cmd/compile: optimize arm's bit operation

BFC (Bit Field Clear) was introduced in ARMv7, which can simplify
ANDconst and BICconst. And this CL implements that optimization.

1. The total size of pkg/android_arm decreases about 3KB, excluding
cmd/compile/.

2. There is no regression in the go1 benchmark result, and some
cases (FmtFprintfEmpty-4 and RegexpMatchMedium_32-4) even get
slight improvement.

name                     old time/op    new time/op    delta
BinaryTree17-4              25.3s ± 1%     25.2s ± 1%    ~     (p=0.072 n=30+29)
Fannkuch11-4                13.3s ± 0%     13.3s ± 0%  +0.13%  (p=0.000 n=30+26)
FmtFprintfEmpty-4           407ns ± 0%     394ns ± 0%  -3.19%  (p=0.000 n=26+28)
FmtFprintfString-4          664ns ± 0%     662ns ± 0%  -0.22%  (p=0.000 n=30+30)
FmtFprintfInt-4             712ns ± 0%     706ns ± 0%  -0.79%  (p=0.000 n=30+30)
FmtFprintfIntInt-4         1.06µs ± 0%    1.05µs ± 0%  -0.38%  (p=0.000 n=30+30)
FmtFprintfPrefixedInt-4    1.16µs ± 0%    1.16µs ± 0%  -0.13%  (p=0.000 n=30+29)
FmtFprintfFloat-4          2.24µs ± 0%    2.23µs ± 0%  -0.51%  (p=0.000 n=29+21)
FmtManyArgs-4              4.09µs ± 0%    4.06µs ± 0%  -0.83%  (p=0.000 n=28+30)
GobDecode-4                55.0ms ± 5%    55.4ms ± 5%    ~     (p=0.307 n=30+30)
GobEncode-4                51.2ms ± 1%    51.9ms ± 1%  +1.23%  (p=0.000 n=29+30)
Gzip-4                      2.64s ± 0%     2.60s ± 0%  -1.35%  (p=0.000 n=30+29)
Gunzip-4                    309ms ± 0%     308ms ± 0%  -0.27%  (p=0.000 n=30+30)
HTTPClientServer-4         1.03ms ± 5%    1.02ms ± 4%    ~     (p=0.117 n=30+29)
JSONEncode-4                101ms ± 2%     101ms ± 2%    ~     (p=0.338 n=29+29)
JSONDecode-4                383ms ± 2%     382ms ± 2%    ~     (p=0.751 n=26+30)
Mandelbrot200-4            18.4ms ± 0%    18.4ms ± 0%  -0.10%  (p=0.000 n=29+29)
GoParse-4                  22.6ms ± 0%    22.5ms ± 0%  -0.39%  (p=0.000 n=30+30)
RegexpMatchEasy0_32-4       761ns ± 0%     750ns ± 0%  -1.47%  (p=0.000 n=26+29)
RegexpMatchEasy0_1K-4      4.33µs ± 0%    4.34µs ± 0%  +0.27%  (p=0.000 n=25+28)
RegexpMatchEasy1_32-4       809ns ± 0%     795ns ± 0%  -1.74%  (p=0.000 n=27+25)
RegexpMatchEasy1_1K-4      5.54µs ± 0%    5.53µs ± 0%  -0.18%  (p=0.000 n=29+29)
RegexpMatchMedium_32-4     1.11µs ± 0%    1.08µs ± 0%  -2.78%  (p=0.000 n=27+29)
RegexpMatchMedium_1K-4      255µs ± 0%     255µs ± 0%  -0.02%  (p=0.029 n=30+30)
RegexpMatchHard_32-4       14.7µs ± 0%    14.7µs ± 0%  -0.28%  (p=0.000 n=30+29)
RegexpMatchHard_1K-4        439µs ± 0%     439µs ± 0%    ~     (p=0.907 n=23+27)
Revcomp-4                  41.9ms ± 1%    41.9ms ± 1%    ~     (p=0.230 n=28+30)
Template-4                  522ms ± 1%     528ms ± 1%  +1.25%  (p=0.000 n=30+30)
TimeParse-4                3.34µs ± 0%    3.35µs ± 0%  +0.23%  (p=0.000 n=30+27)
TimeFormat-4               6.06µs ± 0%    6.13µs ± 0%  +1.08%  (p=0.000 n=29+29)
[Geo mean]                  384µs          382µs       -0.37%

