go/src/cmd/compile/internal/ssa/gen/S390X.rules

// Copyright 2016 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

// Lowering arithmetic
(Add(64|Ptr) ...) => (ADD ...)
(Add(32|16|8) ...) => (ADDW ...)
(Add32F x y) => (Select0 (FADDS x y))
(Add64F x y) => (Select0 (FADD x y))

(Sub(64|Ptr) ...) => (SUB ...)
(Sub(32|16|8) ...) => (SUBW ...)
(Sub32F x y) => (Select0 (FSUBS x y))
(Sub64F x y) => (Select0 (FSUB x y))

(Mul64 ...) => (MULLD ...)
(Mul(32|16|8) ...) => (MULLW ...)
(Mul32F ...) => (FMULS ...)
(Mul64F ...) => (FMUL ...)
(Mul64uhilo ...) => (MLGR ...)

(Div32F ...) => (FDIVS ...)
(Div64F ...) => (FDIV ...)

(Div64 x y) => (DIVD x y)
(Div64u ...) => (DIVDU ...)
// DIVW/DIVWU has a 64-bit dividend and a 32-bit divisor,
// so a sign/zero extension of the dividend is required.
(Div32  x y) => (DIVW  (MOVWreg x) y)
(Div32u x y) => (DIVWU (MOVWZreg x) y)
(Div16  x y) => (DIVW  (MOVHreg x) (MOVHreg y))
(Div16u x y) => (DIVWU (MOVHZreg x) (MOVHZreg y))
(Div8   x y) => (DIVW  (MOVBreg x) (MOVBreg y))
(Div8u  x y) => (DIVWU (MOVBZreg x) (MOVBZreg y))

(Hmul(64|64u) ...) => (MULH(D|DU) ...)
(Hmul32  x y) => (SRDconst [32] (MULLD (MOVWreg x) (MOVWreg y)))
(Hmul32u x y) => (SRDconst [32] (MULLD (MOVWZreg x) (MOVWZreg y)))

(Mod64 x y) => (MODD x y)
(Mod64u ...) => (MODDU ...)
// MODW/MODWU has a 64-bit dividend and a 32-bit divisor,
// so a sign/zero extension of the dividend is required.
(Mod32  x y) => (MODW  (MOVWreg x) y)
(Mod32u x y) => (MODWU (MOVWZreg x) y)
(Mod16  x y) => (MODW  (MOVHreg x) (MOVHreg y))
(Mod16u x y) => (MODWU (MOVHZreg x) (MOVHZreg y))
(Mod8   x y) => (MODW  (MOVBreg x) (MOVBreg y))
(Mod8u  x y) => (MODWU (MOVBZreg x) (MOVBZreg y))

// (x + y) / 2 with x>=y -> (x - y) / 2 + y
(Avg64u <t> x y) => (ADD (SRDconst <t> (SUB <t> x y) [1]) y)

(And64 ...) => (AND ...)
(And(32|16|8) ...) => (ANDW ...)

(Or64 ...) => (OR ...)
(Or(32|16|8) ...) => (ORW ...)

(Xor64 ...) => (XOR ...)
(Xor(32|16|8) ...) => (XORW ...)

(Neg64 ...) => (NEG ...)
(Neg(32|16|8) ...) => (NEGW ...)
(Neg32F ...) => (FNEGS ...)
(Neg64F ...) => (FNEG ...)

(Com64 ...) => (NOT ...)
(Com(32|16|8) ...) => (NOTW ...)
(NOT x) => (XOR (MOVDconst [-1]) x)
(NOTW x) => (XORWconst [-1] x)

// Lowering boolean ops
(AndB ...) => (ANDW ...)
(OrB ...) => (ORW ...)
(Not x) => (XORWconst [1] x)

// Lowering pointer arithmetic
(OffPtr [off] ptr:(SP)) => (MOVDaddr [int32(off)] ptr)
(OffPtr [off] ptr) && is32Bit(off) => (ADDconst [int32(off)] ptr)
(OffPtr [off] ptr) => (ADD (MOVDconst [off]) ptr)

// TODO: optimize these cases?
(Ctz64NonZero ...) => (Ctz64 ...)
(Ctz32NonZero ...) => (Ctz32 ...)

// Ctz(x) = 64 - findLeftmostOne((x-1)&^x)
(Ctz64 <t> x) => (SUB (MOVDconst [64]) (FLOGR (AND <t> (SUBconst <t> [1] x) (NOT <t> x))))
(Ctz32 <t> x) => (SUB (MOVDconst [64]) (FLOGR (MOVWZreg (ANDW <t> (SUBWconst <t> [1] x) (NOTW <t> x)))))

(BitLen64 x) => (SUB (MOVDconst [64]) (FLOGR x))

// POPCNT treats the input register as a vector of 8 bytes, producing
// a population count for each individual byte. For inputs larger than
// a single byte we therefore need to sum the individual bytes produced
// by the POPCNT instruction. For example, the following instruction
// sequence could be used to calculate the population count of a 4-byte
// value:
//
//     MOVD   $0x12345678, R1 // R1=0x12345678 <-- input
//     POPCNT R1, R2          // R2=0x02030404
//     SRW    $16, R2, R3     // R3=0x00000203
//     ADDW   R2, R3, R4      // R4=0x02030607
//     SRW    $8, R4, R5      // R5=0x00020306
//     ADDW   R4, R5, R6      // R6=0x0205090d
//     MOVBZ  R6, R7          // R7=0x0000000d <-- result is 13
//
(PopCount8  x) => (POPCNT (MOVBZreg x))
(PopCount16 x) => (MOVBZreg (SumBytes2 (POPCNT <typ.UInt16> x)))
(PopCount32 x) => (MOVBZreg (SumBytes4 (POPCNT <typ.UInt32> x)))
(PopCount64 x) => (MOVBZreg (SumBytes8 (POPCNT <typ.UInt64> x)))

// SumBytes{2,4,8} pseudo operations sum the values of the rightmost
// 2, 4 or 8 bytes respectively. The result is a single byte however
// other bytes might contain junk so a zero extension is required if
// the desired output type is larger than 1 byte.
(SumBytes2 x) => (ADDW (SRWconst <typ.UInt8> x [8]) x)
(SumBytes4 x) => (SumBytes2 (ADDW <typ.UInt16> (SRWconst <typ.UInt16> x [16]) x))
(SumBytes8 x) => (SumBytes4 (ADDW <typ.UInt32> (SRDconst <typ.UInt32> x [32]) x))

(Bswap64 ...) => (MOVDBR ...)
(Bswap32 ...) => (MOVWBR ...)

// add with carry
(Select0 (Add64carry x y c))
  => (Select0 <typ.UInt64> (ADDE x y (Select1 <types.TypeFlags> (ADDCconst c [-1]))))
(Select1 (Add64carry x y c))
  => (Select0 <typ.UInt64> (ADDE (MOVDconst [0]) (MOVDconst [0]) (Select1 <types.TypeFlags> (ADDE x y (Select1 <types.TypeFlags> (ADDCconst c [-1]))))))

// subtract with borrow
(Select0 (Sub64borrow x y c))
  => (Select0 <typ.UInt64> (SUBE x y (Select1 <types.TypeFlags> (SUBC (MOVDconst [0]) c))))
(Select1 (Sub64borrow x y c))
  => (NEG (Select0 <typ.UInt64> (SUBE (MOVDconst [0]) (MOVDconst [0]) (Select1 <types.TypeFlags> (SUBE x y (Select1 <types.TypeFlags> (SUBC (MOVDconst [0]) c)))))))

// math package intrinsics
(Sqrt      ...) => (FSQRT ...)
(Floor       x) => (FIDBR [7] x)
(Ceil        x) => (FIDBR [6] x)
(Trunc       x) => (FIDBR [5] x)
(RoundToEven x) => (FIDBR [4] x)
(Round       x) => (FIDBR [1] x)
(FMA     x y z) => (FMADD z x y)

// Atomic loads and stores.
// The SYNC instruction (fast-BCR-serialization) prevents store-load
// reordering. Other sequences of memory operations (load-load,
// store-store and load-store) are already guaranteed not to be reordered.
(AtomicLoad(8|32|Acq32|64|Ptr) ptr mem) => (MOV(BZ|WZ|WZ|D|D)atomicload ptr mem)
(AtomicStore(8|32|64|PtrNoWB) ptr val mem) => (SYNC (MOV(B|W|D|D)atomicstore ptr val mem))

// Store-release doesn't require store-load ordering.
(AtomicStoreRel32 ptr val mem) => (MOVWatomicstore ptr val mem)

// Atomic adds.
(AtomicAdd32 ptr val mem) => (AddTupleFirst32 val (LAA ptr val mem))
(AtomicAdd64 ptr val mem) => (AddTupleFirst64 val (LAAG ptr val mem))
(Select0 <t> (AddTupleFirst32 val tuple)) => (ADDW val (Select0 <t> tuple))
(Select1     (AddTupleFirst32   _ tuple)) => (Select1 tuple)
(Select0 <t> (AddTupleFirst64 val tuple)) => (ADD val (Select0 <t> tuple))
(Select1     (AddTupleFirst64   _ tuple)) => (Select1 tuple)

// Atomic exchanges.
(AtomicExchange32 ptr val mem) => (LoweredAtomicExchange32 ptr val mem)
(AtomicExchange64 ptr val mem) => (LoweredAtomicExchange64 ptr val mem)

// Atomic compare and swap.
(AtomicCompareAndSwap32 ptr old new_ mem) => (LoweredAtomicCas32 ptr old new_ mem)
(AtomicCompareAndSwap64 ptr old new_ mem) => (LoweredAtomicCas64 ptr old new_ mem)

// Atomic and: *(*uint8)(ptr) &= val
//
// Round pointer down to nearest word boundary and pad value with ones before
// applying atomic AND operation to target word.
//
// *(*uint32)(ptr &^ 3) &= rotateleft(uint32(val) | 0xffffff00, ((3 << 3) ^ ((ptr & 3) << 3))
//
(AtomicAnd8 ptr val mem)
  => (LANfloor
       ptr
       (RLL <typ.UInt32>
         (ORWconst <typ.UInt32> val [-1<<8])
         (RXSBG <typ.UInt32> {s390x.NewRotateParams(59, 60, 3)} (MOVDconst [3<<3]) ptr))
       mem)

// Atomic or: *(*uint8)(ptr) |= val
//
// Round pointer down to nearest word boundary and pad value with zeros before
// applying atomic OR operation to target word.
//
// *(*uint32)(ptr &^ 3) |= uint32(val) << ((3 << 3) ^ ((ptr & 3) << 3))
//
(AtomicOr8  ptr val mem)
  => (LAOfloor
       ptr
       (SLW <typ.UInt32>
         (MOVBZreg <typ.UInt32> val)
         (RXSBG <typ.UInt32> {s390x.NewRotateParams(59, 60, 3)} (MOVDconst [3<<3]) ptr))
       mem)

(AtomicAnd32 ...) => (LAN ...)
(AtomicOr32  ...) => (LAO ...)

