2 +func (x Uint64x2) ShiftAllLeftConcatMasked(shift uint8, y Uint64x2, mask Mask64x2) Uint64x2 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9575,9 +9575,9 @@ func (x Uint64x2) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint64x2, ma // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x4) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint64x4, mask Mask64x4) Uint64x4 +func (x Uint64x4) ShiftAllLeftConcatMasked(shift uint8, y Uint64x4, mask Mask64x4) Uint64x4 -// ShiftAllLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftAllLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the upper bits of y to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9585,7 +9585,7 @@ func (x Uint64x4) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint64x4, ma // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHLDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x8) ShiftAllLeftAndFillUpperFromMasked(shift uint8, y Uint64x8, mask Mask64x8) Uint64x8 +func (x Uint64x8) ShiftAllLeftConcatMasked(shift uint8, y Uint64x8, mask Mask64x8) Uint64x8 /* ShiftAllLeftMasked */ @@ -9807,155 +9807,155 @@ func (x Uint64x4) ShiftAllRight(y uint64) Uint64x4 // Asm: VPSRLQ, CPU Feature: AVX512F func (x Uint64x8) ShiftAllRight(y uint64) Uint64x8 -/* ShiftAllRightAndFillUpperFrom */ +/* ShiftAllRightConcat */ -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Int16x8) ShiftAllRightAndFillUpperFrom(shift uint8, y Int16x8) Int16x8 +func (x Int16x8) ShiftAllRightConcat(shift uint8, y Int16x8) Int16x8 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Int16x16) ShiftAllRightAndFillUpperFrom(shift uint8, y Int16x16) Int16x16 +func (x Int16x16) ShiftAllRightConcat(shift uint8, y Int16x16) Int16x16 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Int16x32) ShiftAllRightAndFillUpperFrom(shift uint8, y Int16x32) Int16x32 +func (x Int16x32) ShiftAllRightConcat(shift uint8, y Int16x32) Int16x32 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Int32x4) ShiftAllRightAndFillUpperFrom(shift uint8, y Int32x4) Int32x4 +func (x Int32x4) ShiftAllRightConcat(shift uint8, y Int32x4) Int32x4 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Int32x8) ShiftAllRightAndFillUpperFrom(shift uint8, y Int32x8) Int32x8 +func (x Int32x8) ShiftAllRightConcat(shift uint8, y Int32x8) Int32x8 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Int32x16) ShiftAllRightAndFillUpperFrom(shift uint8, y Int32x16) Int32x16 +func (x Int32x16) ShiftAllRightConcat(shift uint8, y Int32x16) Int32x16 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Int64x2) ShiftAllRightAndFillUpperFrom(shift uint8, y Int64x2) Int64x2 +func (x Int64x2) ShiftAllRightConcat(shift uint8, y Int64x2) Int64x2 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Int64x4) ShiftAllRightAndFillUpperFrom(shift uint8, y Int64x4) Int64x4 +func (x Int64x4) ShiftAllRightConcat(shift uint8, y Int64x4) Int64x4 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Int64x8) ShiftAllRightAndFillUpperFrom(shift uint8, y Int64x8) Int64x8 +func (x Int64x8) ShiftAllRightConcat(shift uint8, y Int64x8) Int64x8 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Uint16x8) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint16x8) Uint16x8 +func (x Uint16x8) ShiftAllRightConcat(shift uint8, y Uint16x8) Uint16x8 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Uint16x16) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint16x16) Uint16x16 +func (x Uint16x16) ShiftAllRightConcat(shift uint8, y Uint16x16) Uint16x16 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Uint16x32) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint16x32) Uint16x32 +func (x Uint16x32) ShiftAllRightConcat(shift uint8, y Uint16x32) Uint16x32 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Uint32x4) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint32x4) Uint32x4 +func (x Uint32x4) ShiftAllRightConcat(shift uint8, y Uint32x4) Uint32x4 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Uint32x8) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint32x8) Uint32x8 +func (x Uint32x8) ShiftAllRightConcat(shift uint8, y Uint32x8) Uint32x8 