]> Cypherpunks repositories - gostls13.git/commit
cmd/compile: add patterns for bitfield opcodes on loong64
authorXiaolin Zhao <zhaoxiaolin@loongson.cn>
Wed, 14 Aug 2024 09:11:08 +0000 (17:11 +0800)
committerabner chenc <chenguoqi@loongson.cn>
Fri, 18 Oct 2024 01:09:11 +0000 (01:09 +0000)
commite45c125a3c343767b3bb68f3512d8cffbf7691b9
treee5a402bcd85fda1f09600568eb35ea24b34c9181
parentef3e1dae2f151ddca4ba50ed8b9a98381d7e9158
cmd/compile: add patterns for bitfield opcodes on loong64

goos: linux
goarch: loong64
pkg: math/bits
cpu: Loongson-3A6000 @ 2500.00MHz
                |  bench.old   |              bench.new               |
                |    sec/op    |    sec/op     vs base                |
LeadingZeros      1.0095n ± 0%   0.8011n ± 0%  -20.64% (p=0.000 n=10)
LeadingZeros8      1.201n ± 0%    1.167n ± 0%   -2.83% (p=0.000 n=10)
LeadingZeros16     1.201n ± 0%    1.167n ± 0%   -2.83% (p=0.000 n=10)
LeadingZeros32     1.201n ± 0%    1.134n ± 0%   -5.58% (p=0.000 n=10)
LeadingZeros64    0.8007n ± 0%   1.0115n ± 0%  +26.32% (p=0.000 n=10)
TrailingZeros     0.8054n ± 0%   0.8106n ± 1%   +0.65% (p=0.000 n=10)
TrailingZeros8     1.067n ± 0%    1.002n ± 1%   -6.09% (p=0.000 n=10)
TrailingZeros16   1.0540n ± 0%   0.8389n ± 0%  -20.40% (p=0.000 n=10)
TrailingZeros32   0.8014n ± 0%   0.8117n ± 0%   +1.29% (p=0.000 n=10)
TrailingZeros64   0.8015n ± 0%   0.8124n ± 1%   +1.36% (p=0.000 n=10)
OnesCount          3.418n ± 0%    3.417n ± 0%        ~ (p=0.911 n=10)
OnesCount8        0.8004n ± 0%   0.8004n ± 0%        ~ (p=1.000 n=10)
OnesCount16        1.440n ± 0%    1.299n ± 0%   -9.79% (p=0.000 n=10)
OnesCount32        2.969n ± 0%    2.940n ± 0%   -0.94% (p=0.000 n=10)
OnesCount64        3.563n ± 0%    3.558n ± 0%   -0.14% (p=0.000 n=10)
RotateLeft        0.6677n ± 0%   0.6670n ± 0%        ~ (p=0.055 n=10)
RotateLeft8        1.318n ± 1%    1.321n ± 0%        ~ (p=0.117 n=10)
RotateLeft16      0.8457n ± 1%   0.8442n ± 0%        ~ (p=0.325 n=10)
RotateLeft32      0.8004n ± 0%   0.8004n ± 0%        ~ (p=0.837 n=10)
RotateLeft64      0.6678n ± 0%   0.6670n ± 0%   -0.13% (p=0.000 n=10)
Reverse           0.8004n ± 0%   0.8004n ± 0%        ~ (p=1.000 n=10)
Reverse8          0.6989n ± 0%   0.6969n ± 1%        ~ (p=0.138 n=10)
Reverse16         0.6998n ± 1%   0.7004n ± 1%        ~ (p=0.985 n=10)
Reverse32         0.4158n ± 1%   0.4159n ± 1%        ~ (p=0.870 n=10)
Reverse64         0.4165n ± 1%   0.4194n ± 2%        ~ (p=0.093 n=10)
ReverseBytes      0.8004n ± 0%   0.8004n ± 0%        ~ (p=1.000 n=10)
ReverseBytes16    0.4183n ± 2%   0.4148n ± 1%        ~ (p=0.055 n=10)
ReverseBytes32    0.4143n ± 2%   0.4153n ± 1%        ~ (p=0.869 n=10)
ReverseBytes64    0.4168n ± 1%   0.4177n ± 1%        ~ (p=0.184 n=10)
Add                1.201n ± 0%    1.201n ± 0%        ~ (p=0.087 n=10)
Add32              1.603n ± 0%    1.601n ± 0%   -0.12% (p=0.000 n=10)
Add64              1.201n ± 0%    1.201n ± 0%        ~ (p=0.211 n=10)
Add64multiple      1.839n ± 0%    1.835n ± 0%   -0.24% (p=0.001 n=10)
Sub                1.202n ± 0%    1.201n ± 0%   -0.04% (p=0.033 n=10)
Sub32              2.401n ± 0%    1.601n ± 0%  -33.32% (p=0.000 n=10)
Sub64              1.201n ± 0%    1.201n ± 0%        ~ (p=1.000 n=10)
Sub64multiple      2.105n ± 0%    2.096n ± 0%   -0.40% (p=0.000 n=10)
Mul               0.8008n ± 0%   0.8004n ± 0%   -0.05% (p=0.000 n=10)
Mul32             0.8041n ± 0%   0.8014n ± 0%   -0.34% (p=0.000 n=10)
Mul64             0.8008n ± 0%   0.8004n ± 0%   -0.05% (p=0.000 n=10)
Div                8.977n ± 0%    8.945n ± 0%   -0.36% (p=0.000 n=10)
Div32              4.084n ± 0%    4.086n ± 0%        ~ (p=0.445 n=10)
Div64              9.316n ± 0%    9.301n ± 0%   -0.17% (p=0.000 n=10)
geomean            1.141n         1.117n        -2.09%

Change-Id: I4dc1eaab6728f771bc722ed331fe5c6429bd1037
Reviewed-on: https://go-review.googlesource.com/c/go/+/618475
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Reviewed-by: Michael Knyszek <mknyszek@google.com>
Reviewed-by: Meidan Li <limeidan@loongson.cn>
Reviewed-by: abner chenc <chenguoqi@loongson.cn>
Reviewed-by: Qiqi Huang <huangqiqi@loongson.cn>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
src/cmd/compile/internal/loong64/ssa.go
src/cmd/compile/internal/ssa/_gen/LOONG64.rules
src/cmd/compile/internal/ssa/_gen/LOONG64Ops.go
src/cmd/compile/internal/ssa/opGen.go
src/cmd/compile/internal/ssa/rewriteLOONG64.go