// Lowering extension
// Note: we always extend to 64 bits even though some ops don't need that many result bits.
(SignExt8to(16|32|64) ...) => (MOVBreg ...)
(SignExt16to(32|64) ...) => (MOVHreg ...)
(SignExt32to64 ...) => (MOVWreg ...)

(ZeroExt8to(16|32|64) ...) => (MOVBZreg ...)
(ZeroExt16to(32|64) ...) => (MOVHZreg ...)
(ZeroExt32to64 ...) => (MOVWZreg ...)

(Slicemask <t> x) => (SRADconst (NEG <t> x) [63])

// Lowering truncation
// Because we ignore high parts of registers, truncates are just copies.
(Trunc(16|32|64)to8 ...) => (Copy ...)
(Trunc(32|64)to16 ...) => (Copy ...)
(Trunc64to32 ...) => (Copy ...)

// Lowering float <-> int
(Cvt32to32F ...) => (CEFBRA ...)
(Cvt32to64F ...) => (CDFBRA ...)
(Cvt64to32F ...) => (CEGBRA ...)
(Cvt64to64F ...) => (CDGBRA ...)

(Cvt32Fto32 ...) => (CFEBRA ...)
(Cvt32Fto64 ...) => (CGEBRA ...)
(Cvt64Fto32 ...) => (CFDBRA ...)
(Cvt64Fto64 ...) => (CGDBRA ...)

// Lowering float <-> uint
(Cvt32Uto32F ...) => (CELFBR ...)
(Cvt32Uto64F ...) => (CDLFBR ...)
(Cvt64Uto32F ...) => (CELGBR ...)
(Cvt64Uto64F ...) => (CDLGBR ...)

(Cvt32Fto32U ...) => (CLFEBR ...)
(Cvt32Fto64U ...) => (CLGEBR ...)
(Cvt64Fto32U ...) => (CLFDBR ...)
(Cvt64Fto64U ...) => (CLGDBR ...)

// Lowering float32 <-> float64
(Cvt32Fto64F ...) => (LDEBR ...)
(Cvt64Fto32F ...) => (LEDBR ...)

(CvtBoolToUint8 ...) => (Copy ...)

(Round(32|64)F ...) => (LoweredRound(32|64)F ...)

// Lowering shifts

// Lower bounded shifts first. No need to check shift value.
(Lsh64x(64|32|16|8)  x y) && shiftIsBounded(v) => (SLD x y)
(Lsh32x(64|32|16|8)  x y) && shiftIsBounded(v) => (SLW x y)
(Lsh16x(64|32|16|8)  x y) && shiftIsBounded(v) => (SLW x y)
(Lsh8x(64|32|16|8)   x y) && shiftIsBounded(v) => (SLW x y)
(Rsh64Ux(64|32|16|8) x y) && shiftIsBounded(v) => (SRD x y)
(Rsh32Ux(64|32|16|8) x y) && shiftIsBounded(v) => (SRW x y)
(Rsh16Ux(64|32|16|8) x y) && shiftIsBounded(v) => (SRW (MOVHZreg x) y)
(Rsh8Ux(64|32|16|8)  x y) && shiftIsBounded(v) => (SRW (MOVBZreg x) y)
(Rsh64x(64|32|16|8)  x y) && shiftIsBounded(v) => (SRAD x y)
(Rsh32x(64|32|16|8)  x y) && shiftIsBounded(v) => (SRAW x y)
(Rsh16x(64|32|16|8)  x y) && shiftIsBounded(v) => (SRAW (MOVHreg x) y)
(Rsh8x(64|32|16|8)   x y) && shiftIsBounded(v) => (SRAW (MOVBreg x) y)

// Unsigned shifts need to return 0 if shift amount is >= width of shifted value.
//   result = shift >= 64 ? 0 : arg << shift
(Lsh(64|32|16|8)x64 <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SL(D|W|W|W) <t> x y) (MOVDconst [0]) (CMPUconst y [64]))
(Lsh(64|32|16|8)x32 <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SL(D|W|W|W) <t> x y) (MOVDconst [0]) (CMPWUconst y [64]))
(Lsh(64|32|16|8)x16 <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SL(D|W|W|W) <t> x y) (MOVDconst [0]) (CMPWUconst (MOVHZreg y) [64]))
(Lsh(64|32|16|8)x8  <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SL(D|W|W|W) <t> x y) (MOVDconst [0]) (CMPWUconst (MOVBZreg y) [64]))

(Rsh(64|32)Ux64 <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SR(D|W) <t> x y) (MOVDconst [0]) (CMPUconst y [64]))
(Rsh(64|32)Ux32 <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SR(D|W) <t> x y) (MOVDconst [0]) (CMPWUconst y [64]))
(Rsh(64|32)Ux16 <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SR(D|W) <t> x y) (MOVDconst [0]) (CMPWUconst (MOVHZreg y) [64]))
(Rsh(64|32)Ux8  <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SR(D|W) <t> x y) (MOVDconst [0]) (CMPWUconst (MOVBZreg y) [64]))

(Rsh(16|8)Ux64 <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SRW <t> (MOV(H|B)Zreg x) y) (MOVDconst [0]) (CMPUconst y [64]))
(Rsh(16|8)Ux32 <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SRW <t> (MOV(H|B)Zreg x) y) (MOVDconst [0]) (CMPWUconst y [64]))
(Rsh(16|8)Ux16 <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SRW <t> (MOV(H|B)Zreg x) y) (MOVDconst [0]) (CMPWUconst (MOVHZreg y) [64]))
(Rsh(16|8)Ux8  <t> x y) => (LOCGR {s390x.GreaterOrEqual} <t> (SRW <t> (MOV(H|B)Zreg x) y) (MOVDconst [0]) (CMPWUconst (MOVBZreg y) [64]))

// Signed right shift needs to return 0/-1 if shift amount is >= width of shifted value.
// We implement this by setting the shift value to 63 (all ones) if the shift value is more than 63.
//   result = arg >> (shift >= 64 ? 63 : shift)
(Rsh(64|32)x64 x y) => (SRA(D|W) x (LOCGR {s390x.GreaterOrEqual} <y.Type> y (MOVDconst <y.Type> [63]) (CMPUconst  y [64])))
(Rsh(64|32)x32 x y) => (SRA(D|W) x (LOCGR {s390x.GreaterOrEqual} <y.Type> y (MOVDconst <y.Type> [63]) (CMPWUconst y [64])))
(Rsh(64|32)x16 x y) => (SRA(D|W) x (LOCGR {s390x.GreaterOrEqual} <y.Type> y (MOVDconst <y.Type> [63]) (CMPWUconst (MOVHZreg y) [64])))
(Rsh(64|32)x8  x y) => (SRA(D|W) x (LOCGR {s390x.GreaterOrEqual} <y.Type> y (MOVDconst <y.Type> [63]) (CMPWUconst (MOVBZreg y) [64])))

(Rsh(16|8)x64 x y) => (SRAW (MOV(H|B)reg x) (LOCGR {s390x.GreaterOrEqual} <y.Type> y (MOVDconst <y.Type> [63]) (CMPUconst  y [64])))
(Rsh(16|8)x32 x y) => (SRAW (MOV(H|B)reg x) (LOCGR {s390x.GreaterOrEqual} <y.Type> y (MOVDconst <y.Type> [63]) (CMPWUconst y [64])))
(Rsh(16|8)x16 x y) => (SRAW (MOV(H|B)reg x) (LOCGR {s390x.GreaterOrEqual} <y.Type> y (MOVDconst <y.Type> [63]) (CMPWUconst (MOVHZreg y) [64])))
(Rsh(16|8)x8  x y) => (SRAW (MOV(H|B)reg x) (LOCGR {s390x.GreaterOrEqual} <y.Type> y (MOVDconst <y.Type> [63]) (CMPWUconst (MOVBZreg y) [64])))

// Lowering rotates
(RotateLeft8 <t> x (MOVDconst [c])) => (Or8 (Lsh8x64 <t> x (MOVDconst [c&7])) (Rsh8Ux64 <t> x (MOVDconst [-c&7])))
(RotateLeft16 <t> x (MOVDconst [c])) => (Or16 (Lsh16x64 <t> x (MOVDconst [c&15])) (Rsh16Ux64 <t> x (MOVDconst [-c&15])))
(RotateLeft32 ...) => (RLL  ...)
(RotateLeft64 ...) => (RLLG ...)

