cmd/compile: simplify bounded shift on loong64

Use the shiftIsBounded function to generate more efficient shift instructions.
This change also optimize shift ops when the shift value is v&63 and v&31.

goos: linux
goarch: loong64
pkg: math/bits
cpu: Loongson-3A6000-HV @ 2500.00MHz
                |  CL 627855   |               this CL                |
                |    sec/op    |    sec/op     vs base                |
LeadingZeros      1.1005n ± 0%   0.8425n ± 1%  -23.44% (p=0.000 n=10)
LeadingZeros8      1.502n ± 0%    1.501n ± 0%   -0.07% (p=0.001 n=10)
LeadingZeros16     1.502n ± 0%    1.501n ± 0%   -0.07% (p=0.000 n=10)
LeadingZeros32    0.9511n ± 0%   0.8050n ± 0%  -15.36% (p=0.000 n=10)
LeadingZeros64    1.1195n ± 0%   0.8423n ± 0%  -24.76% (p=0.000 n=10)
TrailingZeros     0.8086n ± 0%   0.8005n ± 0%   -1.00% (p=0.000 n=10)
TrailingZeros8     1.031n ± 1%    1.035n ± 1%        ~ (p=0.136 n=10)
TrailingZeros16   0.8114n ± 0%   0.8254n ± 1%   +1.73% (p=0.000 n=10)
TrailingZeros32   0.8090n ± 0%   0.8005n ± 0%   -1.05% (p=0.000 n=10)
TrailingZeros64   0.8089n ± 1%   0.8005n ± 0%   -1.04% (p=0.000 n=10)
OnesCount         0.8677n ± 0%   1.2010n ± 0%  +38.41% (p=0.000 n=10)
OnesCount8        0.8009n ± 0%   0.8004n ± 0%   -0.06% (p=0.000 n=10)
OnesCount16       0.9344n ± 0%   1.2010n ± 0%  +28.53% (p=0.000 n=10)
OnesCount32       0.8677n ± 0%   1.2010n ± 0%  +38.41% (p=0.000 n=10)
OnesCount64       1.2010n ± 0%   0.8671n ± 0%  -27.80% (p=0.000 n=10)
RotateLeft        0.8009n ± 0%   0.6671n ± 0%  -16.71% (p=0.000 n=10)
RotateLeft8        1.202n ± 0%    1.327n ± 0%  +10.40% (p=0.000 n=10)
RotateLeft16      0.8036n ± 0%   0.8218n ± 0%   +2.26% (p=0.000 n=10)
RotateLeft32      0.6674n ± 0%   0.8004n ± 0%  +19.94% (p=0.000 n=10)
RotateLeft64      0.6674n ± 0%   0.8004n ± 0%  +19.94% (p=0.000 n=10)
Reverse           0.4067n ± 1%   0.4122n ± 1%   +1.38% (p=0.001 n=10)
Reverse8          0.8009n ± 0%   0.8004n ± 0%   -0.06% (p=0.000 n=10)
Reverse16         0.8009n ± 0%   0.8005n ± 0%   -0.05% (p=0.000 n=10)
Reverse32         0.8009n ± 0%   0.8004n ± 0%   -0.06% (p=0.001 n=10)
Reverse64         0.8009n ± 0%   0.8004n ± 0%   -0.06% (p=0.008 n=10)
ReverseBytes      0.4057n ± 1%   0.4133n ± 1%   +1.90% (p=0.000 n=10)
ReverseBytes16    0.8009n ± 0%   0.8004n ± 0%   -0.07% (p=0.000 n=10)
ReverseBytes32    0.8009n ± 0%   0.8005n ± 0%   -0.05% (p=0.000 n=10)
ReverseBytes64    0.8009n ± 0%   0.8004n ± 0%   -0.06% (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      1.832n ± 0%    1.828n ± 0%   -0.22% (p=0.001 n=10)
Sub                1.201n ± 0%    1.201n ± 0%        ~ (p=1.000 n=10)
Sub32              1.602n ± 0%    1.601n ± 0%   -0.06% (p=0.000 n=10)
Sub64              1.201n ± 0%    1.201n ± 0%        ~ (p=0.474 n=10)
Sub64multiple      2.402n ± 0%    2.400n ± 0%   -0.10% (p=0.000 n=10)
Mul               0.8009n ± 0%   0.8004n ± 0%   -0.06% (p=0.000 n=10)
Mul32             0.8009n ± 0%   0.8004n ± 0%   -0.06% (p=0.000 n=10)
Mul64             0.8008n ± 0%   0.8004n ± 0%   -0.05% (p=0.000 n=10)
Div                9.083n ± 0%    7.638n ± 0%  -15.91% (p=0.000 n=10)
Div32              4.011n ± 0%    4.009n ± 0%   -0.05% (p=0.000 n=10)
Div64              9.711n ± 0%    8.204n ± 0%  -15.51% (p=0.000 n=10)
geomean            1.083n         1.078n        -0.40%

