diff options
Diffstat (limited to 'src/cmd/compile/internal/ssa/gen/S390X.rules')
-rw-r--r-- | src/cmd/compile/internal/ssa/gen/S390X.rules | 885 |
1 files changed, 238 insertions, 647 deletions
diff --git a/src/cmd/compile/internal/ssa/gen/S390X.rules b/src/cmd/compile/internal/ssa/gen/S390X.rules index 5e4c436ca1..e564f638d3 100644 --- a/src/cmd/compile/internal/ssa/gen/S390X.rules +++ b/src/cmd/compile/internal/ssa/gen/S390X.rules @@ -498,27 +498,19 @@ // Remove zero extensions after zero extending load. // Note: take care that if x is spilled it is restored correctly. (MOV(B|H|W)Zreg x:(MOVBZload _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 1) => x -(MOV(B|H|W)Zreg x:(MOVBZloadidx _ _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 1) => x (MOV(H|W)Zreg x:(MOVHZload _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 2) => x -(MOV(H|W)Zreg x:(MOVHZloadidx _ _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 2) => x (MOVWZreg x:(MOVWZload _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 4) => x -(MOVWZreg x:(MOVWZloadidx _ _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 4) => x // Remove sign extensions after sign extending load. // Note: take care that if x is spilled it is restored correctly. (MOV(B|H|W)reg x:(MOVBload _ _)) && (x.Type.IsSigned() || x.Type.Size() == 8) => x -(MOV(B|H|W)reg x:(MOVBloadidx _ _ _)) && (x.Type.IsSigned() || x.Type.Size() == 8) => x (MOV(H|W)reg x:(MOVHload _ _)) && (x.Type.IsSigned() || x.Type.Size() == 8) => x -(MOV(H|W)reg x:(MOVHloadidx _ _ _)) && (x.Type.IsSigned() || x.Type.Size() == 8) => x (MOVWreg x:(MOVWload _ _)) && (x.Type.IsSigned() || x.Type.Size() == 8) => x -(MOVWreg x:(MOVWloadidx _ _ _)) && (x.Type.IsSigned() || x.Type.Size() == 8) => x // Remove sign extensions after zero extending load. // These type checks are probably unnecessary but do them anyway just in case. (MOV(H|W)reg x:(MOVBZload _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 1) => x -(MOV(H|W)reg x:(MOVBZloadidx _ _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 1) => x (MOVWreg x:(MOVHZload _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 2) => x -(MOVWreg x:(MOVHZloadidx _ _ _)) && (!x.Type.IsSigned() || x.Type.Size() > 2) => x // Fold sign and zero extensions into loads. // @@ -538,14 +530,6 @@ && x.Uses == 1 && clobber(x) => @x.Block (MOV(B|H|W)load <t> [o] {s} p mem) -(MOV(B|H|W)Zreg <t> x:(MOV(B|H|W)loadidx [o] {s} p i mem)) - && x.Uses == 1 - && clobber(x) - => @x.Block (MOV(B|H|W)Zloadidx <t> [o] {s} p i mem) -(MOV(B|H|W)reg <t> x:(MOV(B|H|W)Zloadidx [o] {s} p i mem)) - && x.Uses == 1 - && clobber(x) - => @x.Block (MOV(B|H|W)loadidx <t> [o] {s} p i mem) // Remove zero extensions after argument load. (MOVBZreg x:(Arg <t>)) && !t.IsSigned() && t.Size() == 1 => x @@ -641,41 +625,37 @@ (BRC {c} (CMPWUconst x [y]) yes no) && y == int32( int8(y)) && (c == s390x.Equal || c == s390x.LessOrGreater) => (CIJ {c} x [ int8(y)] yes no) // Fold constants into instructions. -(ADD x (MOVDconst [c])) && is32Bit(c) -> (ADDconst [c] x) -(ADDW x (MOVDconst [c])) -> (ADDWconst [int64(int32(c))] x) +(ADD x (MOVDconst [c])) && is32Bit(c) => (ADDconst [int32(c)] x) +(ADDW x (MOVDconst [c])) => (ADDWconst [int32(c)] x) -(SUB x (MOVDconst [c])) && is32Bit(c) -> (SUBconst x [c]) -(SUB (MOVDconst [c]) x) && is32Bit(c) -> (NEG (SUBconst <v.Type> x [c])) -(SUBW x (MOVDconst [c])) -> (SUBWconst x [int64(int32(c))]) -(SUBW (MOVDconst [c]) x) -> (NEGW (SUBWconst <v.Type> x [int64(int32(c))])) +(SUB x (MOVDconst [c])) && is32Bit(c) => (SUBconst x [int32(c)]) +(SUB (MOVDconst [c]) x) && is32Bit(c) => (NEG (SUBconst <v.Type> x [int32(c)])) +(SUBW x (MOVDconst [c])) => (SUBWconst x [int32(c)]) +(SUBW (MOVDconst [c]) x) => (NEGW (SUBWconst <v.Type> x [int32(c)])) -(MULLD x (MOVDconst [c])) && is32Bit(c) -> (MULLDconst [c] x) -(MULLW x (MOVDconst [c])) -> (MULLWconst [int64(int32(c))] x) +(MULLD x (MOVDconst [c])) && is32Bit(c) => (MULLDconst [int32(c)] x) +(MULLW x (MOVDconst [c])) => (MULLWconst [int32(c)] x) // NILF instructions leave the high 32 bits unchanged which is // equivalent to the leftmost 32 bits being set. // TODO(mundaym): modify the assembler to accept 64-bit values // and use isU32Bit(^c). (AND x (MOVDconst [c])) && is32Bit(c) && c < 0 => (ANDconst [c] x) -(AND x (MOVDconst [c])) && is32Bit(c) && c >= 0 -> (MOVWZreg (ANDWconst <typ.UInt32> [int64(int32(c))] x)) -(ANDW x (MOVDconst [c])) -> (ANDWconst [int64(int32(c))] x) +(AND x (MOVDconst [c])) && is32Bit(c) && c >= 0 => (MOVWZreg (ANDWconst <typ.UInt32> [int32(c)] x)) +(ANDW x (MOVDconst [c])) => (ANDWconst [int32(c)] x) -(ANDWconst [c] (ANDWconst [d] x)) => (ANDWconst [c & d] x) -(ANDconst [c] (ANDconst [d] x)) => (ANDconst [c & d] x) +((AND|ANDW)const [c] ((AND|ANDW)const [d] x)) => ((AND|ANDW)const [c&d] x) -(OR x (MOVDconst [c])) && isU32Bit(c) => (ORconst [c] x) -(ORW x (MOVDconst [c])) -> (ORWconst [int64(int32(c))] x) - -(XOR x (MOVDconst [c])) && isU32Bit(c) => (XORconst [c] x) -(XORW x (MOVDconst [c])) -> (XORWconst [int64(int32(c))] x) +((OR|XOR) x (MOVDconst [c])) && isU32Bit(c) => ((OR|XOR)const [c] x) +((OR|XOR)W x (MOVDconst [c])) => ((OR|XOR)Wconst [int32(c)] x) // Constant shifts. (S(LD|RD|RAD|LW|RW|RAW) x (MOVDconst [c])) - -> (S(LD|RD|RAD|LW|RW|RAW)const x [c&63]) + => (S(LD|RD|RAD|LW|RW|RAW)const x [int8(c&63)]) // Shifts only use the rightmost 6 bits of the shift value. (S(LD|RD|RAD|LW|RW|RAW) x (AND (MOVDconst [c]) y)) - -> (S(LD|RD|RAD|LW|RW|RAW) x (ANDWconst <typ.UInt32> [c&63] y)) + => (S(LD|RD|RAD|LW|RW|RAW) x (ANDWconst <typ.UInt32> [int32(c&63)] y)) (S(LD|RD|RAD|LW|RW|RAW) x (ANDWconst [c] y)) && c&63 == 63 => (S(LD|RD|RAD|LW|RW|RAW) x y) (SLD x (MOV(W|H|B|WZ|HZ|BZ)reg y)) => (SLD x y) @@ -686,8 +666,8 @@ (SRAW x (MOV(W|H|B|WZ|HZ|BZ)reg y)) => (SRAW x y) // Constant rotate generation -(RLL x (MOVDconst [c])) -> (RLLconst x [c&31]) -(RLLG x (MOVDconst [c])) -> (RLLGconst x [c&63]) +(RLL x (MOVDconst [c])) => (RLLconst x [int8(c&31)]) +(RLLG x (MOVDconst [c])) => (RLLGconst x [int8(c&63)]) (ADD (SLDconst x [c]) (SRDconst x [d])) && d == 64-c => (RLLGconst [c] x) ( OR (SLDconst x [c]) (SRDconst x [d])) && d == 64-c => (RLLGconst [c] x) @@ -697,14 +677,17 @@ ( ORW (SLWconst x [c]) (SRWconst x [d])) && d == 32-c => (RLLconst [c] x) (XORW (SLWconst x [c]) (SRWconst x [d])) && d == 32-c => (RLLconst [c] x) -(CMP x (MOVDconst [c])) && is32Bit(c) -> (CMPconst x [c]) -(CMP (MOVDconst [c]) x) && is32Bit(c) -> (InvertFlags (CMPconst x [c])) -(CMPW x (MOVDconst [c])) -> (CMPWconst x [int64(int32(c))]) -(CMPW (MOVDconst [c]) x) -> (InvertFlags (CMPWconst x [int64(int32(c))])) -(CMPU x (MOVDconst [c])) && isU32Bit(c) -> (CMPUconst x [int64(int32(c))]) -(CMPU (MOVDconst [c]) x) && isU32Bit(c) -> (InvertFlags (CMPUconst x [int64(int32(c))])) -(CMPWU x (MOVDconst [c])) -> (CMPWUconst x [int64(int32(c))]) -(CMPWU (MOVDconst [c]) x) -> (InvertFlags (CMPWUconst x [int64(int32(c))])) +// Signed 64-bit comparison with immediate. +(CMP x (MOVDconst [c])) && is32Bit(c) => (CMPconst x [int32(c)]) +(CMP (MOVDconst [c]) x) && is32Bit(c) => (InvertFlags (CMPconst x [int32(c)])) + +// Unsigned 64-bit comparison with immediate. +(CMPU x (MOVDconst [c])) && isU32Bit(c) => (CMPUconst x [int32(c)]) +(CMPU (MOVDconst [c]) x) && isU32Bit(c) => (InvertFlags (CMPUconst x [int32(c)])) + +// Signed and unsigned 32-bit comparison with immediate. +(CMP(W|WU) x (MOVDconst [c])) => (CMP(W|WU)const x [int32(c)]) +(CMP(W|WU) (MOVDconst [c]) x) => (InvertFlags (CMP(W|WU)const x [int32(c)])) // Canonicalize the order of arguments to comparisons - helps with CSE. ((CMP|CMPW|CMPU|CMPWU) x y) && x.ID > y.ID => (InvertFlags ((CMP|CMPW|CMPU|CMPWU) y x)) @@ -752,14 +735,14 @@ (SL(D|W)const <t> x [int8(log32(-c+(-c&^(-c-1))))])) // Fold ADD into MOVDaddr. Odd offsets from SB shouldn't be folded (LARL can't handle them). -(ADDconst [c] (MOVDaddr [d] {s} x:(SB))) && ((c+d)&1 == 0) && is32Bit(c+d) -> (MOVDaddr [c+d] {s} x) -(ADDconst [c] (MOVDaddr [d] {s} x)) && x.Op != OpSB && is20Bit(c+d) -> (MOVDaddr [c+d] {s} x) -(ADD idx (MOVDaddr [c] {s} ptr)) && ptr.Op != OpSB && idx.Op != OpSB => (MOVDaddridx [c] {s} ptr idx) +(ADDconst [c] (MOVDaddr [d] {s} x:(SB))) && ((c+d)&1 == 