math/big: optimize addVW 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_addvw.log │      test/new_3c5000_addvw.log      │
                │          sec/op           │   sec/op     vs base                │
AddVW/1                         9.555n ± 0%   5.915n ± 0%  -38.09% (p=0.000 n=20)
AddVW/2                        11.370n ± 0%   6.825n ± 0%  -39.97% (p=0.000 n=20)
AddVW/3                        12.485n ± 0%   7.970n ± 0%  -36.16% (p=0.000 n=20)
AddVW/4                        14.980n ± 0%   9.718n ± 0%  -35.13% (p=0.000 n=20)
AddVW/5                         16.73n ± 0%   10.63n ± 0%  -36.46% (p=0.000 n=20)
AddVW/10                        24.57n ± 0%   15.18n ± 0%  -38.23% (p=0.000 n=20)
AddVW/100                       184.9n ± 0%   102.4n ± 0%  -44.62% (p=0.000 n=20)
AddVW/1000                     1721.0n ± 0%   921.4n ± 0%  -46.46% (p=0.000 n=20)
AddVW/10000                     16.83µ ± 0%   11.68µ ± 0%  -30.58% (p=0.000 n=20)
AddVW/100000                    184.7µ ± 0%   131.3µ ± 0%  -28.93% (p=0.000 n=20)
AddVWext/1                      9.554n ± 0%   5.915n ± 0%  -38.09% (p=0.000 n=20)
AddVWext/2                     11.370n ± 0%   6.825n ± 0%  -39.97% (p=0.000 n=20)
AddVWext/3                     12.505n ± 0%   7.969n ± 0%  -36.27% (p=0.000 n=20)
AddVWext/4                     14.980n ± 0%   9.718n ± 0%  -35.13% (p=0.000 n=20)
AddVWext/5                      16.70n ± 0%   10.63n ± 0%  -36.33% (p=0.000 n=20)
AddVWext/10                     24.54n ± 0%   15.18n ± 0%  -38.13% (p=0.000 n=20)
AddVWext/100                    185.0n ± 0%   102.4n ± 0%  -44.65% (p=0.000 n=20)
AddVWext/1000                  1721.0n ± 0%   921.4n ± 0%  -46.46% (p=0.000 n=20)
AddVWext/10000                  16.83µ ± 0%   11.68µ ± 0%  -30.60% (p=0.000 n=20)
AddVWext/100000                 184.9µ ± 0%   130.4µ ± 0%  -29.51% (p=0.000 n=20)
geomean                         155.5n        96.87n       -37.70%

Change-Id: I824a90cb365e09d7d0d4a2c53ff4b30cf057a75e
Reviewed-on: https://go-review.googlesource.com/c/go/+/659876
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: abner chenc <chenguoqi@loongson.cn>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Reviewed-by: Carlos Amedee <carlos@golang.org>

diff --git a/src/math/big/arith_loong64.s b/src/math/big/arith_loong64.s
index 12cfb84eea9397a48278235ecb82d79a1023a2db..a0130efc31737392ff8a0a117013aa612b491e36 100644 (file)
--- a/src/math/big/arith_loong64.s
+++ b/src/math/big/arith_loong64.s
@@ -15,8 +15,30 @@ TEXT ·addVV(SB),NOSPLIT,$0
 TEXT ·subVV(SB),NOSPLIT,$0
        JMP ·subVV_g(SB)
 
+// func addVW(z, x []Word, y Word) (c Word)
 TEXT ·addVW(SB),NOSPLIT,$0
-       JMP ·addVW_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
+loop:
+       BEQ     R5, R6, done
+       MOVV    (R6)(R7), R8
+       ADDV    R8, R10, R9     // x1 + c = z1, if z1 < x1 then z1 overflow
+       SGTU    R8, R9, R10
+       MOVV    R9, (R6)(R4)
+       ADDV    $8, R6
+       JMP     loop
+done:
+       MOVV    R10, c+56(FP)
+       RET
 
 TEXT ·subVW(SB),NOSPLIT,$0
        JMP ·subVW_g(SB)