goos: linux
goarch: loong64
pkg: math/bits
cpu: Loongson-3A5000 @ 2500.00MHz
                |  CL 627855   |               this CL                |
                |    sec/op    |    sec/op     vs base                |
LeadingZeros       1.341n ± 4%    1.331n ± 2%   -0.71% (p=0.008 n=10)
LeadingZeros8      1.781n ± 0%    1.766n ± 1%   -0.84% (p=0.011 n=10)
LeadingZeros16     1.782n ± 0%    1.767n ± 0%   -0.79% (p=0.001 n=10)
LeadingZeros32     1.341n ± 1%    1.333n ± 0%   -0.52% (p=0.001 n=10)
LeadingZeros64     1.338n ± 0%    1.333n ± 0%   -0.37% (p=0.008 n=10)
TrailingZeros     0.9025n ± 0%   0.8077n ± 0%  -10.50% (p=0.000 n=10)
TrailingZeros8     1.056n ± 0%    1.089n ± 1%   +3.17% (p=0.001 n=10)
TrailingZeros16    1.101n ± 0%    1.102n ± 0%   +0.09% (p=0.011 n=10)
TrailingZeros32   0.9024n ± 1%   0.8083n ± 0%  -10.43% (p=0.000 n=10)
TrailingZeros64   0.9028n ± 1%   0.8087n ± 0%  -10.43% (p=0.000 n=10)
OnesCount          1.482n ± 1%    1.302n ± 0%  -12.15% (p=0.000 n=10)
OnesCount8         1.206n ± 0%    1.207n ± 2%   +0.12% (p=0.000 n=10)
OnesCount16        1.534n ± 0%    1.402n ± 0%   -8.58% (p=0.000 n=10)
OnesCount32        1.531n ± 1%    1.302n ± 0%  -14.99% (p=0.000 n=10)
OnesCount64        1.302n ± 0%    1.538n ± 1%  +18.16% (p=0.000 n=10)
RotateLeft        0.8083n ± 0%   0.8087n ± 1%        ~ (p=0.579 n=10)
RotateLeft8        1.310n ± 0%    1.323n ± 0%   +0.95% (p=0.001 n=10)
RotateLeft16       1.149n ± 0%    1.165n ± 1%   +1.35% (p=0.001 n=10)
RotateLeft32      0.8093n ± 0%   0.8105n ± 0%        ~ (p=0.393 n=10)
RotateLeft64      0.8088n ± 0%   0.8090n ± 0%        ~ (p=0.739 n=10)
Reverse           0.5109n ± 0%   0.5172n ± 1%   +1.25% (p=0.000 n=10)
Reverse8          0.8010n ± 0%   0.8011n ± 0%   +0.01% (p=0.000 n=10)
Reverse16         0.8010n ± 0%   0.8011n ± 0%   +0.01% (p=0.002 n=10)
Reverse32         0.8010n ± 0%   0.8011n ± 0%   +0.01% (p=0.000 n=10)
Reverse64         0.8010n ± 0%   0.8011n ± 0%   +0.01% (p=0.005 n=10)
ReverseBytes      0.5122n ± 2%   0.5182n ± 1%        ~ (p=0.060 n=10)
ReverseBytes16    0.8010n ± 0%   0.8011n ± 0%   +0.01% (p=0.005 n=10)
ReverseBytes32    0.8010n ± 0%   0.8011n ± 0%   +0.01% (p=0.005 n=10)
ReverseBytes64    0.8010n ± 0%   0.8011n ± 0%   +0.01% (p=0.001 n=10)
Add                1.201n ± 4%    1.202n ± 0%   +0.08% (p=0.028 n=10)
Add32              1.201n ± 0%    1.202n ± 2%   +0.08% (p=0.014 n=10)
Add64              1.201n ± 1%    1.202n ± 0%   +0.08% (p=0.025 n=10)
Add64multiple      1.902n ± 0%    1.913n ± 0%   +0.55% (p=0.004 n=10)
Sub                1.201n ± 0%    1.202n ± 3%   +0.08% (p=0.001 n=10)
Sub32              1.654n ± 0%    1.656n ± 1%        ~ (p=0.117 n=10)
Sub64              1.201n ± 0%    1.202n ± 0%   +0.08% (p=0.001 n=10)
Sub64multiple      2.180n ± 4%    2.159n ± 1%   -0.96% (p=0.006 n=10)
Mul               0.9345n ± 0%   0.9346n ± 0%   +0.01% (p=0.000 n=10)
Mul32              1.030n ± 0%    1.050n ± 1%   +1.94% (p=0.000 n=10)
Mul64             0.9345n ± 0%   0.9346n ± 1%   +0.01% (p=0.000 n=10)
Div                11.57n ± 1%    11.12n ± 0%   -3.85% (p=0.000 n=10)
Div32              4.337n ± 1%    4.341n ± 1%        ~ (p=0.286 n=10)
Div64              12.76n ± 0%    12.02n ± 3%   -5.80% (p=0.000 n=10)
geomean            1.252n         1.235n        -1.32%