// Lowering comparisons
(Less64      x y) => (LOCGR {s390x.Less} (MOVDconst [0]) (MOVDconst [1]) (CMP x y))
(Less32      x y) => (LOCGR {s390x.Less} (MOVDconst [0]) (MOVDconst [1]) (CMPW x y))
(Less(16|8)  x y) => (LOCGR {s390x.Less} (MOVDconst [0]) (MOVDconst [1]) (CMPW (MOV(H|B)reg x) (MOV(H|B)reg y)))
(Less64U     x y) => (LOCGR {s390x.Less} (MOVDconst [0]) (MOVDconst [1]) (CMPU x y))
(Less32U     x y) => (LOCGR {s390x.Less} (MOVDconst [0]) (MOVDconst [1]) (CMPWU x y))
(Less(16|8)U x y) => (LOCGR {s390x.Less} (MOVDconst [0]) (MOVDconst [1]) (CMPWU (MOV(H|B)Zreg x) (MOV(H|B)Zreg y)))
(Less64F     x y) => (LOCGR {s390x.Less} (MOVDconst [0]) (MOVDconst [1]) (FCMP x y))
(Less32F     x y) => (LOCGR {s390x.Less} (MOVDconst [0]) (MOVDconst [1]) (FCMPS x y))

(Leq64      x y) => (LOCGR {s390x.LessOrEqual} (MOVDconst [0]) (MOVDconst [1]) (CMP x y))
(Leq32      x y) => (LOCGR {s390x.LessOrEqual} (MOVDconst [0]) (MOVDconst [1]) (CMPW x y))
(Leq(16|8)  x y) => (LOCGR {s390x.LessOrEqual} (MOVDconst [0]) (MOVDconst [1]) (CMPW (MOV(H|B)reg x) (MOV(H|B)reg y)))
(Leq64U     x y) => (LOCGR {s390x.LessOrEqual} (MOVDconst [0]) (MOVDconst [1]) (CMPU x y))
(Leq32U     x y) => (LOCGR {s390x.LessOrEqual} (MOVDconst [0]) (MOVDconst [1]) (CMPWU x y))
(Leq(16|8)U x y) => (LOCGR {s390x.LessOrEqual} (MOVDconst [0]) (MOVDconst [1]) (CMPWU (MOV(H|B)Zreg x) (MOV(H|B)Zreg y)))
(Leq64F     x y) => (LOCGR {s390x.LessOrEqual} (MOVDconst [0]) (MOVDconst [1]) (FCMP x y))
(Leq32F     x y) => (LOCGR {s390x.LessOrEqual} (MOVDconst [0]) (MOVDconst [1]) (FCMPS x y))

(Eq(64|Ptr) x y) => (LOCGR {s390x.Equal} (MOVDconst [0]) (MOVDconst [1]) (CMP x y))
(Eq32       x y) => (LOCGR {s390x.Equal} (MOVDconst [0]) (MOVDconst [1]) (CMPW x y))
(Eq(16|8|B) x y) => (LOCGR {s390x.Equal} (MOVDconst [0]) (MOVDconst [1]) (CMPW (MOV(H|B|B)reg x) (MOV(H|B|B)reg y)))
(Eq64F      x y) => (LOCGR {s390x.Equal} (MOVDconst [0]) (MOVDconst [1]) (FCMP x y))
(Eq32F      x y) => (LOCGR {s390x.Equal} (MOVDconst [0]) (MOVDconst [1]) (FCMPS x y))

(Neq(64|Ptr) x y) => (LOCGR {s390x.NotEqual} (MOVDconst [0]) (MOVDconst [1]) (CMP x y))
(Neq32       x y) => (LOCGR {s390x.NotEqual} (MOVDconst [0]) (MOVDconst [1]) (CMPW x y))
(Neq(16|8|B) x y) => (LOCGR {s390x.NotEqual} (MOVDconst [0]) (MOVDconst [1]) (CMPW (MOV(H|B|B)reg x) (MOV(H|B|B)reg y)))
(Neq64F      x y) => (LOCGR {s390x.NotEqual} (MOVDconst [0]) (MOVDconst [1]) (FCMP x y))
(Neq32F      x y) => (LOCGR {s390x.NotEqual} (MOVDconst [0]) (MOVDconst [1]) (FCMPS x y))

// Lowering loads
(Load <t> ptr mem) && (is64BitInt(t) || isPtr(t)) => (MOVDload ptr mem)
(Load <t> ptr mem) && is32BitInt(t) && isSigned(t) => (MOVWload ptr mem)
(Load <t> ptr mem) && is32BitInt(t) && !isSigned(t) => (MOVWZload ptr mem)
(Load <t> ptr mem) && is16BitInt(t) && isSigned(t) => (MOVHload ptr mem)
(Load <t> ptr mem) && is16BitInt(t) && !isSigned(t) => (MOVHZload ptr mem)
(Load <t> ptr mem) && is8BitInt(t) && isSigned(t) => (MOVBload ptr mem)
(Load <t> ptr mem) && (t.IsBoolean() || (is8BitInt(t) && !isSigned(t))) => (MOVBZload ptr mem)
(Load <t> ptr mem) && is32BitFloat(t) => (FMOVSload ptr mem)
(Load <t> ptr mem) && is64BitFloat(t) => (FMOVDload ptr mem)

// Lowering stores
// These more-specific FP versions of Store pattern should come first.
(Store {t} ptr val mem) && t.Size() == 8 && is64BitFloat(val.Type) => (FMOVDstore ptr val mem)
(Store {t} ptr val mem) && t.Size() == 4 && is32BitFloat(val.Type) => (FMOVSstore ptr val mem)

(Store {t} ptr val mem) && t.Size() == 8 => (MOVDstore ptr val mem)
(Store {t} ptr val mem) && t.Size() == 4 => (MOVWstore ptr val mem)
(Store {t} ptr val mem) && t.Size() == 2 => (MOVHstore ptr val mem)
(Store {t} ptr val mem) && t.Size() == 1 => (MOVBstore ptr val mem)

// Lowering moves

// Load and store for small copies.
(Move [0] _ _ mem) => mem
(Move [1] dst src mem) => (MOVBstore dst (MOVBZload src mem) mem)
(Move [2] dst src mem) => (MOVHstore dst (MOVHZload src mem) mem)
(Move [4] dst src mem) => (MOVWstore dst (MOVWZload src mem) mem)
(Move [8] dst src mem) => (MOVDstore dst (MOVDload src mem) mem)
(Move [16] dst src mem) =>
	(MOVDstore [8] dst (MOVDload [8] src mem)
		(MOVDstore dst (MOVDload src mem) mem))
(Move [24] dst src mem) =>
        (MOVDstore [16] dst (MOVDload [16] src mem)
	        (MOVDstore [8] dst (MOVDload [8] src mem)
                (MOVDstore dst (MOVDload src mem) mem)))
(Move [3] dst src mem) =>
	(MOVBstore [2] dst (MOVBZload [2] src mem)
		(MOVHstore dst (MOVHZload src mem) mem))
(Move [5] dst src mem) =>
	(MOVBstore [4] dst (MOVBZload [4] src mem)
		(MOVWstore dst (MOVWZload src mem) mem))
(Move [6] dst src mem) =>
	(MOVHstore [4] dst (MOVHZload [4] src mem)
		(MOVWstore dst (MOVWZload src mem) mem))
(Move [7] dst src mem) =>
	(MOVBstore [6] dst (MOVBZload [6] src mem)
		(MOVHstore [4] dst (MOVHZload [4] src mem)
			(MOVWstore dst (MOVWZload src mem) mem)))

// MVC for other moves. Use up to 4 instructions (sizes up to 1024 bytes).
(Move [s] dst src mem) && s > 0 && s <= 256 && logLargeCopy(v, s) =>
	(MVC [makeValAndOff32(int32(s), 0)] dst src mem)
(Move [s] dst src mem) && s > 256 && s <= 512 && logLargeCopy(v, s) =>
	(MVC [makeValAndOff32(int32(s)-256, 256)] dst src (MVC [makeValAndOff32(256, 0)] dst src mem))
(Move [s] dst src mem) && s > 512 && s <= 768 && logLargeCopy(v, s) =>
	(MVC [makeValAndOff32(int32(s)-512, 512)] dst src (MVC [makeValAndOff32(256, 256)] dst src (MVC [makeValAndOff32(256, 0)] dst src mem)))
(Move [s] dst src mem) && s > 768 && s <= 1024 && logLargeCopy(v, s) =>
	(MVC [makeValAndOff32(int32(s)-768, 768)] dst src (MVC [makeValAndOff32(256, 512)] dst src (MVC [makeValAndOff32(256, 256)] dst src (MVC [makeValAndOff32(256, 0)] dst src mem))))

// Move more than 1024 bytes using a loop.
(Move [s] dst src mem) && s > 1024 && logLargeCopy(v, s) =>
	(LoweredMove [s%256] dst src (ADD <src.Type> src (MOVDconst [(s/256)*256])) mem)

// Lowering Zero instructions
(Zero [0] _ mem) => mem
(Zero [1] destptr mem) => (MOVBstoreconst [0] destptr mem)
(Zero [2] destptr mem) => (MOVHstoreconst [0] destptr mem)
(Zero [4] destptr mem) => (MOVWstoreconst [0] destptr mem)
(Zero [8] destptr mem) => (MOVDstoreconst [0] destptr mem)
(Zero [3] destptr mem) =>
	(MOVBstoreconst [makeValAndOff32(0,2)] destptr
		(MOVHstoreconst [0] destptr mem))
(Zero [5] destptr mem) =>
	(MOVBstoreconst [makeValAndOff32(0,4)] destptr
		(MOVWstoreconst [0] destptr mem))
(Zero [6] destptr mem) =>
	(MOVHstoreconst [makeValAndOff32(0,4)] destptr
		(MOVWstoreconst [0] destptr mem))
(Zero [7] destptr mem) =>
	(MOVWstoreconst [makeValAndOff32(0,3)] destptr
		(MOVWstoreconst [0] destptr mem))

(Zero [s] destptr mem) && s > 0 && s <= 1024 =>
	(CLEAR [makeValAndOff32(int32(s), 0)] destptr mem)

// Zero more than 1024 bytes using a loop.
(Zero [s] destptr mem) && s > 1024 =>
	(LoweredZero [s%256] destptr (ADDconst <destptr.Type> destptr [(int32(s)/256)*256]) mem)

// Lowering constants
(Const(64|32|16|8) [val]) => (MOVDconst [int64(val)])
(Const(32|64)F ...) => (FMOV(S|D)const ...)
(ConstNil) => (MOVDconst [0])
(ConstBool [b]) => (MOVDconst [b2i(b)])

// Lowering calls
(StaticCall ...) => (CALLstatic ...)
(ClosureCall ...) => (CALLclosure ...)
(InterCall ...) => (CALLinter ...)