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Uint32x16) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint32x16) Uint32x16 +func (x Uint32x16) ShiftAllRightConcat(shift uint8, y Uint32x16) Uint32x16 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x2) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint64x2) Uint64x2 +func (x Uint64x2) ShiftAllRightConcat(shift uint8, y Uint64x2) Uint64x2 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x4) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint64x4) Uint64x4 +func (x Uint64x4) ShiftAllRightConcat(shift uint8, y Uint64x4) Uint64x4 -// ShiftAllRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcat shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x8) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint64x8) Uint64x8 +func (x Uint64x8) ShiftAllRightConcat(shift uint8, y Uint64x8) Uint64x8 -/* ShiftAllRightAndFillUpperFromMasked */ +/* ShiftAllRightConcatMasked */ -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9963,9 +9963,9 @@ func (x Uint64x8) ShiftAllRightAndFillUpperFrom(shift uint8, y Uint64x8) Uint64x // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Int16x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int16x8, mask Mask16x8) Int16x8 +func (x Int16x8) ShiftAllRightConcatMasked(shift uint8, y Int16x8, mask Mask16x8) Int16x8 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9973,9 +9973,9 @@ func (x Int16x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int16x8, mas // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Int16x16) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int16x16, mask Mask16x16) Int16x16 +func (x Int16x16) ShiftAllRightConcatMasked(shift uint8, y Int16x16, mask Mask16x16) Int16x16 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9983,9 +9983,9 @@ func (x Int16x16) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int16x16, m // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Int16x32) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int16x32, mask Mask16x32) Int16x32 +func (x Int16x32) ShiftAllRightConcatMasked(shift uint8, y Int16x32, mask Mask16x32) Int16x32 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -9993,9 +9993,9 @@ func (x Int16x32) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int16x32, m // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Int32x4) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int32x4, mask Mask32x4) Int32x4 +func (x Int32x4) ShiftAllRightConcatMasked(shift uint8, y Int32x4, mask Mask32x4) Int32x4 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10003,9 +10003,9 @@ func (x Int32x4) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int32x4, mas // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Int32x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int32x8, mask Mask32x8) Int32x8 +func (x Int32x8) ShiftAllRightConcatMasked(shift uint8, y Int32x8, mask Mask32x8) Int32x8 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10013,9 +10013,9 @@ func (x Int32x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int32x8, mas // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Int32x16) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int32x16, mask Mask32x16) Int32x16 +func (x Int32x16) ShiftAllRightConcatMasked(shift uint8, y Int32x16, mask Mask32x16) Int32x16 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10023,9 +10023,9 @@ func (x Int32x16) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int32x16, m // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Int64x2) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int64x2, mask Mask64x2) Int64x2 +func (x Int64x2) ShiftAllRightConcatMasked(shift uint8, y Int64x2, mask Mask64x2) Int64x2 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10033,9 +10033,9 @@ func (x Int64x2) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int64x2, mas // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Int64x4) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int64x4, mask Mask64x4) Int64x4 +func (x Int64x4) ShiftAllRightConcatMasked(shift uint8, y Int64x4, mask Mask64x4) Int64x4 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10043,9 +10043,9 @@ func (x