1
0
mirror of https://github.com/golang/go synced 2024-11-17 02:54:45 -07:00

cmd/compile: optimize 386 binary operations with a memory operand

Some integer/float binary operations of 386 can take a direct memory
operand, which is more efficient than loading to a register.

These CL does this optimization by copying the similar solution
of amd64. And the go1 benchmark shows some inprovements, especially
the test case Template. (excluding noise)

name                     old time/op    new time/op    delta
BinaryTree17-4              3.42s ± 2%     3.40s ± 2%    ~     (p=0.069 n=38+39)
Fannkuch11-4                3.48s ± 1%     3.53s ± 1%  +1.59%  (p=0.000 n=40+40)
FmtFprintfEmpty-4          46.7ns ± 4%    46.3ns ± 3%  -1.03%  (p=0.001 n=40+40)
FmtFprintfString-4         80.1ns ± 3%    80.6ns ± 3%  +0.56%  (p=0.029 n=40+40)
FmtFprintfInt-4            92.4ns ± 2%    92.3ns ± 3%    ~     (p=0.847 n=40+40)
FmtFprintfIntInt-4          147ns ± 3%     144ns ± 3%  -1.87%  (p=0.000 n=40+40)
FmtFprintfPrefixedInt-4     182ns ± 2%     184ns ± 3%  +0.99%  (p=0.002 n=40+40)
FmtFprintfFloat-4           387ns ± 3%     384ns ± 3%    ~     (p=0.069 n=40+40)
FmtManyArgs-4               619ns ± 3%     616ns ± 3%    ~     (p=0.320 n=40+40)
GobDecode-4                7.28ms ± 6%    7.27ms ± 5%    ~     (p=0.897 n=40+40)
GobEncode-4                7.33ms ± 6%    7.21ms ± 6%  -1.56%  (p=0.022 n=38+40)
Gzip-4                      357ms ± 4%     357ms ± 4%    ~     (p=0.071 n=40+40)
Gunzip-4                   45.3ms ± 3%    45.4ms ± 3%    ~     (p=0.452 n=40+40)
HTTPClientServer-4         63.0µs ± 2%    62.9µs ± 3%    ~     (p=0.760 n=38+39)
JSONEncode-4               22.0ms ± 4%    21.7ms ± 4%  -1.49%  (p=0.000 n=40+40)
JSONDecode-4               67.7ms ± 4%    68.3ms ± 3%  +0.86%  (p=0.039 n=40+40)
Mandelbrot200-4            5.16ms ± 3%    5.17ms ± 3%    ~     (p=0.418 n=40+40)
GoParse-4                  3.30ms ± 2%    3.32ms ± 3%  +0.55%  (p=0.017 n=40+40)
RegexpMatchEasy0_32-4       104ns ± 3%     104ns ± 4%    ~     (p=0.992 n=40+40)
RegexpMatchEasy0_1K-4       852ns ± 3%     851ns ± 2%    ~     (p=0.344 n=40+40)
RegexpMatchEasy1_32-4       113ns ± 4%     113ns ± 5%    ~     (p=0.937 n=40+40)
RegexpMatchEasy1_1K-4      1.03µs ± 5%    1.04µs ± 4%    ~     (p=0.430 n=40+40)
RegexpMatchMedium_32-4      132ns ± 4%     131ns ± 3%  -1.06%  (p=0.027 n=40+40)
RegexpMatchMedium_1K-4     43.0µs ± 3%    43.2µs ± 3%    ~     (p=0.122 n=40+40)
RegexpMatchHard_32-4       2.21µs ± 4%    2.20µs ± 4%    ~     (p=0.146 n=40+40)
RegexpMatchHard_1K-4       67.1µs ± 4%    67.2µs ± 3%    ~     (p=0.859 n=40+40)
Revcomp-4                   1.85s ± 2%     1.85s ± 3%    ~     (p=0.184 n=40+40)
Template-4                 70.1ms ± 4%    67.5ms ± 3%  -3.65%  (p=0.000 n=40+40)
TimeParse-4                 457ns ±16%     439ns ± 4%    ~     (p=0.683 n=40+34)
TimeFormat-4                413ns ± 3%     414ns ± 3%    ~     (p=0.850 n=40+40)
[Geo mean]                 67.5µs         67.3µs       -0.38%

