mirror of
https://github.com/golang/go
synced 2024-09-24 23:20:12 -06:00
cmd/compile: optimize arm64's comparison
Add more optimization with TST/CMN. 1. A tiny benchmark shows more than 12% improvement. TSTCMN-4 378µs ± 0% 332µs ± 0% -12.15% (p=0.000 n=30+27) (https://github.com/benshi001/ugo1/blob/master/tstcmn_test.go) 2. There is little regression in the go1 benchmark, excluding noise. name old time/op new time/op delta BinaryTree17-4 19.1s ± 0% 19.1s ± 0% ~ (p=0.994 n=28+29) Fannkuch11-4 10.0s ± 0% 10.0s ± 0% ~ (p=0.198 n=30+25) FmtFprintfEmpty-4 233ns ± 0% 233ns ± 0% +0.14% (p=0.002 n=24+30) FmtFprintfString-4 428ns ± 0% 428ns ± 0% ~ (all equal) FmtFprintfInt-4 472ns ± 0% 472ns ± 0% ~ (all equal) FmtFprintfIntInt-4 725ns ± 0% 725ns ± 0% ~ (all equal) FmtFprintfPrefixedInt-4 889ns ± 0% 888ns ± 0% ~ (p=0.632 n=28+30) FmtFprintfFloat-4 1.20µs ± 0% 1.20µs ± 0% +0.05% (p=0.001 n=18+30) FmtManyArgs-4 3.00µs ± 0% 2.99µs ± 0% -0.07% (p=0.001 n=27+30) GobDecode-4 42.1ms ± 0% 42.2ms ± 0% +0.29% (p=0.000 n=28+28) GobEncode-4 38.6ms ± 9% 38.8ms ± 9% ~ (p=0.912 n=30+30) Gzip-4 2.07s ± 1% 2.05s ± 1% -0.64% (p=0.000 n=29+30) Gunzip-4 175ms ± 0% 175ms ± 0% -0.15% (p=0.001 n=30+30) HTTPClientServer-4 872µs ± 5% 880µs ± 6% ~ (p=0.196 n=30+29) JSONEncode-4 88.5ms ± 1% 89.8ms ± 1% +1.49% (p=0.000 n=23+24) JSONDecode-4 393ms ± 1% 390ms ± 1% -0.89% (p=0.000 n=28+30) Mandelbrot200-4 19.5ms ± 0% 19.5ms ± 0% ~ (p=0.405 n=29+28) GoParse-4 19.9ms ± 0% 20.0ms ± 0% +0.27% (p=0.000 n=30+30) RegexpMatchEasy0_32-4 431ns ± 0% 431ns ± 0% ~ (p=1.000 n=30+30) RegexpMatchEasy0_1K-4 1.61µs ± 0% 1.61µs ± 0% ~ (p=0.527 n=26+26) RegexpMatchEasy1_32-4 443ns ± 0% 443ns ± 0% ~ (all equal) RegexpMatchEasy1_1K-4 2.58µs ± 1% 2.58µs ± 1% ~ (p=0.578 n=27+25) RegexpMatchMedium_32-4 740ns ± 0% 740ns ± 0% ~ (p=0.357 n=30+30) RegexpMatchMedium_1K-4 223µs ± 0% 223µs ± 0% +0.16% (p=0.000 n=30+29) RegexpMatchHard_32-4 12.3µs ± 0% 12.3µs ± 0% ~ (p=0.236 n=27+27) RegexpMatchHard_1K-4 371µs ± 0% 371µs ± 0% +0.09% (p=0.000 n=30+27) Revcomp-4 2.85s ± 0% 2.85s ± 0% ~ (p=0.057 n=28+25) Template-4 408ms ± 1% 409ms ± 1% ~ (p=0.117 n=29+29) TimeParse-4 1.93µs ± 0% 1.93µs ± 0% ~ (p=0.535 n=29+28) TimeFormat-4 1.99µs ± 0% 1.99µs ± 0% ~ (p=0.168 n=29+28) [Geo mean] 306µs 307µs +0.07% name old speed new speed delta GobDecode-4 18.3MB/s ± 0% 18.2MB/s ± 0% -0.31% (p=0.000 n=28+29) GobEncode-4 19.9MB/s ± 8% 19.8MB/s ± 9% ~ (p=0.923 n=30+30) Gzip-4 9.39MB/s ± 1% 9.45MB/s ± 1% +0.65% (p=0.000 n=29+30) Gunzip-4 111MB/s ± 0% 111MB/s ± 0% +0.15% (p=0.001 n=30+30) JSONEncode-4 21.9MB/s ± 1% 21.6MB/s ± 1% -1.45% (p=0.000 n=23+23) JSONDecode-4 4.94MB/s ± 1% 4.98MB/s ± 1% +0.84% (p=0.000 n=27+30) GoParse-4 2.91MB/s ± 0% 2.90MB/s ± 0% -0.34% (p=0.000 n=21+22) RegexpMatchEasy0_32-4 74.1MB/s ± 0% 74.1MB/s ± 0% ~ (p=0.469 n=29+28) RegexpMatchEasy0_1K-4 634MB/s ± 0% 634MB/s ± 0% ~ (p=0.978 n=24+28) RegexpMatchEasy1_32-4 72.2MB/s ± 0% 72.2MB/s ± 0% ~ (p=0.064 n=27+29) RegexpMatchEasy1_1K-4 396MB/s ± 1% 396MB/s ± 1% ~ (p=0.583 n=27+25) RegexpMatchMedium_32-4 1.35MB/s ± 0% 1.35MB/s ± 0% ~ (all equal) RegexpMatchMedium_1K-4 4.60MB/s ± 0% 4.59MB/s ± 0% -0.14% (p=0.000 n=30+26) RegexpMatchHard_32-4 2.61MB/s ± 0% 2.61MB/s ± 0% ~ (all equal) RegexpMatchHard_1K-4 2.76MB/s ± 0% 2.76MB/s ± 0% ~ (all equal) Revcomp-4 89.1MB/s ± 0% 89.1MB/s ± 0% ~ (p=0.059 n=28+25) Template-4 4.75MB/s ± 1% 4.75MB/s ± 1% ~ (p=0.106 n=29+29) [Geo mean] 18.3MB/s 18.3MB/s -0.07% Change-Id: I3cd76ce63e84b0c3cebabf9fa3573b76a7343899 Reviewed-on: https://go-review.googlesource.com/124935 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
This commit is contained in:
Ben Shi
parent
b444215116
commit
0e9f1de0b7
@ -574,8 +574,17 @@
|
||||
|
||||
(EQ (CMPconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (EQ (TST x y) yes no)
|
||||
(NE (CMPconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (NE (TST x y) yes no)
|
||||
(LT (CMPconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (LT (TST x y) yes no)
|
||||
(LE (CMPconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (LE (TST x y) yes no)
|
||||
(GT (CMPconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (GT (TST x y) yes no)
|
||||
(GE (CMPconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (GE (TST x y) yes no)
|
||||
|
||||
(EQ (CMPWconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (EQ (TSTW x y) yes no)
|
||||
(NE (CMPWconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (NE (TSTW x y) yes no)
|
||||
(LT (CMPWconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (LT (TSTW x y) yes no)
|
||||
(LE (CMPWconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (LE (TSTW x y) yes no)
|
||||
(GT (CMPWconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (GT (TSTW x y) yes no)
|
||||
(GE (CMPWconst [0] z:(AND x y)) yes no) && z.Uses == 1 -> (GE (TSTW x y) yes no)
|
||||
|
||||
(EQ (CMPconst [0] x:(ANDconst [c] y)) yes no) && x.Uses == 1 -> (EQ (TSTconst [c] y) yes no)
|
||||
(NE (CMPconst [0] x:(ANDconst [c] y)) yes no) && x.Uses == 1 -> (NE (TSTconst [c] y) yes no)
|
||||
@ -584,10 +593,47 @@
|
||||
(GT (CMPconst [0] x:(ANDconst [c] y)) yes no) && x.Uses == 1 -> (GT (TSTconst [c] y) yes no)
|
||||
(GE (CMPconst [0] x:(ANDconst [c] y)) yes no) && x.Uses == 1 -> (GE (TSTconst [c] y) yes no)
|
||||
|
||||
(EQ (CMPconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (EQ (CMNconst [c] y) yes no)
|
||||
(NE (CMPconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (NE (CMNconst [c] y) yes no)
|
||||
(LT (CMPconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (LT (CMNconst [c] y) yes no)
|
||||
(LE (CMPconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (LE (CMNconst [c] y) yes no)
|
||||
