cmd/compile: optimize 386's ADDLconstmodifyidx4

This CL optimize ADDLconstmodifyidx4 to INCL/DECL, when the
constant is +1/-1.

1. The total size of pkg/linux_386/ decreases 28 bytes, excluding
cmd/compile.

2. There is no regression in the go1 benchmark test, excluding noise.
name                     old time/op    new time/op    delta
BinaryTree17-4              3.25s ± 2%     3.23s ± 3%  -0.70%  (p=0.040 n=30+30)
Fannkuch11-4                3.50s ± 1%     3.47s ± 1%  -0.68%  (p=0.000 n=30+30)
FmtFprintfEmpty-4          44.6ns ± 3%    44.8ns ± 3%  +0.46%  (p=0.029 n=30+30)
FmtFprintfString-4         79.0ns ± 3%    78.7ns ± 3%    ~     (p=0.053 n=30+30)
FmtFprintfInt-4            89.2ns ± 2%    89.4ns ± 3%    ~     (p=0.665 n=30+29)
FmtFprintfIntInt-4          142ns ± 3%     142ns ± 3%    ~     (p=0.435 n=30+30)
FmtFprintfPrefixedInt-4     182ns ± 2%     182ns ± 2%    ~     (p=0.964 n=30+30)
FmtFprintfFloat-4           407ns ± 3%     411ns ± 4%    ~     (p=0.080 n=30+30)
FmtManyArgs-4               597ns ± 3%     593ns ± 4%    ~     (p=0.222 n=30+30)
GobDecode-4                7.09ms ± 6%    7.07ms ± 7%    ~     (p=0.633 n=30+30)
GobEncode-4                6.81ms ± 9%    6.81ms ± 8%    ~     (p=0.982 n=30+30)
Gzip-4                      398ms ± 4%     400ms ± 6%    ~     (p=0.177 n=30+30)
Gunzip-4                   41.3ms ± 3%    40.6ms ± 4%  -1.71%  (p=0.005 n=30+30)
HTTPClientServer-4         63.4µs ± 3%    63.4µs ± 4%    ~     (p=0.646 n=30+28)
JSONEncode-4               16.0ms ± 3%    16.1ms ± 3%    ~     (p=0.057 n=30+30)
JSONDecode-4               63.3ms ± 8%    63.1ms ± 7%    ~     (p=0.786 n=30+30)
Mandelbrot200-4            5.17ms ± 3%    5.15ms ± 8%    ~     (p=0.654 n=30+30)
GoParse-4                  3.24ms ± 3%    3.23ms ± 2%    ~     (p=0.091 n=30+30)
RegexpMatchEasy0_32-4       103ns ± 4%     103ns ± 4%    ~     (p=0.575 n=30+30)
RegexpMatchEasy0_1K-4       823ns ± 2%     821ns ± 3%    ~     (p=0.827 n=30+30)
RegexpMatchEasy1_32-4       113ns ± 3%     112ns ± 3%    ~     (p=0.076 n=30+30)
RegexpMatchEasy1_1K-4      1.02µs ± 4%    1.01µs ± 5%    ~     (p=0.087 n=30+30)
RegexpMatchMedium_32-4      129ns ± 3%     127ns ± 4%  -1.55%  (p=0.009 n=30+30)
RegexpMatchMedium_1K-4     39.3µs ± 4%    39.7µs ± 3%    ~     (p=0.054 n=30+30)
RegexpMatchHard_32-4       2.15µs ± 4%    2.15µs ± 4%    ~     (p=0.712 n=30+30)
RegexpMatchHard_1K-4       66.0µs ± 3%    65.1µs ± 3%  -1.32%  (p=0.002 n=30+30)
Revcomp-4                   1.85s ± 2%     1.85s ± 3%    ~     (p=0.168 n=30+30)
Template-4                 69.5ms ± 7%    68.9ms ± 6%    ~     (p=0.250 n=28+28)
TimeParse-4                 434ns ± 3%     432ns ± 4%    ~     (p=0.629 n=30+30)
TimeFormat-4                403ns ± 4%     408ns ± 3%  +1.23%  (p=0.019 n=30+29)
[Geo mean]                 65.5µs         65.3µs       -0.20%

