cmd/compile: optimize arm64 with indexed FP load/store

The FP load/store on arm64 have register indexed forms. And this
CL implements this optimization.

1. The total size of pkg/android_arm64 (excluding cmd/compile)
decreases about 400 bytes.

2. There is no regression in the go1 benchmark, the test case
GobEncode even gets slight improvement, excluding noise.

name                     old time/op    new time/op    delta
BinaryTree17-4              19.0s ± 0%     19.0s ± 1%    ~     (p=0.817 n=29+29)
Fannkuch11-4                9.94s ± 0%     9.95s ± 0%  +0.03%  (p=0.010 n=24+30)
FmtFprintfEmpty-4           233ns ± 0%     233ns ± 0%    ~     (all equal)
FmtFprintfString-4          427ns ± 0%     427ns ± 0%    ~     (p=0.649 n=30+30)
FmtFprintfInt-4             471ns ± 0%     471ns ± 0%    ~     (all equal)
FmtFprintfIntInt-4          730ns ± 0%     730ns ± 0%    ~     (all equal)
FmtFprintfPrefixedInt-4     889ns ± 0%     889ns ± 0%    ~     (all equal)
FmtFprintfFloat-4          1.21µs ± 0%    1.21µs ± 0%  +0.04%  (p=0.012 n=20+30)
FmtManyArgs-4              2.99µs ± 0%    2.99µs ± 0%    ~     (p=0.651 n=29+29)
GobDecode-4                42.4ms ± 1%    42.3ms ± 1%  -0.27%  (p=0.001 n=29+28)
GobEncode-4                37.8ms ±11%    36.0ms ± 0%  -4.67%  (p=0.000 n=30+26)
Gzip-4                      1.98s ± 1%     1.96s ± 1%  -1.26%  (p=0.000 n=30+30)
Gunzip-4                    175ms ± 0%     175ms ± 0%    ~     (p=0.988 n=29+29)
HTTPClientServer-4          854µs ± 5%     860µs ± 5%    ~     (p=0.236 n=28+29)
JSONEncode-4               88.8ms ± 0%    87.9ms ± 0%  -1.00%  (p=0.000 n=24+26)
JSONDecode-4                390ms ± 1%     392ms ± 2%  +0.48%  (p=0.025 n=30+30)
Mandelbrot200-4            19.5ms ± 0%    19.5ms ± 0%    ~     (p=0.894 n=24+29)
GoParse-4                  20.3ms ± 0%    20.1ms ± 1%  -0.94%  (p=0.000 n=27+26)
RegexpMatchEasy0_32-4       451ns ± 0%     451ns ± 0%    ~     (p=0.578 n=30+30)
RegexpMatchEasy0_1K-4      1.63µs ± 0%    1.63µs ± 0%    ~     (p=0.298 n=30+28)
RegexpMatchEasy1_32-4       431ns ± 0%     434ns ± 0%  +0.67%  (p=0.000 n=30+29)
RegexpMatchEasy1_1K-4      2.60µs ± 0%    2.64µs ± 0%  +1.36%  (p=0.000 n=28+26)
RegexpMatchMedium_32-4      744ns ± 0%     744ns ± 0%    ~     (p=0.474 n=29+29)
RegexpMatchMedium_1K-4      223µs ± 0%     223µs ± 0%  -0.08%  (p=0.038 n=26+30)
RegexpMatchHard_32-4       12.2µs ± 0%    12.3µs ± 0%  +0.27%  (p=0.000 n=29+30)
RegexpMatchHard_1K-4        373µs ± 0%     373µs ± 0%    ~     (p=0.219 n=29+28)
Revcomp-4                   2.84s ± 0%     2.84s ± 0%    ~     (p=0.130 n=28+28)
Template-4                  394ms ± 1%     392ms ± 1%  -0.52%  (p=0.001 n=30+30)
TimeParse-4                1.93µs ± 0%    1.93µs ± 0%    ~     (p=0.587 n=29+30)
TimeFormat-4               2.00µs ± 0%    2.00µs ± 0%  +0.07%  (p=0.001 n=28+27)
[Geo mean]                  306µs          305µs       -0.17%

name                     old speed      new speed      delta
GobDecode-4              18.1MB/s ± 1%  18.2MB/s ± 1%  +0.27%  (p=0.001 n=29+28)
GobEncode-4              20.3MB/s ±10%  21.3MB/s ± 0%  +4.64%  (p=0.000 n=30+26)
Gzip-4                   9.79MB/s ± 1%  9.91MB/s ± 1%  +1.28%  (p=0.000 n=30+30)
Gunzip-4                  111MB/s ± 0%   111MB/s ± 0%    ~     (p=0.988 n=29+29)
JSONEncode-4             21.8MB/s ± 0%  22.1MB/s ± 0%  +1.02%  (p=0.000 n=24+26)
JSONDecode-4             4.97MB/s ± 1%  4.95MB/s ± 2%  -0.45%  (p=0.031 n=30+30)
GoParse-4                2.85MB/s ± 1%  2.88MB/s ± 1%  +1.03%  (p=0.000 n=30+26)
RegexpMatchEasy0_32-4    70.9MB/s ± 0%  70.9MB/s ± 0%    ~     (p=0.904 n=29+28)
RegexpMatchEasy0_1K-4     627MB/s ± 0%   627MB/s ± 0%    ~     (p=0.156 n=30+30)
RegexpMatchEasy1_32-4    74.2MB/s ± 0%  73.7MB/s ± 0%  -0.67%  (p=0.000 n=30+29)
RegexpMatchEasy1_1K-4     393MB/s ± 0%   388MB/s ± 0%  -1.34%  (p=0.000 n=28+26)
RegexpMatchMedium_32-4   1.34MB/s ± 0%  1.34MB/s ± 0%    ~     (all equal)
RegexpMatchMedium_1K-4   4.59MB/s ± 0%  4.59MB/s ± 0%  +0.07%  (p=0.035 n=25+30)
RegexpMatchHard_32-4     2.61MB/s ± 0%  2.61MB/s ± 0%  -0.11%  (p=0.002 n=28+30)
RegexpMatchHard_1K-4     2.75MB/s ± 0%  2.75MB/s ± 0%  +0.15%  (p=0.001 n=30+24)
Revcomp-4                89.4MB/s ± 0%  89.4MB/s ± 0%    ~     (p=0.140 n=28+28)
Template-4               4.93MB/s ± 1%  4.95MB/s ± 1%  +0.51%  (p=0.001 n=30+30)
[Geo mean]               18.4MB/s       18.4MB/s       +0.37%

Change-Id: I9a6b521a971b21cfb51064e8e9b853cef8a1d071
Reviewed-on: https://go-review.googlesource.com/124636
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>

1 files changed, 17 insertions, 11 deletions

diff --git a/src/cmd/compile/internal/ssa/gen/ARM64Ops.go b/src/cmd/compile/internal/ssa/gen/ARM64Ops.go
index 648d5a59a6..96f2ac3ceb 100644
--- a/src/cmd/compile/internal/ssa/gen/ARM64Ops.go
+++ b/src/cmd/compile/internal/ssa/gen/ARM64Ops.go
@@ -158,7 +158,9 @@ func init() {
 		fp31      = regInfo{inputs: []regMask{fp, fp, fp}, outputs: []regMask{fp}}
 		fp2flags  = regInfo{inputs: []regMask{fp, fp}}
 		fpload    = regInfo{inputs: []regMask{gpspsbg}, outputs: []regMask{fp}}
+		fp2load   = regInfo{inputs: []regMask{gpspsbg, gpg}, outputs: []regMask{fp}}
 		fpstore   = regInfo{inputs: []regMask{gpspsbg, fp}}
+		fpstore2  = regInfo{inputs: []regMask{gpspsbg, gpg, fp}}
 		readflags = regInfo{inputs: nil, outputs: []regMask{gp}}
 	)
 	ops := []opData{
@@ -324,13 +326,15 @@ func init() {
 		{name: "FMOVDload", argLength: 2, reg: fpload, aux: "SymOff", asm: "FMOVD", typ: "Float64", faultOnNilArg0: true, symEffect: "Read"}, // load from arg0 + auxInt + aux.  arg1=mem.
 
