cmd/compile: optimize shifts of int32 and uint32 on loong64

goos: linux
goarch: loong64
pkg: math/bits
cpu: Loongson-3A6000-HV @ 2500.00MHz
                |  bench.old   |              bench.new               |
                |    sec/op    |    sec/op     vs base                |
LeadingZeros       1.100n ± 1%    1.101n ± 0%        ~ (p=0.566 n=10)
LeadingZeros8      1.501n ± 0%    1.502n ± 0%   +0.07% (p=0.000 n=10)
LeadingZeros16     1.501n ± 0%    1.502n ± 0%   +0.07% (p=0.000 n=10)
LeadingZeros32    1.2010n ± 0%   0.9511n ± 0%  -20.81% (p=0.000 n=10)
LeadingZeros64     1.104n ± 1%    1.119n ± 0%   +1.40% (p=0.000 n=10)
TrailingZeros     0.8137n ± 0%   0.8086n ± 0%   -0.63% (p=0.001 n=10)
TrailingZeros8     1.031n ± 1%    1.031n ± 1%        ~ (p=0.956 n=10)
TrailingZeros16   0.8204n ± 1%   0.8114n ± 0%   -1.11% (p=0.000 n=10)
TrailingZeros32   0.8145n ± 0%   0.8090n ± 0%   -0.68% (p=0.000 n=10)
TrailingZeros64   0.8159n ± 0%   0.8089n ± 1%   -0.86% (p=0.000 n=10)
OnesCount         0.8672n ± 0%   0.8677n ± 0%   +0.06% (p=0.000 n=10)
OnesCount8        0.8005n ± 0%   0.8009n ± 0%   +0.06% (p=0.000 n=10)
OnesCount16       0.9339n ± 0%   0.9344n ± 0%   +0.05% (p=0.000 n=10)
OnesCount32       0.8672n ± 0%   0.8677n ± 0%   +0.06% (p=0.000 n=10)
OnesCount64        1.201n ± 0%    1.201n ± 0%        ~ (p=0.474 n=10)
RotateLeft        0.8005n ± 0%   0.8009n ± 0%   +0.05% (p=0.000 n=10)
RotateLeft8        1.202n ± 0%    1.202n ± 0%        ~ (p=0.210 n=10)
RotateLeft16      0.8050n ± 0%   0.8036n ± 0%   -0.17% (p=0.002 n=10)
RotateLeft32      0.6674n ± 0%   0.6674n ± 0%        ~ (p=1.000 n=10)
RotateLeft64      0.6673n ± 0%   0.6674n ± 0%        ~ (p=0.072 n=10)
Reverse           0.4123n ± 0%   0.4067n ± 1%   -1.37% (p=0.000 n=10)
Reverse8          0.8005n ± 0%   0.8009n ± 0%   +0.05% (p=0.000 n=10)
Reverse16         0.8004n ± 0%   0.8009n ± 0%   +0.06% (p=0.000 n=10)
Reverse32         0.8004n ± 0%   0.8009n ± 0%   +0.06% (p=0.000 n=10)
Reverse64         0.8004n ± 0%   0.8009n ± 0%   +0.06% (p=0.001 n=10)
ReverseBytes      0.4100n ± 1%   0.4057n ± 1%   -1.06% (p=0.002 n=10)
ReverseBytes16    0.8004n ± 0%   0.8009n ± 0%   +0.07% (p=0.000 n=10)
ReverseBytes32    0.8005n ± 0%   0.8009n ± 0%   +0.05% (p=0.000 n=10)
ReverseBytes64    0.8005n ± 0%   0.8009n ± 0%   +0.05% (p=0.000 n=10)
Add                1.201n ± 0%    1.201n ± 0%        ~ (p=1.000 n=10)
Add32              1.201n ± 0%    1.201n ± 0%        ~ (p=0.474 n=10)
Add64              1.201n ± 0%    1.201n ± 0%        ~ (p=1.000 n=10)
Add64multiple      1.831n ± 0%    1.832n ± 0%        ~ (p=1.000 n=10)
Sub                1.201n ± 0%    1.201n ± 0%        ~ (p=1.000 n=10)
Sub32              1.601n ± 0%    1.602n ± 0%   +0.06% (p=0.000 n=10)
Sub64              1.201n ± 0%    1.201n ± 0%        ~ (p=0.474 n=10)
Sub64multiple      2.400n ± 0%    2.402n ± 0%   +0.10% (p=0.000 n=10)
Mul               0.8005n ± 0%   0.8009n ± 0%   +0.05% (p=0.000 n=10)
Mul32             0.8005n ± 0%   0.8009n ± 0%   +0.05% (p=0.000 n=10)
Mul64             0.8004n ± 0%   0.8008n ± 0%   +0.05% (p=0.000 n=10)
Div                9.107n ± 0%    9.083n ± 0%        ~ (p=0.255 n=10)
Div32              4.009n ± 0%    4.011n ± 0%   +0.05% (p=0.000 n=10)
Div64              9.705n ± 0%    9.711n ± 0%   +0.06% (p=0.000 n=10)
geomean            1.089n         1.083n        -0.62%

