go/test/codegen/divmod.go

1116 lines
23 KiB
Go
Raw Normal View History

cmd/compile: make prove understand div, mod better This CL introduces new divisible and divmod passes that rewrite divisibility checks and div, mod, and mul. These happen after prove, so that prove can make better sense of the code for deriving bounds, and they must run before decompose, so that 64-bit ops can be lowered to 32-bit ops on 32-bit systems. And then they need another generic pass as well, to optimize the generated code before decomposing. The three opt passes are "opt", "middle opt", and "late opt". (Perhaps instead they should be "generic", "opt", and "late opt"?) The "late opt" pass repeats the "middle opt" work on any new code that has been generated in the interim. There will not be new divs or mods, but there may be new muls. The x%c==0 rewrite rules are much simpler now, since they can match before divs have been rewritten. This has the effect of applying them more consistently and making the rewrite rules independent of the exact div rewrites. Prove is also now charged with marking signed div/mod as unsigned when the arguments call for it, allowing simpler code to be emitted in various cases. For example, t.Seconds()/2 and len(x)/2 are now recognized as unsigned, meaning they compile to a simple shift (unsigned division), avoiding the more complex fixup we need for signed values. https://gist.github.com/rsc/99d9d3bd99cde87b6a1a390e3d85aa32 shows a diff of 'go build -a -gcflags=-d=ssa/prove/debug=1 std' output before and after. "Proved Rsh64x64 shifts to zero" is replaced by the higher-level "Proved Div64 is unsigned" (the shift was in the signed expansion of div by constant), but otherwise prove is only finding more things to prove. One short example, in code that does x[i%len(x)]: < runtime/mfinal.go:131:34: Proved Rsh64x64 shifts to zero --- > runtime/mfinal.go:131:34: Proved Div64 is unsigned > runtime/mfinal.go:131:38: Proved IsInBounds A longer example: < crypto/internal/fips140/sha3/shake.go:28:30: Proved Rsh64x64 shifts to zero < crypto/internal/fips140/sha3/shake.go:38:27: Proved Rsh64x64 shifts to zero < crypto/internal/fips140/sha3/shake.go:53:46: Proved Rsh64x64 shifts to zero < crypto/internal/fips140/sha3/shake.go:55:46: Proved Rsh64x64 shifts to zero --- > crypto/internal/fips140/sha3/shake.go:28:30: Proved Div64 is unsigned > crypto/internal/fips140/sha3/shake.go:28:30: Proved IsInBounds > crypto/internal/fips140/sha3/shake.go:28:30: Proved IsSliceInBounds > crypto/internal/fips140/sha3/shake.go:38:27: Proved Div64 is unsigned > crypto/internal/fips140/sha3/shake.go:45:7: Proved IsSliceInBounds > crypto/internal/fips140/sha3/shake.go:46:4: Proved IsInBounds > crypto/internal/fips140/sha3/shake.go:53:46: Proved Div64 is unsigned > crypto/internal/fips140/sha3/shake.go:53:46: Proved IsInBounds > crypto/internal/fips140/sha3/shake.go:53:46: Proved IsSliceInBounds > crypto/internal/fips140/sha3/shake.go:55:46: Proved Div64 is unsigned > crypto/internal/fips140/sha3/shake.go:55:46: Proved IsInBounds > crypto/internal/fips140/sha3/shake.go:55:46: Proved IsSliceInBounds These diffs are due to the smaller opt being better and taking work away from prove: < image/jpeg/dct.go:307:5: Proved IsInBounds < image/jpeg/dct.go:308:5: Proved IsInBounds ... < image/jpeg/dct.go:442:5: Proved IsInBounds In the old opt, Mul by 8 was rewritten to Lsh by 3 early. This CL delays that rule to help prove recognize mods, but it also helps opt constant-fold the slice x[8*i:8*i+8:8*i+8]. Specifically, computing the length, opt can now do: (Sub64 (Add (Mul 8 i) 8) (Add (Mul 8 i) 8)) -> (Add 8 (Sub (Mul 8 i) (Mul 8 i))) -> (Add 8 (Mul 8 (Sub i i))) -> (Add 8 (Mul 8 0)) -> (Add 8 0) -> 8 The key step is (Sub (Mul x y) (Mul x z)) -> (Mul x (Sub y z)), Leaving the multiply as Mul enables using that step; the old rewrite to Lsh blocked it, leaving prove to figure out the length and then remove the bounds checks. But now opt can evaluate the length down to a constant 8 and then constant-fold away the bounds checks 0 < 8, 1 < 8, and so on. After that, the compiler has nothing left to prove. Benchmarks are noisy in general; I checked the assembly for the many large increases below, and the vast majority are unchanged and presumably hitting the caches differently in some