math/big: implement addVW in riscv64 assembly

This provides an assembly implementation of addVW for riscv64,
processing up to four words per loop, resulting in a significant
performance gain.

On a StarFive VisionFive 2:

                  │   addvw.1    │               addvw.2               │
                  │    sec/op    │   sec/op     vs base                │
AddVW/1-4            57.43n ± 0%   41.45n ± 0%  -27.83% (p=0.000 n=10)
AddVW/2-4            69.31n ± 0%   48.15n ± 0%  -30.53% (p=0.000 n=10)
AddVW/3-4            76.12n ± 0%   54.97n ± 0%  -27.79% (p=0.000 n=10)
AddVW/4-4            85.47n ± 0%   56.14n ± 0%  -34.32% (p=0.000 n=10)
AddVW/5-4            96.16n ± 0%   62.82n ± 0%  -34.67% (p=0.000 n=10)
AddVW/10-4          149.60n ± 0%   89.55n ± 0%  -40.14% (p=0.000 n=10)
AddVW/100-4         1115.0n ± 0%   549.3n ± 0%  -50.74% (p=0.000 n=10)
AddVW/1000-4        10.732µ ± 0%   5.060µ ± 0%  -52.85% (p=0.000 n=10)
AddVW/10000-4        151.7µ ± 0%   103.7µ ± 0%  -31.63% (p=0.000 n=10)
AddVW/100000-4       1.523m ± 0%   1.050m ± 0%  -31.03% (p=0.000 n=10)
AddVWext/1-4         57.42n ± 0%   41.45n ± 0%  -27.81% (p=0.000 n=10)
AddVWext/2-4         69.32n ± 0%   48.15n ± 0%  -30.54% (p=0.000 n=10)
AddVWext/3-4         76.12n ± 0%   54.87n ± 0%  -27.92% (p=0.000 n=10)
AddVWext/4-4         85.47n ± 0%   56.14n ± 0%  -34.32% (p=0.000 n=10)
AddVWext/5-4         96.15n ± 0%   62.82n ± 0%  -34.66% (p=0.000 n=10)
AddVWext/10-4       149.60n ± 0%   89.55n ± 0%  -40.14% (p=0.000 n=10)
AddVWext/100-4      1115.0n ± 0%   549.3n ± 0%  -50.74% (p=0.000 n=10)
AddVWext/1000-4     10.732µ ± 0%   5.060µ ± 0%  -52.85% (p=0.000 n=10)
AddVWext/10000-4     150.5µ ± 0%   103.7µ ± 0%  -31.10% (p=0.000 n=10)
AddVWext/100000-4    1.530m ± 0%   1.049m ± 0%  -31.41% (p=0.000 n=10)
geomean              1.003µ        633.9n       -36.79%

                  │   addvw.1    │                addvw.2                 │
                  │     B/s      │      B/s       vs base                 │
AddVW/1-4           132.8Mi ± 0%    184.1Mi ± 0%   +38.55% (p=0.000 n=10)
AddVW/2-4           220.1Mi ± 0%    316.9Mi ± 0%   +43.96% (p=0.000 n=10)
AddVW/3-4           300.7Mi ± 0%    416.4Mi ± 0%   +38.48% (p=0.000 n=10)
AddVW/4-4           357.1Mi ± 0%    543.6Mi ± 0%   +52.25% (p=0.000 n=10)
AddVW/5-4           396.7Mi ± 0%    607.2Mi ± 0%   +53.06% (p=0.000 n=10)
AddVW/10-4          510.1Mi ± 0%    852.0Mi ± 0%   +67.02% (p=0.000 n=10)
AddVW/100-4         684.1Mi ± 0%   1389.0Mi ± 0%  +103.03% (p=0.000 n=10)
AddVW/1000-4        710.9Mi ± 0%   1507.8Mi ± 0%  +112.08% (p=0.000 n=10)
AddVW/10000-4       503.1Mi ± 0%    735.8Mi ± 0%   +46.26% (p=0.000 n=10)
AddVW/100000-4      501.0Mi ± 0%    726.5Mi ± 0%   +45.00% (p=0.000 n=10)
AddVWext/1-4        132.9Mi ± 0%    184.1Mi ± 0%   +38.55% (p=0.000 n=10)
AddVWext/2-4        220.1Mi ± 0%    316.9Mi ± 0%   +43.98% (p=0.000 n=10)
AddVWext/3-4        300.7Mi ± 0%    417.1Mi ± 0%   +38.73% (p=0.000 n=10)
AddVWext/4-4        357.1Mi ± 0%    543.6Mi ± 0%   +52.25% (p=0.000 n=10)
AddVWext/5-4        396.7Mi ± 0%    607.2Mi ± 0%   +53.05% (p=0.000 n=10)
AddVWext/10-4       510.1Mi ± 0%    852.0Mi ± 0%   +67.02% (p=0.000 n=10)
AddVWext/100-4      684.2Mi ± 0%   1389.0Mi ± 0%  +103.02% (p=0.000 n=10)
AddVWext/1000-4     710.9Mi ± 0%   1507.7Mi ± 0%  +112.08% (p=0.000 n=10)
AddVWext/10000-4    506.9Mi ± 0%    735.8Mi ± 0%   +45.15% (p=0.000 n=10)
AddVWext/100000-4   498.6Mi ± 0%    727.0Mi ± 0%   +45.79% (p=0.000 n=10)
geomean             388.3Mi         614.3Mi        +58.19%