name                     old speed      new speed      delta
GobDecode-4               108MB/s ± 6%   109MB/s ± 6%    ~     (p=0.636 n=30+30)
GobEncode-4               113MB/s ±10%   113MB/s ± 9%    ~     (p=0.982 n=30+30)
Gzip-4                   48.8MB/s ± 4%  48.6MB/s ± 5%    ~     (p=0.178 n=30+30)
Gunzip-4                  470MB/s ± 3%   479MB/s ± 4%  +1.72%  (p=0.006 n=30+30)
JSONEncode-4              121MB/s ± 3%   120MB/s ± 3%    ~     (p=0.057 n=30+30)
JSONDecode-4             30.7MB/s ± 8%  30.8MB/s ± 8%    ~     (p=0.784 n=30+30)
GoParse-4                17.9MB/s ± 3%  17.9MB/s ± 2%    ~     (p=0.090 n=30+30)
RegexpMatchEasy0_32-4     309MB/s ± 4%   309MB/s ± 3%    ~     (p=0.530 n=30+30)
RegexpMatchEasy0_1K-4    1.24GB/s ± 2%  1.25GB/s ± 3%    ~     (p=0.976 n=30+30)
RegexpMatchEasy1_32-4     282MB/s ± 3%   284MB/s ± 3%  +0.81%  (p=0.041 n=30+30)
RegexpMatchEasy1_1K-4    1.00GB/s ± 3%  1.01GB/s ± 4%    ~     (p=0.091 n=30+30)
RegexpMatchMedium_32-4   7.71MB/s ± 3%  7.84MB/s ± 4%  +1.71%  (p=0.000 n=30+30)
RegexpMatchMedium_1K-4   26.1MB/s ± 4%  25.8MB/s ± 3%    ~     (p=0.051 n=30+30)
RegexpMatchHard_32-4     14.9MB/s ± 4%  14.9MB/s ± 4%    ~     (p=0.712 n=30+30)
RegexpMatchHard_1K-4     15.5MB/s ± 3%  15.7MB/s ± 3%  +1.34%  (p=0.003 n=30+30)
Revcomp-4                 138MB/s ± 2%   137MB/s ± 3%    ~     (p=0.174 n=30+30)
Template-4               28.0MB/s ± 6%  28.2MB/s ± 6%    ~     (p=0.251 n=28+28)
[Geo mean]               82.3MB/s       82.6MB/s       +0.36%

Change-Id: I389829699ffe9500a013fcf31be58a97e98043e1
Reviewed-on: https://go-review.googlesource.com/c/140701
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>

1 files changed, 20 insertions, 1 deletions

diff --git a/src/cmd/compile/internal/x86/ssa.go b/src/cmd/compile/internal/x86/ssa.go
index 4ed46b9c8c..e0aebb449c 100644
--- a/src/cmd/compile/internal/x86/ssa.go
+++ b/src/cmd/compile/internal/x86/ssa.go
@@ -603,8 +603,27 @@ func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
 		p.To.Type = obj.TYPE_MEM
 		p.To.Reg = v.Args[0].Reg()
 		gc.AddAux2(&p.To, v, sc.Off())
+	case ssa.Op386ADDLconstmodifyidx4:
+		sc := v.AuxValAndOff()
+		val := sc.Val()
+		if val == 1 || val == -1 {
+			var p *obj.Prog
+			if val == 1 {
+				p = s.Prog(x86.AINCL)
+			} else {
+				p = s.Prog(x86.ADECL)
+			}
+			off := sc.Off()
+			p.To.Type = obj.TYPE_MEM
+			p.To.Reg = v.Args[0].Reg()
+			p.To.Scale = 4
+			p.To.Index = v.Args[1].Reg()
+			gc.AddAux2(&p.To, v, off)
+			break
+		}
+		fallthrough
 	case ssa.Op386MOVLstoreconstidx1, ssa.Op386MOVLstoreconstidx4, ssa.Op386MOVWstoreconstidx1, ssa.Op386MOVWstoreconstidx2, ssa.Op386MOVBstoreconstidx1,
-		ssa.Op386ADDLconstmodifyidx4, ssa.Op386ANDLconstmodifyidx4, ssa.Op386ORLconstmodifyidx4, ssa.Op386XORLconstmodifyidx4:
+		ssa.Op386ANDLconstmodifyidx4, ssa.Op386ORLconstmodifyidx4, ssa.Op386XORLconstmodifyidx4:
 		p := s.Prog(v.Op.Asm())
 		p.From.Type = obj.TYPE_CONST
 		sc := v.AuxValAndOff()