way. The divisibility optimizations were not reliably triggering before. This leads to a very large improvement in some cases, like DivisiblePow2constI64, DivisibleconstI64 on 64-bit systems and DivisbleconstU64 on 32-bit systems. Another way the divisibility optimizations were unreliable before was incorrectly triggering for x/3, x%3 even though they are written not to do that. There is a real but small slowdown in the DivisibleWDivconst benchmarks on Mac because in the cases used in the benchmark, it is still faster (on Mac) to do the divisibility check than to remultiply. This may be worth further study. Perhaps when there is no rotate (meaning the divisor is odd), the divisibility optimization should be enabled always. In any event, this CL makes it possible to study that. benchmark \ host s7 linux-amd64 mac linux-arm64 linux-ppc64le linux-386 s7:GOARCH=386 linux-arm vs base vs base vs base vs base vs base vs base vs base vs base LoadAdd ~ ~ ~ ~ ~ -1.59% ~ ~ ExtShift ~ ~ -42.14% +0.10% ~ +1.44% +5.66% +8.50% Modify ~ ~ ~ ~ ~ ~ ~ -1.53% MullImm ~ ~ ~ ~ ~ +37.90% -21.87% +3.05% ConstModify ~ ~ ~ ~ -49.14% ~ ~ ~ BitSet ~ ~ ~ ~ -15.86% -14.57% +6.44% +0.06% BitClear ~ ~ ~ ~ ~ +1.78% +3.50% +0.06% BitToggle ~ ~ ~ ~ ~ -16.09% +2.91% ~ BitSetConst ~ ~ ~ ~ ~ ~ ~ -0.49% BitClearConst ~ ~ ~ ~ -28.29% ~ ~ -0.40% BitToggleConst ~ ~ ~ +8.89% -31.19% ~ ~ -0.77% MulNeg ~ ~ ~ ~ ~ ~ ~ ~ Mul2Neg ~ ~ -4.83% ~ ~ -13.75% -5.92% ~ DivconstI64 ~ ~ ~ ~ ~ -30.12% ~ +0.50% ModconstI64 ~ ~ -9.94% -4.63% ~ +3.15% ~ +5.32% DivisiblePow2constI64 -34.49% -12.58% ~ ~ -12.25% ~ ~ ~ DivisibleconstI64 -24.69% -25.06% -0.40% -2.27% -42.61% -3.31% ~ +1.63% DivisibleWDivconstI64 ~ ~ ~ ~ ~ -17.55% ~ -0.60% DivconstU64/3 ~ ~ ~ ~ ~ +1.51% ~ ~ DivconstU64/5 ~ ~ ~ ~ ~ ~ ~ ~ DivconstU64/37 ~ ~ -0.18% ~ ~ +2.70% ~ ~ DivconstU64/1234567 ~ ~ ~ ~ ~ ~ ~ +0.12% ModconstU64 ~ ~ ~ -0.24% ~ -5.10% -1.07% -1.56% DivisibleconstU64 ~ ~ ~ ~ ~ -29.01% -59.13% -50.72% DivisibleWDivconstU64 ~ ~ -12.18% -18.88% ~ -5.50% -3.91% +5.17% DivconstI32 ~ ~ -0.48% ~ -34.69% +89.01% -6.01% -16.67% ModconstI32 ~ +2.95% -0.33% ~ ~ -2.98% -5.40% -8.30% DivisiblePow2constI32 ~ ~ ~ ~ ~ ~ ~ -16.22% DivisibleconstI32 ~ ~ ~ ~ ~ -37.27% -47.75% -25.03% DivisibleWDivconstI32 -11.59% +5.22% -12.99% -23.83% ~ +45.95% -7.03% -10.01% DivconstU32 ~ ~ ~ ~ ~ +74.71% +4.81% ~ ModconstU32 ~ ~ +0.53% +0.18% ~ +51.16% ~ ~ DivisibleconstU32 ~ ~ ~ -0.62% ~ -4.25% ~ ~ DivisibleWDivconstU32 -2.77% +5.56% +11.12% -5.15% ~ +48.70% +25.11% -4.07% DivconstI16 -6.06% ~ -0.33% +0.22% ~ ~ -9.68% +5.47% ModconstI16 ~ ~ +4.44% +2.82% ~ ~ ~ +5.06% DivisiblePow2constI16 ~ ~ ~ ~ ~ ~ ~ -0.17% DivisibleconstI16 ~ ~ -0.23% ~ ~ ~ +4.60% +6.64% DivisibleWDivconstI16 -1.44% -0.43% +13.48% -5.76% ~ +1.62% -23.15% -9.06% DivconstU16 +1.61% ~ -0.35% -0.47% ~ ~ +15.59% ~ ModconstU16 ~ ~ ~ ~ ~ -0.72% ~ +14.23% DivisibleconstU16 ~ ~ -0.05% +3.00% ~ ~ ~ +5.06% DivisibleWDivconstU16 +52.10% +0.75% +17.28% +4.79% ~ -37.39% +5.28% -9.06% DivconstI8 ~ ~ -0.34% -0.96% ~ ~ -9.20% ~ ModconstI8 +2.29% ~ +4.38% +2.96% ~ ~ ~ ~ DivisiblePow2constI8 ~ ~ ~ ~ ~ ~ ~ ~ DivisibleconstI8 ~ ~ ~ ~ ~ ~ +6.04% ~ DivisibleWDivconstI8 -26.44% +1.69% +17.03% +4.05% ~ +32.48% -24.90% ~ DivconstU8 -4.50% +14.06% -0.28% ~ ~ ~ +4.16% +0.88% ModconstU8 ~ ~ +25.84% -0.64% ~ ~ ~ ~ DivisibleconstU8 ~ ~ -5.70% ~ ~ ~ ~ ~ DivisibleWDivconstU8 +49.55% +9.07% ~ +4.03% +53.87% -40.03% +39.72% -3.01% Mul2 ~ ~ ~ ~ ~ ~ ~ ~ MulNeg2 ~ ~ ~ ~ -11.73% ~ ~ -0.02% EfaceInteger ~ ~ ~ ~ ~ +18.11% ~ +2.53% TypeAssert +33.90% +2.86% ~ ~ ~ -1.07% -5.29% -1.04% Div64UnsignedSmall ~ ~ ~ ~ ~ ~ ~ ~ Div64Small ~ ~ ~ ~ ~ -0.88% ~ +2.39% Div64SmallNegDivisor ~ ~ ~ ~ ~ ~ ~ +0.35% Div64SmallNegDividend ~ ~ ~ ~ ~ -0.84% ~ +3.57% Div64SmallNegBoth ~ ~ ~ ~ ~ -0.86% ~ +3.55% Div64Unsigned ~ ~ ~ ~ ~ ~ ~ -0.11% Div64 ~ ~ ~ ~ ~ ~ ~ +0.11% Div64NegDivisor ~ ~ ~ ~ ~ -1.29% ~ ~ Div64NegDividend ~ ~ ~ ~ ~ -1.44% ~ ~ Div64NegBoth ~ ~ ~ ~ ~ ~ ~ +0.28% Mod64UnsignedSmall ~ ~ ~ ~ ~ +0.48% ~ +0.93% Mod64Small ~ ~ ~ ~ ~ ~ ~ ~ Mod64SmallNegDivisor ~ ~ ~ ~ ~ ~ ~ +1.44% Mod64SmallNegDividend ~ ~ ~ ~ ~ +0.22% ~ +1.37% Mod64SmallNegBoth ~ ~ ~ ~ ~ ~ ~ -2.22% Mod64Unsigned ~ ~ ~ ~ ~ -0.95% ~ +0.11% Mod64 ~ ~ ~ ~ ~ ~ ~ ~ Mod64NegDivisor ~ ~ ~ ~ ~ ~ ~ -0.02% Mod64NegDividend ~ ~ ~ ~ ~ ~ ~ ~ Mod64NegBoth ~ ~ ~ ~ ~ ~ ~ -0.02% MulconstI32/3 ~ ~ ~ -25.00% ~ ~ ~ +47.37% MulconstI32/5 ~ ~ ~ +33.28% ~ ~ ~ +32.21% MulconstI32/12 ~ ~ ~ -2.13% ~ ~ ~ -0.02% MulconstI32/120 ~ ~ ~ +2.93% ~ ~ ~ -0.03% MulconstI32/-120 ~ ~ ~ -2.17% ~ ~ ~ -0.03% MulconstI32/65537 ~ ~ ~ ~ ~ ~ ~ +0.03% MulconstI32/65538 ~ ~ ~ ~ ~ -33.38% ~ +0.04% MulconstI64/3 ~ ~ ~ +33.35% ~ -0.37% ~ -0.13% MulconstI64/5 ~ ~ ~ -25.00% ~ -0.34% ~ ~ MulconstI64/12 ~ ~ ~ +2.13% ~ +11.62% ~ +2.30% MulconstI64/120 ~ ~ ~ -1.98% ~ ~ ~ ~ MulconstI64/-120 ~ ~ ~ +0.75% ~ ~ ~ ~ MulconstI64/65537 ~ ~ ~ ~ ~ +5.61% ~ ~ MulconstI64/65538 ~ ~ ~ ~ ~ +5.25% ~ ~ MulconstU32/3 ~ +0.81% ~ +33.39% ~ +77.92% ~ -32.31% MulconstU32/5 ~ ~ ~ -24.97% ~ +77.92% ~ -24.47% MulconstU32/12 ~ ~ ~ +2.06% ~ ~ ~ +0.03% MulconstU32/120 ~ ~ ~ -2.74% ~ ~ ~ +0.03% MulconstU32/65537 ~ ~ ~ ~ ~ ~ ~ +0.03% MulconstU32/65538 ~ ~ ~ ~ ~ -33.42% ~ -0.03% MulconstU64/3 ~ ~ ~ +33.33% ~ -0.28% ~ +1.22% MulconstU64/5 ~ ~ ~ -25.00% ~ ~ ~ -0.64% MulconstU64/12 ~ ~ ~ +2.30% ~ +11.59% ~ +0.14% MulconstU64/120 ~ ~ ~ -2.82% ~ ~ ~ +0.04% MulconstU64/65537 ~ +0.37% ~ ~ ~ +5.58% ~ ~ MulconstU64/65538 ~ ~ ~ ~ ~ +5.16% ~ ~ ShiftArithmeticRight ~ ~ ~ ~ ~ -10.81% ~ +0.31% Switch8Predictable +14.69% ~ ~ ~ ~ -24.85% ~ ~ Switch8Unpredictable ~ -0.58% -3.80% ~ ~ -11.78% ~ -0.79% Switch32Predictable -10.33% +17.89% ~ ~ ~ +5.76% ~ ~ Switch32Unpredictable -3.15% +1.19% +9.42% ~ ~ -10.30% -5.09% +0.44% SwitchStringPredictable +70.88% +20.48% ~ ~ ~ +2.39% ~ +0.31% SwitchStringUnpredictable ~ +3.91% -5.06% -0.98% ~ +0.61% +2.03% ~ SwitchTypePredictable +146.58% -1.10% ~ -12.45% ~ -0.46% -3.81% ~ SwitchTypeUnpredictable +0.46% -0.83% ~ +4.18% ~ +0.43% ~ +0.62% SwitchInterfaceTypePredictable -13.41% -10.13% +11.03% ~ ~ -4.38% ~ +0.75% SwitchInterfaceTypeUnpredictable -6.37% -2.14% ~ -3.21% ~ -4.20% ~ +1.08% Fixes #63110. Fixes #75954. Change-Id: I55a876f08c6c14f419ce1a8cbba2eaae6c6efbf0 Reviewed-on: https://go-review.googlesource.com/c/go/+/714160 Reviewed-by: Keith Randall <khr@golang.org> Reviewed-by: Keith Randall <khr@google.com> Auto-Submit: Russ Cox <rsc@golang.org> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
2025-10-22 22:22:51 -04:00
// asmcheck
// Copyright 2018 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.
package codegen
// Div and mod rewrites, testing cmd/compile/internal/ssa/_gen/divmod.rules.
// See comments there for "Case 1" etc.
// Convert multiplication by a power of two to a shift.
func mul32_uint8(i uint8) uint8 {
// 386: "SHLL [$]5,"
// arm64: "LSL [$]5,"
return i * 32
}
func mul32_uint16(i uint16) uint16 {
// 386: "SHLL [$]5,"
// arm64: "LSL [$]5,"
return i * 32
}
func mul32_uint32(i uint32) uint32 {
// 386: "SHLL [$]5,"
// arm64: "LSL [$]5,"
return i * 32
}
func mul32_uint64(i uint64) uint64 {
// 386: "SHLL [$]5,"
// 386: "SHRL [$]27,"
// arm64: "LSL [$]5,"
return i * 32
}
func mulNeg32_int8(i int8) int8 {
// 386: "SHLL [$]5,"
// 386: "NEGL"
// arm64: "NEG R[0-9]+<<5,"
return i * -32
}
func mulNeg32_int16(i int16) int16 {
// 386: "SHLL [$]5,"
// 386: "NEGL"
// arm64: "NEG R[0-9]+<<5,"
return i * -32
}
func mulNeg32_int32(i int32) int32 {
// 386: "SHLL [$]5,"
// 386: "NEGL"
// arm64: "NEG R[0-9]+<<5,"
return i * -32
}
func mulNeg32_int64(i int64) int64 {
// 386: "SHLL [$]5,"
// 386: "SHRL [$]27,"
// 386: "SBBL"
// arm64: "NEG R[0-9]+<<5,"
return i * -32
}
// Signed divide by power of 2.
func div32_int8(i int8) int8 {
// 386: "SARB [$]7,"
// 386: "SHRB [$]3,"
// 386: "ADDL"
// 386: "SARB [$]5,"
// arm64: "SBFX [$]7, R[0-9]+, [$]1,"
// arm64: "ADD R[0-9]+>>3,"
// arm64: "SBFX [$]5, R[0-9]+, [$]3,"
return i / 32
}
func div32_int16(i int16) int16 {
// 386: "SARW [$]15,"
// 386: "SHRW [$]11,"
// 386: "ADDL"
// 386: "SARW [$]5,"
// arm64: "SBFX [$]15, R[0-9]+, [$]1,"
// arm64: "ADD R[0-9]+>>11,"
// arm64: "SBFX [$]5, R[0-9]+, [$]11,"
return i / 32
}
func div32_int32(i int32) int32 {
// 386: "SARL [$]31,"
// 386: "SHRL [$]27,"
// 386: "ADDL"
// 386: "SARL [$]5,"
// arm64: "SBFX [$]31, R[0-9]+, [$]1,"
// arm64: "ADD R[0-9]+>>27,"
// arm64: "SBFX [$]5, R[0-9]+, [$]27,"
return i / 32
}
func div32_int64(i int64) int64 {
// 386: "SARL [$]31,"
// 386: "SHRL [$]27,"
// 386: "ADDL"
// 386: "SARL [$]5,"
// 386: "SHRL [$]5,"
// 386: "SHLL [$]27,"
// arm64: "ASR [$]63,"
// arm64: "ADD R[0-9]+>>59,"
// arm64: "ASR [$]5,"
return i / 32
}
// Case 1. Signed divides where 2N ≤ register size.