// Miscellaneous
(IsNonNil p) => (LOCGR {s390x.NotEqual} (MOVDconst [0]) (MOVDconst [1]) (CMPconst p [0]))
(IsInBounds idx len) => (LOCGR {s390x.Less} (MOVDconst [0]) (MOVDconst [1]) (CMPU idx len))
(IsSliceInBounds idx len) => (LOCGR {s390x.LessOrEqual} (MOVDconst [0]) (MOVDconst [1]) (CMPU idx len))
(NilCheck ...) => (LoweredNilCheck ...)
(GetG ...) => (LoweredGetG ...)
(GetClosurePtr ...) => (LoweredGetClosurePtr ...)
(GetCallerSP ...) => (LoweredGetCallerSP ...)
(GetCallerPC ...) => (LoweredGetCallerPC ...)
(Addr {sym} base) => (MOVDaddr {sym} base)
(LocalAddr {sym} base _) => (MOVDaddr {sym} base)
(ITab (Load ptr mem)) => (MOVDload ptr mem)

// block rewrites
(If cond yes no) => (CLIJ {s390x.LessOrGreater} (MOVBZreg <typ.Bool> cond) [0] yes no)

// Write barrier.
(WB ...) => (LoweredWB ...)

(PanicBounds [kind] x y mem) && boundsABI(kind) == 0 => (LoweredPanicBoundsA [kind] x y mem)
(PanicBounds [kind] x y mem) && boundsABI(kind) == 1 => (LoweredPanicBoundsB [kind] x y mem)
(PanicBounds [kind] x y mem) && boundsABI(kind) == 2 => (LoweredPanicBoundsC [kind] x y mem)

// ***************************
// Above: lowering rules
// Below: optimizations
// ***************************
// TODO: Should the optimizations be a separate pass?

// Note: when removing unnecessary sign/zero extensions.
//
// After a value is spilled it is restored using a sign- or zero-extension
// to register-width as appropriate for its type. For example, a uint8 will
// be restored using a MOVBZ (llgc) instruction which will zero extend the
// 8-bit value to 64-bits.
//
// This is a hazard when folding sign- and zero-extensions since we need to
// ensure not only that the value in the argument register is correctly
// extended but also that it will still be correctly extended if it is
// spilled and restored.
//
// In general this means we need type checks when the RHS of a rule is an
// OpCopy (i.e. "(... x:(...) ...) -> x").

// Merge double extensions.
(MOV(H|HZ)reg e:(MOV(B|BZ)reg x)) && clobberIfDead(e) => (MOV(B|BZ)reg x)
(MOV(W|WZ)reg e:(MOV(B|BZ)reg x)) && clobberIfDead(e) => (MOV(B|BZ)reg x)
(MOV(W|WZ)reg e:(MOV(H|HZ)reg x)) && clobberIfDead(e) => (MOV(H|HZ)reg x)

// Bypass redundant sign extensions.
(MOV(B|BZ)reg e:(MOVBreg x)) && clobberIfDead(e) => (MOV(B|BZ)reg x)
(MOV(B|BZ)reg e:(MOVHreg x)) && clobberIfDead(e) => (MOV(B|BZ)reg x)
(MOV(B|BZ)reg e:(MOVWreg x)) && clobberIfDead(e) => (MOV(B|BZ)reg x)
(MOV(H|HZ)reg e:(MOVHreg x)) && clobberIfDead(e) => (MOV(H|HZ)reg x)
(MOV(H|HZ)reg e:(MOVWreg x)) && clobberIfDead(e) => (MOV(H|HZ)reg x)
(MOV(W|WZ)reg e:(MOVWreg x)) && clobberIfDead(e) => (MOV(W|WZ)reg x)

// Bypass redundant zero extensions.
(MOV(B|BZ)reg e:(MOVBZreg x)) && clobberIfDead(e) => (MOV(B|BZ)reg x)
(MOV(B|BZ)reg e:(MOVHZreg x)) && clobberIfDead(e) => (MOV(B|BZ)reg x)
(MOV(B|BZ)reg e:(MOVWZreg x)) && clobberIfDead(e) => (MOV(B|BZ)reg x)
(MOV(H|HZ)reg e:(MOVHZreg x)) && clobberIfDead(e) => (MOV(H|HZ)reg x)
(MOV(H|HZ)reg e:(MOVWZreg x)) && clobberIfDead(e) => (MOV(H|HZ)reg x)
(MOV(W|WZ)reg e:(MOVWZreg x)) && clobberIfDead(e) => (MOV(W|WZ)reg x)

// 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(H|W)Zreg   x:(MOVHZload    _   _)) && (!x.Type.IsSigned() || x.Type.Size() > 2) => x
(MOVWZreg       x:(MOVWZload    _   _)) && (!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(H|W)reg   x:(MOVHload    _   _)) && (x.Type.IsSigned() || x.Type.Size() == 8) => x
(MOVWreg       x:(MOVWload    _   _)) && (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
(MOVWreg     x:(MOVHZload    _   _)) && (!x.Type.IsSigned() || x.Type.Size() > 2) => x

// Fold sign and zero extensions into loads.
//
// Note: The combined instruction must end up in the same block
// as the original load. If not, we end up making a value with
// memory type live in two different blocks, which can lead to
// multiple memory values alive simultaneously.
//
// Make sure we don't combine these ops if the load has another use.
// This prevents a single load from being split into multiple loads
// which then might return different values.  See test/atomicload.go.
(MOV(B|H|W)Zreg <t> x:(MOV(B|H|W)load [o] {s} p mem))
  && x.Uses == 1
  && clobber(x)
  => @x.Block (MOV(B|H|W)Zload <t> [o] {s} p mem)
(MOV(B|H|W)reg <t> x:(MOV(B|H|W)Zload [o] {s} p mem))
  && x.Uses == 1
  && clobber(x)
  => @x.Block (MOV(B|H|W)load <t> [o] {s} p mem)

// Remove zero extensions after argument load.
(MOVBZreg x:(Arg <t>)) && !t.IsSigned() && t.Size() == 1 => x
(MOVHZreg x:(Arg <t>)) && !t.IsSigned() && t.Size() <= 2 => x
(MOVWZreg x:(Arg <t>)) && !t.IsSigned() && t.Size() <= 4 => x

// Remove sign extensions after argument load.
(MOVBreg x:(Arg <t>)) && t.IsSigned() && t.Size() == 1 => x
(MOVHreg x:(Arg <t>)) && t.IsSigned() && t.Size() <= 2 => x
(MOVWreg x:(Arg <t>)) && t.IsSigned() && t.Size() <= 4 => x

// Fold zero extensions into constants.
(MOVBZreg (MOVDconst [c])) => (MOVDconst [int64( uint8(c))])
(MOVHZreg (MOVDconst [c])) => (MOVDconst [int64(uint16(c))])
(MOVWZreg (MOVDconst [c])) => (MOVDconst [int64(uint32(c))])

// Fold sign extensions into constants.
(MOVBreg (MOVDconst [c])) => (MOVDconst [int64( int8(c))])
(MOVHreg (MOVDconst [c])) => (MOVDconst [int64(int16(c))])
(MOVWreg (MOVDconst [c])) => (MOVDconst [int64(int32(c))])

// Remove zero extension of conditional move.
// Note: only for MOVBZreg for now since it is added as part of 'if' statement lowering.
(MOVBZreg x:(LOCGR (MOVDconst [c]) (MOVDconst [d]) _))
  && int64(uint8(c)) == c
  && int64(uint8(d)) == d
  && (!x.Type.IsSigned() || x.Type.Size() > 1)
  => x

// Fold boolean tests into blocks.
// Note: this must match If statement lowering.
(CLIJ {s390x.LessOrGreater} (LOCGR {d} (MOVDconst [0]) (MOVDconst [x]) cmp) [0] yes no)
  && int32(x) != 0
  => (BRC {d} cmp yes no)

// Canonicalize BRC condition code mask by removing impossible conditions.
// Integer comparisons cannot generate the unordered condition.
(BRC {c} x:((CMP|CMPW|CMPU|CMPWU)    _ _) yes no) && c&s390x.Unordered != 0 => (BRC {c&^s390x.Unordered} x yes no)
(BRC {c} x:((CMP|CMPW|CMPU|CMPWU)const _) yes no) && c&s390x.Unordered != 0 => (BRC {c&^s390x.Unordered} x yes no)

// Compare-and-branch.
// Note: bit 3 (unordered) must not be set so we mask out s390x.Unordered.
(BRC {c} (CMP   x y) yes no) => (CGRJ  {c&^s390x.Unordered} x y yes no)
(BRC {c} (CMPW  x y) yes no) => (CRJ   {c&^s390x.Unordered} x y yes no)
(BRC {c} (CMPU  x y) yes no) => (CLGRJ {c&^s390x.Unordered} x y yes no)
(BRC {c} (CMPWU x y) yes no) => (CLRJ  {c&^s390x.Unordered} x y yes no)

// Compare-and-branch (immediate).
// Note: bit 3 (unordered) must not be set so we mask out s390x.Unordered.
(BRC {c} (CMPconst   x [y]) yes no) && y == int32( int8(y)) => (CGIJ  {c&^s390x.Unordered} x [ int8(y)] yes no)
(BRC {c} (CMPWconst  x [y]) yes no) && y == int32( int8(y)) => (CIJ   {c&^s390x.Unordered} x [ int8(y)] yes no)
(BRC {c} (CMPUconst  x [y]) yes no) && y == int32(uint8(y)) => (CLGIJ {c&^s390x.Unordered} x [uint8(y)] yes no)
(BRC {c} (CMPWUconst x [y]) yes no) && y == int32(uint8(y)) => (CLIJ  {c&^s390x.Unordered} x [uint8(y)] yes no)

// Absorb immediate into compare-and-branch.
(C(R|GR)J  {c} x (MOVDconst [y]) yes no) && is8Bit(y)  => (C(I|GI)J  {c} x [ int8(y)] yes no)
(CL(R|GR)J {c} x (MOVDconst [y]) yes no) && isU8Bit(y) => (CL(I|GI)J {c} x [uint8(y)] yes no)
(C(R|GR)J  {c} (MOVDconst [x]) y yes no) && is8Bit(x)  => (C(I|GI)J  {c.ReverseComparison()} y [ int8(x)] yes no)
(CL(R|GR)J {c} (MOVDconst [x]) y yes no) && isU8Bit(x) => (CL(I|GI)J {c.ReverseComparison()} y [uint8(x)] yes no)