Int64x4) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int64x4, mas // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Int64x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int64x8, mask Mask64x8) Int64x8 +func (x Int64x8) ShiftAllRightConcatMasked(shift uint8, y Int64x8, mask Mask64x8) Int64x8 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10053,9 +10053,9 @@ func (x Int64x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Int64x8, mas // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Uint16x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint16x8, mask Mask16x8) Uint16x8 +func (x Uint16x8) ShiftAllRightConcatMasked(shift uint8, y Uint16x8, mask Mask16x8) Uint16x8 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10063,9 +10063,9 @@ func (x Uint16x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint16x8, m // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Uint16x16) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint16x16, mask Mask16x16) Uint16x16 +func (x Uint16x16) ShiftAllRightConcatMasked(shift uint8, y Uint16x16, mask Mask16x16) Uint16x16 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10073,9 +10073,9 @@ func (x Uint16x16) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint16x16, // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDW, CPU Feature: AVX512VBMI2 -func (x Uint16x32) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint16x32, mask Mask16x32) Uint16x32 +func (x Uint16x32) ShiftAllRightConcatMasked(shift uint8, y Uint16x32, mask Mask16x32) Uint16x32 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10083,9 +10083,9 @@ func (x Uint16x32) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint16x32, // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Uint32x4) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint32x4, mask Mask32x4) Uint32x4 +func (x Uint32x4) ShiftAllRightConcatMasked(shift uint8, y Uint32x4, mask Mask32x4) Uint32x4 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10093,9 +10093,9 @@ func (x Uint32x4) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint32x4, m // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Uint32x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint32x8, mask Mask32x8) Uint32x8 +func (x Uint32x8) ShiftAllRightConcatMasked(shift uint8, y Uint32x8, mask Mask32x8) Uint32x8 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10103,9 +10103,9 @@ func (x Uint32x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint32x8, m // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDD, CPU Feature: AVX512VBMI2 -func (x Uint32x16) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint32x16, mask Mask32x16) Uint32x16 +func (x Uint32x16) ShiftAllRightConcatMasked(shift uint8, y Uint32x16, mask Mask32x16) Uint32x16 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10113,9 +10113,9 @@ func (x Uint32x16) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint32x16, // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x2) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint64x2, mask Mask64x2) Uint64x2 +func (x Uint64x2) ShiftAllRightConcatMasked(shift uint8, y Uint64x2, mask Mask64x2) Uint64x2 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10123,9 +10123,9 @@ func (x Uint64x2) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint64x2, m // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x4) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint64x4, mask Mask64x4) Uint64x4 +func (x Uint64x4) ShiftAllRightConcatMasked(shift uint8, y Uint64x4, mask Mask64x4) Uint64x4 -// ShiftAllRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftAllRightConcatMasked shifts each element of x to the right by the number of bits specified by the // immediate(only the lower 5 bits are used), and then copies the lower bits of y to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. @@ -10133,7 +10133,7 @@ func (x Uint64x4) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint64x4, m // shift is expected to be a constant, non-constant value will trigger a runtime panic. // // Asm: VPSHRDQ, CPU Feature: AVX512VBMI2 -func (x Uint64x8) ShiftAllRightAndFillUpperFromMasked(shift uint8, y Uint64x8, mask