func div7_int8(i int8) int8 {
// 386: "SARL [$]31,"
// 386: "IMUL3L [$]147,"
// 386: "SARL [$]10,"
// 386: "SUBL"
// arm64: "MOVD [$]147,"
// arm64: "MULW"
// arm64: "SBFX [$]10, R[0-9]+, [$]22,"
// arm64: "SUB R[0-9]+->31,"
return i / 7
}
func div7_int16(i int16) int16 {
// 386: "SARL [$]31,"
// 386: "IMUL3L [$]37450,"
// 386: "SARL [$]18,"
// 386: "SUBL"
// arm64: "MOVD [$]37450,"
// arm64: "MULW"
// arm64: "SBFX [$]18, R[0-9]+, [$]14,"
// arm64: "SUB R[0-9]+->31,"
return i / 7
}
func div7_int32(i int32) int32 {
// 64-bit only
// arm64: "MOVD [$]2454267027,"
// arm64: "MUL "
// arm64: "ASR [$]34,"
// arm64: "SUB R[0-9]+->63,"
return i / 7
}
// Case 2. Signed divides where m is even.
func div9_int32(i int32) int32 {
// 386: "SARL [$]31,"
// 386: "MOVL [$]1908874354,"
// 386: "IMULL"
// 386: "SARL [$]2,"
// 386: "SUBL"
// arm64: "MOVD [$]3817748708,"
// arm64: "MUL "
// arm64: "ASR [$]35,"
// arm64: "SUB R[0-9]+->63,"
return i / 9
}
func div7_int64(i int64) int64 {
// 64-bit only
// arm64 MOVD $5270498306774157605, SMULH, ASR $1, SUB ->63
// arm64: "MOVD [$]5270498306774157605,"
// arm64: "SMULH"
// arm64: "ASR [$]1,"
// arm64: "SUB R[0-9]+->63,"
return i / 7
}
// Case 3. Signed divides where m is odd.
func div3_int32(i int32) int32 {
// 386: "SARL [$]31,"
// 386: "MOVL [$]-1431655765,"
// 386: "IMULL"
// 386: "SARL [$]1,"
// 386: "SUBL"
// arm64: "MOVD [$]2863311531,"
// arm64: "MUL"
// arm64: "ASR [$]33,"
// arm64: "SUB R[0-9]+->63,"
return i / 3
}
func div3_int64(i int64) int64 {
// 64-bit only
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "SMULH"
// arm64: "ADD"
// arm64: "ASR [$]1,"
// arm64: "SUB R[0-9]+->63,"
return i / 3
}
// Case 4. Unsigned divide where x < 1<<(N-1).
func div7_int16u(i int16) int16 {
if i < 0 {
return 0
}
// 386: "IMUL3L [$]37450,"
// 386: "SHRL [$]18,"
// 386: -"SUBL"
// arm64: "MOVD [$]37450,"
// arm64: "MULW"
// arm64: "UBFX [$]18, R[0-9]+, [$]14,"
// arm64: -"SUB"
return i / 7
}
func div7_int32u(i int32) int32 {
if i < 0 {
return 0
}
// 386: "MOVL [$]-1840700269,"
// 386: "MULL"
// 386: "SHRL [$]2"
// 386: -"SUBL"
// arm64: "MOVD [$]2454267027,"
// arm64: "MUL"
// arm64: "LSR [$]34,"
// arm64: -"SUB"
return i / 7
}
func div7_int64u(i int64) int64 {
// 64-bit only
if i < 0 {
return 0
}
// arm64: "MOVD [$]-7905747460161236406,"
// arm64: "UMULH"
// arm64: "LSR [$]2,"
// arm64: -"SUB"
return i / 7
}
// Case 5. Unsigned divide where 2N+1 ≤ register size.
func div7_uint8(i uint8) uint8 {
// 386: "IMUL3L [$]293,"
// 386: "SHRL [$]11,"
// arm64: "MOVD [$]293,"
// arm64: "MULW"
// arm64: "UBFX [$]11, R[0-9]+, [$]21,"
return i / 7
}
func div7_uint16(i uint16) uint16 {
// only 64-bit
// arm64: "MOVD [$]74899,"
// arm64: "MUL"
// arm64: "LSR [$]19,"
return i / 7
}
// Case 6. Unsigned divide where m is even.
func div3_uint16(i uint16) uint16 {
// 386: "IMUL3L [$]43691," "SHRL [$]17,"
// arm64: "MOVD [$]87382,"
// arm64: "MUL"
// arm64: "LSR [$]18,"
return i / 3
}
func div3_uint32(i uint32) uint32 {
// 386: "MOVL [$]-1431655765," "MULL", "SHRL [$]1,"
// arm64: "MOVD [$]2863311531,"
// arm64: "MUL"
// arm64: "LSR [$]33,"
return i / 3
}
func div3_uint64(i uint64) uint64 {
// 386 "CALL"
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "UMULH"
// arm64: "LSR [$]1,"
return i / 3
}
// Case 7. Unsigned divide where c is even.
func div14_uint16(i uint16) uint16 {
// 32-bit only
// 386: "SHRL [$]1,"
// 386: "IMUL3L [$]37450,"
// 386: "SHRL [$]18,"
return i / 14
}
func div14_uint32(i uint32) uint32 {
// 386: "SHRL [$]1,"
// 386: "MOVL [$]-1840700269,"
// 386: "SHRL [$]2,"
// arm64: "UBFX [$]1, R[0-9]+, [$]31,"
// arm64: "MOVD [$]2454267027,"
// arm64: "MUL"
// arm64: "LSR [$]34,"
return i / 14
}
func div14_uint64(i uint64) uint64 {
// 386 "CALL"
// arm64: "MOVD [$]-7905747460161236406,"
// arm64: "UMULH"
// arm64: "LSR [$]2,"
return i / 14
}
// Case 8. Unsigned divide on systems with avg.