// Prefer comparison with immediate to compare-and-branch.
(CGRJ  {c} x (MOVDconst [y]) yes no) && !is8Bit(y)  && is32Bit(y)  => (BRC {c} (CMPconst   x [int32(y)]) yes no)
(CRJ   {c} x (MOVDconst [y]) yes no) && !is8Bit(y)  && is32Bit(y)  => (BRC {c} (CMPWconst  x [int32(y)]) yes no)
(CLGRJ {c} x (MOVDconst [y]) yes no) && !isU8Bit(y) && isU32Bit(y) => (BRC {c} (CMPUconst  x [int32(y)]) yes no)
(CLRJ  {c} x (MOVDconst [y]) yes no) && !isU8Bit(y) && isU32Bit(y) => (BRC {c} (CMPWUconst x [int32(y)]) yes no)
(CGRJ  {c} (MOVDconst [x]) y yes no) && !is8Bit(x)  && is32Bit(x)  => (BRC {c.ReverseComparison()} (CMPconst   y [int32(x)]) yes no)
(CRJ   {c} (MOVDconst [x]) y yes no) && !is8Bit(x)  && is32Bit(x)  => (BRC {c.ReverseComparison()} (CMPWconst  y [int32(x)]) yes no)
(CLGRJ {c} (MOVDconst [x]) y yes no) && !isU8Bit(x) && isU32Bit(x) => (BRC {c.ReverseComparison()} (CMPUconst  y [int32(x)]) yes no)
(CLRJ  {c} (MOVDconst [x]) y yes no) && !isU8Bit(x) && isU32Bit(x) => (BRC {c.ReverseComparison()} (CMPWUconst y [int32(x)]) yes no)

// Absorb sign/zero extensions into 32-bit compare-and-branch.
(CIJ  {c} (MOV(W|WZ)reg x) [y] yes no) => (CIJ  {c} x [y] yes no)
(CLIJ {c} (MOV(W|WZ)reg x) [y] yes no) => (CLIJ {c} x [y] yes no)

// Bring out-of-range signed immediates into range by varying branch condition.
(BRC {s390x.Less}           (CMPconst  x [ 128]) yes no) => (CGIJ {s390x.LessOrEqual}    x [ 127] yes no)
(BRC {s390x.Less}           (CMPWconst x [ 128]) yes no) => (CIJ  {s390x.LessOrEqual}    x [ 127] yes no)
(BRC {s390x.LessOrEqual}    (CMPconst  x [-129]) yes no) => (CGIJ {s390x.Less}           x [-128] yes no)
(BRC {s390x.LessOrEqual}    (CMPWconst x [-129]) yes no) => (CIJ  {s390x.Less}           x [-128] yes no)
(BRC {s390x.Greater}        (CMPconst  x [-129]) yes no) => (CGIJ {s390x.GreaterOrEqual} x [-128] yes no)
(BRC {s390x.Greater}        (CMPWconst x [-129]) yes no) => (CIJ  {s390x.GreaterOrEqual} x [-128] yes no)
(BRC {s390x.GreaterOrEqual} (CMPconst  x [ 128]) yes no) => (CGIJ {s390x.Greater}        x [ 127] yes no)
(BRC {s390x.GreaterOrEqual} (CMPWconst x [ 128]) yes no) => (CIJ  {s390x.Greater}        x [ 127] yes no)

// Bring out-of-range unsigned immediates into range by varying branch condition.
(BRC {s390x.Less}           (CMP(WU|U)const  x [256]) yes no) => (C(L|LG)IJ {s390x.LessOrEqual} x [255] yes no)
(BRC {s390x.GreaterOrEqual} (CMP(WU|U)const  x [256]) yes no) => (C(L|LG)IJ {s390x.Greater}     x [255] yes no)

// Bring out-of-range immediates into range by switching signedness (only == and !=).
(BRC {c} (CMPconst   x [y]) yes no) && y == int32(uint8(y)) && (c == s390x.Equal || c == s390x.LessOrGreater) => (CLGIJ {c} x [uint8(y)] yes no)
(BRC {c} (CMPWconst  x [y]) yes no) && y == int32(uint8(y)) && (c == s390x.Equal || c == s390x.LessOrGreater) => (CLIJ  {c} x [uint8(y)] yes no)
(BRC {c} (CMPUconst  x [y]) yes no) && y == int32( int8(y)) && (c == s390x.Equal || c == s390x.LessOrGreater) => (CGIJ  {c} x [ int8(y)] yes no)
(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 [int32(c)] x)
(ADDW x (MOVDconst [c])) => (ADDWconst [int32(c)] x)

(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 [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]))
  && s390x.NewRotateParams(0, 63, 0).OutMerge(uint64(c)) != nil
  => (RISBGZ x {*s390x.NewRotateParams(0, 63, 0).OutMerge(uint64(c))})
(AND x (MOVDconst [c]))
  && is32Bit(c)
  && c < 0
  => (ANDconst [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)

((AND|ANDW)const [c] ((AND|ANDW)const [d] x)) => ((AND|ANDW)const [c&d] 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) x (MOVDconst [c])) => (S(LD|RD|RAD)const x [uint8(c&63)])
(S(LW|RW|RAW) x (MOVDconst [c])) && c&32 == 0 => (S(LW|RW|RAW)const x [uint8(c&31)])
(S(LW|RW)     _ (MOVDconst [c])) && c&32 != 0 => (MOVDconst [0])
(SRAW         x (MOVDconst [c])) && c&32 != 0 => (SRAWconst x [31])

// Shifts only use the rightmost 6 bits of the shift value.
(S(LD|RD|RAD|LW|RW|RAW) x (RISBGZ y {r}))
  && r.Amount == 0
  && r.OutMask()&63 == 63
  => (S(LD|RD|RAD|LW|RW|RAW) x y)
(S(LD|RD|RAD|LW|RW|RAW) x (AND (MOVDconst [c]) 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)
(SRD  x (MOV(W|H|B|WZ|HZ|BZ)reg y)) => (SRD  x y)
(SRAD x (MOV(W|H|B|WZ|HZ|BZ)reg y)) => (SRAD x y)
(SLW  x (MOV(W|H|B|WZ|HZ|BZ)reg y)) => (SLW  x y)
(SRW  x (MOV(W|H|B|WZ|HZ|BZ)reg y)) => (SRW  x y)
(SRAW x (MOV(W|H|B|WZ|HZ|BZ)reg y)) => (SRAW x y)

// Match rotate by constant.
(RLLG x (MOVDconst [c])) => (RISBGZ x {s390x.NewRotateParams(0, 63, uint8(c&63))})
(RLL  x (MOVDconst [c])) => (RLLconst x [uint8(c&31)])

// Match rotate by constant pattern.
((ADD|OR|XOR)  (SLDconst x [c]) (SRDconst x [64-c])) => (RISBGZ x {s390x.NewRotateParams(0, 63, c)})
((ADD|OR|XOR)W (SLWconst x [c]) (SRWconst x [32-c])) => (RLLconst x [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)]))

// Match (x >> c) << d to 'rotate then insert selected bits [into zero]'.
(SLDconst (SRDconst x [c]) [d]) => (RISBGZ x {s390x.NewRotateParams(uint8(max8(0, int8(c-d))), 63-d, uint8(int8(d-c)&63))})

// Match (x << c) >> d to 'rotate then insert selected bits [into zero]'.
(SRDconst (SLDconst x [c]) [d]) => (RISBGZ x {s390x.NewRotateParams(d, uint8(min8(63, int8(63-c+d))), uint8(int8(c-d)&63))})

// Absorb input zero extension into 'rotate then insert selected bits [into zero]'.
(RISBGZ (MOVWZreg x) {r}) && r.InMerge(0xffffffff) != nil => (RISBGZ x {*r.InMerge(0xffffffff)})
(RISBGZ (MOVHZreg x) {r}) && r.InMerge(0x0000ffff) != nil => (RISBGZ x {*r.InMerge(0x0000ffff)})
(RISBGZ (MOVBZreg x) {r}) && r.InMerge(0x000000ff) != nil => (RISBGZ x {*r.InMerge(0x000000ff)})

// Absorb 'rotate then insert selected bits [into zero]' into zero extension.
(MOVWZreg (RISBGZ x {r})) && r.OutMerge(0xffffffff) != nil => (RISBGZ x {*r.OutMerge(0xffffffff)})
(MOVHZreg (RISBGZ x {r})) && r.OutMerge(0x0000ffff) != nil => (RISBGZ x {*r.OutMerge(0x0000ffff)})
(MOVBZreg (RISBGZ x {r})) && r.OutMerge(0x000000ff) != nil => (RISBGZ x {*r.OutMerge(0x000000ff)})

// Absorb shift into 'rotate then insert selected bits [into zero]'.
//
// Any unsigned shift can be represented as a rotate and mask operation:
//
//   x << c => RotateLeft64(x, c) & (^uint64(0) << c)
//   x >> c => RotateLeft64(x, -c) & (^uint64(0) >> c)
//
// Therefore when a shift is used as the input to a rotate then insert
// selected bits instruction we can merge the two together. We just have
// to be careful that the resultant mask is representable (non-zero and
// contiguous). For example, assuming that x is variable and c, y and m
// are constants, a shift followed by a rotate then insert selected bits
// could be represented as:
//
//   RotateLeft64(RotateLeft64(x, c) & (^uint64(0) << c), y) & m
//
// We can split the rotation by y into two, one rotate for x and one for
// the mask:
//
//   RotateLeft64(RotateLeft64(x, c), y) & (RotateLeft64(^uint64(0) << c, y)) & m
//
// The rotations of x by c followed by y can then be combined:
//
//   RotateLeft64(x, c+y) & (RotateLeft64(^uint64(0) << c, y)) & m
//   ^^^^^^^^^^^^^^^^^^^^   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
//          rotate                          mask
//
// To perform this optimization we therefore just need to check that it
// is valid to merge the shift mask (^(uint64(0)<<c)) into the selected
// bits mask (i.e. that the resultant mask is non-zero and contiguous).
//
(RISBGZ (SLDconst x [c]) {r}) && r.InMerge(^uint64(0)<<c) != nil => (RISBGZ x {(*r.InMerge(^uint64(0)<<c)).RotateLeft(c)})
(RISBGZ (SRDconst x [c]) {r}) && r.InMerge(^uint64(0)>>c) != nil => (RISBGZ x {(*r.InMerge(^uint64(0)>>c)).RotateLeft(-c)})