Mask64x8) Uint64x8 +func (x Uint64x8) ShiftAllRightConcatMasked(shift uint8, y Uint64x8, mask Mask64x8) Uint64x8 /* ShiftAllRightMasked */ @@ -10355,261 +10355,261 @@ func (x Uint64x4) ShiftLeft(y Uint64x4) Uint64x4 // Asm: VPSLLVQ, CPU Feature: AVX512F func (x Uint64x8) ShiftLeft(y Uint64x8) Uint64x8 -/* ShiftLeftAndFillUpperFrom */ +/* ShiftLeftConcat */ -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Int16x8) ShiftLeftAndFillUpperFrom(y Int16x8, z Int16x8) Int16x8 +func (x Int16x8) ShiftLeftConcat(y Int16x8, z Int16x8) Int16x8 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Int16x16) ShiftLeftAndFillUpperFrom(y Int16x16, z Int16x16) Int16x16 +func (x Int16x16) ShiftLeftConcat(y Int16x16, z Int16x16) Int16x16 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Int16x32) ShiftLeftAndFillUpperFrom(y Int16x32, z Int16x32) Int16x32 +func (x Int16x32) ShiftLeftConcat(y Int16x32, z Int16x32) Int16x32 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Int32x4) ShiftLeftAndFillUpperFrom(y Int32x4, z Int32x4) Int32x4 +func (x Int32x4) ShiftLeftConcat(y Int32x4, z Int32x4) Int32x4 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Int32x8) ShiftLeftAndFillUpperFrom(y Int32x8, z Int32x8) Int32x8 +func (x Int32x8) ShiftLeftConcat(y Int32x8, z Int32x8) Int32x8 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Int32x16) ShiftLeftAndFillUpperFrom(y Int32x16, z Int32x16) Int32x16 +func (x Int32x16) ShiftLeftConcat(y Int32x16, z Int32x16) Int32x16 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x2) ShiftLeftAndFillUpperFrom(y Int64x2, z Int64x2) Int64x2 +func (x Int64x2) ShiftLeftConcat(y Int64x2, z Int64x2) Int64x2 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x4) ShiftLeftAndFillUpperFrom(y Int64x4, z Int64x4) Int64x4 +func (x Int64x4) ShiftLeftConcat(y Int64x4, z Int64x4) Int64x4 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x8) ShiftLeftAndFillUpperFrom(y Int64x8, z Int64x8) Int64x8 +func (x Int64x8) ShiftLeftConcat(y Int64x8, z Int64x8) Int64x8 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x8) ShiftLeftAndFillUpperFrom(y Uint16x8, z Uint16x8) Uint16x8 +func (x Uint16x8) ShiftLeftConcat(y Uint16x8, z Uint16x8) Uint16x8 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x16) ShiftLeftAndFillUpperFrom(y Uint16x16, z Uint16x16) Uint16x16 +func (x Uint16x16) ShiftLeftConcat(y Uint16x16, z Uint16x16) Uint16x16 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x32) ShiftLeftAndFillUpperFrom(y Uint16x32, z Uint16x32) Uint16x32 +func (x Uint16x32) ShiftLeftConcat(y Uint16x32, z Uint16x32) Uint16x32 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x4) ShiftLeftAndFillUpperFrom(y Uint32x4, z Uint32x4) Uint32x4 +func (x Uint32x4) ShiftLeftConcat(y Uint32x4, z Uint32x4) Uint32x4 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x8) ShiftLeftAndFillUpperFrom(y Uint32x8, z Uint32x8) Uint32x8 +func (x Uint32x8) ShiftLeftConcat(y Uint32x8, z Uint32x8) Uint32x8 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x16) ShiftLeftAndFillUpperFrom(y Uint32x16, z Uint32x16) Uint32x16 +func (x Uint32x16) ShiftLeftConcat(y Uint32x16, z Uint32x16) Uint32x16 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x2) ShiftLeftAndFillUpperFrom(y Uint64x2, z Uint64x2) Uint64x2 +func (x Uint64x2) ShiftLeftConcat(y Uint64x2, z Uint64x2) Uint64x2 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x4) ShiftLeftAndFillUpperFrom(y Uint64x4, z Uint64x4) Uint64x4 +func (x Uint64x4) ShiftLeftConcat(y Uint64x4, z Uint64x4) Uint64x4 -// ShiftLeftAndFillUpperFrom shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcat shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x8) ShiftLeftAndFillUpperFrom(y Uint64x8, z Uint64x8) Uint64x8 +func (x Uint64x8) ShiftLeftConcat(y Uint64x8, z Uint64x8) Uint64x8 -/* ShiftLeftAndFillUpperFromMasked */ +/* ShiftLeftConcatMasked */ -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Int16x8) ShiftLeftAndFillUpperFromMasked(y Int16x8, z Int16x8, mask Mask16x8) Int16x8 +func (x Int16x8) ShiftLeftConcatMasked(y Int16x8, z Int16x8, mask Mask16x8) Int16x8 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Int16x16) ShiftLeftAndFillUpperFromMasked(y Int16x16, z