0) && is32Bit(int64(c)+int64(d)) => (MOVDaddr [c+d] {s} x) +(ADDconst [c] (MOVDaddr [d] {s} x)) && x.Op != OpSB && is20Bit(int64(c)+int64(d)) => (MOVDaddr [c+d] {s} x) +(ADD idx (MOVDaddr [c] {s} ptr)) && ptr.Op != OpSB => (MOVDaddridx [c] {s} ptr idx) // fold ADDconst into MOVDaddrx -(ADDconst [c] (MOVDaddridx [d] {s} x y)) && is20Bit(c+d) -> (MOVDaddridx [c+d] {s} x y) -(MOVDaddridx [c] {s} (ADDconst [d] x) y) && is20Bit(c+d) && x.Op != OpSB -> (MOVDaddridx [c+d] {s} x y) -(MOVDaddridx [c] {s} x (ADDconst [d] y)) && is20Bit(c+d) && y.Op != OpSB -> (MOVDaddridx [c+d] {s} x y) +(ADDconst [c] (MOVDaddridx [d] {s} x y)) && is20Bit(int64(c)+int64(d)) => (MOVDaddridx [c+d] {s} x y) +(MOVDaddridx [c] {s} (ADDconst [d] x) y) && is20Bit(int64(c)+int64(d)) => (MOVDaddridx [c+d] {s} x y) +(MOVDaddridx [c] {s} x (ADDconst [d] y)) && is20Bit(int64(c)+int64(d)) => (MOVDaddridx [c+d] {s} x y) // reverse ordering of compare instruction (LOCGR {c} x y (InvertFlags cmp)) => (LOCGR {c.ReverseComparison()} x y cmp) @@ -799,11 +782,11 @@ // detect copysign (OR (SLDconst [63] (SRDconst [63] (LGDR x))) (LGDR (LPDFR <t> y))) => (LGDR (CPSDR <t> y x)) -(OR (SLDconst [63] (SRDconst [63] (LGDR x))) (MOVDconst [c])) && c & -1<<63 == 0 -> (LGDR (CPSDR <x.Type> (FMOVDconst <x.Type> [c]) x)) +(OR (SLDconst [63] (SRDconst [63] (LGDR x))) (MOVDconst [c])) && c & -1<<63 == 0 => (LGDR (CPSDR <x.Type> (FMOVDconst <x.Type> [math.Float64frombits(uint64(c))]) x)) (OR (AND (MOVDconst [-1<<63]) (LGDR x)) (LGDR (LPDFR <t> y))) => (LGDR (CPSDR <t> y x)) -(OR (AND (MOVDconst [-1<<63]) (LGDR x)) (MOVDconst [c])) && c & -1<<63 == 0 -> (LGDR (CPSDR <x.Type> (FMOVDconst <x.Type> [c]) x)) -(CPSDR y (FMOVDconst [c])) && c & -1<<63 == 0 -> (LPDFR y) -(CPSDR y (FMOVDconst [c])) && c & -1<<63 != 0 -> (LNDFR y) +(OR (AND (MOVDconst [-1<<63]) (LGDR x)) (MOVDconst [c])) && c & -1<<63 == 0 => (LGDR (CPSDR <x.Type> (FMOVDconst <x.Type> [math.Float64frombits(uint64(c))]) x)) +(CPSDR y (FMOVDconst [c])) && !math.Signbit(c) => (LPDFR y) +(CPSDR y (FMOVDconst [c])) && math.Signbit(c) => (LNDFR y) // absorb negations into set/clear sign bit (FNEG (LPDFR x)) => (LNDFR x) @@ -832,216 +815,131 @@ // the ADDconst get eliminated, we still have to compute the ADDconst and we now // have potentially two live values (ptr and (ADDconst [off] ptr)) instead of one. // Nevertheless, let's do it! -(MOVDload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(off1+off2) -> (MOVDload [off1+off2] {sym} ptr mem) -(MOVWload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(off1+off2) -> (MOVWload [off1+off2] {sym} ptr mem) -(MOVHload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(off1+off2) -> (MOVHload [off1+off2] {sym} ptr mem) -(MOVBload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(off1+off2) -> (MOVBload [off1+off2] {sym} ptr mem) -(MOVWZload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(off1+off2) -> (MOVWZload [off1+off2] {sym} ptr mem) -(MOVHZload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(off1+off2) -> (MOVHZload [off1+off2] {sym} ptr mem) -(MOVBZload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(off1+off2) -> (MOVBZload [off1+off2] {sym} ptr mem) -(FMOVSload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(off1+off2) -> (FMOVSload [off1+off2] {sym} ptr mem) -(FMOVDload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(off1+off2) -> (FMOVDload [off1+off2] {sym} ptr mem) - -(MOVDstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(off1+off2) -> (MOVDstore [off1+off2] {sym} ptr val mem) -(MOVWstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(off1+off2) -> (MOVWstore [off1+off2] {sym} ptr val mem) -(MOVHstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(off1+off2) -> (MOVHstore [off1+off2] {sym} ptr val mem) -(MOVBstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(off1+off2) -> (MOVBstore [off1+off2] {sym} ptr val mem) -(FMOVSstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(off1+off2) -> (FMOVSstore [off1+off2] {sym} ptr val mem) -(FMOVDstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(off1+off2) -> (FMOVDstore [off1+off2] {sym} ptr val mem) - -(ADDload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (ADDload [off1+off2] {sym} x ptr mem) -(ADDWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (ADDWload [off1+off2] {sym} x ptr mem) -(MULLDload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (MULLDload [off1+off2] {sym} x ptr mem) -(MULLWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (MULLWload [off1+off2] {sym} x ptr mem) -(SUBload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (SUBload [off1+off2] {sym} x ptr mem) -(SUBWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (SUBWload [off1+off2] {sym} x ptr mem) - -(ANDload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (ANDload [off1+off2] {sym} x ptr mem) -(ANDWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (ANDWload [off1+off2] {sym} x ptr mem) -(ORload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (ORload [off1+off2] {sym} x ptr mem) -(ORWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (ORWload [off1+off2] {sym} x ptr mem) -(XORload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (XORload [off1+off2] {sym} x ptr mem) -(XORWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(off1+off2) -> (XORWload [off1+off2] {sym} x ptr mem) +(MOVDload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(int64(off1)+int64(off2)) => (MOVDload [off1+off2] {sym} ptr mem) +(MOVWload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(int64(off1)+int64(off2)) => (MOVWload [off1+off2] {sym} ptr mem) +(MOVHload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(int64(off1)+int64(off2)) => (MOVHload [off1+off2] {sym} ptr mem) +(MOVBload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(int64(off1)+int64(off2)) => (MOVBload [off1+off2] {sym} ptr mem) +(MOVWZload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(int64(off1)+int64(off2)) => (MOVWZload [off1+off2] {sym} ptr mem) +(MOVHZload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(int64(off1)+int64(off2)) => (MOVHZload [off1+off2] {sym} ptr mem) +(MOVBZload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(int64(off1)+int64(off2)) => (MOVBZload [off1+off2] {sym} ptr mem) +(FMOVSload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(int64(off1)+int64(off2)) => (FMOVSload [off1+off2] {sym} ptr mem) +(FMOVDload [off1] {sym} (ADDconst [off2] ptr) mem) && is20Bit(int64(off1)+int64(off2)) => (FMOVDload [off1+off2] {sym} ptr mem) + +(MOVDstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(int64(off1)+int64(off2)) => (MOVDstore [off1+off2] {sym} ptr val mem) +(MOVWstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(int64(off1)+int64(off2)) => (MOVWstore [off1+off2] {sym} ptr val mem) +(MOVHstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(int64(off1)+int64(off2)) => (MOVHstore [off1+off2] {sym} ptr val mem) +(MOVBstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(int64(off1)+int64(off2)) => (MOVBstore [off1+off2] {sym} ptr val mem) +(FMOVSstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(int64(off1)+int64(off2)) => (FMOVSstore [off1+off2] {sym} ptr val mem) +(FMOVDstore [off1] {sym} (ADDconst [off2] ptr) val mem) && is20Bit(int64(off1)+int64(off2)) => (FMOVDstore [off1+off2] {sym} ptr val mem) + +(ADDload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (ADDload [off1+off2] {sym} x ptr mem) +(ADDWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (ADDWload [off1+off2] {sym} x ptr mem) +(MULLDload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (MULLDload [off1+off2] {sym} x ptr mem) +(MULLWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (MULLWload [off1+off2] {sym} x ptr mem) +(SUBload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (SUBload [off1+off2] {sym} x ptr mem) +(SUBWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (SUBWload [off1+off2] {sym} x ptr mem) + +(ANDload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (ANDload [off1+off2] {sym} x ptr mem) +(ANDWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (ANDWload [off1+off2] {sym} x ptr mem) +(ORload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (ORload [off1+off2] {sym} x ptr