(GT (CMPconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (GT (CMNconst [c] y) yes no)
|
||||
(GE (CMPconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (GE (CMNconst [c] y) yes no)
|
||||
|
||||
(EQ (CMPWconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (EQ (CMNWconst [c] y) yes no)
|
||||
(NE (CMPWconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (NE (CMNWconst [c] y) yes no)
|
||||
(LT (CMPWconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (LT (CMNWconst [c] y) yes no)
|
||||
(LE (CMPWconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (LE (CMNWconst [c] y) yes no)
|
||||
(GT (CMPWconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (GT (CMNWconst [c] y) yes no)
|
||||
(GE (CMPWconst [0] x:(ADDconst [c] y)) yes no) && x.Uses == 1 -> (GE (CMNWconst [c] y) yes no)
|
||||
|
||||
(EQ (CMPconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (EQ (CMN x y) yes no)
|
||||
(NE (CMPconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (NE (CMN x y) yes no)
|
||||
(LT (CMPconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (LT (CMN x y) yes no)
|
||||
(LE (CMPconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (LE (CMN x y) yes no)
|
||||
(GT (CMPconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (GT (CMN x y) yes no)
|
||||
(GE (CMPconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (GE (CMN x y) yes no)
|
||||
|
||||
(EQ (CMPWconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (EQ (CMNW x y) yes no)
|
||||
(NE (CMPWconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (NE (CMNW x y) yes no)
|
||||
(LT (CMPWconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (LT (CMNW x y) yes no)
|
||||
(LE (CMPWconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (LE (CMNW x y) yes no)
|
||||
(GT (CMPWconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (GT (CMNW x y) yes no)
|
||||
(GE (CMPWconst [0] z:(ADD x y)) yes no) && z.Uses == 1 -> (GE (CMNW x y) yes no)
|
||||
|
||||
(EQ (CMP x z:(NEG y)) yes no) && z.Uses == 1 -> (EQ (CMN x y) yes no)
|
||||
(NE (CMP x z:(NEG y)) yes no) && z.Uses == 1 -> (NE (CMN x y) yes no)
|
||||
(LT (CMP x z:(NEG y)) yes no) && z.Uses == 1 -> (LT (CMN x y) yes no)
|
||||
(LE (CMP x z:(NEG y)) yes no) && z.Uses == 1 -> (LE (CMN x y) yes no)
|
||||
(GT (CMP x z:(NEG y)) yes no) && z.Uses == 1 -> (GT (CMN x y) yes no)
|
||||
(GE (CMP x z:(NEG y)) yes no) && z.Uses == 1 -> (GE (CMN x y) yes no)
|
||||
|
||||
(EQ (CMPW x z:(NEG y)) yes no) && z.Uses == 1 -> (EQ (CMNW x y) yes no)
|
||||
(NE (CMPW x z:(NEG y)) yes no) && z.Uses == 1 -> (NE (CMNW x y) yes no)
|
||||
(LT (CMPW x z:(NEG y)) yes no) && z.Uses == 1 -> (LT (CMNW x y) yes no)
|
||||
(LE (CMPW x z:(NEG y)) yes no) && z.Uses == 1 -> (LE (CMNW x y) yes no)
|
||||
(GT (CMPW x z:(NEG y)) yes no) && z.Uses == 1 -> (GT (CMNW x y) yes no)
|
||||
(GE (CMPW x z:(NEG y)) yes no) && z.Uses == 1 -> (GE (CMNW x y) yes no)