Int16x16, mask Mask16x16) Int16x16 +func (x Int16x16) ShiftLeftConcatMasked(y Int16x16, z Int16x16, mask Mask16x16) Int16x16 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Int16x32) ShiftLeftAndFillUpperFromMasked(y Int16x32, z Int16x32, mask Mask16x32) Int16x32 +func (x Int16x32) ShiftLeftConcatMasked(y Int16x32, z Int16x32, mask Mask16x32) Int16x32 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Int32x4) ShiftLeftAndFillUpperFromMasked(y Int32x4, z Int32x4, mask Mask32x4) Int32x4 +func (x Int32x4) ShiftLeftConcatMasked(y Int32x4, z Int32x4, mask Mask32x4) Int32x4 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Int32x8) ShiftLeftAndFillUpperFromMasked(y Int32x8, z Int32x8, mask Mask32x8) Int32x8 +func (x Int32x8) ShiftLeftConcatMasked(y Int32x8, z Int32x8, mask Mask32x8) Int32x8 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Int32x16) ShiftLeftAndFillUpperFromMasked(y Int32x16, z Int32x16, mask Mask32x16) Int32x16 +func (x Int32x16) ShiftLeftConcatMasked(y Int32x16, z Int32x16, mask Mask32x16) Int32x16 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x2) ShiftLeftAndFillUpperFromMasked(y Int64x2, z Int64x2, mask Mask64x2) Int64x2 +func (x Int64x2) ShiftLeftConcatMasked(y Int64x2, z Int64x2, mask Mask64x2) Int64x2 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x4) ShiftLeftAndFillUpperFromMasked(y Int64x4, z Int64x4, mask Mask64x4) Int64x4 +func (x Int64x4) ShiftLeftConcatMasked(y Int64x4, z Int64x4, mask Mask64x4) Int64x4 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x8) ShiftLeftAndFillUpperFromMasked(y Int64x8, z Int64x8, mask Mask64x8) Int64x8 +func (x Int64x8) ShiftLeftConcatMasked(y Int64x8, z Int64x8, mask Mask64x8) Int64x8 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x8) ShiftLeftAndFillUpperFromMasked(y Uint16x8, z Uint16x8, mask Mask16x8) Uint16x8 +func (x Uint16x8) ShiftLeftConcatMasked(y Uint16x8, z Uint16x8, mask Mask16x8) Uint16x8 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x16) ShiftLeftAndFillUpperFromMasked(y Uint16x16, z Uint16x16, mask Mask16x16) Uint16x16 +func (x Uint16x16) ShiftLeftConcatMasked(y Uint16x16, z Uint16x16, mask Mask16x16) Uint16x16 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x32) ShiftLeftAndFillUpperFromMasked(y Uint16x32, z Uint16x32, mask Mask16x32) Uint16x32 +func (x Uint16x32) ShiftLeftConcatMasked(y Uint16x32, z Uint16x32, mask Mask16x32) Uint16x32 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x4) ShiftLeftAndFillUpperFromMasked(y Uint32x4, z Uint32x4, mask Mask32x4) Uint32x4 +func (x Uint32x4) ShiftLeftConcatMasked(y Uint32x4, z Uint32x4, mask Mask32x4) Uint32x4 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x8) ShiftLeftAndFillUpperFromMasked(y Uint32x8, z Uint32x8, mask Mask32x8) Uint32x8 +func (x Uint32x8) ShiftLeftConcatMasked(y Uint32x8, z Uint32x8, mask Mask32x8) Uint32x8 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x16) ShiftLeftAndFillUpperFromMasked(y Uint32x16, z Uint32x16, mask Mask32x16) Uint32x16 +func (x Uint32x16) ShiftLeftConcatMasked(y Uint32x16, z Uint32x16, mask Mask32x16) Uint32x16 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x2) ShiftLeftAndFillUpperFromMasked(y Uint64x2, z Uint64x2, mask Mask64x2) Uint64x2 +func (x Uint64x2) ShiftLeftConcatMasked(y Uint64x2, z Uint64x2, mask Mask64x2) Uint64x2 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x4) ShiftLeftAndFillUpperFromMasked(y Uint64x4, z Uint64x4, mask Mask64x4) Uint64x4 +func (x Uint64x4) ShiftLeftConcatMasked(y Uint64x4, z Uint64x4, mask Mask64x4) Uint64x4 -// ShiftLeftAndFillUpperFromMasked shifts each element of x to the left by the number of bits specified by the +// ShiftLeftConcatMasked shifts each element of x to the left by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the upper bits of z to the emptied lower bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHLDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x8) ShiftLeftAndFillUpperFromMasked(y Uint64x8, z Uint64x8, mask Mask64x8) Uint64x8 +func (x Uint64x8) ShiftLeftConcatMasked(y Uint64x8, z Uint64x8, mask Mask64x8) Uint64x8 /* ShiftLeftMasked */ @@ -10831,261 +10831,261 @@ func (x Uint64x4) ShiftRight(y Uint64x4) Uint64x4 // Asm: VPSRLVQ, CPU Feature: AVX512F func (x Uint64x8) ShiftRight(y Uint64x8) Uint64x8 -/* ShiftRightAndFillUpperFrom */ +/* ShiftRightConcat */ -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Int16x8) ShiftRightAndFillUpperFrom(y Int16x8, z Int16x8) Int16x8 +func (x Int16x8) ShiftRightConcat(y Int16x8, z Int16x8) Int16x8 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Int16x16) ShiftRightAndFillUpperFrom(y Int16x16, z Int16x16) Int16x16 +func (x Int16x16) ShiftRightConcat(y Int16x16, z Int16x16) Int16x16 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Int16x32) ShiftRightAndFillUpperFrom(y Int16x32, z Int16x32) Int16x32 +func (x Int16x32) ShiftRightConcat(y Int16x32, z Int16x32) Int16x32 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Int32x4) ShiftRightAndFillUpperFrom(y Int32x4, z Int32x4) Int32x4 +func (x Int32x4) ShiftRightConcat(y Int32x4, z Int32x4) Int32x4 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Int32x8) ShiftRightAndFillUpperFrom(y Int32x8, z Int32x8) Int32x8 +func (x Int32x8) ShiftRightConcat(y Int32x8, z Int32x8) Int32x8 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Int32x16) ShiftRightAndFillUpperFrom(y Int32x16, z Int32x16) Int32x16 +func (x Int32x16) ShiftRightConcat(y Int32x16, z Int32x16) Int32x16 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x2) ShiftRightAndFillUpperFrom(y Int64x2, z Int64x2) Int64x2 +func (x Int64x2) ShiftRightConcat(y Int64x2, z Int64x2) Int64x2 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x4) ShiftRightAndFillUpperFrom(y Int64x4, z Int64x4) Int64x4 +func (x Int64x4) ShiftRightConcat(y Int64x4, z Int64x4) Int64x4 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x8) ShiftRightAndFillUpperFrom(y Int64x8, z Int64x8) Int64x8 +func (x Int64x8) ShiftRightConcat(y Int64x8, z Int64x8) Int64x8 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x8) ShiftRightAndFillUpperFrom(y Uint16x8, z Uint16x8) Uint16x8 +func (x Uint16x8) ShiftRightConcat(y Uint16x8, z Uint16x8) Uint16x8 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x16) ShiftRightAndFillUpperFrom(y Uint16x16, z Uint16x16) Uint16x16 +func (x Uint16x16) ShiftRightConcat(y Uint16x16, z Uint16x16) Uint16x16 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x32) ShiftRightAndFillUpperFrom(y Uint16x32, z Uint16x32) Uint16x32 +func (x Uint16x32) ShiftRightConcat(y Uint16x32, z Uint16x32) Uint16x32 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x4) ShiftRightAndFillUpperFrom(y Uint32x4, z Uint32x4) Uint32x4 +func (x Uint32x4) ShiftRightConcat(y Uint32x4, z Uint32x4) Uint32x4 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x8) ShiftRightAndFillUpperFrom(y Uint32x8, z Uint32x8) Uint32x8 +func (x Uint32x8) ShiftRightConcat(y Uint32x8, z Uint32x8) Uint32x8 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x16) ShiftRightAndFillUpperFrom(y Uint32x16, z Uint32x16) Uint32x16 +func (x Uint32x16) ShiftRightConcat(y Uint32x16, z Uint32x16) Uint32x16 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x2) ShiftRightAndFillUpperFrom(y Uint64x2, z Uint64x2) Uint64x2 +func (x Uint64x2) ShiftRightConcat(y Uint64x2, z Uint64x2) Uint64x2 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x4) ShiftRightAndFillUpperFrom(y Uint64x4, z Uint64x4) Uint64x4 +func (x Uint64x4) ShiftRightConcat(y Uint64x4, z Uint64x4) Uint64x4 -// ShiftRightAndFillUpperFrom shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcat shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x8) ShiftRightAndFillUpperFrom(y Uint64x8, z Uint64x8) Uint64x8 +func (x Uint64x8) ShiftRightConcat(y Uint64x8, z Uint64x8) Uint64x8 -/* ShiftRightAndFillUpperFromMasked */ +/* ShiftRightConcatMasked */ -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Int16x8) ShiftRightAndFillUpperFromMasked(y Int16x8, z Int16x8, mask Mask16x8) Int16x8 +func (x Int16x8) ShiftRightConcatMasked(y Int16x8, z Int16x8, mask Mask16x8) Int16x8 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Int16x16) ShiftRightAndFillUpperFromMasked(y Int16x16, z Int16x16, mask Mask16x16) Int16x16 +func (x Int16x16) ShiftRightConcatMasked(y Int16x16, z Int16x16, mask Mask16x16) Int16x16 