// Absorb 'rotate then insert selected bits [into zero]' into left shift.
(SLDconst (RISBGZ x {r}) [c])
  && s390x.NewRotateParams(0, 63-c, c).InMerge(r.OutMask()) != nil
  => (RISBGZ x {(*s390x.NewRotateParams(0, 63-c, c).InMerge(r.OutMask())).RotateLeft(r.Amount)})

// Absorb 'rotate then insert selected bits [into zero]' into right shift.
(SRDconst (RISBGZ x {r}) [c])
  && s390x.NewRotateParams(c, 63, -c&63).InMerge(r.OutMask()) != nil
  => (RISBGZ x {(*s390x.NewRotateParams(c, 63, -c&63).InMerge(r.OutMask())).RotateLeft(r.Amount)})

// Merge 'rotate then insert selected bits [into zero]' instructions together.
(RISBGZ (RISBGZ x {y}) {z})
  && z.InMerge(y.OutMask()) != nil
  => (RISBGZ x {(*z.InMerge(y.OutMask())).RotateLeft(y.Amount)})

// Convert RISBGZ into 64-bit shift (helps CSE).
(RISBGZ x {r}) && r.End == 63 && r.Start == -r.Amount&63 => (SRDconst x [-r.Amount&63])
(RISBGZ x {r}) && r.Start == 0 && r.End == 63-r.Amount => (SLDconst x [r.Amount])

// Optimize single bit isolation when it is known to be equivalent to
// the most significant bit due to mask produced by arithmetic shift.
// Simply isolate the most significant bit itself and place it in the
// correct position.
//
// Example: (int64(x) >> 63) & 0x8 -> RISBGZ $60, $60, $4, Rsrc, Rdst
(RISBGZ (SRADconst x [c]) {r})
  && r.Start == r.End           // single bit selected
  && (r.Start+r.Amount)&63 <= c // equivalent to most significant bit of x
  => (RISBGZ x {s390x.NewRotateParams(r.Start, r.Start, -r.Start&63)})

// Canonicalize the order of arguments to comparisons - helps with CSE.
((CMP|CMPW|CMPU|CMPWU) x y) && canonLessThan(x,y) => (InvertFlags ((CMP|CMPW|CMPU|CMPWU) y x))

// Use sign/zero extend instead of RISBGZ.
(RISBGZ x {r}) && r == s390x.NewRotateParams(56, 63, 0) => (MOVBZreg x)
(RISBGZ x {r}) && r == s390x.NewRotateParams(48, 63, 0) => (MOVHZreg x)
(RISBGZ x {r}) && r == s390x.NewRotateParams(32, 63, 0) => (MOVWZreg x)

// Use sign/zero extend instead of ANDW.
(ANDWconst [0x00ff] x) => (MOVBZreg x)
(ANDWconst [0xffff] x) => (MOVHZreg x)

// Strength reduce multiplication to the sum (or difference) of two powers of two.
//
// Examples:
//     5x -> 4x + 1x
//    10x -> 8x + 2x
//   120x -> 128x - 8x
//  -120x -> 8x - 128x
//
// We know that the rightmost bit of any positive value, once isolated, must either
// be a power of 2 (because it is a single bit) or 0 (if the original value is 0).
// In all of these rules we use a rightmost bit calculation to determine one operand
// for the addition or subtraction. We then just need to calculate if the other
// operand is a valid power of 2 before we can match the rule.
//
// Notes:
//   - the generic rules have already matched single powers of two so we ignore them here
//   - isPowerOfTwo32 asserts that its argument is greater than 0
//   - c&(c-1) = clear rightmost bit
//   - c&^(c-1) = isolate rightmost bit

// c = 2ˣ + 2ʸ => c - 2ˣ = 2ʸ
(MULL(D|W)const <t> x [c]) && isPowerOfTwo32(c&(c-1))
  => ((ADD|ADDW) (SL(D|W)const <t> x [uint8(log32(c&(c-1)))])
                 (SL(D|W)const <t> x [uint8(log32(c&^(c-1)))]))

// c = 2ʸ - 2ˣ => c + 2ˣ = 2ʸ
(MULL(D|W)const <t> x [c]) && isPowerOfTwo32(c+(c&^(c-1)))
  => ((SUB|SUBW) (SL(D|W)const <t> x [uint8(log32(c+(c&^(c-1))))])
                 (SL(D|W)const <t> x [uint8(log32(c&^(c-1)))]))

// c = 2ˣ - 2ʸ => -c + 2ˣ = 2ʸ
(MULL(D|W)const <t> x [c]) && isPowerOfTwo32(-c+(-c&^(-c-1)))
  => ((SUB|SUBW) (SL(D|W)const <t> x [uint8(log32(-c&^(-c-1)))])
                 (SL(D|W)const <t> x [uint8(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(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(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)

// replace load from same location as preceding store with copy
(MOVDload  [off] {sym} ptr1 (MOVDstore  [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => x
(MOVWload  [off] {sym} ptr1 (MOVWstore  [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => (MOVWreg x)
(MOVHload  [off] {sym} ptr1 (MOVHstore  [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => (MOVHreg x)
(MOVBload  [off] {sym} ptr1 (MOVBstore  [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => (MOVBreg x)
(MOVWZload [off] {sym} ptr1 (MOVWstore  [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => (MOVWZreg x)
(MOVHZload [off] {sym} ptr1 (MOVHstore  [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => (MOVHZreg x)
(MOVBZload [off] {sym} ptr1 (MOVBstore  [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => (MOVBZreg x)
(MOVDload  [off] {sym} ptr1 (FMOVDstore [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => (LGDR x)
(FMOVDload [off] {sym} ptr1 (MOVDstore  [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => (LDGR x)
(FMOVDload [off] {sym} ptr1 (FMOVDstore [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => x
(FMOVSload [off] {sym} ptr1 (FMOVSstore [off] {sym} ptr2 x _)) && isSamePtr(ptr1, ptr2) => x

// prefer FPR <-> GPR moves over combined load ops
(MULLDload <t> [off] {sym} x ptr1 (FMOVDstore [off] {sym} ptr2 y _)) && isSamePtr(ptr1, ptr2) => (MULLD x (LGDR <t> y))
(ADDload   <t> [off] {sym} x ptr1 (FMOVDstore [off] {sym} ptr2 y _)) && isSamePtr(ptr1, ptr2) => (ADD   x (LGDR <t> y))
(SUBload   <t> [off] {sym} x ptr1 (FMOVDstore [off] {sym} ptr2 y _)) && isSamePtr(ptr1, ptr2) => (SUB   x (LGDR <t> y))
(ORload    <t> [off] {sym} x ptr1 (FMOVDstore [off] {sym} ptr2 y _)) && isSamePtr(ptr1, ptr2) => (OR    x (LGDR <t> y))
(ANDload   <t> [off] {sym} x ptr1 (FMOVDstore [off] {sym} ptr2 y _)) && isSamePtr(ptr1, ptr2) => (AND   x (LGDR <t> y))
(XORload   <t> [off] {sym} x ptr1 (FMOVDstore [off] {sym} ptr2 y _)) && isSamePtr(ptr1, ptr2) => (XOR   x (LGDR <t> y))

// detect attempts to set/clear the sign bit
// may need to be reworked when NIHH/OIHH are added
(RISBGZ (LGDR <t> x) {r}) && r == s390x.NewRotateParams(1, 63, 0) => (LGDR <t> (LPDFR <x.Type> x))
(LDGR <t> (RISBGZ x {r})) && r == s390x.NewRotateParams(1, 63, 0) => (LPDFR (LDGR <t> x))
(OR (MOVDconst [-1<<63]) (LGDR <t> x)) => (LGDR <t> (LNDFR <x.Type> x))
(LDGR <t> (OR (MOVDconst [-1<<63]) x)) => (LNDFR (LDGR <t> x))

// detect attempts to set the sign bit with load
(LDGR <t> x:(ORload <t1> [off] {sym} (MOVDconst [-1<<63]) ptr mem)) && x.Uses == 1 && clobber(x) => @x.Block (LNDFR <t> (LDGR <t> (MOVDload <t1> [off] {sym} ptr mem)))

// detect copysign
(OR (RISBGZ (LGDR x) {r}) (LGDR (LPDFR <t> y)))
  && r == s390x.NewRotateParams(0, 0, 0)
  => (LGDR (CPSDR <t> y x))
(OR (RISBGZ (LGDR x) {r}) (MOVDconst [c]))
  && c >= 0
  && r == s390x.NewRotateParams(0, 0, 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)
(FNEG  (LNDFR x)) => (LPDFR x)
(FNEGS (LPDFR x)) => (LNDFR x)
(FNEGS (LNDFR x)) => (LPDFR x)

// no need to convert float32 to float64 to set/clear sign bit
(LEDBR (LPDFR (LDEBR x))) => (LPDFR x)
(LEDBR (LNDFR (LDEBR x))) => (LNDFR x)

// remove unnecessary FPR <-> GPR moves
(LDGR (LGDR x)) => x
(LGDR (LDGR x)) => x

// Don't extend before storing
(MOVWstore [off] {sym} ptr (MOVWreg x) mem) => (MOVWstore [off] {sym} ptr x mem)
(MOVHstore [off] {sym} ptr (MOVHreg x) mem) => (MOVHstore [off] {sym} ptr x mem)
(MOVBstore [off] {sym} ptr (MOVBreg x) mem) => (MOVBstore [off] {sym} ptr x mem)
(MOVWstore [off] {sym} ptr (MOVWZreg x) mem) => (MOVWstore [off] {sym} ptr x mem)
(MOVHstore [off] {sym} ptr (MOVHZreg x) mem) => (MOVHstore [off] {sym} ptr x mem)
(MOVBstore [off] {sym} ptr (MOVBZreg x) mem) => (MOVBstore [off] {sym} ptr x mem)

