cmd/asm: add asimd instruction 'rev16' on arm64

Add support to the asimd instruction rev16 which reverses elements in
16-bit halfwords.

syntax:
	VREV16 <Vn>.<T>, <Vd>.<T>
<T> should be either B8 or B16.

Change-Id: I7a7b8e772589c51ca9eb6dca98bab1aac863c6c2
Reviewed-on: https://go-review.googlesource.com/c/go/+/213738
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>

diff --git a/src/cmd/asm/internal/asm/testdata/arm64enc.s b/src/cmd/asm/internal/asm/testdata/arm64enc.s
index 71270ce43f499eeec55ff8b0c283f2a4c38848b7..a483c731b81224ddf86d51304141bdbf0def59d3 100644 (file)
--- a/src/cmd/asm/internal/asm/testdata/arm64enc.s
+++ b/src/cmd/asm/internal/asm/testdata/arm64enc.s
@@ -712,6 +712,8 @@ TEXT asmtest(SB),DUPOK|NOSPLIT,$-8
    VPMULL2 V2.B16, V1.B16, V4.H8                               // 24e0224e
    VRBIT V10.B16, V21.B16                                      // 5559606e
    VREV32 V2.H8, V1.H8                                         // 4108606e
+   VREV16 V2.B8, V1.B8                                         // 4118200e
+   VREV16 V5.B16, V16.B16                                      // b018204e
    SCVTFWS R6, F17                                             // d100221e
    SCVTFWD R3, F15                                             // 6f00621e
    SCVTFS R20, F25                                             // 9902229e

diff --git a/src/cmd/asm/internal/asm/testdata/arm64error.s b/src/cmd/asm/internal/asm/testdata/arm64error.s
index 7dfca1a1fe7e4fce7aac4e0cb55fb6a4551e51df..0661a474b44c286d363a06c631d985a4a24a009b 100644 (file)
--- a/src/cmd/asm/internal/asm/testdata/arm64error.s
+++ b/src/cmd/asm/internal/asm/testdata/arm64error.s
@@ -106,6 +106,9 @@ TEXT errors(SB),$0
        VST1.P  [V1.B16], (R8)(R9<<1)                            // ERROR "invalid extended register"
        VREV64  V1.H4, V2.H8                                     // ERROR "invalid arrangement"
        VREV64  V1.D1, V2.D1                                     // ERROR "invalid arrangement"
+       VREV16  V1.D1, V2.D1                                     // ERROR "invalid arrangement"
+       VREV16  V1.B8, V2.B16                                    // ERROR "invalid arrangement"
+       VREV16  V1.H4, V2.H4                                     // ERROR "invalid arrangement"
        FLDPD   (R0), (R1, R2)                                   // ERROR "invalid register pair"
        FLDPD   (R1), (F2, F2)                                   // ERROR "constrained unpredictable behavior"
        FLDPS   (R2), (F3, F3)                                   // ERROR "constrained unpredictable behavior"

diff --git a/src/cmd/internal/obj/arm64/a.out.go b/src/cmd/internal/obj/arm64/a.out.go
index 30362081e1a685df27f867b0d284f33c2e650916..152c493a6598f5e08394a07778b39ef95b30fa0b 100644 (file)
--- a/src/cmd/internal/obj/arm64/a.out.go
+++ b/src/cmd/internal/obj/arm64/a.out.go
@@ -962,6 +962,7 @@ const (
        AVLD3R
        AVLD4R
        AVORR
+       AVREV16
        AVREV32
        AVREV64
        AVST1

diff --git a/src/cmd/internal/obj/arm64/anames.go b/src/cmd/internal/obj/arm64/anames.go
index e4dd5f2eb1e686b7f2a00c23d3e79244ea19b6d2..565f70aaf939c4e39977b1c89c7ee80e9ab3cb90 100644 (file)
--- a/src/cmd/internal/obj/arm64/anames.go
+++ b/src/cmd/internal/obj/arm64/anames.go
@@ -469,6 +469,7 @@ var Anames = []string{
        "VLD3R",
        "VLD4R",
        "VORR",
+       "VREV16",
        "VREV32",
        "VREV64",
        "VST1",

diff --git a/src/cmd/internal/obj/arm64/asm7.go b/src/cmd/internal/obj/arm64/asm7.go
index 971e1bdd6491855f4af38a72997dedcbcad9472f..b7e5b9fc172e5096e349a9e8ad42c8ea78ca7066 100644 (file)
--- a/src/cmd/internal/obj/arm64/asm7.go
+++ b/src/cmd/internal/obj/arm64/asm7.go
@@ -2719,6 +2719,7 @@ func buildop(ctxt *obj.Link) {
                case AVREV32:
                        oprangeset(AVRBIT, t)
                        oprangeset(AVREV64, t)
+                       oprangeset(AVREV16, t)
 
                case AVZIP1:
                        oprangeset(AVZIP2, t)
@@ -4471,6 +4472,10 @@ func (c *ctxt7) asmout(p *obj.Prog, o *Optab, out []uint32) {
                        c.ctxt.Diag("invalid arrangement: %v", p)
                }
 
+               if p.As == AVREV16 && af != ARNG_8B && af != ARNG_16B {
+                       c.ctxt.Diag("invalid arrangement: %v", p)
+               }
+
                if p.As == AVMOV {
                        o1 |= uint32(rf&31) << 16
                }
@@ -5594,6 +5599,9 @@ func (c *ctxt7) oprrr(p *obj.Prog, a obj.As) uint32 {
        case AVORR:
                return 7<<25 | 5<<21 | 7<<10
 
+       case AVREV16:
+               return 3<<26 | 2<<24 | 1<<21 | 3<<11
+
        case AVREV32:
                return 11<<26 | 2<<24 | 1<<21 | 1<<11