name                     old speed      new speed      delta
GobDecode-4               105MB/s ± 6%   106MB/s ± 5%    ~     (p=0.893 n=40+40)
GobEncode-4               105MB/s ± 6%   107MB/s ± 7%  +1.60%  (p=0.023 n=38+40)
Gzip-4                   54.4MB/s ± 4%  54.5MB/s ± 4%    ~     (p=0.073 n=40+40)
Gunzip-4                  429MB/s ± 3%   428MB/s ± 3%    ~     (p=0.453 n=40+40)
JSONEncode-4             88.3MB/s ± 5%  89.6MB/s ± 4%  +1.51%  (p=0.000 n=40+40)
JSONDecode-4             28.7MB/s ± 4%  28.4MB/s ± 3%  -0.87%  (p=0.039 n=40+40)
GoParse-4                17.6MB/s ± 3%  17.5MB/s ± 3%  -0.55%  (p=0.020 n=40+40)
RegexpMatchEasy0_32-4     308MB/s ± 4%   308MB/s ± 5%    ~     (p=0.988 n=40+40)
RegexpMatchEasy0_1K-4    1.20GB/s ± 3%  1.20GB/s ± 2%    ~     (p=0.329 n=40+40)
RegexpMatchEasy1_32-4     283MB/s ± 4%   283MB/s ± 4%    ~     (p=0.507 n=40+40)
RegexpMatchEasy1_1K-4     991MB/s ± 5%   987MB/s ± 4%    ~     (p=0.446 n=40+40)
RegexpMatchMedium_32-4   7.54MB/s ± 4%  7.63MB/s ± 3%  +1.26%  (p=0.004 n=40+40)
RegexpMatchMedium_1K-4   23.8MB/s ± 3%  23.7MB/s ± 4%    ~     (p=0.121 n=40+40)
RegexpMatchHard_32-4     14.5MB/s ± 4%  14.6MB/s ± 4%    ~     (p=0.145 n=40+40)
RegexpMatchHard_1K-4     15.3MB/s ± 4%  15.2MB/s ± 3%    ~     (p=0.874 n=40+40)
Revcomp-4                 137MB/s ± 2%   137MB/s ± 3%    ~     (p=0.179 n=40+40)
Template-4               27.7MB/s ± 4%  28.7MB/s ± 3%  +3.78%  (p=0.000 n=40+40)
[Geo mean]               78.9MB/s       79.2MB/s       +0.38%

Change-Id: I3ba688c253b665485c1ebdf5a75f4ce82cc3def3
Reviewed-on: https://go-review.googlesource.com/102036
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
Reviewed-by: Keith Randall <khr@golang.org>
This commit is contained in:
Ben Shi 2018-03-22 02:18:50 +00:00 committed by Brad Fitzpatrick
parent eef42f928d
commit 20cf5c4962
5 changed files with 1476 additions and 35 deletions