func div7_uint16a(i uint16) uint16 {
// only 32-bit
// 386: "SHLL [$]16,"
// 386: "IMUL3L [$]9363,"
// 386: "ADDL"
// 386: "RCRL [$]1,"
// 386: "SHRL [$]18,"
return i / 7
}
func div7_uint32(i uint32) uint32 {
// 386: "MOVL [$]613566757,"
// 386: "MULL"
// 386: "ADDL"
// 386: "RCRL [$]1,"
// 386: "SHRL [$]2,"
// arm64: "UBFIZ [$]32, R[0-9]+, [$]32,"
// arm64: "MOVD [$]613566757,"
// arm64: "MUL"
// arm64: "SUB"
// arm64: "ADD R[0-9]+>>1,"
// arm64: "LSR [$]34,"
return i / 7
}
func div7_uint64(i uint64) uint64 {
// 386 "CALL"
// arm64: "MOVD [$]2635249153387078803,"
// arm64: "UMULH"
// arm64: "SUB",
// arm64: "ADD R[0-9]+>>1,"
// arm64: "LSR [$]2,"
return i / 7
}
func div12345_uint64(i uint64) uint64 {
// 386 "CALL"
// arm64: "MOVD [$]-6205696892516465602,"
// arm64: "UMULH"
// arm64: "LSR [$]13,"
return i / 12345
}
// Divisibility and non-divisibility by power of two.
func divis32_uint8(i uint8) bool {
// 386: "TESTB [$]31,"
// arm64: "TSTW [$]31,"
return i%32 == 0
}
func ndivis32_uint8(i uint8) bool {
// 386: "TESTB [$]31,"
// arm64: "TSTW [$]31,"
return i%32 != 0
}
func divis32_uint16(i uint16) bool {
// 386: "TESTW [$]31,"
// arm64: "TSTW [$]31,"
return i%32 == 0
}
func ndivis32_uint16(i uint16) bool {
// 386: "TESTW [$]31,"
// arm64: "TSTW [$]31,"
return i%32 != 0
}
func divis32_uint32(i uint32) bool {
// 386: "TESTL [$]31,"
// arm64: "TSTW [$]31,"
return i%32 == 0
}
func ndivis32_uint32(i uint32) bool {
// 386: "TESTL [$]31,"
// arm64: "TSTW [$]31,"
return i%32 != 0
}
func divis32_uint64(i uint64) bool {
// 386: "TESTL [$]31,"
// arm64: "TST [$]31,"
return i%32 == 0
}
func ndivis32_uint64(i uint64) bool {
// 386: "TESTL [$]31,"
// arm64: "TST [$]31,"
return i%32 != 0
}
func divis32_int8(i int8) bool {
// 386: "TESTB [$]31,"
// arm64: "TSTW [$]31,"
return i%32 == 0
}
func ndivis32_int8(i int8) bool {
// 386: "TESTB [$]31,"
// arm64: "TSTW [$]31,"
return i%32 != 0
}
func divis32_int16(i int16) bool {
// 386: "TESTW [$]31,"
// arm64: "TSTW [$]31,"
return i%32 == 0
}
func ndivis32_int16(i int16) bool {
// 386: "TESTW [$]31,"
// arm64: "TSTW [$]31,"
return i%32 != 0
}
func divis32_int32(i int32) bool {
// 386: "TESTL [$]31,"
// arm64: "TSTW [$]31,"
return i%32 == 0
}
func ndivis32_int32(i int32) bool {
// 386: "TESTL [$]31,"
// arm64: "TSTW [$]31,"
return i%32 != 0
}
func divis32_int64(i int64) bool {
// 386: "TESTL [$]31,"
// arm64: "TST [$]31,"
return i%32 == 0
}
func ndivis32_int64(i int64) bool {
// 386: "TESTL [$]31,"
// arm64: "TST [$]31,"
return i%32 != 0
}
// Divide with divisibility check; reuse divide intermediate mod.
func div_divis32_uint8(i uint8) (uint8, bool) {
// 386: "SHRB [$]5,"
// 386: "TESTB [$]31,",
// 386: "SETEQ"
// arm64: "UBFX [$]5, R[0-9]+, [$]3"
// arm64: "TSTW [$]31,"
// arm64: "CSET EQ"
return i/32, i%32 == 0
}
func div_ndivis32_uint8(i uint8) (uint8, bool) {
// 386: "SHRB [$]5,"
// 386: "TESTB [$]31,",
// 386: "SETNE"
// arm64: "UBFX [$]5, R[0-9]+, [$]3"
// arm64: "TSTW [$]31,"
// arm64: "CSET NE"
return i/32, i%32 != 0
}
func div_divis32_uint16(i uint16) (uint16, bool) {
// 386: "SHRW [$]5,"
// 386: "TESTW [$]31,",
// 386: "SETEQ"
// arm64: "UBFX [$]5, R[0-9]+, [$]11"
// arm64: "TSTW [$]31,"
// arm64: "CSET EQ"
return i/32, i%32 == 0
}
func div_ndivis32_uint16(i uint16) (uint16, bool) {
// 386: "SHRW [$]5,"
// 386: "TESTW [$]31,",
// 386: "SETNE"
// arm64: "UBFX [$]5, R[0-9]+, [$]11,"
// arm64: "TSTW [$]31,"
// arm64: "CSET NE"
return i/32, i%32 != 0
}
func div_divis32_uint32(i uint32) (uint32, bool) {
// 386: "SHRL [$]5,"
// 386: "TESTL [$]31,",
// 386: "SETEQ"
// arm64: "UBFX [$]5, R[0-9]+, [$]27,"
// arm64: "TSTW [$]31,"
// arm64: "CSET EQ"
return i/32, i%32 == 0
}
func div_ndivis32_uint32(i uint32) (uint32, bool) {
// 386: "SHRL [$]5,"
// 386: "TESTL [$]31,",
// 386: "SETNE"
// arm64: "UBFX [$]5, R[0-9]+, [$]27,"
// arm64: "TSTW [$]31,"
// arm64: "CSET NE"
return i/32, i%32 != 0
}
func div_divis32_uint64(i uint64) (uint64, bool) {
// 386: "SHRL [$]5,"
// 386: "SHLL [$]27,"
// 386: "TESTL [$]31,",
// 386: "SETEQ"
// arm64: "LSR [$]5,"
// arm64: "TST [$]31,"
// arm64: "CSET EQ"
return i/32, i%32 == 0
}
func div_ndivis32_uint64(i uint64) (uint64, bool) {