goos: linux
goarch: loong64
pkg: math/bits
cpu: Loongson-3A5000 @ 2500.00MHz
                |  bench.old   |              bench.new               |
                |    sec/op    |    sec/op     vs base                |
LeadingZeros       1.352n ± 0%    1.341n ± 4%   -0.81% (p=0.024 n=10)
LeadingZeros8      1.766n ± 0%    1.781n ± 0%   +0.88% (p=0.000 n=10)
LeadingZeros16     1.766n ± 0%    1.782n ± 0%   +0.88% (p=0.000 n=10)
LeadingZeros32     1.536n ± 0%    1.341n ± 1%  -12.73% (p=0.000 n=10)
LeadingZeros64     1.351n ± 1%    1.338n ± 0%   -0.96% (p=0.000 n=10)
TrailingZeros     0.9037n ± 0%   0.9025n ± 0%   -0.12% (p=0.020 n=10)
TrailingZeros8     1.087n ± 3%    1.056n ± 0%        ~ (p=0.060 n=10)
TrailingZeros16    1.101n ± 0%    1.101n ± 0%        ~ (p=0.211 n=10)
TrailingZeros32   0.9040n ± 0%   0.9024n ± 1%   -0.18% (p=0.017 n=10)
TrailingZeros64   0.9043n ± 0%   0.9028n ± 1%        ~ (p=0.118 n=10)
OnesCount          1.503n ± 2%    1.482n ± 1%   -1.43% (p=0.001 n=10)
OnesCount8         1.207n ± 0%    1.206n ± 0%   -0.12% (p=0.000 n=10)
OnesCount16        1.501n ± 0%    1.534n ± 0%   +2.13% (p=0.000 n=10)
OnesCount32        1.483n ± 1%    1.531n ± 1%   +3.27% (p=0.000 n=10)
OnesCount64        1.301n ± 0%    1.302n ± 0%   +0.08% (p=0.000 n=10)
RotateLeft        0.8136n ± 4%   0.8083n ± 0%   -0.66% (p=0.002 n=10)
RotateLeft8        1.311n ± 0%    1.310n ± 0%        ~ (p=0.786 n=10)
RotateLeft16       1.165n ± 0%    1.149n ± 0%   -1.33% (p=0.001 n=10)
RotateLeft32      0.8138n ± 1%   0.8093n ± 0%   -0.57% (p=0.017 n=10)
RotateLeft64      0.8149n ± 1%   0.8088n ± 0%   -0.74% (p=0.000 n=10)
Reverse           0.5195n ± 1%   0.5109n ± 0%   -1.67% (p=0.000 n=10)
Reverse8          0.8007n ± 0%   0.8010n ± 0%   +0.04% (p=0.000 n=10)
Reverse16         0.8007n ± 0%   0.8010n ± 0%   +0.04% (p=0.000 n=10)
Reverse32         0.8007n ± 0%   0.8010n ± 0%   +0.04% (p=0.012 n=10)
Reverse64         0.8007n ± 0%   0.8010n ± 0%   +0.04% (p=0.010 n=10)
ReverseBytes      0.5120n ± 1%   0.5122n ± 2%        ~ (p=0.306 n=10)
ReverseBytes16    0.8007n ± 0%   0.8010n ± 0%   +0.04% (p=0.000 n=10)
ReverseBytes32    0.8007n ± 0%   0.8010n ± 0%   +0.04% (p=0.000 n=10)
ReverseBytes64    0.8007n ± 0%   0.8010n ± 0%   +0.04% (p=0.000 n=10)
Add                1.201n ± 0%    1.201n ± 4%        ~ (p=0.334 n=10)
Add32              1.201n ± 0%    1.201n ± 0%        ~ (p=0.563 n=10)
Add64              1.201n ± 0%    1.201n ± 1%        ~ (p=0.652 n=10)
Add64multiple      1.909n ± 0%    1.902n ± 0%        ~ (p=0.126 n=10)
Sub                1.201n ± 0%    1.201n ± 0%        ~ (p=1.000 n=10)
Sub32              1.655n ± 0%    1.654n ± 0%        ~ (p=0.589 n=10)
Sub64              1.201n ± 0%    1.201n ± 0%        ~ (p=1.000 n=10)
Sub64multiple      2.150n ± 0%    2.180n ± 4%   +1.37% (p=0.000 n=10)
Mul               0.9341n ± 0%   0.9345n ± 0%   +0.04% (p=0.011 n=10)
Mul32              1.053n ± 0%    1.030n ± 0%   -2.23% (p=0.000 n=10)
Mul64             0.9341n ± 0%   0.9345n ± 0%   +0.04% (p=0.018 n=10)
Div                11.59n ± 0%    11.57n ± 1%        ~ (p=0.091 n=10)
Div32              4.337n ± 0%    4.337n ± 1%        ~ (p=0.783 n=10)
Div64              12.81n ± 0%    12.76n ± 0%   -0.39% (p=0.001 n=10)
geomean            1.257n         1.252n        -0.46%

