cmd/compile: optimize ARM's comparision

Optimize (CMPconst [0] (ADD x y)) to (CMN x y) will only get benefits
when the result of the addition is no longer used, otherwise there
might be even performance drop. And this CL fixes that issue for
CMP/CMN/TST/TEQ.

There is little regression in the go1 benchmark (excluding noise),
and the test case JSONDecode-4 even gets improvement.

name                     old time/op    new time/op    delta
BinaryTree17-4              21.6s ± 1%     21.6s ± 0%  -0.22%  (p=0.013 n=30+30)
Fannkuch11-4                11.1s ± 0%     11.1s ± 0%  +0.11%  (p=0.000 n=30+29)
FmtFprintfEmpty-4           297ns ± 0%     297ns ± 0%  +0.08%  (p=0.007 n=26+28)
FmtFprintfString-4          589ns ± 1%     589ns ± 0%    ~     (p=0.659 n=30+25)
FmtFprintfInt-4             644ns ± 1%     650ns ± 0%  +0.88%  (p=0.000 n=30+24)
FmtFprintfIntInt-4          964ns ± 0%     977ns ± 0%  +1.33%  (p=0.000 n=30+30)
FmtFprintfPrefixedInt-4    1.06µs ± 0%    1.07µs ± 0%  +1.31%  (p=0.000 n=29+27)
FmtFprintfFloat-4          1.89µs ± 0%    1.92µs ± 0%  +1.25%  (p=0.000 n=29+29)
FmtManyArgs-4              3.63µs ± 0%    3.67µs ± 0%  +1.33%  (p=0.000 n=29+27)
GobDecode-4                38.1ms ± 1%    37.9ms ± 1%  -0.60%  (p=0.000 n=29+29)
GobEncode-4                35.3ms ± 2%    35.2ms ± 1%    ~     (p=0.286 n=30+30)
Gzip-4                      2.36s ± 0%     2.37s ± 2%    ~     (p=0.277 n=24+28)
Gunzip-4                    264ms ± 1%     264ms ± 1%    ~     (p=0.104 n=28+30)
HTTPClientServer-4         1.04ms ± 4%    1.02ms ± 4%  -1.65%  (p=0.000 n=28+28)
JSONEncode-4               78.5ms ± 1%    79.6ms ± 1%  +1.34%  (p=0.000 n=27+28)
JSONDecode-4                379ms ± 4%     352ms ± 5%  -7.09%  (p=0.000 n=29+30)
Mandelbrot200-4            17.6ms ± 0%    17.6ms ± 0%    ~     (p=0.206 n=28+29)
GoParse-4                  21.9ms ± 1%    22.1ms ± 1%  +0.87%  (p=0.000 n=28+26)
RegexpMatchEasy0_32-4       631ns ± 0%     641ns ± 0%  +1.63%  (p=0.000 n=29+30)
RegexpMatchEasy0_1K-4      4.11µs ± 0%    4.11µs ± 0%    ~     (p=0.700 n=30+30)
RegexpMatchEasy1_32-4       670ns ± 0%     679ns ± 0%  +1.37%  (p=0.000 n=21+30)
RegexpMatchEasy1_1K-4      5.31µs ± 0%    5.26µs ± 0%  -1.03%  (p=0.000 n=25+28)
RegexpMatchMedium_32-4      905ns ± 0%     906ns ± 0%  +0.14%  (p=0.001 n=30+30)
RegexpMatchMedium_1K-4      192µs ± 0%     191µs ± 0%  -0.45%  (p=0.000 n=29+27)
RegexpMatchHard_32-4       11.8µs ± 0%    11.7µs ± 0%  -0.39%  (p=0.000 n=29+28)
RegexpMatchHard_1K-4        347µs ± 0%     347µs ± 0%    ~     (p=0.084 n=29+30)
Revcomp-4                  37.5ms ± 1%    37.5ms ± 1%    ~     (p=0.279 n=29+29)
Template-4                  519ms ± 2%     519ms ± 2%    ~     (p=0.652 n=28+29)
TimeParse-4                2.83µs ± 0%    2.78µs ± 0%  -1.90%  (p=0.000 n=27+28)
TimeFormat-4               5.79µs ± 0%    5.60µs ± 0%  -3.23%  (p=0.000 n=29+29)
[Geo mean]                  331µs          330µs       -0.16%