// 386: "SHRL [$]5,"
// 386: "SHLL [$]27,"
// 386: "TESTL [$]31,",
// 386: "SETNE"
// arm64: "LSR [$]5,"
// arm64: "TST [$]31,"
// arm64: "CSET NE"
return i/32, i%32 != 0
}
func div_divis32_int8(i int8) (int8, bool) {
// 386: "SARB [$]7,"
// 386: "SHRB [$]3,"
// 386: "SARB [$]5,"
// 386: "TESTB [$]31,",
// 386: "SETEQ"
// arm64: "SBFX [$]7, R[0-9]+, [$]1,"
// arm64: "ADD R[0-9]+>>3,"
// arm64: "SBFX [$]5, R[0-9]+, [$]3,"
// arm64: "TSTW [$]31,"
// arm64: "CSET EQ"
return i/32, i%32 == 0
}
func div_ndivis32_int8(i int8) (int8, bool) {
// 386: "SARB [$]7,"
// 386: "SHRB [$]3,"
// 386: "SARB [$]5,"
// 386: "TESTB [$]31,",
// 386: "SETNE"
// arm64: "SBFX [$]7, R[0-9]+, [$]1,"
// arm64: "ADD R[0-9]+>>3,"
// arm64: "SBFX [$]5, R[0-9]+, [$]3,"
// arm64: "TSTW [$]31,"
// arm64: "CSET NE"
return i/32, i%32 != 0
}
func div_divis32_int16(i int16) (int16, bool) {
// 386: "SARW [$]15,"
// 386: "SHRW [$]11,"
// 386: "SARW [$]5,"
// 386: "TESTW [$]31,",
// 386: "SETEQ"
// arm64: "SBFX [$]15, R[0-9]+, [$]1,"
// arm64: "ADD R[0-9]+>>11,"
// arm64: "SBFX [$]5, R[0-9]+, [$]11,"
// arm64: "TSTW [$]31,"
// arm64: "CSET EQ"
return i/32, i%32 == 0
}
func div_ndivis32_int16(i int16) (int16, bool) {
// 386: "SARW [$]15,"
// 386: "SHRW [$]11,"
// 386: "SARW [$]5,"
// 386: "TESTW [$]31,",
// 386: "SETNE"
// arm64: "SBFX [$]15, R[0-9]+, [$]1,"
// arm64: "ADD R[0-9]+>>11,"
// arm64: "SBFX [$]5, R[0-9]+, [$]11,"
// arm64: "TSTW [$]31,"
// arm64: "CSET NE"
return i/32, i%32 != 0
}
func div_divis32_int32(i int32) (int32, bool) {
// 386: "SARL [$]31,"
// 386: "SHRL [$]27,"
// 386: "SARL [$]5,"
// 386: "TESTL [$]31,",
// 386: "SETEQ"
// arm64: "SBFX [$]31, R[0-9]+, [$]1,"
// arm64: "ADD R[0-9]+>>27,"
// arm64: "SBFX [$]5, R[0-9]+, [$]27,"
// arm64: "TSTW [$]31,"
// arm64: "CSET EQ"
return i/32, i%32 == 0
}
func div_ndivis32_int32(i int32) (int32, bool) {
// 386: "SARL [$]31,"
// 386: "SHRL [$]27,"
// 386: "SARL [$]5,"
// 386: "TESTL [$]31,",
// 386: "SETNE"
// arm64: "SBFX [$]31, R[0-9]+, [$]1,"
// arm64: "ADD R[0-9]+>>27,"
// arm64: "SBFX [$]5, R[0-9]+, [$]27,"
// arm64: "TSTW [$]31,"
// arm64: "CSET NE"
return i/32, i%32 != 0
}
func div_divis32_int64(i int64) (int64, bool) {
// 386: "SARL [$]31,"
// 386: "SHRL [$]27,"
// 386: "SARL [$]5,"
// 386: "SHLL [$]27,"
// 386: "TESTL [$]31,",
// 386: "SETEQ"
// arm64: "ASR [$]63,"
// arm64: "ADD R[0-9]+>>59,"
// arm64: "ASR [$]5,"
// arm64: "TST [$]31,"
// arm64: "CSET EQ"
return i/32, i%32 == 0
}
func div_ndivis32_int64(i int64) (int64, bool) {
// 386: "SARL [$]31,"
// 386: "SHRL [$]27,"
// 386: "SARL [$]5,"
// 386: "SHLL [$]27,"
// 386: "TESTL [$]31,",
// 386: "SETNE"
// arm64: "ASR [$]63,"
// arm64: "ADD R[0-9]+>>59,"
// arm64: "ASR [$]5,"
// arm64: "TST [$]31,"
// arm64: "CSET NE"
return i/32, i%32 != 0
}
// Divisibility and non-divisibility by non-power-of-two.
func divis6_uint8(i uint8) bool {
// 386: "IMUL3L [$]-85,"
// 386: "ROLB [$]7,"
// 386: "CMPB .*, [$]42"
// 386: "SETLS"
// arm64: "MOVD [$]-85,"
// arm64: "MULW"
// arm64: "UBFX [$]1, R[0-9]+, [$]7,"
// arm64: "ORR R[0-9]+<<7"
// arm64: "CMPW [$]42,"
// arm64: "CSET LS"
return i%6 == 0
}
func ndivis6_uint8(i uint8) bool {
// 386: "IMUL3L [$]-85,"
// 386: "ROLB [$]7,"
// 386: "CMPB .*, [$]42"
// 386: "SETHI"
// arm64: "MOVD [$]-85,"
// arm64: "MULW"
// arm64: "UBFX [$]1, R[0-9]+, [$]7,"
// arm64: "ORR R[0-9]+<<7"
// arm64: "CMPW [$]42,"
// arm64: "CSET HI"
return i%6 != 0
}
func divis6_uint16(i uint16) bool {
// 386: "IMUL3L [$]-21845,"
// 386: "ROLW [$]15,"
// 386: "CMPW .*, [$]10922"
// 386: "SETLS"
// arm64: "MOVD [$]-21845,"
// arm64: "MULW"
// arm64: "ORR R[0-9]+<<16"
// arm64: "RORW [$]17,"
// arm64: "MOVD [$]10922,"
// arm64: "CSET LS"
return i%6 == 0
}
func ndivis6_uint16(i uint16) bool {
// 386: "IMUL3L [$]-21845,"
// 386: "ROLW [$]15,"
// 386: "CMPW .*, [$]10922"
// 386: "SETHI"
// arm64: "MOVD [$]-21845,"
// arm64: "MULW"
// arm64: "ORR R[0-9]+<<16"
// arm64: "RORW [$]17,"
// arm64: "MOVD [$]10922,"
// arm64: "CSET HI"
return i%6 != 0
}
func divis6_uint32(i uint32) bool {
// 386: "IMUL3L [$]-1431655765,"
// 386: "ROLL [$]31,"
// 386: "CMPL .*, [$]715827882"
// 386: "SETLS"
// arm64: "MOVD [$]-1431655765,"