 		// register indexed load
-		{name: "MOVDloadidx", argLength: 3, reg: gp2load, asm: "MOVD", typ: "UInt64"},   // load 64-bit dword from arg0 + arg1, arg2 = mem.
-		{name: "MOVWloadidx", argLength: 3, reg: gp2load, asm: "MOVW", typ: "Int32"},    // load 32-bit word from arg0 + arg1, sign-extended to 64-bit, arg2=mem.
-		{name: "MOVWUloadidx", argLength: 3, reg: gp2load, asm: "MOVWU", typ: "UInt32"}, // load 32-bit word from arg0 + arg1, zero-extended to 64-bit, arg2=mem.
-		{name: "MOVHloadidx", argLength: 3, reg: gp2load, asm: "MOVH", typ: "Int16"},    // load 16-bit word from arg0 + arg1, sign-extended to 64-bit, arg2=mem.
-		{name: "MOVHUloadidx", argLength: 3, reg: gp2load, asm: "MOVHU", typ: "UInt16"}, // load 16-bit word from arg0 + arg1, zero-extended to 64-bit, arg2=mem.
-		{name: "MOVBloadidx", argLength: 3, reg: gp2load, asm: "MOVB", typ: "Int8"},     // load 8-bit word from arg0 + arg1, sign-extended to 64-bit, arg2=mem.
-		{name: "MOVBUloadidx", argLength: 3, reg: gp2load, asm: "MOVBU", typ: "UInt8"},  // load 8-bit word from arg0 + arg1, zero-extended to 64-bit, arg2=mem.
+		{name: "MOVDloadidx", argLength: 3, reg: gp2load, asm: "MOVD", typ: "UInt64"},    // load 64-bit dword from arg0 + arg1, arg2 = mem.
+		{name: "MOVWloadidx", argLength: 3, reg: gp2load, asm: "MOVW", typ: "Int32"},     // load 32-bit word from arg0 + arg1, sign-extended to 64-bit, arg2=mem.
+		{name: "MOVWUloadidx", argLength: 3, reg: gp2load, asm: "MOVWU", typ: "UInt32"},  // load 32-bit word from arg0 + arg1, zero-extended to 64-bit, arg2=mem.
+		{name: "MOVHloadidx", argLength: 3, reg: gp2load, asm: "MOVH", typ: "Int16"},     // load 16-bit word from arg0 + arg1, sign-extended to 64-bit, arg2=mem.
+		{name: "MOVHUloadidx", argLength: 3, reg: gp2load, asm: "MOVHU", typ: "UInt16"},  // load 16-bit word from arg0 + arg1, zero-extended to 64-bit, arg2=mem.
+		{name: "MOVBloadidx", argLength: 3, reg: gp2load, asm: "MOVB", typ: "Int8"},      // load 8-bit word from arg0 + arg1, sign-extended to 64-bit, arg2=mem.
+		{name: "MOVBUloadidx", argLength: 3, reg: gp2load, asm: "MOVBU", typ: "UInt8"},   // load 8-bit word from arg0 + arg1, zero-extended to 64-bit, arg2=mem.
+		{name: "FMOVSloadidx", argLength: 3, reg: fp2load, asm: "FMOVS", typ: "Float32"}, // load 32-bit float from arg0 + arg1, arg2=mem.
+		{name: "FMOVDloadidx", argLength: 3, reg: fp2load, asm: "FMOVD", typ: "Float64"}, // load 64-bit float from arg0 + arg1, arg2=mem.
 
 		// shifted register indexed load
 		{name: "MOVHloadidx2", argLength: 3, reg: gp2load, asm: "MOVH", typ: "Int16"},    // load 16-bit half-word from arg0 + arg1*2, sign-extended to 64-bit, arg2=mem.
@@ -348,10 +352,12 @@ func init() {
 		{name: "FMOVDstore", argLength: 3, reg: fpstore, aux: "SymOff", asm: "FMOVD", typ: "Mem", faultOnNilArg0: true, symEffect: "Write"}, // store 8 bytes of arg1 to arg0 + auxInt + aux.  arg2=mem.
 
 		// register indexed store
-		{name: "MOVBstoreidx", argLength: 4, reg: gpstore2, asm: "MOVB", typ: "Mem"}, // store 1 byte of arg2 to arg0 + arg1, arg3 = mem.
-		{name: "MOVHstoreidx", argLength: 4, reg: gpstore2, asm: "MOVH", typ: "Mem"}, // store 2 bytes of arg2 to arg0 + arg1, arg3 = mem.
-		{name: "MOVWstoreidx", argLength: 4, reg: gpstore2, asm: "MOVW", typ: "Mem"}, // store 4 bytes of arg2 to arg0 + arg1, arg3 = mem.
-		{name: "MOVDstoreidx", argLength: 4, reg: gpstore2, asm: "MOVD", typ: "Mem"}, // store 8 bytes of arg2 to arg0 + arg1, arg3 = mem.
+		{name: "MOVBstoreidx", argLength: 4, reg: gpstore2, asm: "MOVB", typ: "Mem"},   // store 1 byte of arg2 to arg0 + arg1, arg3 = mem.
+		{name: "MOVHstoreidx", argLength: 4, reg: gpstore2, asm: "MOVH", typ: "Mem"},   // store 2 bytes of arg2 to arg0 + arg1, arg3 = mem.
+		{name: "MOVWstoreidx", argLength: 4, reg: gpstore2, asm: "MOVW", typ: "Mem"},   // store 4 bytes of arg2 to arg0 + arg1, arg3 = mem.
+		{name: "MOVDstoreidx", argLength: 4, reg: gpstore2, asm: "MOVD", typ: "Mem"},   // store 8 bytes of arg2 to arg0 + arg1, arg3 = mem.
+		{name: "FMOVSstoreidx", argLength: 4, reg: fpstore2, asm: "FMOVS", typ: "Mem"}, // store 32-bit float of arg2 to arg0 + arg1, arg3=mem.
+		{name: "FMOVDstoreidx", argLength: 4, reg: fpstore2, asm: "FMOVD", typ: "Mem"}, // store 64-bit float of arg2 to arg0 + arg1, arg3=mem.
 
 		// shifted register indexed store
 		{name: "MOVHstoreidx2", argLength: 4, reg: gpstore2, asm: "MOVH", typ: "Mem"}, // store 2 bytes of arg2 to arg0 + arg1*2, arg3 = mem.