View File

@ -636,6 +636,13 @@
(MOVSSstore [off1] {sym} (ADDLconst [off2] ptr) val mem) && is32Bit(off1+off2) -> (MOVSSstore [off1+off2] {sym} ptr val mem)
(MOVSDstore [off1] {sym} (ADDLconst [off2] ptr) val mem) && is32Bit(off1+off2) -> (MOVSDstore [off1+off2] {sym} ptr val mem)
((ADD|SUB|AND|OR|XOR)Lmem [off1] {sym} val (ADDLconst [off2] base) mem) && is32Bit(off1+off2) ->
((ADD|SUB|AND|OR|XOR)Lmem [off1+off2] {sym} val base mem)
((ADD|SUB|MUL)SSmem [off1] {sym} val (ADDLconst [off2] base) mem) && is32Bit(off1+off2) ->
((ADD|SUB|MUL)SSmem [off1+off2] {sym} val base mem)
((ADD|SUB|MUL)SDmem [off1] {sym} val (ADDLconst [off2] base) mem) && is32Bit(off1+off2) ->
((ADD|SUB|MUL)SDmem [off1+off2] {sym} val base mem)
// Fold constants into stores.
(MOVLstore [off] {sym} ptr (MOVLconst [c]) mem) && validOff(off) ->
(MOVLstoreconst [makeValAndOff(int64(int32(c)),off)] {sym} ptr mem)
@ -748,6 +755,16 @@
(MOVSDstore [off1] {sym1} (LEAL8 [off2] {sym2} ptr idx) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) ->
(MOVSDstoreidx8 [off1+off2] {mergeSym(sym1,sym2)} ptr idx val mem)
((ADD|SUB|AND|OR|XOR)Lmem [off1] {sym1} val (LEAL [off2] {sym2} base) mem)
&& is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || !config.ctxt.Flag_shared) ->
((ADD|SUB|AND|OR|XOR)Lmem [off1+off2] {mergeSym(sym1,sym2)} val base mem)
((ADD|SUB|MUL)SSmem [off1] {sym1} val (LEAL [off2] {sym2} base) mem)
&& is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || !config.ctxt.Flag_shared) ->
((ADD|SUB|MUL)SSmem [off1+off2] {mergeSym(sym1,sym2)} val base mem)
((ADD|SUB|MUL)SDmem [off1] {sym1} val (LEAL [off2] {sym2} base) mem)
&& is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || !config.ctxt.Flag_shared) ->
((ADD|SUB|MUL)SDmem [off1+off2] {mergeSym(sym1,sym2)} val base mem)
(MOVBload [off] {sym} (ADDL ptr idx) mem) && ptr.Op != OpSB -> (MOVBloadidx1 [off] {sym} ptr idx mem)
(MOVWload [off] {sym} (ADDL ptr idx) mem) && ptr.Op != OpSB -> (MOVWloadidx1 [off] {sym} ptr idx mem)
(MOVLload [off] {sym} (ADDL ptr idx) mem) && ptr.Op != OpSB -> (MOVLloadidx1 [off] {sym} ptr idx mem)
@ -823,6 +840,11 @@
(MOVSDstoreidx1 [c] {sym} ptr (ADDLconst [d] idx) val mem) -> (MOVSDstoreidx1 [int64(int32(c+d))] {sym} ptr idx val mem)
(MOVSDstoreidx8 [c] {sym} ptr (ADDLconst [d] idx) val mem) -> (MOVSDstoreidx8 [int64(int32(c+8*d))] {sym} ptr idx val mem)
// Merge load to op
((ADD|AND|OR|XOR)L x l:(MOVLload [off] {sym} ptr mem)) && canMergeLoad(v, l, x) && clobber(l) -> ((ADD|AND|OR|XOR)Lmem x [off] {sym} ptr mem)
((ADD|SUB|MUL)SD x l:(MOVSDload [off] {sym} ptr mem)) && canMergeLoad(v, l, x) && clobber(l) -> ((ADD|SUB|MUL)SDmem x [off] {sym} ptr mem)
((ADD|SUB|MUL)SS x l:(MOVSSload [off] {sym} ptr mem)) && canMergeLoad(v, l, x) && clobber(l) -> ((ADD|SUB|MUL)SSmem x [off] {sym} ptr mem)
(MOVBstoreconstidx1 [x] {sym} (ADDLconst [c] ptr) idx mem) ->
(MOVBstoreconstidx1 [ValAndOff(x).add(c)] {sym} ptr idx mem)
(MOVWstoreconstidx1 [x] {sym} (ADDLconst [c] ptr) idx mem) ->
@ -1231,4 +1253,4 @@
// For PIC, break floating-point constant loading into two instructions so we have
// a register to use for holding the address of the constant pool entry.
(MOVSSconst [c]) && config.ctxt.Flag_shared -> (MOVSSconst2 (MOVSSconst1 [c]))
(MOVSDconst [c]) && config.ctxt.Flag_shared -> (MOVSDconst2 (MOVSDconst1 [c]))
(MOVSDconst [c]) && config.ctxt.Flag_shared -> (MOVSDconst2 (MOVSDconst1 [c]))