name                     old speed      new speed      delta
GobDecode-4              20.1MB/s ± 1%  20.3MB/s ± 1%  +0.61%  (p=0.000 n=29+29)
GobEncode-4              21.7MB/s ± 2%  21.8MB/s ± 1%    ~     (p=0.294 n=30+30)
Gzip-4                   8.23MB/s ± 1%  8.20MB/s ± 2%    ~     (p=0.099 n=26+28)
Gunzip-4                 73.5MB/s ± 1%  73.4MB/s ± 1%    ~     (p=0.107 n=28+30)
JSONEncode-4             24.7MB/s ± 1%  24.4MB/s ± 1%  -1.32%  (p=0.000 n=27+28)
JSONDecode-4             5.13MB/s ± 4%  5.52MB/s ± 5%  +7.65%  (p=0.000 n=29+30)
GoParse-4                2.65MB/s ± 1%  2.63MB/s ± 1%  -0.87%  (p=0.000 n=28+26)
RegexpMatchEasy0_32-4    50.7MB/s ± 0%  49.9MB/s ± 0%  -1.58%  (p=0.000 n=29+29)
RegexpMatchEasy0_1K-4     249MB/s ± 0%   249MB/s ± 0%    ~     (p=0.342 n=30+28)
RegexpMatchEasy1_32-4    47.7MB/s ± 0%  47.1MB/s ± 0%  -1.39%  (p=0.000 n=26+30)
RegexpMatchEasy1_1K-4     193MB/s ± 0%   195MB/s ± 0%  +1.04%  (p=0.000 n=25+28)
RegexpMatchMedium_32-4   1.10MB/s ± 0%  1.10MB/s ± 0%  -0.42%  (p=0.000 n=30+26)
RegexpMatchMedium_1K-4   5.33MB/s ± 0%  5.36MB/s ± 0%  +0.43%  (p=0.000 n=29+29)
RegexpMatchHard_32-4     2.72MB/s ± 0%  2.73MB/s ± 0%  +0.37%  (p=0.000 n=29+30)
RegexpMatchHard_1K-4     2.95MB/s ± 0%  2.95MB/s ± 0%    ~     (all equal)
Revcomp-4                67.8MB/s ± 1%  67.7MB/s ± 1%    ~     (p=0.273 n=29+29)
Template-4               3.74MB/s ± 2%  3.74MB/s ± 2%    ~     (p=0.665 n=28+29)
[Geo mean]               15.2MB/s       15.2MB/s       +0.21%

Change-Id: Ifed1fb8cc02d5ca52c8bc6c21b6b5bf6dbb2701a
Reviewed-on: https://go-review.googlesource.com/132115
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>

test/codegen/comparisons.go

@@ -158,9 +158,11 @@ func CmpZero4(a int64, ptr *int) {
 	}
 }
 
-func CmpToZero(a, b, d int32) int32 {
+func CmpToZero(a, b, d int32, e, f int64) int32 {
 	// arm:`TST`,-`AND`
 	// arm64:`TSTW`,-`AND`
+	// 386:`TESTL`,-`ANDL`
+	// amd64:`TESTL`,-`ANDL`
 	c0 := a&b < 0
 	// arm:`CMN`,-`ADD`
 	// arm64:`CMNW`,-`ADD`
@@ -168,14 +170,17 @@ func CmpToZero(a, b, d int32) int32 {
 	// arm:`TEQ`,-`XOR`
 	c2 := a^b < 0
 	// arm64:`TST`,-`AND`
-	c3 := int64(a)&int64(b) < 0
+	// amd64:`TESTQ`,-`ANDQ`
+	c3 := e&f < 0
 	// arm64:`CMN`,-`ADD`
-	c4 := int64(a)+int64(b) < 0
-	// not optimized to CMNW/CMN due to further use of b+d
+	c4 := e+f < 0
+	// not optimized to single CMNW/CMN due to further use of b+d
 	// arm64:`ADD`,-`CMNW`
+	// arm:`ADD`,-`CMN`
 	c5 := b+d == 0
-	// not optimized to TSTW/TST due to further use of a&d
+	// not optimized to single TSTW/TST due to further use of a&d
 	// arm64:`AND`,-`TSTW`
+	// arm:`AND`,-`TST`
 	c6 := a&d >= 0
 	if c0 {
 		return 1