mem) +(ORWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (ORWload [off1+off2] {sym} x ptr mem) +(XORload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (XORload [off1+off2] {sym} x ptr mem) +(XORWload [off1] {sym} x (ADDconst [off2] ptr) mem) && ptr.Op != OpSB && is20Bit(int64(off1)+int64(off2)) => (XORWload [off1+off2] {sym} x ptr mem) // Fold constants into stores. -(MOVDstore [off] {sym} ptr (MOVDconst [c]) mem) && is16Bit(c) && isU12Bit(off) && ptr.Op != OpSB -> - (MOVDstoreconst [makeValAndOff(c,off)] {sym} ptr mem) -(MOVWstore [off] {sym} ptr (MOVDconst [c]) mem) && is16Bit(c) && isU12Bit(off) && ptr.Op != OpSB -> - (MOVWstoreconst [makeValAndOff(int64(int32(c)),off)] {sym} ptr mem) -(MOVHstore [off] {sym} ptr (MOVDconst [c]) mem) && isU12Bit(off) && ptr.Op != OpSB -> - (MOVHstoreconst [makeValAndOff(int64(int16(c)),off)] {sym} ptr mem) -(MOVBstore [off] {sym} ptr (MOVDconst [c]) mem) && is20Bit(off) && ptr.Op != OpSB -> - (MOVBstoreconst [makeValAndOff(int64(int8(c)),off)] {sym} ptr mem) +(MOVDstore [off] {sym} ptr (MOVDconst [c]) mem) && is16Bit(c) && isU12Bit(int64(off)) && ptr.Op != OpSB => + (MOVDstoreconst [makeValAndOff32(int32(c),off)] {sym} ptr mem) +(MOVWstore [off] {sym} ptr (MOVDconst [c]) mem) && is16Bit(c) && isU12Bit(int64(off)) && ptr.Op != OpSB => + (MOVWstoreconst [makeValAndOff32(int32(c),off)] {sym} ptr mem) +(MOVHstore [off] {sym} ptr (MOVDconst [c]) mem) && isU12Bit(int64(off)) && ptr.Op != OpSB => + (MOVHstoreconst [makeValAndOff32(int32(int16(c)),off)] {sym} ptr mem) +(MOVBstore [off] {sym} ptr (MOVDconst [c]) mem) && is20Bit(int64(off)) && ptr.Op != OpSB => + (MOVBstoreconst [makeValAndOff32(int32(int8(c)),off)] {sym} ptr mem) // Fold address offsets into constant stores. -(MOVDstoreconst [sc] {s} (ADDconst [off] ptr) mem) && isU12Bit(ValAndOff(sc).Off()+off) -> - (MOVDstoreconst [ValAndOff(sc).add(off)] {s} ptr mem) -(MOVWstoreconst [sc] {s} (ADDconst [off] ptr) mem) && isU12Bit(ValAndOff(sc).Off()+off) -> - (MOVWstoreconst [ValAndOff(sc).add(off)] {s} ptr mem) -(MOVHstoreconst [sc] {s} (ADDconst [off] ptr) mem) && isU12Bit(ValAndOff(sc).Off()+off) -> - (MOVHstoreconst [ValAndOff(sc).add(off)] {s} ptr mem) -(MOVBstoreconst [sc] {s} (ADDconst [off] ptr) mem) && is20Bit(ValAndOff(sc).Off()+off) -> - (MOVBstoreconst [ValAndOff(sc).add(off)] {s} ptr mem) +(MOVDstoreconst [sc] {s} (ADDconst [off] ptr) mem) && isU12Bit(sc.Off()+int64(off)) => + (MOVDstoreconst [sc.addOffset32(off)] {s} ptr mem) +(MOVWstoreconst [sc] {s} (ADDconst [off] ptr) mem) && isU12Bit(sc.Off()+int64(off)) => + (MOVWstoreconst [sc.addOffset32(off)] {s} ptr mem) +(MOVHstoreconst [sc] {s} (ADDconst [off] ptr) mem) && isU12Bit(sc.Off()+int64(off)) => + (MOVHstoreconst [sc.addOffset32(off)] {s} ptr mem) +(MOVBstoreconst [sc] {s} (ADDconst [off] ptr) mem) && is20Bit(sc.Off()+int64(off)) => + (MOVBstoreconst [sc.addOffset32(off)] {s} ptr mem) // Merge address calculations into loads and stores. // Offsets from SB must not be merged into unaligned memory accesses because // loads/stores using PC-relative addressing directly must be aligned to the // size of the target. -(MOVDload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%8 == 0 && (off1+off2)%8 == 0)) -> - (MOVDload [off1+off2] {mergeSym(sym1,sym2)} base mem) -(MOVWZload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%4 == 0 && (off1+off2)%4 == 0)) -> - (MOVWZload [off1+off2] {mergeSym(sym1,sym2)} base mem) -(MOVHZload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%2 == 0 && (off1+off2)%2 == 0)) -> - (MOVHZload [off1+off2] {mergeSym(sym1,sym2)} base mem) -(MOVBZload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVBZload [off1+off2] {mergeSym(sym1,sym2)} base mem) -(FMOVSload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (FMOVSload [off1+off2] {mergeSym(sym1,sym2)} base mem) -(FMOVDload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (FMOVDload [off1+off2] {mergeSym(sym1,sym2)} base mem) - -(MOVWload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%4 == 0 && (off1+off2)%4 == 0)) -> - (MOVWload [off1+off2] {mergeSym(sym1,sym2)} base mem) -(MOVHload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%2 == 0 && (off1+off2)%2 == 0)) -> - (MOVHload [off1+off2] {mergeSym(sym1,sym2)} base mem) -(MOVBload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVBload [off1+off2] {mergeSym(sym1,sym2)} base mem) - -(MOVDstore [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%8 == 0 && (off1+off2)%8 == 0)) -> - (MOVDstore [off1+off2] {mergeSym(sym1,sym2)} base val mem) -(MOVWstore [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%4 == 0 && (off1+off2)%4 == 0)) -> - (MOVWstore [off1+off2] {mergeSym(sym1,sym2)} base val mem) -(MOVHstore [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%2 == 0 && (off1+off2)%2 == 0)) -> - (MOVHstore [off1+off2] {mergeSym(sym1,sym2)} base val mem) -(MOVBstore [off1] {sym1} (MOVDaddr [off2] {sym2} base) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVBstore [off1+off2] {mergeSym(sym1,sym2)} base val mem) -(FMOVSstore [off1] {sym1} (MOVDaddr [off2] {sym2} base) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (FMOVSstore [off1+off2] {mergeSym(sym1,sym2)} base val mem) -(FMOVDstore [off1] {sym1} (MOVDaddr [off2] {sym2} base) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (FMOVDstore [off1+off2] {mergeSym(sym1,sym2)} base val mem) - -(ADDload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (ADDload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(ADDWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (ADDWload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(MULLDload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (MULLDload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(MULLWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (MULLWload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(SUBload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (SUBload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(SUBWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (SUBWload [o1+o2] {mergeSym(s1, s2)} x ptr mem) - -(ANDload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (ANDload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(ANDWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (ANDWload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(ORload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (ORload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(ORWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (ORWload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(XORload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (XORload [o1+o2] {mergeSym(s1, s2)} x ptr mem) -(XORWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(o1+o2) && canMergeSym(s1, s2) -> (XORWload [o1+o2] {mergeSym(s1, s2)} x ptr mem) +(MOVDload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%8 == 0 && (off1+off2)%8 == 0)) => + (MOVDload [off1+off2] {mergeSymTyped(sym1,sym2)} base mem) +(MOVWZload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%4 == 0 && (off1+off2)%4 == 0)) => + (MOVWZload [off1+off2] {mergeSymTyped(sym1,sym2)} base mem) +(MOVHZload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%2 == 0 && (off1+off2)%2 == 0)) => + (MOVHZload [off1+off2] {mergeSymTyped(sym1,sym2)} base mem) +(MOVBZload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) => + (MOVBZload [off1+off2] {mergeSymTyped(sym1,sym2)} base mem) +(FMOVSload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) => + (FMOVSload [off1+off2] {mergeSymTyped(sym1,sym2)} base mem) +(FMOVDload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) => + (FMOVDload [off1+off2] {mergeSymTyped(sym1,sym2)} base mem) + +(MOVWload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%4 == 0 && (off1+off2)%4 == 0)) => + (MOVWload [off1+off2] {mergeSymTyped(sym1,sym2)} base mem) +(MOVHload [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%2 == 0 && (off1+off2)%2 == 0)) => + (MOVHload [off1+off2] {mergeSymTyped(sym1,sym2)} base mem) +(MOVBload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) => + (MOVBload [off1+off2] {mergeSymTyped(sym1,sym2)} base mem) + +(MOVDstore [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) val mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%8 == 0 && (off1+off2)%8 == 0)) => + (MOVDstore [off1+off2] {mergeSymTyped(sym1,sym2)} base val mem) +(MOVWstore [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) val mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%4 == 0 && (off1+off2)%4 == 0)) => + (MOVWstore [off1+off2] {mergeSymTyped(sym1,sym2)} base val mem) +(MOVHstore [off1] {sym1} (MOVDaddr <t> [off2] {sym2} base) val mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && (base.Op != OpSB || (t.IsPtr() && t.Elem().Alignment()%2 == 0 && (off1+off2)%2 == 0)) => + (MOVHstore [off1+off2] {mergeSymTyped(sym1,sym2)} base val mem) +(MOVBstore [off1] {sym1} (MOVDaddr [off2] {sym2} base) val mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) => + (MOVBstore [off1+off2] {mergeSymTyped(sym1,sym2)} base val mem) +(FMOVSstore [off1] {sym1} (MOVDaddr [off2] {sym2} base) val mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) => + (FMOVSstore [off1+off2] {mergeSymTyped(sym1,sym2)} base val mem) +(FMOVDstore [off1] {sym1} (MOVDaddr [off2] {sym2} base) val mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) => + (FMOVDstore [off1+off2] {mergeSymTyped(sym1,sym2)} base val mem) + +(ADDload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (ADDload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(ADDWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (ADDWload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(MULLDload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (MULLDload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(MULLWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (MULLWload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(SUBload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (SUBload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(SUBWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (SUBWload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) + +(ANDload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (ANDload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(ANDWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (ANDWload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(ORload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (ORload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(ORWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (ORWload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(XORload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (XORload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) +(XORWload [o1] {s1} x (MOVDaddr [o2] {s2} ptr) mem) && ptr.Op != OpSB && is20Bit(int64(o1)+int64(o2)) && canMergeSym(s1, s2) => (XORWload [o1+o2] {mergeSymTyped(s1, s2)} x ptr mem) // Cannot store constant to SB directly (no 'move relative long immediate' instructions). -(MOVDstoreconst [sc] {sym1} (MOVDaddr [off] {sym2} ptr) mem) && ptr.Op != OpSB && canMergeSym(sym1, sym2) && ValAndOff(sc).canAdd(off) -> - (MOVDstoreconst [ValAndOff(sc).add(off)] {mergeSym(sym1, sym2)} ptr mem) -(MOVWstoreconst [sc] {sym1} (MOVDaddr [off] {sym2} ptr) mem) && ptr.Op != OpSB && canMergeSym(sym1, sym2) && ValAndOff(sc).canAdd(off) -> - (MOVWstoreconst [ValAndOff(sc).add(off)] {mergeSym(sym1, sym2)} ptr mem) -(MOVHstoreconst [sc] {sym1} (MOVDaddr [off] {sym2} ptr) mem) && ptr.Op != OpSB && canMergeSym(sym1, sym2) && ValAndOff(sc).canAdd(off) -> - (MOVHstoreconst [ValAndOff(sc).add(off)] {mergeSym(sym1, sym2)} ptr mem) -(MOVBstoreconst [sc] {sym1} (MOVDaddr [off] {sym2} ptr) mem) && ptr.Op != OpSB && canMergeSym(sym1, sym2) && ValAndOff(sc).canAdd(off) -> - (MOVBstoreconst [ValAndOff(sc).add(off)] {mergeSym(sym1, sym2)} ptr mem) - -// generating indexed loads and stores -(MOVBZload [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVBZloadidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx mem) -(MOVBload [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVBloadidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx mem) -(MOVHZload [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVHZloadidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx mem) -(MOVHload [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVHloadidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx mem) -(MOVWZload [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVWZloadidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx mem) -(MOVWload [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVWloadidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx mem) -(MOVDload [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVDloadidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx mem) -(FMOVSload [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (FMOVSloadidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx mem) -(FMOVDload [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (FMOVDloadidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx mem) - -(MOVBstore [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVBstoreidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx val mem) -(MOVHstore [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVHstoreidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx val mem) -(MOVWstore [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVWstoreidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx val mem) -(MOVDstore [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (MOVDstoreidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx val mem) -(FMOVSstore [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (FMOVSstoreidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx val mem) -(FMOVDstore [off1] {sym1} (MOVDaddridx [off2] {sym2} ptr idx) val mem) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) -> - (FMOVDstoreidx [off1+off2] {mergeSym(sym1,sym2)} ptr idx val mem) - -(MOVBZload [off] {sym} (ADD ptr idx) mem) && ptr.Op != OpSB => (MOVBZloadidx [off] {sym} ptr idx mem) -(MOVBload [off] {sym} (ADD ptr idx) mem) && ptr.Op != OpSB => (MOVBloadidx [off] {sym} ptr idx mem) -(MOVHZload [off] {sym} (ADD ptr idx) mem) && ptr.Op != OpSB => (MOVHZloadidx [off] {sym} ptr idx mem) -(MOVHload [off] {sym} (ADD ptr idx) mem) && ptr.Op != OpSB => (MOVHloadidx [off] {sym} ptr idx mem) -(MOVWZload [off] {sym} (ADD ptr idx) mem) && ptr.Op != OpSB => (MOVWZloadidx [off] {sym} ptr idx mem) -(MOVWload [off] {sym} (ADD ptr idx) mem) && ptr.Op != OpSB => (MOVWloadidx [off] {sym} ptr idx mem) -(MOVDload [off] {sym} (ADD ptr idx) mem) && ptr.Op != OpSB => (MOVDloadidx [off] {sym} ptr idx mem) -(FMOVSload [off] {sym} (ADD ptr idx) mem) && ptr.Op != OpSB => (FMOVSloadidx [off] {sym} ptr idx mem) -(FMOVDload [off] {sym} (ADD ptr idx) mem) && ptr.Op != OpSB => (FMOVDloadidx [off] {sym} ptr idx mem) - -(MOVBstore [off] {sym} (ADD ptr idx) val mem) && ptr.Op != OpSB => (MOVBstoreidx [off] {sym} ptr idx val mem) -(MOVHstore [off] {sym} (ADD ptr idx) val mem) && ptr.Op != OpSB => (MOVHstoreidx [off] {sym} ptr idx val mem) -(MOVWstore [off] {sym} (ADD ptr idx) val mem) && ptr.Op != OpSB => (MOVWstoreidx [off] {sym} ptr idx val mem) -(MOVDstore [off] {sym} (ADD ptr idx) val mem) && ptr.Op != OpSB => (MOVDstoreidx [off] {sym} ptr idx val mem) -(FMOVSstore [off] {sym} (ADD ptr idx) val mem) && ptr.Op != OpSB => (FMOVSstoreidx [off] {sym} ptr idx val mem) -(FMOVDstore [off] {sym} (ADD ptr idx) val mem) && ptr.Op != OpSB => (FMOVDstoreidx [off] {sym} ptr idx val mem) - -// combine ADD into indexed loads and stores -(MOVBZloadidx [c] {sym} (ADDconst [d] ptr) idx mem) && is20Bit(c+d) -> (MOVBZloadidx [c+d] {sym} ptr idx mem) -(MOVBloadidx [c] {sym} (ADDconst [d] ptr) idx mem) && is20Bit(c+d) -> (MOVBloadidx [c+d] {sym} ptr idx mem) -(MOVHZloadidx [c] {sym} (ADDconst [d] ptr) idx mem) && is20Bit(c+d) -> (MOVHZloadidx [c+d] {sym} ptr idx mem) -(MOVHloadidx [c] {sym} (ADDconst [d] ptr) idx mem) && is20Bit(c+d) -> (MOVHloadidx [c+d] {sym} ptr idx mem) -(MOVWZloadidx [c] {sym} (ADDconst [d] ptr) idx mem) && is20Bit(c+d) -> (MOVWZloadidx [c+d] {sym} ptr idx mem) -(MOVWloadidx [c] {sym} (ADDconst [d] ptr) idx mem) && is20Bit(c+d) -> (MOVWloadidx [c+d] {sym} ptr idx mem) -(MOVDloadidx [c] {sym} (ADDconst [d] ptr) idx mem) && is20Bit(c+d) -> (MOVDloadidx [c+d] {sym} ptr idx mem) -(FMOVSloadidx [c] {sym} (ADDconst [d] ptr) idx mem) && is20Bit(c+d) -> (FMOVSloadidx [c+d] {sym} ptr idx mem) -(FMOVDloadidx [c] {sym} (ADDconst [d] ptr) idx mem) && is20Bit(c+d) -> (FMOVDloadidx [c+d] {sym} ptr idx mem) - -(MOVBstoreidx [c] {sym} (ADDconst [d] ptr) idx val mem) && is20Bit(c+d) -> (MOVBstoreidx [c+d] {sym} ptr idx val mem) -(MOVHstoreidx [c] {sym} (ADDconst [d] ptr) idx val mem) && is20Bit(c+d) -> (MOVHstoreidx [c+d] {sym} ptr idx val mem) -(MOVWstoreidx [c] {sym} (ADDconst [d] ptr) idx val mem) && is20Bit(c+d) -> (MOVWstoreidx [c+d] {sym} ptr idx val mem) -(MOVDstoreidx [c] {sym} (ADDconst [d] ptr) idx val mem) && is20Bit(c+d) -> (MOVDstoreidx [c+d] {sym} ptr idx val mem) -(FMOVSstoreidx [c] {sym} (ADDconst [d] ptr) idx val mem) && is20Bit(c+d) -> (FMOVSstoreidx [c+d] {sym} ptr idx val mem) -(FMOVDstoreidx [c] {sym} (ADDconst [d] ptr) idx val mem) && is20Bit(c+d) -> (FMOVDstoreidx [c+d] {sym} ptr idx val mem) - -(MOVBZloadidx [c] {sym} ptr (ADDconst [d] idx) mem) && is20Bit(c+d) -> (MOVBZloadidx [c+d] {sym} ptr idx mem) -(MOVBloadidx [c] {sym} ptr (ADDconst [d] idx) mem) && is20Bit(c+d) -> (MOVBloadidx [c+d] {sym} ptr idx mem) -(MOVHZloadidx [c] {sym} ptr (ADDconst [d] idx) mem) && is20Bit(c+d) -> (MOVHZloadidx [c+d] {sym} ptr idx mem) -(MOVHloadidx [c] {sym} ptr (ADDconst [d] idx) mem) && is20Bit(c+d) -> (MOVHloadidx [c+d] {sym} ptr idx mem) -(MOVWZloadidx [c] {sym} ptr (ADDconst [d] idx) mem) && is20Bit(c+d) -> (MOVWZloadidx [c+d] {sym} ptr idx mem) -(MOVWloadidx [c] {sym} ptr (ADDconst [d] idx) mem) && is20Bit(c+d) -> (MOVWloadidx [c+d] {sym} ptr idx mem) -(MOVDloadidx [c] {sym} ptr (ADDconst [d] idx) mem) && is20Bit(c+d) -> (MOVDloadidx [c+d] {sym} ptr idx mem) -(FMOVSloadidx [c] {sym} ptr (ADDconst [d] idx) mem) && is20Bit(c+d) -> (FMOVSloadidx [c+d] {sym} ptr idx mem) -(FMOVDloadidx [c] {sym} ptr (ADDconst [d] idx) mem) && is20Bit(c+d) -> (FMOVDloadidx [c+d] {sym} ptr idx mem) - -(MOVBstoreidx [c] {sym} ptr (ADDconst [d] idx) val mem) && is20Bit(c+d) -> (MOVBstoreidx [c+d] {sym} ptr idx val mem) -(MOVHstoreidx [c] {sym} ptr (ADDconst [d] idx) val mem) && is20Bit(c+d) -> (MOVHstoreidx [c+d] {sym} ptr idx val mem) -(MOVWstoreidx [c] {sym} ptr (ADDconst [d] idx) val mem) && is20Bit(c+d) -> (MOVWstoreidx [c+d] {sym} ptr idx val mem) -(MOVDstoreidx [c] {sym} ptr (ADDconst [d] idx) val mem) && is20Bit(c+d) -> (MOVDstoreidx [c+d] {sym} ptr idx val mem) -(FMOVSstoreidx [c] {sym} ptr (ADDconst [d] idx) val mem) && is20Bit(c+d) -> (FMOVSstoreidx [c+d] {sym} ptr idx val mem) -(FMOVDstoreidx [c] {sym} ptr (ADDconst [d] idx) val mem) && is20Bit(c+d) -> (FMOVDstoreidx [c+d] {sym} ptr idx val mem) +(MOVDstoreconst [sc] {sym1} (MOVDaddr [off] {sym2} ptr) mem) && ptr.Op != OpSB && canMergeSym(sym1, sym2) && sc.canAdd32(off) => + (MOVDstoreconst [sc.addOffset32(off)] {mergeSymTyped(sym1, sym2)} ptr mem) +(MOVWstoreconst [sc] {sym1} (MOVDaddr [off] {sym2} ptr) mem) && ptr.Op != OpSB && canMergeSym(sym1, sym2) && sc.canAdd32(off) => + (MOVWstoreconst [sc.addOffset32(off)] {mergeSymTyped(sym1, sym2)} ptr mem) +(MOVHstoreconst [sc] {sym1} (MOVDaddr [off] {sym2} ptr) mem) && ptr.Op != OpSB && canMergeSym(sym1, sym2) && sc.canAdd32(off) => + (MOVHstoreconst [sc.addOffset32(off)] {mergeSymTyped(sym1, sym2)} ptr mem) +(MOVBstoreconst [sc] {sym1} (MOVDaddr [off] {sym2} ptr) mem) && ptr.Op != OpSB && canMergeSym(sym1, sym2) && sc.canAdd32(off) => + (MOVBstoreconst [sc.addOffset32(off)] {mergeSymTyped(sym1, sym2)} ptr mem) // MOVDaddr into MOVDaddridx -(MOVDaddridx [off1] {sym1} (MOVDaddr [off2] {sym2} x) y) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && x.Op != OpSB -> - (MOVDaddridx [off1+off2] {mergeSym(sym1,sym2)} x y) -(MOVDaddridx [off1] {sym1} x (MOVDaddr [off2] {sym2} y)) && is32Bit(off1+off2) && canMergeSym(sym1, sym2) && y.Op != OpSB -> - (MOVDaddridx [off1+off2] {mergeSym(sym1,sym2)} x y) +(MOVDaddridx [off1] {sym1} (MOVDaddr [off2] {sym2} x) y) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && x.Op != OpSB => + (MOVDaddridx [off1+off2] {mergeSymTyped(sym1,sym2)} x y) +(MOVDaddridx [off1] {sym1} x (MOVDaddr [off2] {sym2} y)) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && y.Op != OpSB => + (MOVDaddridx [off1+off2] {mergeSymTyped(sym1,sym2)} x y) // Absorb InvertFlags into branches. (BRC {c} (InvertFlags cmp) yes no) => (BRC {c.ReverseComparison()} cmp yes no) // Constant comparisons. -(CMPconst (MOVDconst [x]) [y]) && x==y -> (FlagEQ) -(CMPconst (MOVDconst [x]) [y]) && x<y -> (FlagLT) -(CMPconst (MOVDconst [x]) [y]) && x>y -> (FlagGT) +(CMPconst (MOVDconst [x]) [y]) && x==int64(y) => (FlagEQ) +(CMPconst (MOVDconst [x]) [y]) && x<int64(y) => (FlagLT) +(CMPconst (MOVDconst [x]) [y]) && x>int64(y) => (FlagGT) (CMPUconst (MOVDconst [x]) [y]) && uint64(x)==uint64(y) => (FlagEQ) (CMPUconst (MOVDconst [x]) [y]) && uint64(x)<uint64(y) => (FlagLT) (CMPUconst (MOVDconst [x]) [y]) && uint64(x)>uint64(y) => (FlagGT) @@ -1158,31 +1056,31 @@ // Convert constant subtracts to constant adds. (SUBconst [c] x) && c != -(1<<31) => (ADDconst [-c] x) -(SUBWconst [c] x) -> (ADDWconst [int64(int32(-c))] x) +(SUBWconst [c] x) => (ADDWconst [-int32(c)] x) // generic constant folding // TODO: more of this -(ADDconst [c] (MOVDconst [d])) -> (MOVDconst [c+d]) -(ADDWconst [c] (MOVDconst [d])) -> (MOVDconst [int64(int32(c+d))]) -(ADDconst [c] (ADDconst [d] x)) && is32Bit(c+d) -> (ADDconst [c+d] x) -(ADDWconst [c] (ADDWconst [d] x)) -> (ADDWconst [int64(int32(c+d))] x) -(SUBconst (MOVDconst [d]) [c]) -> (MOVDconst [d-c]) -(SUBconst (SUBconst x [d]) [c]) && is32Bit(-c-d) -> (ADDconst [-c-d] x) +(ADDconst [c] (MOVDconst [d])) => (MOVDconst [int64(c)+d]) +(ADDWconst [c] (MOVDconst [d])) => (MOVDconst [int64(c)+d]) +(ADDconst [c] (ADDconst [d] x)) && is32Bit(int64(c)+int64(d)) => (ADDconst [c+d] x) +(ADDWconst [c] (ADDWconst [d] x)) => (ADDWconst [int32(c+d)] x) +(SUBconst (MOVDconst [d]) [c]) => (MOVDconst [d-int64(c)]) +(SUBconst (SUBconst x [d]) [c]) && is32Bit(-int64(c)-int64(d)) => (ADDconst [-c-d] x) (SRADconst [c] (MOVDconst [d])) => (MOVDconst [d>>uint64(c)]) (SRAWconst [c] (MOVDconst [d])) => (MOVDconst [int64(int32(d))>>uint64(c)]) (NEG (MOVDconst [c])) => (MOVDconst [-c]) (NEGW (MOVDconst [c])) => (MOVDconst [int64(int32(-c))]) -(MULLDconst [c] (MOVDconst [d])) -> (MOVDconst [c*d]) -(MULLWconst [c] (MOVDconst [d])) -> (MOVDconst [int64(int32(c*d))]) +(MULLDconst [c] (MOVDconst [d])) => (MOVDconst [int64(c)*d]) +(MULLWconst [c] (MOVDconst [d])) => (MOVDconst [int64(c*int32(d))]) (AND (MOVDconst [c]) (MOVDconst [d])) => (MOVDconst [c&d]) (ANDconst [c] (MOVDconst [d])) => (MOVDconst [c&d]) -(ANDWconst [c] (MOVDconst [d])) -> (MOVDconst [c&d]) +(ANDWconst [c] (MOVDconst [d])) => (MOVDconst [int64(c)&d]) (OR (MOVDconst [c]) (MOVDconst [d])) => (MOVDconst [c|d]) (ORconst [c] (MOVDconst [d])) => (MOVDconst [c|d]) -(ORWconst [c] (MOVDconst [d])) -> (MOVDconst [c|d]) +(ORWconst [c] (MOVDconst [d])) => (MOVDconst [int64(c)|d]) (XOR (MOVDconst [c]) (MOVDconst [d])) => (MOVDconst [c^d]) (XORconst [c] (MOVDconst [d])) => (MOVDconst [c^d]) -(XORWconst [c] (MOVDconst [d])) -> (MOVDconst [c^d]) +(XORWconst [c] (MOVDconst [d])) => (MOVDconst [int64(c)^d]) (LoweredRound32F x:(FMOVSconst)) => x (LoweredRound64F x:(FMOVDconst)) => x @@ -1199,19 +1097,19 @@ (XOR x x) => (MOVDconst [0]) (XORW x x) => (MOVDconst [0]) (NEG (ADDconst [c] (NEG x))) && c != -(1<<31) => (ADDconst [-c] x) -(MOVBZreg (ANDWconst [m] x)) -> (MOVWZreg (ANDWconst <typ.UInt32> [int64( uint8(m))] x)) -(MOVHZreg (ANDWconst [m] x)) -> (MOVWZreg (ANDWconst <typ.UInt32> [int64(uint16(m))] x)) -(MOVBreg (ANDWconst [m] x)) && int8(m) >= 0 -> (MOVWZreg (ANDWconst <typ.UInt32> [int64( uint8(m))] x)) -(MOVHreg (ANDWconst [m] x)) && int16(m) >= 0 -> (MOVWZreg (ANDWconst <typ.UInt32> [int64(uint16(m))] x)) +(MOVBZreg (ANDWconst [m] x)) => (MOVWZreg (ANDWconst <typ.UInt32> [int32( uint8(m))] x)) +(MOVHZreg (ANDWconst [m] x)) => (MOVWZreg (ANDWconst <typ.UInt32> [int32(uint16(m))] x)) +(MOVBreg (ANDWconst [m] x)) && int8(m) >= 0 => (MOVWZreg (ANDWconst <typ.UInt32> [int32( uint8(m))] x)) +(MOVHreg (ANDWconst [m] x)) && int16(m) >= 0 => (MOVWZreg (ANDWconst <typ.UInt32> [int32(uint16(m))] x)) // carry