// arm64: "MULW"
// arm64: "RORW [$]1,"
// arm64: "MOVD [$]715827882,"
// arm64: "CSET LS"
return i%6 == 0
}
func ndivis6_uint32(i uint32) bool {
// 386: "IMUL3L [$]-1431655765,"
// 386: "ROLL [$]31,"
// 386: "CMPL .*, [$]715827882"
// 386: "SETHI"
// arm64: "MOVD [$]-1431655765,"
// arm64: "MULW"
// arm64: "RORW [$]1,"
// arm64: "MOVD [$]715827882,"
// arm64: "CSET HI"
return i%6 != 0
}
func divis6_uint64(i uint64) bool {
// 386: "IMUL3L [$]-1431655766,"
// 386: "IMUL3L [$]-1431655765,"
// 386: "MULL"
// 386: "SHRL [$]1,"
// 386: "SHLL [$]31,"
// 386: "CMPL .*, [$]715827882"
// 386: "SETLS"
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "MUL "
// arm64: "ROR [$]1,"
// arm64: "MOVD [$]3074457345618258602,"
// arm64: "CSET LS"
return i%6 == 0
}
func ndivis6_uint64(i uint64) bool {
// 386: "IMUL3L [$]-1431655766,"
// 386: "IMUL3L [$]-1431655765,"
// 386: "MULL"
// 386: "SHRL [$]1,"
// 386: "SHLL [$]31,"
// 386: "CMPL .*, [$]715827882"
// 386: "SETHI"
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "MUL "
// arm64: "ROR [$]1,"
// arm64: "MOVD [$]3074457345618258602,"
// arm64: "CSET HI"
return i%6 != 0
}
func divis6_int8(i int8) bool {
// 386: "IMUL3L [$]-85,"
// 386: "ADDL [$]42,"
// 386: "ROLB [$]7,"
// 386: "CMPB .*, [$]42"
// 386: "SETLS"
// arm64: "MOVD [$]-85,"
// arm64: "MULW"
// arm64: "ADD [$]42,"
// arm64: "UBFX [$]1, R[0-9]+, [$]7,"
// arm64: "ORR R[0-9]+<<7"
// arm64: "CMPW [$]42,"
// arm64: "CSET LS"
return i%6 == 0
}
func ndivis6_int8(i int8) bool {
// 386: "IMUL3L [$]-85,"
// 386: "ADDL [$]42,"
// 386: "ROLB [$]7,"
// 386: "CMPB .*, [$]42"
// 386: "SETHI"
// arm64: "MOVD [$]-85,"
// arm64: "MULW"
// arm64: "ADD [$]42,"
// arm64: "UBFX [$]1, R[0-9]+, [$]7,"
// arm64: "ORR R[0-9]+<<7"
// arm64: "CMPW [$]42,"
// arm64: "CSET HI"
return i%6 != 0
}
func divis6_int16(i int16) bool {
// 386: "IMUL3L [$]-21845,"
// 386: "ADDL [$]10922,"
// 386: "ROLW [$]15,"
// 386: "CMPW .*, [$]10922"
// 386: "SETLS"
// arm64: "MOVD [$]-21845,"
// arm64: "MULW"
// arm64: "MOVD [$]10922,"
// arm64: "ADD "
// arm64: "ORR R[0-9]+<<16"
// arm64: "RORW [$]17,"
// arm64: "MOVD [$]10922,"
// arm64: "CSET LS"
return i%6 == 0
}
func ndivis6_int16(i int16) bool {
// 386: "IMUL3L [$]-21845,"
// 386: "ADDL [$]10922,"
// 386: "ROLW [$]15,"
// 386: "CMPW .*, [$]10922"
// 386: "SETHI"
// arm64: "MOVD [$]-21845,"
// arm64: "MULW"
// arm64: "MOVD [$]10922,"
// arm64: "ADD "
// arm64: "ORR R[0-9]+<<16"
// arm64: "RORW [$]17,"
// arm64: "MOVD [$]10922,"
// arm64: "CSET HI"
return i%6 != 0
}
func divis6_int32(i int32) bool {
// 386: "IMUL3L [$]-1431655765,"
// 386: "ADDL [$]715827882,"
// 386: "ROLL [$]31,"
// 386: "CMPL .*, [$]715827882"
// 386: "SETLS"
// arm64: "MOVD [$]-1431655765,"
// arm64: "MULW"
// arm64: "MOVD [$]715827882,"
// arm64: "ADD "
// arm64: "RORW [$]1,"
// arm64: "CSET LS"
return i%6 == 0
}
func ndivis6_int32(i int32) bool {
// 386: "IMUL3L [$]-1431655765,"
// 386: "ADDL [$]715827882,"
// 386: "ROLL [$]31,"
// 386: "CMPL .*, [$]715827882"
// 386: "SETHI"
// arm64: "MOVD [$]-1431655765,"
// arm64: "MULW"
// arm64: "MOVD [$]715827882,"
// arm64: "ADD "
// arm64: "RORW [$]1,"
// arm64: "CSET HI"
return i%6 != 0
}
func divis6_int64(i int64) bool {
// 386 "CALL"
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "MUL "
// arm64: "MOVD [$]3074457345618258602,"
// arm64: "ADD "
// arm64: "ROR [$]1,"
// arm64: "CSET LS"
return i%6 == 0
}
func ndivis6_int64(i int64) bool {
// 386 "CALL"
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "MUL "
// arm64: "MOVD [$]3074457345618258602,"
// arm64: "ADD "
// arm64: "ROR [$]1,"
// arm64: "CSET HI"
return i%6 != 0
}
func div_divis6_uint8(i uint8) (uint8, bool) {
// 386: "IMUL3L [$]342,"
// 386: "SHRL [$]11,"
// 386: "SETEQ"
// 386: -"RO[RL]"
// arm64: "MOVD [$]342,"
// arm64: "MULW"
// arm64: "UBFX [$]11, R[0-9]+, [$]21,"
// arm64: "CSET EQ"
// arm64: -"RO[RL]"
return i/6, i%6 == 0
}
func div_ndivis6_uint8(i uint8) (uint8, bool) {
// 386: "IMUL3L [$]342,"
// 386: "SHRL [$]11,"
// 386: "SETNE"
// 386: -"RO[RL]"
// arm64: "MOVD [$]342,"
// arm64: "MULW"
// arm64: "UBFX [$]11, R[0-9]+, [$]21,"
// arm64: "CSET NE"
// arm64: -"RO[RL]"
return i/6, i%6 != 0
}