Change-Id: Ib14a4b8c1d81e710753bbf6dd5546bbca44fe3f1
Reviewed-on: https://go-review.googlesource.com/c/go/+/595397
Reviewed-by: Meng Zhuo <mengzhuo1203@gmail.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Mark Ryan <markdryan@rivosinc.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>

diff --git a/src/math/big/arith_riscv64.s b/src/math/big/arith_riscv64.s
index 897d08229eef185c75287f6184b955b3fbed6dea..0029a5b6b44841b9022bce93a5889a7f65da97a1 100644 (file)
--- a/src/math/big/arith_riscv64.s
+++ b/src/math/big/arith_riscv64.s
@@ -174,7 +174,64 @@ done:
        RET
 
 TEXT ·addVW(SB),NOSPLIT,$0
-       JMP ·addVW_g(SB)
+       MOV     x+24(FP), X5
+       MOV     y+48(FP), X6
+       MOV     z+0(FP), X7
+       MOV     z_len+8(FP), X30
+
+       MOV     $4, X28
+       MOV     X6, X29         // c = y
+
+       BEQZ    X30, done
+       BLTU    X30, X28, loop1
+
+loop4:
+       MOV     0(X5), X8       // x[0]
+       MOV     8(X5), X11      // x[1]
+       MOV     16(X5), X14     // x[2]
+       MOV     24(X5), X17     // x[3]
+
+       ADD     X8, X29, X10    // z[0] = x[0] + c
+       SLTU    X8, X10, X29    // next c
+
+       ADD     X11, X29, X13   // z[1] = x[1] + c
+       SLTU    X11, X13, X29   // next c
+
+       ADD     X14, X29, X16   // z[2] = x[2] + c
+       SLTU    X14, X16, X29   // next c
+
+       ADD     X17, X29, X19   // z[3] = x[3] + c
+       SLTU    X17, X19, X29   // next c
+
+       MOV     X10, 0(X7)      // z[0]
+       MOV     X13, 8(X7)      // z[1]
+       MOV     X16, 16(X7)     // z[2]
+       MOV     X19, 24(X7)     // z[3]
+
+       ADD     $32, X5
+       ADD     $32, X7
+       SUB     $4, X30
+
+       BGEU    X30, X28, loop4
+       BEQZ    X30, done
+
+loop1:
+       MOV     0(X5), X10      // x
+
+       ADD     X10, X29, X12   // z = x + c
+       SLTU    X10, X12, X29   // next c
+
+       MOV     X12, 0(X7)      // z
+
+       ADD     $8, X5
+       ADD     $8, X7
+       SUB     $1, X30
+
+       BNEZ    X30, loop1
+
+done:
+       MOV     X29, c+56(FP)   // return c
+       RET
 
 TEXT ·subVW(SB),NOSPLIT,$0
        JMP ·subVW_g(SB)