flag generation // (only constant fold carry of zero) (Select1 (ADDCconst (MOVDconst [c]) [d])) - && uint64(c+d) >= uint64(c) && c+d == 0 - -> (FlagEQ) + && uint64(c+int64(d)) >= uint64(c) && c+int64(d) == 0 + => (FlagEQ) (Select1 (ADDCconst (MOVDconst [c]) [d])) - && uint64(c+d) >= uint64(c) && c+d != 0 - -> (FlagLT) + && uint64(c+int64(d)) >= uint64(c) && c+int64(d) != 0 + => (FlagLT) // borrow flag generation // (only constant fold borrow of zero) @@ -1225,8 +1123,8 @@ // add with carry (ADDE x y (FlagEQ)) => (ADDC x y) (ADDE x y (FlagLT)) => (ADDC x y) -(ADDC x (MOVDconst [c])) && is16Bit(c) -> (ADDCconst x [c]) -(Select0 (ADDCconst (MOVDconst [c]) [d])) -> (MOVDconst [c+d]) +(ADDC x (MOVDconst [c])) && is16Bit(c) => (ADDCconst x [int16(c)]) +(Select0 (ADDCconst (MOVDconst [c]) [d])) => (MOVDconst [c+int64(d)]) // subtract with borrow (SUBE x y (FlagGT)) => (SUBC x y) @@ -1256,14 +1154,12 @@ (C(G|LG)IJ {s390x.Greater} (NEG (Select0 (SUBE (MOVDconst [0]) (MOVDconst [0]) borrow))) [0]) => (BRC {s390x.Borrow} borrow) // fused multiply-add -(Select0 (F(ADD|SUB) (FMUL y z) x)) -> (FM(ADD|SUB) x y z) -(Select0 (F(ADDS|SUBS) (FMULS y z) x)) -> (FM(ADDS|SUBS) x y z) +(Select0 (F(ADD|SUB) (FMUL y z) x)) => (FM(ADD|SUB) x y z) +(Select0 (F(ADDS|SUBS) (FMULS y z) x)) => (FM(ADDS|SUBS) x y z) // Convert floating point comparisons against zero into 'load and test' instructions. -(FCMP x (FMOVDconst [c])) && auxTo64F(c) == 0 -> (LTDBR x) -(FCMPS x (FMOVSconst [c])) && auxTo32F(c) == 0 -> (LTEBR x) -(FCMP (FMOVDconst [c]) x) && auxTo64F(c) == 0 -> (InvertFlags (LTDBR <v.Type> x)) -(FCMPS (FMOVSconst [c]) x) && auxTo32F(c) == 0 -> (InvertFlags (LTEBR <v.Type> x)) +(F(CMP|CMPS) x (FMOV(D|S)const [0.0])) => (LT(D|E)BR x) +(F(CMP|CMPS) (FMOV(D|S)const [0.0]) x) => (InvertFlags (LT(D|E)BR <v.Type> x)) // FSUB, FSUBS, FADD, FADDS now produce a condition code representing the // comparison of the result with 0.0. If a compare with zero instruction @@ -1274,30 +1170,30 @@ // but moving the flag generating value to a different block seems to // increase the likelihood that the flags value will have to be regenerated // by flagalloc which is not what we want. -(LTDBR (Select0 x:(F(ADD|SUB) _ _))) && b == x.Block -> (Select1 x) -(LTEBR (Select0 x:(F(ADDS|SUBS) _ _))) && b == x.Block -> (Select1 x) +(LTDBR (Select0 x:(F(ADD|SUB) _ _))) && b == x.Block => (Select1 x) +(LTEBR (Select0 x:(F(ADDS|SUBS) _ _))) && b == x.Block => (Select1 x) // Fold memory operations into operations. // Exclude global data (SB) because these instructions cannot handle relative addresses. // TODO(mundaym): indexed versions of these? ((ADD|SUB|MULLD|AND|OR|XOR) <t> x g:(MOVDload [off] {sym} ptr mem)) && ptr.Op != OpSB - && is20Bit(off) + && is20Bit(int64(off)) && canMergeLoadClobber(v, g, x) && clobber(g) - -> ((ADD|SUB|MULLD|AND|OR|XOR)load <t> [off] {sym} x ptr mem) + => ((ADD|SUB|MULLD|AND|OR|XOR)load <t> [off] {sym} x ptr mem) ((ADD|SUB|MULL|AND|OR|XOR)W <t> x g:(MOVWload [off] {sym} ptr mem)) && ptr.Op != OpSB - && is20Bit(off) + && is20Bit(int64(off)) && canMergeLoadClobber(v, g, x) && clobber(g) - -> ((ADD|SUB|MULL|AND|OR|XOR)Wload <t> [off] {sym} x ptr mem) + => ((ADD|SUB|MULL|AND|OR|XOR)Wload <t> [off] {sym} x ptr mem) ((ADD|SUB|MULL|AND|OR|XOR)W <t> x g:(MOVWZload [off] {sym} ptr mem)) && ptr.Op != OpSB - && is20Bit(off) + && is20Bit(int64(off)) && canMergeLoadClobber(v, g, x) && clobber(g) - -> ((ADD|SUB|MULL|AND|OR|XOR)Wload <t> [off] {sym} x ptr mem) + => ((ADD|SUB|MULL|AND|OR|XOR)Wload <t> [off] {sym} x ptr mem) // Combine constant stores into larger (unaligned) stores. // Avoid SB because constant stores to relative offsets are @@ -1305,21 +1201,21 @@ (MOVBstoreconst [c] {s} p x:(MOVBstoreconst [a] {s} p mem)) && p.Op != OpSB && x.Uses == 1 - && ValAndOff(a).Off() + 1 == ValAndOff(c).Off() + && a.Off() + 1 == c.Off() && clobber(x) - -> (MOVHstoreconst [makeValAndOff(ValAndOff(c).Val()&0xff | ValAndOff(a).Val()<<8, ValAndOff(a).Off())] {s} p mem) + => (MOVHstoreconst [makeValAndOff32(c.Val32()&0xff | a.Val32()<<8, a.Off32())] {s} p mem) (MOVHstoreconst [c] {s} p x:(MOVHstoreconst [a] {s} p mem)) && p.Op != OpSB && x.Uses == 1 - && ValAndOff(a).Off() + 2 == ValAndOff(c).Off() + && a.Off() + 2 == c.Off() && clobber(x) - -> (MOVWstore [ValAndOff(a).Off()] {s} p (MOVDconst [int64(int32(ValAndOff(c).Val()&0xffff | ValAndOff(a).Val()<<16))]) mem) + => (MOVWstore [a.Off32()] {s} p (MOVDconst [int64(c.Val32()&0xffff | a.Val32()<<16)]) mem) (MOVWstoreconst [c] {s} p x:(MOVWstoreconst [a] {s} p mem)) && p.Op != OpSB && x.Uses == 1 - && ValAndOff(a).Off() + 4 == ValAndOff(c).Off() + && a.Off() + 4 == c.Off() && clobber(x) - -> (MOVDstore [ValAndOff(a).Off()] {s} p (MOVDconst [ValAndOff(c).Val()&0xffffffff | ValAndOff(a).Val()<<32]) mem) + => (MOVDstore [a.Off32()] {s} p (MOVDconst [c.Val()&0xffffffff | a.Val()<<32]) mem) // Combine stores into larger (unaligned) stores. // It doesn't work on global data (based on SB) because stores with relative addressing @@ -1328,93 +1224,52 @@ && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVHstore [i-1] {s} p w mem) + => (MOVHstore [i-1] {s} p w mem) (MOVBstore [i] {s} p w0:(SRDconst [j] w) x:(MOVBstore [i-1] {s} p (SRDconst [j+8] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVHstore [i-1] {s} p w0 mem) + => (MOVHstore [i-1] {s} p w0 mem) (MOVBstore [i] {s} p w x:(MOVBstore [i-1] {s} p (SRWconst [8] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVHstore [i-1] {s} p w mem) + => (MOVHstore [i-1] {s} p w mem) (MOVBstore [i] {s} p w0:(SRWconst [j] w) x:(MOVBstore [i-1] {s} p (SRWconst [j+8] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVHstore [i-1] {s} p w0 mem) + => (MOVHstore [i-1] {s} p w0 mem) (MOVHstore [i] {s} p w x:(MOVHstore [i-2] {s} p (SRDconst [16] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVWstore [i-2] {s} p w mem) + => (MOVWstore [i-2] {s} p w mem) (MOVHstore [i] {s} p w0:(SRDconst [j] w) x:(MOVHstore [i-2] {s} p (SRDconst [j+16] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVWstore [i-2] {s} p w0 mem) + => (MOVWstore [i-2] {s} p w0 mem) (MOVHstore [i] {s} p w x:(MOVHstore [i-2] {s} p (SRWconst [16] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVWstore [i-2] {s} p w mem) + => (MOVWstore [i-2] {s} p w mem) (MOVHstore [i] {s} p w0:(SRWconst [j] w) x:(MOVHstore [i-2] {s} p (SRWconst [j+16] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVWstore [i-2] {s} p w0 mem) + => (MOVWstore [i-2] {s} p w0 mem) (MOVWstore [i] {s} p (SRDconst [32] w) x:(MOVWstore [i-4] {s} p w mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVDstore [i-4] {s} p w mem) + => (MOVDstore [i-4] {s} p w mem) (MOVWstore [i] {s} p w0:(SRDconst [j] w) x:(MOVWstore [i-4] {s} p (SRDconst [j+32] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVDstore [i-4] {s} p w0 mem) - -(MOVBstoreidx [i] {s} p idx w x:(MOVBstoreidx [i-1] {s} p idx (SRDconst [8] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVHstoreidx [i-1] {s} p idx w mem) -(MOVBstoreidx [i] {s} p idx w0:(SRDconst [j] w) x:(MOVBstoreidx [i-1] {s} p idx (SRDconst [j+8] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVHstoreidx [i-1] {s} p idx w0 mem) -(MOVBstoreidx [i] {s} p idx w x:(MOVBstoreidx [i-1] {s} p idx (SRWconst [8] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVHstoreidx [i-1] {s} p idx w mem) -(MOVBstoreidx [i] {s} p idx w0:(SRWconst [j] w) x:(MOVBstoreidx [i-1] {s} p idx (SRWconst [j+8] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVHstoreidx [i-1] {s} p idx w0 mem) -(MOVHstoreidx [i] {s} p idx w x:(MOVHstoreidx [i-2] {s} p idx (SRDconst [16] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVWstoreidx [i-2] {s} p idx w mem) -(MOVHstoreidx [i] {s} p idx w0:(SRDconst [j] w) x:(MOVHstoreidx [i-2] {s} p idx (SRDconst [j+16] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVWstoreidx [i-2] {s} p idx w0 mem) -(MOVHstoreidx [i] {s} p idx w x:(MOVHstoreidx [i-2] {s} p idx (SRWconst [16] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVWstoreidx [i-2] {s} p idx w mem) -(MOVHstoreidx [i] {s} p idx w0:(SRWconst [j] w) x:(MOVHstoreidx [i-2] {s} p idx (SRWconst [j+16] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVWstoreidx [i-2] {s} p