View File

@ -125,6 +125,7 @@ func init() {
flagsgpax = regInfo{inputs: nil, clobbers: ax, outputs: []regMask{gp &^ ax}}
gpload = regInfo{inputs: []regMask{gpspsb, 0}, outputs: gponly}
gp21load = regInfo{inputs: []regMask{gp, gpspsb, 0}, outputs: gponly}
gploadidx = regInfo{inputs: []regMask{gpspsb, gpsp, 0}, outputs: gponly}
gpstore = regInfo{inputs: []regMask{gpspsb, gpsp, 0}}
@ -134,6 +135,7 @@ func init() {
fp01 = regInfo{inputs: nil, outputs: fponly}
fp21 = regInfo{inputs: []regMask{fp, fp}, outputs: fponly}
fp21load = regInfo{inputs: []regMask{fp, gpspsb, 0}, outputs: fponly}
fpgp = regInfo{inputs: fponly, outputs: gponly}
gpfp = regInfo{inputs: gponly, outputs: fponly}
fp11 = regInfo{inputs: fponly, outputs: fponly}
@ -173,6 +175,13 @@ func init() {
{name: "MOVSDstoreidx1", argLength: 4, reg: fpstoreidx, asm: "MOVSD", aux: "SymOff", symEffect: "Write"}, // fp64 indexed by i store
{name: "MOVSDstoreidx8", argLength: 4, reg: fpstoreidx, asm: "MOVSD", aux: "SymOff", symEffect: "Write"}, // fp64 indexed by 8i store
{name: "ADDSSmem", argLength: 3, reg: fp21load, asm: "ADDSS", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp32 arg0 + tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "ADDSDmem", argLength: 3, reg: fp21load, asm: "ADDSD", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp64 arg0 + tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "SUBSSmem", argLength: 3, reg: fp21load, asm: "SUBSS", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp32 arg0 - tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "SUBSDmem", argLength: 3, reg: fp21load, asm: "SUBSD", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp64 arg0 - tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "MULSSmem", argLength: 3, reg: fp21load, asm: "MULSS", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp32 arg0 * tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "MULSDmem", argLength: 3, reg: fp21load, asm: "MULSD", aux: "SymOff", resultInArg0: true, faultOnNilArg1: true, symEffect: "Read"}, // fp64 arg0 * tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
// binary ops
{name: "ADDL", argLength: 2, reg: gp21sp, asm: "ADDL", commutative: true, clobberFlags: true}, // arg0 + arg1
{name: "ADDLconst", argLength: 1, reg: gp11sp, asm: "ADDL", aux: "Int32", typ: "UInt32", clobberFlags: true}, // arg0 + auxint
@ -258,6 +267,12 @@ func init() {
{name: "ROLWconst", argLength: 1, reg: gp11, asm: "ROLW", aux: "Int16", resultInArg0: true, clobberFlags: true}, // arg0 rotate left auxint, rotate amount 0-15
{name: "ROLBconst", argLength: 1, reg: gp11, asm: "ROLB", aux: "Int8", resultInArg0: true, clobberFlags: true}, // arg0 rotate left auxint, rotate amount 0-7
{name: "ADDLmem", argLength: 3, reg: gp21load, asm: "ADDL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 + tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "SUBLmem", argLength: 3, reg: gp21load, asm: "SUBL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 - tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "ANDLmem", argLength: 3, reg: gp21load, asm: "ANDL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 & tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "ORLmem", argLength: 3, reg: gp21load, asm: "ORL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 | tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
{name: "XORLmem", argLength: 3, reg: gp21load, asm: "XORL", aux: "SymOff", resultInArg0: true, clobberFlags: true, faultOnNilArg1: true, symEffect: "Read"}, // arg0 ^ tmp, tmp loaded from arg1+auxint+aux, arg2 = mem
// unary ops
{name: "NEGL", argLength: 1, reg: gp11, asm: "NEGL", resultInArg0: true, clobberFlags: true}, // -arg0
@ -516,4 +531,4 @@ func init() {
framepointerreg: int8(num["BP"]),
linkreg: -1, // not used
})
}
}