Change-Id: Iec4cfd2b83bb0f946068c1d657369ff081d95b04
Reviewed-on: https://go-review.googlesource.com/c/go/+/628575
Reviewed-by: abner chenc <chenguoqi@loongson.cn>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Junyang Shao <shaojunyang@google.com>
Reviewed-by: David Chase <drchase@google.com>

1 files changed, 16 insertions, 0 deletions

diff --git a/test/codegen/shift.go b/test/codegen/shift.go
index 8254e974df..02842a5739 100644
--- a/test/codegen/shift.go
+++ b/test/codegen/shift.go
@@ -145,6 +145,7 @@ func lshConst64x2Add(x int64) int64 {
 
 func lshMask64x64(v int64, s uint64) int64 {
 	// arm64:"LSL",-"AND"
+	// loong64:"SLLV",-"AND"
 	// ppc64x:"RLDICL",-"ORN",-"ISEL"
 	// riscv64:"SLL",-"AND\t",-"SLTIU"
 	// s390x:-"RISBGZ",-"AND",-"LOCGR"
@@ -153,6 +154,7 @@ func lshMask64x64(v int64, s uint64) int64 {
 
 func rshMask64Ux64(v uint64, s uint64) uint64 {
 	// arm64:"LSR",-"AND",-"CSEL"
+	// loong64:"SRLV",-"AND"
 	// ppc64x:"RLDICL",-"ORN",-"ISEL"
 	// riscv64:"SRL\t",-"AND\t",-"SLTIU"
 	// s390x:-"RISBGZ",-"AND",-"LOCGR"
@@ -161,6 +163,7 @@ func rshMask64Ux64(v uint64, s uint64) uint64 {
 