|
||||
|
||||
(EQ (CMPconst [0] x) yes no) -> (Z x yes no)
|
||||
(NE (CMPconst [0] x) yes no) -> (NZ x yes no)
|
||||
@ -1066,7 +1112,9 @@
|
||||
(OR x (MOVDconst [c])) -> (ORconst [c] x)
|
||||
(XOR x (MOVDconst [c])) -> (XORconst [c] x)
|
||||
(TST x (MOVDconst [c])) -> (TSTconst [c] x)
|
||||
(TSTW x (MOVDconst [c])) -> (TSTWconst [c] x)
|
||||
(CMN x (MOVDconst [c])) -> (CMNconst [c] x)
|
||||
(CMNW x (MOVDconst [c])) -> (CMNWconst [c] x)
|
||||
(BIC x (MOVDconst [c])) -> (ANDconst [^c] x)
|
||||
(EON x (MOVDconst [c])) -> (XORconst [^c] x)
|
||||
(ORN x (MOVDconst [c])) -> (ORconst [^c] x)
|
||||
|
||||
@ -258,13 +258,13 @@ func init() {
|
||||
{name: "CMPconst", argLength: 1, reg: gp1flags, asm: "CMP", aux: "Int64", typ: "Flags"}, // arg0 compare to auxInt
|
||||
{name: "CMPW", argLength: 2, reg: gp2flags, asm: "CMPW", typ: "Flags"}, // arg0 compare to arg1, 32 bit
|
||||
{name: "CMPWconst", argLength: 1, reg: gp1flags, asm: "CMPW", aux: "Int32", typ: "Flags"}, // arg0 compare to auxInt, 32 bit
|
||||
{name: "CMN", argLength: 2, reg: gp2flags, asm: "CMN", typ: "Flags"}, // arg0 compare to -arg1
|
||||
{name: "CMN", argLength: 2, reg: gp2flags, asm: "CMN", typ: "Flags", commutative: true}, // arg0 compare to -arg1
|
||||
{name: "CMNconst", argLength: 1, reg: gp1flags, asm: "CMN", aux: "Int64", typ: "Flags"}, // arg0 compare to -auxInt
|
||||
{name: "CMNW", argLength: 2, reg: gp2flags, asm: "CMNW", typ: "Flags"}, // arg0 compare to -arg1, 32 bit
|
||||
{name: "CMNW", argLength: 2, reg: gp2flags, asm: "CMNW", typ: "Flags", commutative: true}, // arg0 compare to -arg1, 32 bit
|
||||
{name: "CMNWconst", argLength: 1, reg: gp1flags, asm: "CMNW", aux: "Int32", typ: "Flags"}, // arg0 compare to -auxInt, 32 bit
|
||||
{name: "TST", argLength: 2, reg: gp2flags, asm: "TST", typ: "Flags"}, // arg0 & arg1 compare to 0
|
||||
{name: "TST", argLength: 2, reg: gp2flags, asm: "TST", typ: "Flags", commutative: true}, // arg0 & arg1 compare to 0
|
||||
{name: "TSTconst", argLength: 1, reg: gp1flags, asm: "TST", aux: "Int64", typ: "Flags"}, // arg0 & auxInt compare to 0
|
||||
{name: "TSTW", argLength: 2, reg: gp2flags, asm: "TSTW", typ: "Flags"}, // arg0 & arg1 compare to 0, 32 bit
|
||||
{name: "TSTW", argLength: 2, reg: gp2flags, asm: "TSTW", typ: "Flags", commutative: true}, // arg0 & arg1 compare to 0, 32 bit
|
||||
{name: "TSTWconst", argLength: 1, reg: gp1flags, asm: "TSTW", aux: "Int32", typ: "Flags"}, // arg0 & auxInt compare to 0, 32 bit
|
||||
{name: "FCMPS", argLength: 2, reg: fp2flags, asm: "FCMPS", typ: "Flags"}, // arg0 compare to arg1, float32
|
||||
{name: "FCMPD", argLength: 2, reg: fp2flags, asm: "FCMPD", typ: "Flags"}, // arg0 compare to arg1, float64
|
||||
|
||||
@ -15205,9 +15205,10 @@ var opcodeTable = [...]opInfo{
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "CMN",
|
||||
argLen: 2,
|