View File

@ -255,6 +255,12 @@ const (
Op386MOVSSstoreidx4
Op386MOVSDstoreidx1
Op386MOVSDstoreidx8
Op386ADDSSmem
Op386ADDSDmem
Op386SUBSSmem
Op386SUBSDmem
Op386MULSSmem
Op386MULSDmem
Op386ADDL
Op386ADDLconst
Op386ADDLcarry
@ -318,6 +324,11 @@ const (
Op386ROLLconst
Op386ROLWconst
Op386ROLBconst
Op386ADDLmem
Op386SUBLmem
Op386ANDLmem
Op386ORLmem
Op386XORLmem
Op386NEGL
Op386NOTL
Op386BSFL
@ -2487,6 +2498,114 @@ var opcodeTable = [...]opInfo{
},
},
},
{
name: "ADDSSmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.AADDSS,
reg: regInfo{
inputs: []inputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
},
},
},
{
name: "ADDSDmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.AADDSD,
reg: regInfo{
inputs: []inputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
},
},
},
{
name: "SUBSSmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.ASUBSS,
reg: regInfo{
inputs: []inputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
},
},
},
{
name: "SUBSDmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.ASUBSD,
reg: regInfo{
inputs: []inputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
},
},
},
{
name: "MULSSmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.AMULSS,
reg: regInfo{
inputs: []inputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
},
},
},
{
name: "MULSDmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.AMULSD,
reg: regInfo{
inputs: []inputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 65280}, // X0 X1 X2 X3 X4 X5 X6 X7
},
},
},
{
name: "ADDL",
argLen: 2,
@ -3437,6 +3556,101 @@ var opcodeTable = [...]opInfo{
},
},
},
{
name: "ADDLmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
clobberFlags: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.AADDL,
reg: regInfo{
inputs: []inputInfo{
{0, 239}, // AX CX DX BX BP SI DI
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 239}, // AX CX DX BX BP SI DI
},
},
},
{
name: "SUBLmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
clobberFlags: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.ASUBL,
reg: regInfo{
inputs: []inputInfo{
{0, 239}, // AX CX DX BX BP SI DI
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 239}, // AX CX DX BX BP SI DI
},
},
},
{
name: "ANDLmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
clobberFlags: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.AANDL,
reg: regInfo{
inputs: []inputInfo{
{0, 239}, // AX CX DX BX BP SI DI
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 239}, // AX CX DX BX BP SI DI
},
},
},
{
name: "ORLmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
clobberFlags: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.AORL,
reg: regInfo{
inputs: []inputInfo{
{0, 239}, // AX CX DX BX BP SI DI
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 239}, // AX CX DX BX BP SI DI
},
},
},
{
name: "XORLmem",
auxType: auxSymOff,
argLen: 3,
resultInArg0: true,
clobberFlags: true,
faultOnNilArg1: true,
symEffect: SymRead,
asm: x86.AXORL,
reg: regInfo{
inputs: []inputInfo{
{0, 239}, // AX CX DX BX BP SI DI
{1, 65791}, // AX CX DX BX SP BP SI DI SB
},
outputs: []outputInfo{
{0, 239}, // AX CX DX BX BP SI DI
},
},
},
{
name: "NEGL",
argLen: 1,

File diff suppressed because it is too large Load Diff

View File

@ -510,6 +510,17 @@ func ssaGenValue(s *gc.SSAGenState, v *ssa.Value) {
gc.AddAux(&p.From, v)
p.To.Type = obj.TYPE_REG
p.To.Reg = v.Reg()
case ssa.Op386ADDLmem, ssa.Op386SUBLmem, ssa.Op386ANDLmem, ssa.Op386ORLmem, ssa.Op386XORLmem,
ssa.Op386ADDSDmem, ssa.Op386ADDSSmem, ssa.Op386SUBSDmem, ssa.Op386SUBSSmem, ssa.Op386MULSDmem, ssa.Op386MULSSmem:
p := s.Prog(v.Op.Asm())
p.From.Type = obj.TYPE_MEM
p.From.Reg = v.Args[1].Reg()
gc.AddAux(&p.From, v)
p.To.Type = obj.TYPE_REG
p.To.Reg = v.Reg()
if v.Reg() != v.Args[0].Reg() {
v.Fatalf("input[0] and output not in same register %s", v.LongString())
}
case ssa.Op386MOVSSstore, ssa.Op386MOVSDstore, ssa.Op386MOVLstore, ssa.Op386MOVWstore, ssa.Op386MOVBstore:
p := s.Prog(v.Op.Asm())
p.From.Type = obj.TYPE_REG