func div_divis6_uint16(i uint16) (uint16, bool) {
// 386: "IMUL3L [$]43691,"
// 386: "SHRL [$]18,"
// 386: "SHLL [$]1,"
// 386: "SETEQ"
// 386: -"RO[RL]"
// arm64: "MOVD [$]87382,"
// arm64: "MUL "
// arm64: "LSR [$]19,"
// arm64: "CSET EQ"
// arm64: -"RO[RL]"
return i/6, i%6 == 0
}
func div_ndivis6_uint16(i uint16) (uint16, bool) {
// 386: "IMUL3L [$]43691,"
// 386: "SHRL [$]18,"
// 386: "SHLL [$]1,"
// 386: "SETNE"
// 386: -"RO[RL]"
// arm64: "MOVD [$]87382,"
// arm64: "MUL "
// arm64: "LSR [$]19,"
// arm64: "CSET NE"
// arm64: -"RO[RL]"
return i/6, i%6 != 0
}
func div_divis6_uint32(i uint32) (uint32, bool) {
// 386: "MOVL [$]-1431655765,"
// 386: "SHRL [$]2,"
// 386: "SHLL [$]1,"
// 386: "SETEQ"
// 386: -"RO[RL]"
// arm64: "MOVD [$]2863311531,"
// arm64: "MUL "
// arm64: "LSR [$]34,"
// arm64: "CSET EQ"
// arm64: -"RO[RL]"
return i/6, i%6 == 0
}
func div_ndivis6_uint32(i uint32) (uint32, bool) {
// 386: "MOVL [$]-1431655765,"
// 386: "SHRL [$]2,"
// 386: "SHLL [$]1,"
// 386: "SETNE"
// 386: -"RO[RL]"
// arm64: "MOVD [$]2863311531,"
// arm64: "MUL "
// arm64: "LSR [$]34,"
// arm64: "CSET NE"
// arm64: -"RO[RL]"
return i/6, i%6 != 0
}
func div_divis6_uint64(i uint64) (uint64, bool) {
// 386 "CALL"
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "UMULH"
// arm64: "LSR [$]2,"
// arm64: "CSET EQ"
// arm64: -"RO[RL]"
return i/6, i%6 == 0
}
func div_ndivis6_uint64(i uint64) (uint64, bool) {
// 386 "CALL"
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "UMULH"
// arm64: "LSR [$]2,"
// arm64: "CSET NE"
// arm64: -"RO[RL]"
return i/6, i%6 != 0
}
func div_divis6_int8(i int8) (int8, bool) {
// 386: "SARL [$]31,"
// 386: "IMUL3L [$]171,"
// 386: "SARL [$]10,"
// 386: "SHLL [$]1,"
// 386: "SETEQ"
// 386: -"RO[RL]"
// arm64: "MOVD [$]171,"
// arm64: "MULW"
// arm64: "SBFX [$]10, R[0-9]+, [$]22,"
// arm64: "SUB R[0-9]+->31,"
// arm64: "CSET EQ"
// arm64: -"RO[RL]"
return i/6, i%6 == 0
}
func div_ndivis6_int8(i int8) (int8, bool) {
// 386: "SARL [$]31,"
// 386: "IMUL3L [$]171,"
// 386: "SARL [$]10,"
// 386: "SHLL [$]1,"
// 386: "SETNE"
// 386: -"RO[RL]"
// arm64: "MOVD [$]171,"
// arm64: "MULW"
// arm64: "SBFX [$]10, R[0-9]+, [$]22,"
// arm64: "SUB R[0-9]+->31,"
// arm64: "CSET NE"
// arm64: -"RO[RL]"
return i/6, i%6 != 0
}
func div_divis6_int16(i int16) (int16, bool) {
// 386: "SARL [$]31,"
// 386: "IMUL3L [$]43691,"
// 386: "SARL [$]18,"
// 386: "SHLL [$]1,"
// 386: "SETEQ"
// 386: -"RO[RL]"
// arm64: "MOVD [$]43691,"
// arm64: "MULW"
// arm64: "SBFX [$]18, R[0-9]+, [$]14,"
// arm64: "SUB R[0-9]+->31,"
// arm64: "CSET EQ"
// arm64: -"RO[RL]"
return i/6, i%6 == 0
}
func div_ndivis6_int16(i int16) (int16, bool) {
// 386: "SARL [$]31,"
// 386: "IMUL3L [$]43691,"
// 386: "SARL [$]18,"
// 386: "SHLL [$]1,"
// 386: "SETNE"
// 386: -"RO[RL]"
// arm64: "MOVD [$]43691,"
// arm64: "MULW"
// arm64: "SBFX [$]18, R[0-9]+, [$]14,"
// arm64: "SUB R[0-9]+->31,"
// arm64: "CSET NE"
// arm64: -"RO[RL]"
return i/6, i%6 != 0
}
func div_divis6_int32(i int32) (int32, bool) {
// 386: "SARL [$]31,"
// 386: "MOVL [$]-1431655765,"
// 386: "IMULL"
// 386: "SARL [$]2,"
// 386: "SHLL [$]1,"
// 386: "SETEQ"
// 386: -"RO[RL]"
// arm64: "MOVD [$]2863311531,"
// arm64: "MUL "
// arm64: "ASR [$]34,"
// arm64: "SUB R[0-9]+->63,"
// arm64: "CSET EQ"
// arm64: -"RO[RL]"
return i/6, i%6 == 0
}
func div_ndivis6_int32(i int32) (int32, bool) {
// 386: "SARL [$]31,"
// 386: "MOVL [$]-1431655765,"
// 386: "IMULL"
// 386: "SARL [$]2,"
// 386: "SHLL [$]1,"
// 386: "SETNE"
// 386: -"RO[RL]"
// arm64: "MOVD [$]2863311531,"
// arm64: "MUL "
// arm64: "ASR [$]34,"
// arm64: "SUB R[0-9]+->63,"
// arm64: "CSET NE"
// arm64: -"RO[RL]"
return i/6, i%6 != 0
}
func div_divis6_int64(i int64) (int64, bool) {
// 386 "CALL"
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "SMULH"
// arm64: "ADD"
// arm64: "ASR [$]2,"
// arm64: "SUB R[0-9]+->63,"
// arm64: "CSET EQ"
// arm64: -"RO[RL]"
return i/6, i%6 == 0
}
func div_ndivis6_int64(i int64) (int64, bool) {
// 386 "CALL"
// arm64: "MOVD [$]-6148914691236517205,"
// arm64: "SMULH"
// arm64: "ADD"
// arm64: "ASR [$]2,"
// arm64: "SUB R[0-9]+->63,"
// arm64: "CSET NE"
// arm64: -"RO[RL]"
return i/6, i%6 != 0
}