 func rshMask64x64(v int64, s uint64) int64 {
 	// arm64:"ASR",-"AND",-"CSEL"
+	// loong64:"SRAV",-"AND"
 	// ppc64x:"RLDICL",-"ORN",-"ISEL"
 	// riscv64:"SRA\t",-"OR",-"SLTIU"
 	// s390x:-"RISBGZ",-"AND",-"LOCGR"
@@ -169,14 +172,21 @@ func rshMask64x64(v int64, s uint64) int64 {
 
 func lshMask32x64(v int32, s uint64) int32 {
 	// arm64:"LSL",-"AND"
+	// loong64:"SLL\t","AND","SGTU","MASKEQZ"
 	// ppc64x:"ISEL",-"ORN"
 	// riscv64:"SLL",-"AND\t",-"SLTIU"
 	// s390x:-"RISBGZ",-"AND",-"LOCGR"
 	return v << (s & 63)
 }
 
+func lsh5Mask32x64(v int32, s uint64) int32 {
+	// loong64:"SLL\t",-"AND"
+	return v << (s & 31)
+}
+
 func rshMask32Ux64(v uint32, s uint64) uint32 {
 	// arm64:"LSR",-"AND"
+	// loong64:"SRL\t","AND","SGTU","MASKEQZ"
 	// ppc64x:"ISEL",-"ORN"
 	// riscv64:"SRLW","SLTIU","NEG","AND\t",-"SRL\t"
 	// s390x:-"RISBGZ",-"AND",-"LOCGR"
@@ -184,12 +194,14 @@ func rshMask32Ux64(v uint32, s uint64) uint32 {
 }
 
 func rsh5Mask32Ux64(v uint32, s uint64) uint32 {
+	// loong64:"SRL\t",-"AND"
 	// riscv64:"SRLW",-"AND\t",-"SLTIU",-"SRL\t"
 	return v >> (s & 31)
 }
 
 func rshMask32x64(v int32, s uint64) int32 {
 	// arm64:"ASR",-"AND"
+	// loong64:"SRA\t","AND","SGTU","SUBVU","OR"
 	// ppc64x:"ISEL",-"ORN"
 	// riscv64:"SRAW","OR","SLTIU"
 	// s390x:-"RISBGZ",-"AND",-"LOCGR"
@@ -197,12 +209,14 @@ func rshMask32x64(v int32, s uint64) int32 {
 }
 
 func rsh5Mask32x64(v int32, s uint64) int32 {
+	// loong64:"SRA\t",-"AND"
 	// riscv64:"SRAW",-"OR",-"SLTIU"
 	return v >> (s & 31)
 }
 
 func lshMask64x32(v int64, s uint32) int64 {
 	// arm64:"LSL",-"AND"
+	// loong64:"SLLV",-"AND"
 	// ppc64x:"RLDICL",-"ORN"
 	// riscv64:"SLL",-"AND\t",-"SLTIU"
 	// s390x:-"RISBGZ",-"AND",-"LOCGR"
@@ -211,6 +225,7 @@ func lshMask64x32(v int64, s uint32) int64 {
 
 func rshMask64Ux32(v uint64, s uint32) uint64 {
 	// arm64:"LSR",-"AND",-"CSEL"
+	// loong64:"SRLV",-"AND"
 	// ppc64x:"RLDICL",-"ORN"
 	// riscv64:"SRL\t",-"AND\t",-"SLTIU"
 	// s390x:-"RISBGZ",-"AND",-"LOCGR"
@@ -219,6 +234,7 @@ func rshMask64Ux32(v uint64, s uint32) uint64 {
 
 func rshMask64x32(v int64, s uint32) int64 {
 	// arm64:"ASR",-"AND",-"CSEL"
+	// loong64:"SRAV",-"AND"
 	// ppc64x:"RLDICL",-"ORN",-"ISEL"
 	// riscv64:"SRA\t",-"OR",-"SLTIU"
 	// s390x:-"RISBGZ",-"AND",-"LOCGR"