name                     old speed      new speed      delta
GobDecode-4              14.0MB/s ± 5%  13.9MB/s ± 5%    ~     (p=0.308 n=30+30)
GobEncode-4              15.0MB/s ± 1%  14.8MB/s ± 1%  -1.22%  (p=0.000 n=29+30)
Gzip-4                   7.36MB/s ± 0%  7.46MB/s ± 0%  +1.35%  (p=0.000 n=30+30)
Gunzip-4                 62.8MB/s ± 0%  63.0MB/s ± 0%  +0.27%  (p=0.000 n=30+30)
JSONEncode-4             19.2MB/s ± 2%  19.2MB/s ± 2%    ~     (p=0.312 n=29+29)
JSONDecode-4             5.05MB/s ± 3%  5.08MB/s ± 2%    ~     (p=0.356 n=29+30)
GoParse-4                2.56MB/s ± 0%  2.57MB/s ± 0%  +0.39%  (p=0.000 n=23+27)
RegexpMatchEasy0_32-4    42.0MB/s ± 0%  42.6MB/s ± 0%  +1.50%  (p=0.000 n=26+28)
RegexpMatchEasy0_1K-4     236MB/s ± 0%   236MB/s ± 0%  -0.27%  (p=0.000 n=25+28)
RegexpMatchEasy1_32-4    39.6MB/s ± 0%  40.2MB/s ± 0%  +1.73%  (p=0.000 n=27+27)
RegexpMatchEasy1_1K-4     185MB/s ± 0%   185MB/s ± 0%  +0.18%  (p=0.000 n=29+29)
RegexpMatchMedium_32-4    900kB/s ± 0%   920kB/s ± 0%  +2.22%  (p=0.000 n=29+29)
RegexpMatchMedium_1K-4   4.02MB/s ± 0%  4.02MB/s ± 0%  +0.07%  (p=0.004 n=30+27)
RegexpMatchHard_32-4     2.17MB/s ± 0%  2.18MB/s ± 0%  +0.46%  (p=0.000 n=30+26)
RegexpMatchHard_1K-4     2.33MB/s ± 0%  2.33MB/s ± 0%    ~     (all equal)
Revcomp-4                60.6MB/s ± 1%  60.7MB/s ± 1%    ~     (p=0.207 n=28+30)
Template-4               3.72MB/s ± 1%  3.67MB/s ± 1%  -1.23%  (p=0.000 n=30+30)
[Geo mean]               12.9MB/s       12.9MB/s       +0.29%

Change-Id: I07f497f8bb476c950dc555491d00c9066fb64a4e
Reviewed-on: https://go-review.googlesource.com/134232
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>

1 files changed, 47 insertions, 2 deletions

diff --git a/src/cmd/compile/internal/arm/ssa.go b/src/cmd/compile/internal/arm/ssa.go
index 98627344b8..9a8fabf622 100644
--- a/src/cmd/compile/internal/arm/ssa.go
+++ b/src/cmd/compile/internal/arm/ssa.go
@@ -7,6 +7,7 @@ package arm
 import (
 	"fmt"
 	"math"
+	"math/bits"
 
 	"cmd/compile/internal/gc"
 	"cmd/compile/internal/ssa"
@@ -119,6 +120,28 @@ func genregshift(s *gc.SSAGenState, as obj.As, r0, r1, r2, r int16, typ int64) *
 	return p
 }
 
+// find a (lsb, width) pair for BFC
+// lsb must be in [0, 31], width must be in [1, 32 - lsb]
+// return (0xffffffff, 0) if v is not a binary like 0...01...10...0
+func getBFC(v uint32) (uint32, uint32) {
+	var m, l uint32
+	// BFC is not applicable with zero
+	if v == 0 {
+		return 0xffffffff, 0
+	}
+	// find the lowest set bit, for example l=2 for 0x3ffffffc
+	l = uint32(bits.TrailingZeros32(v))
+	// m-1 represents the highest set bit index, for example m=30 for 0x3ffffffc
+	m = 32 - uint32(bits.LeadingZeros32(v))
+	// check if v is a binary like 0...01...10...0
+	if (1<<m)-(1<<l) == v {
+		// it must be m > l for non-zero v
+		return l, m - l
+	}
+	// invalid
+	return 0xffffffff, 0
+}
+
 func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
 	switch v.Op {
 	case ssa.OpCopy, ssa.OpARMMOVWreg:
@@ -267,16 +290,38 @@ func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
 		p.Reg = v.Args[0].Reg()
 		p.To.Type = obj.TYPE_REG
 		p.To.Reg = v.Reg()
+	case ssa.OpARMANDconst, ssa.OpARMBICconst:
+		// try to optimize ANDconst and BICconst to BFC, which saves bytes and ticks
+		// BFC is only available on ARMv7, and its result and source are in the same register
+		if objabi.GOARM == 7 && v.Reg() == v.Args[0].Reg() {
+			var val uint32
+			if v.Op == ssa.OpARMANDconst {
+				val = ^uint32(v.AuxInt)
+			} else { // BICconst
+				val = uint32(v.AuxInt)
+			}
+			lsb, width := getBFC(val)
+			// omit BFC for ARM's imm12
+			if 8 < width && width < 24 {
+				p := s.Prog(arm.ABFC)
+				p.From.Type = obj.TYPE_CONST
+				p.From.Offset = int64(width)
+				p.SetFrom3(obj.Addr{Type: obj.TYPE_CONST, Offset: int64(lsb)})
+				p.To.Type = obj.TYPE_REG
+				p.To.Reg = v.Reg()
+				break
+			}
+		}
+		// fall back to ordinary form
+		fallthrough
 	case ssa.OpARMADDconst,
 		ssa.OpARMADCconst,
 		ssa.OpARMSUBconst,
 		ssa.OpARMSBCconst,
 		ssa.OpARMRSBconst,
 		ssa.OpARMRSCconst,
-		ssa.OpARMANDconst,
 		ssa.OpARMORconst,
 		ssa.OpARMXORconst,
-		ssa.OpARMBICconst,
 		ssa.OpARMSLLconst,
 		ssa.OpARMSRLconst,
 		ssa.OpARMSRAconst: