math/big: optimize subVV function for loong64

Benchmark results on Loongson 3C5000 (which is an LA464 implementation):

goos: linux
goarch: loong64
pkg: math/big
cpu: Loongson-3C5000 @ 2200.00MHz
             │ test/old_3c5000_subvv.log │      test/new_3c5000_subvv.log      │
             │          sec/op           │   sec/op     vs base                │
SubVV/1                     10.920n ± 0%   7.657n ± 0%  -29.88% (p=0.000 n=20)
SubVV/2                     14.100n ± 0%   8.841n ± 0%  -37.30% (p=0.000 n=20)
SubVV/3                      16.38n ± 0%   11.06n ± 0%  -32.48% (p=0.000 n=20)
SubVV/4                      18.65n ± 0%   12.85n ± 0%  -31.10% (p=0.000 n=20)
SubVV/5                      20.93n ± 0%   14.79n ± 0%  -29.34% (p=0.000 n=20)
SubVV/10                     32.30n ± 0%   22.29n ± 0%  -30.99% (p=0.000 n=20)
SubVV/100                    244.3n ± 0%   149.2n ± 0%  -38.93% (p=0.000 n=20)
SubVV/1000                   2.292µ ± 0%   1.378µ ± 0%  -39.88% (p=0.000 n=20)
SubVV/10000                  26.26µ ± 0%   25.64µ ± 0%   -2.33% (p=0.000 n=20)
SubVV/100000                 341.3µ ± 0%   238.0µ ± 0%  -30.26% (p=0.000 n=20)
geomean                      209.1n        144.5n       -30.86%

Change-Id: I3863c2c6728f1b0f8fecbf77de13254299c5b1cb
Reviewed-on: https://go-review.googlesource.com/c/go/+/659877
Reviewed-by: abner chenc <chenguoqi@loongson.cn>
Reviewed-by: Carlos Amedee <carlos@golang.org>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>

diff --git a/src/math/big/arith_loong64.s b/src/math/big/arith_loong64.s
index 9b22a2655347971f97bc61445ef16004b1983c0b..2a2ffafeef6ef1904c9d4f2171469b645c02c4b1 100644 (file)
--- a/src/math/big/arith_loong64.s
+++ b/src/math/big/arith_loong64.s
@@ -12,8 +12,35 @@
 TEXT ·addVV(SB),NOSPLIT,$0
        JMP ·addVV_g(SB)
 
+// func subVV(z, x, y []Word) (c Word)
 TEXT ·subVV(SB),NOSPLIT,$0
-       JMP ·subVV_g(SB)
+       // input:
+       //   R4: z
+       //   R5: z_len
+       //   R7: x
+       //   R10: y
+       MOVV    z+0(FP), R4
+       MOVV    z_len+8(FP), R5
+       MOVV    x+24(FP), R7
+       MOVV    y+48(FP), R10
+       MOVV    $0, R6
+       SLLV    $3, R5
+       MOVV    $0, R8
+loop:
+       BEQ     R5, R6, done
+       MOVV    (R6)(R7), R9
+       MOVV    (R6)(R10), R11
+       SUBV    R11, R9, R11    // x1 - y1 = z1', if z1' > x1 then overflow
+       SUBV    R8, R11, R12    // z1' - c0 = z1, if z1 > z1' then overflow
+       SGTU    R11, R9, R9
+       SGTU    R12, R11, R11
+       MOVV    R12, (R6)(R4)
+       OR      R9, R11, R8
+       ADDV    $8, R6
+       JMP     loop
+done:
+       MOVV    R8, c+72(FP)
+       RET
 
 // func addVW(z, x []Word, y Word) (c Word)
 TEXT ·addVW(SB),NOSPLIT,$0