// Fold constants into memory operations.
// Note that this is not always a good idea because if not all the uses of
// 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(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(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(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(int64(off1)+int64(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(int64(off1)+int64(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(int64(off1)+int64(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(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) =>
	(MOVBZload  [off1+off2] {mergeSym(sym1,sym2)} base mem)
(FMOVSload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) =>
	(FMOVSload [off1+off2] {mergeSym(sym1,sym2)} base mem)
(FMOVDload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) =>
	(FMOVDload [off1+off2] {mergeSym(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] {mergeSym(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] {mergeSym(sym1,sym2)} base mem)
(MOVBload [off1] {sym1} (MOVDaddr [off2] {sym2} base) mem) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) =>
	(MOVBload [off1+off2] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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] {mergeSym(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) && sc.canAdd32(off) =>
	(MOVDstoreconst [sc.addOffset32(off)] {mergeSym(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)] {mergeSym(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)] {mergeSym(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)] {mergeSym(sym1, sym2)} ptr mem)

// MOVDaddr into MOVDaddridx
(MOVDaddridx [off1] {sym1} (MOVDaddr [off2] {sym2} x) y) && is32Bit(int64(off1)+int64(off2)) && canMergeSym(sym1, sym2) && x.Op != OpSB =>
       (MOVDaddridx [off1+off2] {mergeSym(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] {mergeSym(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==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)

(CMPWconst (MOVDconst [x]) [y]) && int32(x)==int32(y) => (FlagEQ)
(CMPWconst (MOVDconst [x]) [y]) && int32(x)<int32(y) => (FlagLT)
(CMPWconst (MOVDconst [x]) [y]) && int32(x)>int32(y) => (FlagGT)
(CMPWUconst (MOVDconst [x]) [y]) && uint32(x)==uint32(y) => (FlagEQ)
(CMPWUconst (MOVDconst [x]) [y]) && uint32(x)<uint32(y) => (FlagLT)
(CMPWUconst (MOVDconst [x]) [y]) && uint32(x)>uint32(y) => (FlagGT)

(CMP(W|WU)const (MOVBZreg _) [c]) &&   0xff < c => (FlagLT)
(CMP(W|WU)const (MOVHZreg _) [c]) && 0xffff < c => (FlagLT)

(CMPconst  (SRDconst _ [c]) [n]) && c > 0 && n < 0 => (FlagGT)
(CMPWconst (SRWconst _ [c]) [n]) && c > 0 && n < 0 => (FlagGT)

(CMPUconst  (SRDconst _ [c]) [n]) && c > 0 && c < 64 && (1<<uint(64-c)) <= uint64(n) => (FlagLT)
(CMPWUconst (SRWconst _ [c]) [n]) && c > 0 && c < 32 && (1<<uint(32-c)) <= uint32(n) => (FlagLT)

(CMPWconst  (ANDWconst _ [m]) [n]) && int32(m) >= 0 &&  int32(m) <  int32(n) => (FlagLT)
(CMPWUconst (ANDWconst _ [m]) [n]) && uint32(m) < uint32(n) => (FlagLT)

(CMPconst  (RISBGZ x {r}) [c]) && c > 0 && r.OutMask() < uint64(c) => (FlagLT)
(CMPUconst (RISBGZ x {r}) [c]) && r.OutMask() < uint64(uint32(c)) => (FlagLT)

// Constant compare-and-branch with immediate.
(CGIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Equal   != 0 &&  int64(x) ==  int64(y) => (First yes no)
(CGIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Less    != 0 &&  int64(x) <   int64(y) => (First yes no)
(CGIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Greater != 0 &&  int64(x) >   int64(y) => (First yes no)
(CIJ   {c} (MOVDconst [x]) [y] yes no) && c&s390x.Equal   != 0 &&  int32(x) ==  int32(y) => (First yes no)
(CIJ   {c} (MOVDconst [x]) [y] yes no) && c&s390x.Less    != 0 &&  int32(x) <   int32(y) => (First yes no)
(CIJ   {c} (MOVDconst [x]) [y] yes no) && c&s390x.Greater != 0 &&  int32(x) >   int32(y) => (First yes no)
(CLGIJ {c} (MOVDconst [x]) [y] yes no) && c&s390x.Equal   != 0 && uint64(x) == uint64(y) => (First yes no)
(CLGIJ {c} (MOVDconst [x]) [y] yes no) && c&s390x.Less    != 0 && uint64(x) <  uint64(y) => (First yes no)
(CLGIJ {c} (MOVDconst [x]) [y] yes no) && c&s390x.Greater != 0 && uint64(x) >  uint64(y) => (First yes no)
(CLIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Equal   != 0 && uint32(x) == uint32(y) => (First yes no)
(CLIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Less    != 0 && uint32(x) <  uint32(y) => (First yes no)
(CLIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Greater != 0 && uint32(x) >  uint32(y) => (First yes no)
(CGIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Equal   == 0 &&  int64(x) ==  int64(y) => (First no yes)
(CGIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Less    == 0 &&  int64(x) <   int64(y) => (First no yes)
(CGIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Greater == 0 &&  int64(x) >   int64(y) => (First no yes)
(CIJ   {c} (MOVDconst [x]) [y] yes no) && c&s390x.Equal   == 0 &&  int32(x) ==  int32(y) => (First no yes)
(CIJ   {c} (MOVDconst [x]) [y] yes no) && c&s390x.Less    == 0 &&  int32(x) <   int32(y) => (First no yes)
(CIJ   {c} (MOVDconst [x]) [y] yes no) && c&s390x.Greater == 0 &&  int32(x) >   int32(y) => (First no yes)
(CLGIJ {c} (MOVDconst [x]) [y] yes no) && c&s390x.Equal   == 0 && uint64(x) == uint64(y) => (First no yes)
(CLGIJ {c} (MOVDconst [x]) [y] yes no) && c&s390x.Less    == 0 && uint64(x) <  uint64(y) => (First no yes)
(CLGIJ {c} (MOVDconst [x]) [y] yes no) && c&s390x.Greater == 0 && uint64(x) >  uint64(y) => (First no yes)
(CLIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Equal   == 0 && uint32(x) == uint32(y) => (First no yes)
(CLIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Less    == 0 && uint32(x) <  uint32(y) => (First no yes)
(CLIJ  {c} (MOVDconst [x]) [y] yes no) && c&s390x.Greater == 0 && uint32(x) >  uint32(y) => (First no yes)

// Constant compare-and-branch with immediate when unsigned comparison with zero.
(C(L|LG)IJ {s390x.GreaterOrEqual} _ [0] yes no) => (First yes no)
(C(L|LG)IJ {s390x.Less}           _ [0] yes no) => (First no yes)

// Constant compare-and-branch when operands match.
(C(GR|R|LGR|LR)J {c} x y yes no) && x == y && c&s390x.Equal != 0 => (First yes no)
(C(GR|R|LGR|LR)J {c} x y yes no) && x == y && c&s390x.Equal == 0 => (First no yes)

// Convert 64-bit comparisons to 32-bit comparisons and signed comparisons
// to unsigned comparisons.
// Helps simplify constant comparison detection.
(CM(P|PU)const (MOV(W|WZ)reg x) [c]) => (CMP(W|WU)const x [c])
(CM(P|P|PU|PU)const x:(MOV(H|HZ|H|HZ)reg _) [c]) => (CMP(W|W|WU|WU)const x [c])
(CM(P|P|PU|PU)const x:(MOV(B|BZ|B|BZ)reg _) [c]) => (CMP(W|W|WU|WU)const x [c])
(CMPconst  (MOV(WZ|W)reg x:(ANDWconst [m] _)) [c]) && int32(m) >= 0 && c >= 0 => (CMPWUconst x [c])
(CMPUconst (MOV(WZ|W)reg x:(ANDWconst [m] _)) [c]) && int32(m) >= 0           => (CMPWUconst x [c])
(CMPconst  x:(SRDconst _ [c]) [n]) && c > 0 && n >= 0 => (CMPUconst  x [n])
(CMPWconst x:(SRWconst _ [c]) [n]) && c > 0 && n >= 0 => (CMPWUconst x [n])

// Absorb sign and zero extensions into 32-bit comparisons.
(CMP(W|W|WU|WU)      x (MOV(W|WZ|W|WZ)reg y))   => (CMP(W|W|WU|WU) x y)
(CMP(W|W|WU|WU)      (MOV(W|WZ|W|WZ)reg x) y)   => (CMP(W|W|WU|WU) x y)
(CMP(W|W|WU|WU)const (MOV(W|WZ|W|WZ)reg x) [c]) => (CMP(W|W|WU|WU)const x [c])

// Absorb flag constants into branches.
(BRC {c} (FlagEQ) yes no) && c&s390x.Equal     != 0 => (First yes no)
(BRC {c} (FlagLT) yes no) && c&s390x.Less      != 0 => (First yes no)
(BRC {c} (FlagGT) yes no) && c&s390x.Greater   != 0 => (First yes no)
(BRC {c} (FlagOV) yes no) && c&s390x.Unordered != 0 => (First yes no)

(BRC {c} (FlagEQ) yes no) && c&s390x.Equal     == 0 => (First no yes)
(BRC {c} (FlagLT) yes no) && c&s390x.Less      == 0 => (First no yes)
(BRC {c} (FlagGT) yes no) && c&s390x.Greater   == 0 => (First no yes)
(BRC {c} (FlagOV) yes no) && c&s390x.Unordered == 0 => (First no yes)

// Absorb flag constants into SETxx ops.
(LOCGR {c} _ x (FlagEQ)) && c&s390x.Equal     != 0 => x
(LOCGR {c} _ x (FlagLT)) && c&s390x.Less      != 0 => x
(LOCGR {c} _ x (FlagGT)) && c&s390x.Greater   != 0 => x
(LOCGR {c} _ x (FlagOV)) && c&s390x.Unordered != 0 => x

(LOCGR {c} x _ (FlagEQ)) && c&s390x.Equal     == 0 => x
(LOCGR {c} x _ (FlagLT)) && c&s390x.Less      == 0 => x
(LOCGR {c} x _ (FlagGT)) && c&s390x.Greater   == 0 => x
(LOCGR {c} x _ (FlagOV)) && c&s390x.Unordered == 0 => x