||||
asm: arm64.ACMN,
|
||||
name: "CMN",
|
||||
argLen: 2,
|
||||
commutative: true,
|
||||
asm: arm64.ACMN,
|
||||
reg: regInfo{
|
||||
inputs: []inputInfo{
|
||||
{0, 805044223}, // R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15 R16 R17 R19 R20 R21 R22 R23 R24 R25 R26 g R30
|
||||
@ -15227,9 +15228,10 @@ var opcodeTable = [...]opInfo{
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "CMNW",
|
||||
argLen: 2,
|
||||
asm: arm64.ACMNW,
|
||||
name: "CMNW",
|
||||
argLen: 2,
|
||||
commutative: true,
|
||||
asm: arm64.ACMNW,
|
||||
reg: regInfo{
|
||||
inputs: []inputInfo{
|
||||
{0, 805044223}, // R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15 R16 R17 R19 R20 R21 R22 R23 R24 R25 R26 g R30
|
||||
@ -15249,9 +15251,10 @@ var opcodeTable = [...]opInfo{
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "TST",
|
||||
argLen: 2,
|
||||
asm: arm64.ATST,
|
||||
name: "TST",
|
||||
argLen: 2,
|
||||
commutative: true,
|
||||
asm: arm64.ATST,
|
||||
reg: regInfo{
|
||||
inputs: []inputInfo{
|
||||
{0, 805044223}, // R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15 R16 R17 R19 R20 R21 R22 R23 R24 R25 R26 g R30
|
||||
@ -15271,9 +15274,10 @@ var opcodeTable = [...]opInfo{
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "TSTW",
|
||||
argLen: 2,
|
||||
asm: arm64.ATSTW,
|
||||
name: "TSTW",
|
||||
argLen: 2,
|
||||
commutative: true,
|
||||
asm: arm64.ATSTW,
|
||||
reg: regInfo{
|
||||
inputs: []inputInfo{
|
||||
{0, 805044223}, // R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15 R16 R17 R19 R20 R21 R22 R23 R24 R25 R26 g R30
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -158,13 +158,39 @@ func CmpZero4(a int64, ptr *int) {
|
||||
}
|
||||
}
|
||||
|
||||
func CmpToZero(a, b int32) int32 {
|
||||
if a&b < 0 { // arm:`TST`,-`AND`
|
||||
func CmpToZero(a, b, d int32) int32 {
|
||||
// arm:`TST`,-`AND`
|
||||
// arm64:`TSTW`,-`AND`
|
||||
c0 := a&b < 0
|
||||
// arm:`CMN`,-`ADD`
|
||||
// arm64:`CMNW`,-`ADD`
|
||||
c1 := a+b < 0
|
||||
// arm:`TEQ`,-`XOR`
|
||||
c2 := a^b < 0
|
||||
// arm64:`TST`,-`AND`
|
||||
c3 := int64(a)&int64(b) < 0
|
||||
// arm64:`CMN`,-`ADD`
|
||||
c4 := int64(a)+int64(b) < 0
|
||||
// not optimized to CMNW/CMN due to further use of b+d
|
||||
// arm64:`ADD`,-`CMNW`
|
||||
c5 := b+d == 0
|
||||
// not optimized to TSTW/TST due to further use of a&d
|
||||
// arm64:`AND`,-`TSTW`
|
||||
c6 := a&d >= 0
|
||||
if c0 {
|
||||
return 1
|
||||
} else if a+b < 0 { // arm:`CMN`,-`ADD`
|
||||
} else if c1 {
|
||||
return 2
|
||||
} else if a^b < 0 { // arm:`TEQ`,-`XOR`
|
||||
} else if c2 {
|
||||
return 3
|
||||
} else if c3 {
|
||||
return 4
|
||||
} else if c4 {
|
||||
return 5
|
||||
} else if c5 {
|
||||
return b + d
|
||||
} else if c6 {
|
||||
return a & d
|
||||
} else {
|
||||
return 0
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user