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Int16x32) ShiftRightAndFillUpperFromMasked(y Int16x32, z Int16x32, mask Mask16x32) Int16x32 +func (x Int16x32) ShiftRightConcatMasked(y Int16x32, z Int16x32, mask Mask16x32) Int16x32 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Int32x4) ShiftRightAndFillUpperFromMasked(y Int32x4, z Int32x4, mask Mask32x4) Int32x4 +func (x Int32x4) ShiftRightConcatMasked(y Int32x4, z Int32x4, mask Mask32x4) Int32x4 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Int32x8) ShiftRightAndFillUpperFromMasked(y Int32x8, z Int32x8, mask Mask32x8) Int32x8 +func (x Int32x8) ShiftRightConcatMasked(y Int32x8, z Int32x8, mask Mask32x8) Int32x8 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Int32x16) ShiftRightAndFillUpperFromMasked(y Int32x16, z Int32x16, mask Mask32x16) Int32x16 +func (x Int32x16) ShiftRightConcatMasked(y Int32x16, z Int32x16, mask Mask32x16) Int32x16 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x2) ShiftRightAndFillUpperFromMasked(y Int64x2, z Int64x2, mask Mask64x2) Int64x2 +func (x Int64x2) ShiftRightConcatMasked(y Int64x2, z Int64x2, mask Mask64x2) Int64x2 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x4) ShiftRightAndFillUpperFromMasked(y Int64x4, z Int64x4, mask Mask64x4) Int64x4 +func (x Int64x4) ShiftRightConcatMasked(y Int64x4, z Int64x4, mask Mask64x4) Int64x4 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Int64x8) ShiftRightAndFillUpperFromMasked(y Int64x8, z Int64x8, mask Mask64x8) Int64x8 +func (x Int64x8) ShiftRightConcatMasked(y Int64x8, z Int64x8, mask Mask64x8) Int64x8 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x8) ShiftRightAndFillUpperFromMasked(y Uint16x8, z Uint16x8, mask Mask16x8) Uint16x8 +func (x Uint16x8) ShiftRightConcatMasked(y Uint16x8, z Uint16x8, mask Mask16x8) Uint16x8 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x16) ShiftRightAndFillUpperFromMasked(y Uint16x16, z Uint16x16, mask Mask16x16) Uint16x16 +func (x Uint16x16) ShiftRightConcatMasked(y Uint16x16, z Uint16x16, mask Mask16x16) Uint16x16 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVW, CPU Feature: AVX512VBMI2 -func (x Uint16x32) ShiftRightAndFillUpperFromMasked(y Uint16x32, z Uint16x32, mask Mask16x32) Uint16x32 +func (x Uint16x32) ShiftRightConcatMasked(y Uint16x32, z Uint16x32, mask Mask16x32) Uint16x32 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x4) ShiftRightAndFillUpperFromMasked(y Uint32x4, z Uint32x4, mask Mask32x4) Uint32x4 +func (x Uint32x4) ShiftRightConcatMasked(y Uint32x4, z Uint32x4, mask Mask32x4) Uint32x4 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x8) ShiftRightAndFillUpperFromMasked(y Uint32x8, z Uint32x8, mask Mask32x8) Uint32x8 +func (x Uint32x8) ShiftRightConcatMasked(y Uint32x8, z Uint32x8, mask Mask32x8) Uint32x8 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVD, CPU Feature: AVX512VBMI2 -func (x Uint32x16) ShiftRightAndFillUpperFromMasked(y Uint32x16, z Uint32x16, mask Mask32x16) Uint32x16 +func (x Uint32x16) ShiftRightConcatMasked(y Uint32x16, z Uint32x16, mask Mask32x16) Uint32x16 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x2) ShiftRightAndFillUpperFromMasked(y Uint64x2, z Uint64x2, mask Mask64x2) Uint64x2 +func (x Uint64x2) ShiftRightConcatMasked(y Uint64x2, z Uint64x2, mask Mask64x2) Uint64x2 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x4) ShiftRightAndFillUpperFromMasked(y Uint64x4, z Uint64x4, mask Mask64x4) Uint64x4 +func (x Uint64x4) ShiftRightConcatMasked(y Uint64x4, z Uint64x4, mask Mask64x4) Uint64x4 -// ShiftRightAndFillUpperFromMasked shifts each element of x to the right by the number of bits specified by the +// ShiftRightConcatMasked shifts each element of x to the right by the number of bits specified by the // corresponding elements in y(only the lower 5 bits are used), and then copies the lower bits of z to the emptied upper bits of the shifted x. // // This operation is applied selectively under a write mask. // // Asm: VPSHRDVQ, CPU Feature: AVX512VBMI2 -func (x Uint64x8) ShiftRightAndFillUpperFromMasked(y Uint64x8, z Uint64x8, mask Mask64x8) Uint64x8 +func (x Uint64x8) ShiftRightConcatMasked(y Uint64x8, z Uint64x8, mask Mask64x8) Uint64x8 /* ShiftRightMasked */