Change-Id: I9e93ea49736760c19dc6b6463d2aa95878121b7b
Reviewed-on: https://go-review.googlesource.com/c/go/+/627855
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: David Chase <drchase@google.com>
Reviewed-by: abner chenc <chenguoqi@loongson.cn>
Reviewed-by: Meidan Li <limeidan@loongson.cn>
Reviewed-by: Junyang Shao <shaojunyang@google.com>

1 files changed, 15 insertions, 0 deletions

diff --git a/test/codegen/shift.go b/test/codegen/shift.go
index 52efefb0ed..8254e974df 100644
--- a/test/codegen/shift.go
+++ b/test/codegen/shift.go
@@ -11,49 +11,58 @@ package codegen
 // ------------------ //
 
 func lshConst64x64(v int64) int64 {
+	// loong64:"SLLV"
 	// ppc64x:"SLD"
 	// riscv64:"SLLI",-"AND",-"SLTIU"
 	return v << uint64(33)
 }
 
 func rshConst64Ux64(v uint64) uint64 {
+	// loong64:"SRLV"
 	// ppc64x:"SRD"
 	// riscv64:"SRLI\t",-"AND",-"SLTIU"
 	return v >> uint64(33)
 }
 
 func rshConst64Ux64Overflow32(v uint32) uint64 {
+	// loong64:"MOVV\t\\$0,",-"SRL\t"
 	// riscv64:"MOV\t\\$0,",-"SRL"
 	return uint64(v) >> 32
 }
 
 func rshConst64Ux64Overflow16(v uint16) uint64 {
+	// loong64:"MOVV\t\\$0,",-"SRLV"
 	// riscv64:"MOV\t\\$0,",-"SRL"
 	return uint64(v) >> 16
 }
 
 func rshConst64Ux64Overflow8(v uint8) uint64 {
+	// loong64:"MOVV\t\\$0,",-"SRLV"
 	// riscv64:"MOV\t\\$0,",-"SRL"
 	return uint64(v) >> 8
 }
 
 func rshConst64x64(v int64) int64 {
+	// loong64:"SRAV"
 	// ppc64x:"SRAD"
 	// riscv64:"SRAI\t",-"OR",-"SLTIU"
 	return v >> uint64(33)
 }
 
 func rshConst64x64Overflow32(v int32) int64 {
+	// loong64:"SRA\t\\$31"
 	// riscv64:"SRAIW",-"SLLI",-"SRAI\t"
 	return int64(v) >> 32
 }
 
 func rshConst64x64Overflow16(v int16) int64 {
+	// loong64:"SLLV\t\\$48","SRAV\t\\$63"
 	// riscv64:"SLLI","SRAI",-"SRAIW"
 	return int64(v) >> 16
 }
 
 func rshConst64x64Overflow8(v int8) int64 {
+	// loong64:"SLLV\t\\$56","SRAV\t\\$63"
 	// riscv64:"SLLI","SRAI",-"SRAIW"
 	return int64(v) >> 8
 }
@@ -69,36 +78,42 @@ func lshConst64x1(v int64) int64 {
 }
 
 func lshConst32x64(v int32) int32 {
+	// loong64:"SLL\t"
 	// ppc64x:"SLW"
 	// riscv64:"SLLI",-"AND",-"SLTIU", -"MOVW"
 	return v << uint64(29)
 }
 
 func rshConst32Ux64(v uint32) uint32 {
+	// loong64:"SRL\t"
 	// ppc64x:"SRW"
 	// riscv64:"SRLIW",-"AND",-"SLTIU", -"MOVW"
 	return v >> uint64(29)
 }
 
 func rshConst32x64(v int32) int32 {
+	// loong64:"SRA\t"
 	// ppc64x:"SRAW"
 	// riscv64:"SRAIW",-"OR",-"SLTIU", -"MOVW"
 	return v >> uint64(29)
 }
 
 func lshConst64x32(v int64) int64 {
+	// loong64:"SLLV"
 	// ppc64x:"SLD"
 	// riscv64:"SLLI",-"AND",-"SLTIU"
 	return v << uint32(33)
 }
 
 func rshConst64Ux32(v uint64) uint64 {
+	// loong64:"SRLV"
 	// ppc64x:"SRD"
 	// riscv64:"SRLI\t",-"AND",-"SLTIU"
 	return v >> uint32(33)
 }
 
 func rshConst64x32(v int64) int64 {
+	// loong64:"SRAV"
 	// ppc64x:"SRAD"
 	// riscv64:"SRAI\t",-"OR",-"SLTIU"
 	return v >> uint32(33)