idx w0 mem) -(MOVWstoreidx [i] {s} p idx w x:(MOVWstoreidx [i-4] {s} p idx (SRDconst [32] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVDstoreidx [i-4] {s} p idx w mem) -(MOVWstoreidx [i] {s} p idx w0:(SRDconst [j] w) x:(MOVWstoreidx [i-4] {s} p idx (SRDconst [j+32] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVDstoreidx [i-4] {s} p idx w0 mem) + => (MOVDstore [i-4] {s} p w0 mem) // Combine stores into larger (unaligned) stores with the bytes reversed (little endian). // Store-with-bytes-reversed instructions do not support relative memory addresses, @@ -1423,87 +1278,46 @@ && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVHBRstore [i-1] {s} p w mem) + => (MOVHBRstore [i-1] {s} p w mem) (MOVBstore [i] {s} p (SRDconst [j] w) x:(MOVBstore [i-1] {s} p w0:(SRDconst [j-8] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVHBRstore [i-1] {s} p w0 mem) + => (MOVHBRstore [i-1] {s} p w0 mem) (MOVBstore [i] {s} p (SRWconst [8] w) x:(MOVBstore [i-1] {s} p w mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVHBRstore [i-1] {s} p w mem) + => (MOVHBRstore [i-1] {s} p w mem) (MOVBstore [i] {s} p (SRWconst [j] w) x:(MOVBstore [i-1] {s} p w0:(SRWconst [j-8] w) mem)) && p.Op != OpSB && x.Uses == 1 && clobber(x) - -> (MOVHBRstore [i-1] {s} p w0 mem) + => (MOVHBRstore [i-1] {s} p w0 mem) (MOVHBRstore [i] {s} p (SRDconst [16] w) x:(MOVHBRstore [i-2] {s} p w mem)) && x.Uses == 1 && clobber(x) - -> (MOVWBRstore [i-2] {s} p w mem) + => (MOVWBRstore [i-2] {s} p w mem) (MOVHBRstore [i] {s} p (SRDconst [j] w) x:(MOVHBRstore [i-2] {s} p w0:(SRDconst [j-16] w) mem)) && x.Uses == 1 && clobber(x) - -> (MOVWBRstore [i-2] {s} p w0 mem) + => (MOVWBRstore [i-2] {s} p w0 mem) (MOVHBRstore [i] {s} p (SRWconst [16] w) x:(MOVHBRstore [i-2] {s} p w mem)) && x.Uses == 1 && clobber(x) - -> (MOVWBRstore [i-2] {s} p w mem) + => (MOVWBRstore [i-2] {s} p w mem) (MOVHBRstore [i] {s} p (SRWconst [j] w) x:(MOVHBRstore [i-2] {s} p w0:(SRWconst [j-16] w) mem)) && x.Uses == 1 && clobber(x) - -> (MOVWBRstore [i-2] {s} p w0 mem) + => (MOVWBRstore [i-2] {s} p w0 mem) (MOVWBRstore [i] {s} p (SRDconst [32] w) x:(MOVWBRstore [i-4] {s} p w mem)) && x.Uses == 1 && clobber(x) - -> (MOVDBRstore [i-4] {s} p w mem) + => (MOVDBRstore [i-4] {s} p w mem) (MOVWBRstore [i] {s} p (SRDconst [j] w) x:(MOVWBRstore [i-4] {s} p w0:(SRDconst [j-32] w) mem)) && x.Uses == 1 && clobber(x) - -> (MOVDBRstore [i-4] {s} p w0 mem) - -(MOVBstoreidx [i] {s} p idx (SRDconst [8] w) x:(MOVBstoreidx [i-1] {s} p idx w mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVHBRstoreidx [i-1] {s} p idx w mem) -(MOVBstoreidx [i] {s} p idx (SRDconst [j] w) x:(MOVBstoreidx [i-1] {s} p idx w0:(SRDconst [j-8] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVHBRstoreidx [i-1] {s} p idx w0 mem) -(MOVBstoreidx [i] {s} p idx (SRWconst [8] w) x:(MOVBstoreidx [i-1] {s} p idx w mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVHBRstoreidx [i-1] {s} p idx w mem) -(MOVBstoreidx [i] {s} p idx (SRWconst [j] w) x:(MOVBstoreidx [i-1] {s} p idx w0:(SRWconst [j-8] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVHBRstoreidx [i-1] {s} p idx w0 mem) -(MOVHBRstoreidx [i] {s} p idx (SRDconst [16] w) x:(MOVHBRstoreidx [i-2] {s} p idx w mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVWBRstoreidx [i-2] {s} p idx w mem) -(MOVHBRstoreidx [i] {s} p idx (SRDconst [j] w) x:(MOVHBRstoreidx [i-2] {s} p idx w0:(SRDconst [j-16] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVWBRstoreidx [i-2] {s} p idx w0 mem) -(MOVHBRstoreidx [i] {s} p idx (SRWconst [16] w) x:(MOVHBRstoreidx [i-2] {s} p idx w mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVWBRstoreidx [i-2] {s} p idx w mem) -(MOVHBRstoreidx [i] {s} p idx (SRWconst [j] w) x:(MOVHBRstoreidx [i-2] {s} p idx w0:(SRWconst [j-16] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVWBRstoreidx [i-2] {s} p idx w0 mem) -(MOVWBRstoreidx [i] {s} p idx (SRDconst [32] w) x:(MOVWBRstoreidx [i-4] {s} p idx w mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVDBRstoreidx [i-4] {s} p idx w mem) -(MOVWBRstoreidx [i] {s} p idx (SRDconst [j] w) x:(MOVWBRstoreidx [i-4] {s} p idx w0:(SRDconst [j-32] w) mem)) - && x.Uses == 1 - && clobber(x) - -> (MOVDBRstoreidx [i-4] {s} p idx w0 mem) + => (MOVDBRstore [i-4] {s} p w0 mem) // Combining byte loads into larger (unaligned) loads. @@ -1518,7 +1332,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVHZload [i0] {s} p mem) + => @mergePoint(b,x0,x1) (MOVHZload [i0] {s} p mem) (OR x1:(MOVBZload [i1] {s} p mem) sh:(SLDconst [8] x0:(MOVBZload [i0] {s} p mem))) @@ -1529,7 +1343,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVHZload [i0] {s} p mem) + => @mergePoint(b,x0,x1) (MOVHZload [i0] {s} p mem) (ORW x1:(MOVHZload [i1] {s} p mem) sh:(SLWconst [16] x0:(MOVHZload [i0] {s} p mem))) @@ -1540,7 +1354,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVWZload [i0] {s} p mem) + => @mergePoint(b,x0,x1) (MOVWZload [i0] {s} p mem) (OR x1:(MOVHZload [i1] {s} p mem) sh:(SLDconst [16] x0:(MOVHZload [i0] {s} p mem))) @@ -1551,7 +1365,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVWZload [i0] {s} p mem) + => @mergePoint(b,x0,x1) (MOVWZload [i0] {s} p mem) (OR x1:(MOVWZload [i1] {s} p mem) sh:(SLDconst [32] x0:(MOVWZload [i0] {s} p mem))) @@ -1562,7 +1376,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVDload [i0] {s} p mem) + => @mergePoint(b,x0,x1) (MOVDload [i0] {s} p mem) (ORW s0:(SLWconst [j0] x0:(MOVBZload [i0] {s} p mem)) @@ -1579,7 +1393,7 @@ && or.Uses == 1 && mergePoint(b,x0,x1,y) != nil && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (ORW <v.Type> (SLWconst <v.Type> [j1] (MOVHZload [i0] {s} p mem)) y) + => @mergePoint(b,x0,x1,y) (ORW <v.Type> (SLWconst <v.Type> [j1] (MOVHZload [i0] {s} p mem)) y) (OR s0:(SLDconst [j0] x0:(MOVBZload [i0] {s} p mem)) @@ -1596,7 +1410,7 @@ && or.Uses == 1 && mergePoint(b,x0,x1,y) != nil && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j1] (MOVHZload [i0] {s} p mem)) y) + => @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j1] (MOVHZload [i0] {s} p mem)) y) (OR s0:(SLDconst [j0] x0:(MOVHZload [i0] {s} p mem)) @@ -1613,115 +1427,7 @@ && or.Uses == 1 && mergePoint(b,x0,x1,y) != nil && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j1] (MOVWZload [i0] {s} p mem)) y) - -// Big-endian indexed loads - -(ORW x1:(MOVBZloadidx [i1] {s} p idx mem) - sh:(SLWconst [8] x0:(MOVBZloadidx [i0] {s} p idx mem))) - && i1 == i0+1 - && p.Op != OpSB - && x0.Uses == 1 - && x1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVHZloadidx [i0] {s} p idx mem) - -(OR x1:(MOVBZloadidx [i1] {s} p idx mem) - sh:(SLDconst [8] x0:(MOVBZloadidx [i0] {s} p idx mem))) - && i1 == i0+1 - && p.Op != OpSB - && x0.Uses == 1 - && x1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVHZloadidx [i0] {s} p idx mem) - -(ORW x1:(MOVHZloadidx [i1] {s} p idx mem) - sh:(SLWconst [16] x0:(MOVHZloadidx [i0] {s} p idx mem))) - && i1 == i0+2 - && p.Op != OpSB - && x0.Uses == 1 - && x1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVWZloadidx [i0] {s} p idx mem) - -(OR x1:(MOVHZloadidx [i1] {s} p idx mem) - sh:(SLDconst [16] x0:(MOVHZloadidx [i0] {s} p idx mem))) - && i1 == i0+2 - && p.Op != OpSB - && x0.Uses == 1 - && x1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVWZloadidx [i0] {s} p idx mem) - -(OR x1:(MOVWZloadidx [i1] {s} p idx mem) - sh:(SLDconst [32] x0:(MOVWZloadidx [i0] {s} p idx mem))) - && i1 == i0+4 - && p.Op != OpSB - && x0.Uses == 1 - && x1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVDloadidx [i0] {s} p idx mem) - -(ORW - s0:(SLWconst [j0] x0:(MOVBZloadidx [i0] {s} p idx mem)) - or:(ORW - s1:(SLWconst [j1] x1:(MOVBZloadidx [i1] {s} p idx mem)) - y)) - && i1 == i0+1 - && j1 == j0-8 - && j1 % 16 == 0 - && x0.Uses == 1 - && x1.Uses == 1 - && s0.Uses == 1 - && s1.Uses == 1 - && or.Uses == 1 - && mergePoint(b,x0,x1,y) != nil - && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (ORW <v.Type> (SLWconst <v.Type> [j1] (MOVHZloadidx [i0] {s} p idx mem)) y) - -(OR - s0:(SLDconst [j0] x0:(MOVBZloadidx [i0] {s} p idx mem)) - or:(OR - s1:(SLDconst [j1] x1:(MOVBZloadidx [i1] {s} p idx mem)) - y)) - && i1 == i0+1 - && j1 == j0-8 - && j1 % 16 == 0 - && x0.Uses == 1 - && x1.Uses == 1 - && s0.Uses == 1 - && s1.Uses == 1 - && or.Uses == 1 - && mergePoint(b,x0,x1,y) != nil - && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j1] (MOVHZloadidx [i0] {s} p idx mem)) y) - -(OR - s0:(SLDconst [j0] x0:(MOVHZloadidx [i0] {s} p idx mem)) - or:(OR - s1:(SLDconst [j1] x1:(MOVHZloadidx [i1] {s} p idx mem)) - y)) - && i1 == i0+2 - && j1 == j0-16 - && j1 % 32 == 0 - && x0.Uses == 1 - && x1.Uses == 1 - && s0.Uses == 1 - && s1.Uses == 1 - && or.Uses == 1 - && mergePoint(b,x0,x1,y) != nil - && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j1] (MOVWZloadidx [i0] {s} p idx mem)) y) + => @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j1] (MOVWZload [i0] {s} p mem)) y) // Little-endian loads @@ -1734,7 +1440,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVHZreg (MOVHBRload [i0] {s} p mem)) + => @mergePoint(b,x0,x1) (MOVHZreg (MOVHBRload [i0] {s} p mem)) (OR x0:(MOVBZload [i0] {s} p mem) sh:(SLDconst [8] x1:(MOVBZload [i1] {s} p mem))) @@ -1745,7 +1451,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVHZreg (MOVHBRload [i0] {s} p mem)) + => @mergePoint(b,x0,x1) (MOVHZreg (MOVHBRload [i0] {s} p mem)) (ORW r0:(MOVHZreg x0:(MOVHBRload [i0] {s} p mem)) sh:(SLWconst [16] r1:(MOVHZreg x1:(MOVHBRload [i1] {s} p mem)))) @@ -1757,7 +1463,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, r0, r1, sh) - -> @mergePoint(b,x0,x1) (MOVWBRload [i0] {s} p mem) + => @mergePoint(b,x0,x1) (MOVWBRload [i0] {s} p mem) (OR r0:(MOVHZreg x0:(MOVHBRload [i0] {s} p mem)) sh:(SLDconst [16] r1:(MOVHZreg x1:(MOVHBRload [i1] {s} p mem)))) @@ -1769,7 +1475,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, r0, r1, sh) - -> @mergePoint(b,x0,x1) (MOVWZreg (MOVWBRload [i0] {s} p mem)) + => @mergePoint(b,x0,x1) (MOVWZreg (MOVWBRload [i0] {s} p mem)) (OR r0:(MOVWZreg x0:(MOVWBRload [i0] {s} p mem)) sh:(SLDconst [32] r1:(MOVWZreg x1:(MOVWBRload [i1] {s} p mem)))) @@ -1781,7 +1487,7 @@ && sh.Uses == 1 && mergePoint(b,x0,x1) != nil && clobber(x0, x1, r0, r1, sh) - -> @mergePoint(b,x0,x1) (MOVDBRload [i0] {s} p mem) + => @mergePoint(b,x0,x1) (MOVDBRload [i0] {s} p mem) (ORW s1:(SLWconst [j1] x1:(MOVBZload [i1] {s} p mem)) @@ -1799,7 +1505,7 @@ && or.Uses == 1 && mergePoint(b,x0,x1,y) != nil && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (ORW <v.Type> (SLWconst <v.Type> [j0] (MOVHZreg (MOVHBRload [i0] {s} p mem))) y) + => @mergePoint(b,x0,x1,y) (ORW <v.Type> (SLWconst <v.Type> [j0] (MOVHZreg (MOVHBRload [i0] {s} p mem))) y) (OR s1:(SLDconst [j1] x1:(MOVBZload [i1] {s} p mem)) @@ -1817,7 +1523,7 @@ && or.Uses == 1 && mergePoint(b,x0,x1,y) != nil && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j0] (MOVHZreg (MOVHBRload [i0] {s} p mem))) y) + => @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j0] (MOVHZreg (MOVHBRload [i0] {s} p mem))) y) (OR s1:(SLDconst [j1] r1:(MOVHZreg x1:(MOVHBRload [i1] {s} p mem))) @@ -1836,168 +1542,53 @@ && or.Uses == 1 && mergePoint(b,x0,x1,y) != nil && clobber(x0, x1, r0, r1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j0] (MOVWZreg (MOVWBRload [i0] {s} p mem))) y) - -// Little-endian indexed loads - -(ORW x0:(MOVBZloadidx [i0] {s} p idx mem) - sh:(SLWconst [8] x1:(MOVBZloadidx [i1] {s} p idx mem))) - && p.Op != OpSB - && i1 == i0+1 - && x0.Uses == 1 - && x1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVHZreg (MOVHBRloadidx [i0] {s} p idx mem)) - -(OR x0:(MOVBZloadidx [i0] {s} p idx mem) - sh:(SLDconst [8] x1:(MOVBZloadidx [i1] {s} p idx mem))) - && p.Op != OpSB - && i1 == i0+1 - && x0.Uses == 1 - && x1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, sh) - -> @mergePoint(b,x0,x1) (MOVHZreg (MOVHBRloadidx [i0] {s} p idx mem)) - -(ORW r0:(MOVHZreg x0:(MOVHBRloadidx [i0] {s} p idx mem)) - sh:(SLWconst [16] r1:(MOVHZreg x1:(MOVHBRloadidx [i1] {s} p idx mem)))) - && i1 == i0+2 - && x0.Uses == 1 - && x1.Uses == 1 - && r0.Uses == 1 - && r1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, r0, r1, sh) - -> @mergePoint(b,x0,x1) (MOVWBRloadidx [i0] {s} p idx mem) - -(OR r0:(MOVHZreg x0:(MOVHBRloadidx [i0] {s} p idx mem)) - sh:(SLDconst [16] r1:(MOVHZreg x1:(MOVHBRloadidx [i1] {s} p idx mem)))) - && i1 == i0+2 - && x0.Uses == 1 - && x1.Uses == 1 - && r0.Uses == 1 - && r1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, r0, r1, sh) - -> @mergePoint(b,x0,x1) (MOVWZreg (MOVWBRloadidx [i0] {s} p idx mem)) - -(OR r0:(MOVWZreg x0:(MOVWBRloadidx [i0] {s} p idx mem)) - sh:(SLDconst [32] r1:(MOVWZreg x1:(MOVWBRloadidx [i1] {s} p idx mem)))) - && i1 == i0+4 - && x0.Uses == 1 - && x1.Uses == 1 - && r0.Uses == 1 - && r1.Uses == 1 - && sh.Uses == 1 - && mergePoint(b,x0,x1) != nil - && clobber(x0, x1, r0, r1, sh) - -> @mergePoint(b,x0,x1) (MOVDBRloadidx [i0] {s} p idx mem) - -(ORW - s1:(SLWconst [j1] x1:(MOVBZloadidx [i1] {s} p idx mem)) - or:(ORW - s0:(SLWconst [j0] x0:(MOVBZloadidx [i0] {s} p idx mem)) - y)) - && p.Op != OpSB - && i1 == i0+1 - && j1 == j0+8 - && j0 % 16 == 0 - && x0.Uses == 1 - && x1.Uses == 1 - && s0.Uses == 1 - && s1.Uses == 1 - && or.Uses == 1 - && mergePoint(b,x0,x1,y) != nil - && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (ORW <v.Type> (SLWconst <v.Type> [j0] (MOVHZreg (MOVHBRloadidx [i0] {s} p idx mem))) y) - -(OR - s1:(SLDconst [j1] x1:(MOVBZloadidx [i1] {s} p idx mem)) - or:(OR - s0:(SLDconst [j0] x0:(MOVBZloadidx [i0] {s} p idx mem)) - y)) - && p.Op != OpSB - && i1 == i0+1 - && j1 == j0+8 - && j0 % 16 == 0 - && x0.Uses == 1 - && x1.Uses == 1 - && s0.Uses == 1 - && s1.Uses == 1 - && or.Uses == 1 - && mergePoint(b,x0,x1,y) != nil - && clobber(x0, x1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j0] (MOVHZreg (MOVHBRloadidx [i0] {s} p idx mem))) y) - -(OR - s1:(SLDconst [j1] r1:(MOVHZreg x1:(MOVHBRloadidx [i1] {s} p idx mem))) - or:(OR - s0:(SLDconst [j0] r0:(MOVHZreg x0:(MOVHBRloadidx [i0] {s} p idx mem))) - y)) - && i1 == i0+2 - && j1 == j0+16 - && j0 % 32 == 0 - && x0.Uses == 1 - && x1.Uses == 1 - && r0.Uses == 1 - && r1.Uses == 1 - && s0.Uses == 1 - && s1.Uses == 1 - && or.Uses == 1 - && mergePoint(b,x0,x1,y) != nil - && clobber(x0, x1, r0, r1, s0, s1, or) - -> @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j0] (MOVWZreg (MOVWBRloadidx [i0] {s} p idx mem))) y) + => @mergePoint(b,x0,x1,y) (OR <v.Type> (SLDconst <v.Type> [j0] (MOVWZreg (MOVWBRload [i0] {s} p mem))) y) // Combine stores into store multiples. // 32-bit (MOVWstore [i] {s} p w1 x:(MOVWstore [i-4] {s} p w0 mem)) && p.Op != OpSB && x.Uses == 1 - && is20Bit(i-4) + && is20Bit(int64(i)-4) && clobber(x) - -> (STM2 [i-4] {s} p w0 w1 mem) + => (STM2 [i-4] {s} p w0 w1 mem) (MOVWstore [i] {s} p w2 x:(STM2 [i-8] {s} p w0 w1 mem)) && x.Uses == 1 - && is20Bit(i-8) + && is20Bit(int64(i)-8) && clobber(x) - -> (STM3 [i-8] {s} p w0 w1 w2 mem) + => (STM3 [i-8] {s} p w0 w1 w2 mem) (MOVWstore [i] {s} p w3 x:(STM3 [i-12] {s} p w0 w1 w2 mem)) && x.Uses == 1 - && is20Bit(i-12) + && is20Bit(int64(i)-12) && clobber(x) - -> (STM4 [i-12] {s} p w0 w1 w2 w3 mem) + => (STM4 [i-12] {s} p w0 w1 w2 w3 mem) (STM2 [i] {s} p w2 w3 x:(STM2 [i-8] {s} p w0 w1 mem)) && x.Uses == 1 - && is20Bit(i-8) + && is20Bit(int64(i)-8) && clobber(x) - -> (STM4 [i-8] {s} p w0 w1 w2 w3 mem) + => (STM4 [i-8] {s} p w0 w1 w2 w3 mem) // 64-bit (MOVDstore [i] {s} p w1 x:(MOVDstore [i-8] {s} p w0 mem)) && p.Op != OpSB && x.Uses == 1 - && is20Bit(i-8) + && is20Bit(int64(i)-8) && clobber(x) - -> (STMG2 [i-8] {s} p w0 w1 mem) + => (STMG2 [i-8] {s} p w0 w1 mem) (MOVDstore [i] {s} p w2 x:(STMG2 [i-16] {s} p w0 w1 mem)) && x.Uses == 1 - && is20Bit(i-16) + && is20Bit(int64(i)-16) && clobber(x) - -> (STMG3 [i-16] {s} p w0 w1 w2 mem) + => (STMG3 [i-16] {s} p w0 w1 w2 mem) (MOVDstore [i] {s} p w3 x:(STMG3 [i-24] {s} p w0 w1 w2 mem)) && x.Uses == 1 - && is20Bit(i-24) + && is20Bit(int64(i)-24) && clobber(x) - -> (STMG4 [i-24] {s} p w0 w1 w2 w3 mem) + => (STMG4 [i-24] {s} p w0 w1 w2 w3 mem) (STMG2 [i] {s} p w2 w3 x:(STMG2 [i-16] {s} p w0 w1 mem)) && x.Uses == 1 - && is20Bit(i-16) + && is20Bit(int64(i)-16) && clobber(x) - -> (STMG4 [i-16] {s} p w0 w1 w2 w3 mem) + => (STMG4 [i-16] {s} p w0 w1 w2 w3 mem) // Convert 32-bit store multiples into 64-bit stores. -(STM2 [i] {s} p (SRDconst [32] x) x mem) -> (MOVDstore [i] {s} p x mem) +(STM2 [i] {s} p (SRDconst [32] x) x mem) => (MOVDstore [i] {s} p x mem) |