// Remove redundant *const ops
(ADDconst [0] x) => x
(ADDWconst [c] x) && int32(c)==0 => x
(SUBconst [0] x) => x
(SUBWconst [c] x) && int32(c) == 0 => x
(ANDconst [0] _)                 => (MOVDconst [0])
(ANDWconst [c] _) && int32(c)==0  => (MOVDconst [0])
(ANDconst [-1] x)                => x
(ANDWconst [c] x) && int32(c)==-1 => x
(ORconst [0] x)                  => x
(ORWconst [c] x) && int32(c)==0   => x
(ORconst [-1] _)                 => (MOVDconst [-1])
(ORWconst [c] _) && int32(c)==-1  => (MOVDconst [-1])
(XORconst [0] x)                  => x
(XORWconst [c] x) && int32(c)==0   => x

// Shifts by zero (may be inserted during multiplication strength reduction).
((SLD|SLW|SRD|SRW|SRAD|SRAW)const x [0]) => x

// Convert constant subtracts to constant adds.
(SUBconst [c] x) && c != -(1<<31) => (ADDconst [-c] x)
(SUBWconst [c] x) => (ADDWconst [-int32(c)] x)

// generic constant folding
// TODO: more of this
(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 [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 [int64(c)&d])
(OR (MOVDconst [c]) (MOVDconst [d])) => (MOVDconst [c|d])
(ORconst [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 [int64(c)^d])
(LoweredRound32F x:(FMOVSconst)) => x
(LoweredRound64F x:(FMOVDconst)) => x

// generic simplifications
// TODO: more of this
(ADD x (NEG y)) => (SUB x y)
(ADDW x (NEGW y)) => (SUBW x y)
(SUB x x) => (MOVDconst [0])
(SUBW x x) => (MOVDconst [0])
(AND x x) => x
(ANDW x x) => x
(OR x x) => x
(ORW x x) => x
(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> [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+int64(d)) >= uint64(c) && c+int64(d) == 0
  => (FlagEQ)
(Select1 (ADDCconst (MOVDconst [c]) [d]))
  && uint64(c+int64(d)) >= uint64(c) && c+int64(d) != 0
  => (FlagLT)

// borrow flag generation
// (only constant fold borrow of zero)
(Select1 (SUBC (MOVDconst [c]) (MOVDconst [d])))
  && uint64(d) <= uint64(c) && c-d == 0
  => (FlagGT)
(Select1 (SUBC (MOVDconst [c]) (MOVDconst [d])))
  && uint64(d) <= uint64(c) && c-d != 0
  => (FlagOV)

// 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 [int16(c)])
(Select0 (ADDCconst (MOVDconst [c]) [d])) => (MOVDconst [c+int64(d)])

// subtract with borrow
(SUBE x y (FlagGT)) => (SUBC x y)
(SUBE x y (FlagOV)) => (SUBC x y)
(Select0 (SUBC (MOVDconst [c]) (MOVDconst [d]))) => (MOVDconst [c-d])

// collapse carry chain
(ADDE x y (Select1 (ADDCconst [-1] (Select0 (ADDE (MOVDconst [0]) (MOVDconst [0]) c)))))
  => (ADDE x y c)

// collapse borrow chain
(SUBE x y (Select1 (SUBC (MOVDconst [0]) (NEG (Select0 (SUBE (MOVDconst [0]) (MOVDconst [0]) c))))))
  => (SUBE x y c)

// branch on carry
(C(G|LG)IJ {s390x.Equal}         (Select0 (ADDE (MOVDconst [0]) (MOVDconst [0]) carry)) [0]) => (BRC {s390x.NoCarry} carry)
(C(G|LG)IJ {s390x.Equal}         (Select0 (ADDE (MOVDconst [0]) (MOVDconst [0]) carry)) [1]) => (BRC {s390x.Carry}   carry)
(C(G|LG)IJ {s390x.LessOrGreater} (Select0 (ADDE (MOVDconst [0]) (MOVDconst [0]) carry)) [0]) => (BRC {s390x.Carry}   carry)
(C(G|LG)IJ {s390x.LessOrGreater} (Select0 (ADDE (MOVDconst [0]) (MOVDconst [0]) carry)) [1]) => (BRC {s390x.NoCarry} carry)
(C(G|LG)IJ {s390x.Greater}       (Select0 (ADDE (MOVDconst [0]) (MOVDconst [0]) carry)) [0]) => (BRC {s390x.Carry}   carry)

// branch on borrow
(C(G|LG)IJ {s390x.Equal}         (NEG (Select0 (SUBE (MOVDconst [0]) (MOVDconst [0]) borrow))) [0]) => (BRC {s390x.NoBorrow} borrow)
(C(G|LG)IJ {s390x.Equal}         (NEG (Select0 (SUBE (MOVDconst [0]) (MOVDconst [0]) borrow))) [1]) => (BRC {s390x.Borrow}   borrow)
(C(G|LG)IJ {s390x.LessOrGreater} (NEG (Select0 (SUBE (MOVDconst [0]) (MOVDconst [0]) borrow))) [0]) => (BRC {s390x.Borrow}   borrow)
(C(G|LG)IJ {s390x.LessOrGreater} (NEG (Select0 (SUBE (MOVDconst [0]) (MOVDconst [0]) borrow))) [1]) => (BRC {s390x.NoBorrow} borrow)
(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)

// Convert floating point comparisons against zero into 'load and test' instructions.
(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
// (e.g. LTDBR) is following one of those instructions, we can use the
// generated flag and remove the comparison instruction.
// Note: when inserting Select1 ops we need to ensure they are in the
// same block as their argument. We could also use @x.Block for this
// 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)

// 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(int64(off))
  && canMergeLoadClobber(v, g, x)
  && clobber(g)
  => ((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(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)W <t> x g:(MOVWZload [off] {sym} ptr mem))
  && ptr.Op != OpSB
  && is20Bit(int64(off))
  && canMergeLoadClobber(v, g, x)
  && clobber(g)
  => ((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
// emulated by the assembler and also can't handle unaligned offsets.
(MOVBstoreconst [c] {s} p x:(MOVBstoreconst [a] {s} p mem))
  && p.Op != OpSB
  && x.Uses == 1
  && a.Off() + 1 == c.Off()
  && clobber(x)
  => (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
  && a.Off() + 2 == c.Off()
  && clobber(x)
  => (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
  && a.Off() + 4 == c.Off()
  && clobber(x)
  => (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
// require that the memory operand be aligned.
(MOVBstore [i] {s} p w x:(MOVBstore [i-1] {s} p (SRDconst [8] w) mem))
  && p.Op != OpSB
  && x.Uses == 1
  && clobber(x)
  => (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)
(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)
(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] {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)
(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)
(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)
(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] {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)
(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)

// Combine stores into larger (unaligned) stores with the bytes reversed (little endian).
// Store-with-bytes-reversed instructions do not support relative memory addresses,
// so these stores can't operate on global data (SB).
(MOVBstore [i] {s} p (SRDconst [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)
(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)
(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)
(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] {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)
(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)
(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)
(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] {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)
(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)

// Combining byte loads into larger (unaligned) loads.

// Big-endian loads

(ORW                 x1:(MOVBZload [i1] {s} p mem)
    sh:(SLWconst [8] x0:(MOVBZload [i0] {s} p 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) (MOVHZload [i0] {s} p mem)

(OR                  x1:(MOVBZload [i1] {s} p mem)
    sh:(SLDconst [8] x0:(MOVBZload [i0] {s} p 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) (MOVHZload [i0] {s} p mem)

(ORW                  x1:(MOVHZload [i1] {s} p mem)
    sh:(SLWconst [16] x0:(MOVHZload [i0] {s} p 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) (MOVWZload [i0] {s} p mem)

(OR                   x1:(MOVHZload [i1] {s} p mem)
    sh:(SLDconst [16] x0:(MOVHZload [i0] {s} p 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) (MOVWZload [i0] {s} p mem)

(OR                   x1:(MOVWZload [i1] {s} p mem)
    sh:(SLDconst [32] x0:(MOVWZload [i0] {s} p 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) (MOVDload [i0] {s} p mem)

(ORW
    s0:(SLWconst [j0] x0:(MOVBZload [i0] {s} p mem))
    or:(ORW
        s1:(SLWconst [j1] x1:(MOVBZload [i1] {s} p 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] (MOVHZload [i0] {s} p mem)) y)

(OR
    s0:(SLDconst [j0] x0:(MOVBZload [i0] {s} p mem))
    or:(OR
        s1:(SLDconst [j1] x1:(MOVBZload [i1] {s} p 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] (MOVHZload [i0] {s} p mem)) y)

(OR
    s0:(SLDconst [j0] x0:(MOVHZload [i0] {s} p mem))
    or:(OR
        s1:(SLDconst [j1] x1:(MOVHZload [i1] {s} p 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] (MOVWZload [i0] {s} p mem)) y)

// Little-endian loads

(ORW                 x0:(MOVBZload [i0] {s} p mem)
    sh:(SLWconst [8] x1:(MOVBZload [i1] {s} p 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 (MOVHBRload [i0] {s} p mem))

(OR                  x0:(MOVBZload [i0] {s} p mem)
    sh:(SLDconst [8] x1:(MOVBZload [i1] {s} p 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 (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))))
  && 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) (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))))
  && 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 (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))))
  && 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) (MOVDBRload [i0] {s} p mem)

(ORW
    s1:(SLWconst [j1] x1:(MOVBZload [i1] {s} p mem))
    or:(ORW
        s0:(SLWconst [j0] x0:(MOVBZload [i0] {s} p 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 (MOVHBRload [i0] {s} p mem))) y)

(OR
    s1:(SLDconst [j1] x1:(MOVBZload [i1] {s} p mem))
    or:(OR
        s0:(SLDconst [j0] x0:(MOVBZload [i0] {s} p 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 (MOVHBRload [i0] {s} p mem))) y)

(OR
    s1:(SLDconst [j1] r1:(MOVHZreg x1:(MOVHBRload [i1] {s} p mem)))
    or:(OR
        s0:(SLDconst [j0] r0:(MOVHZreg x0:(MOVHBRload [i0] {s} p 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 (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(int64(i)-4)
  && clobber(x)
  => (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(int64(i)-8)
  && clobber(x)
  => (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(int64(i)-12)
  && clobber(x)
  => (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(int64(i)-8)
  && clobber(x)
  => (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(int64(i)-8)
  && clobber(x)
  => (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(int64(i)-16)
  && clobber(x)
  => (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(int64(i)-24)
  && clobber(x)
  => (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(int64(i)-16)
  && clobber(x)
  => (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)