qbit/go
1
0
Fork 0
mirror of https://github.com/golang/go synced 2024-09-29 07:14:29 -06:00
Code Releases Activity
2c46cc8b89
go/test/codegen/shift.go

368 lines
9.2 KiB
Go
Raw Normal View History

cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
// 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
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ------------------ //
// constant shifts //
// ------------------ //
func lshConst64x64(v int64) int64 {
cmd/compile: optimise immediate operands with constants on riscv64 Instructions with immediates can be precomputed when operating on a constant - do so for SLTI/SLTIU, SLLI/SRLI/SRAI, NEG/NEGW, ANDI, ORI and ADDI. Additionally, optimise ANDI and ORI when the immediate is all ones or all zeroes. In particular, the RISCV64 logical left and right shift rules (Lsh*x*/Rsh*Ux*) produce sequences that check if the shift amount exceeds 64 and if so returns zero. When the shift amount is a constant we can precompute and eliminate the filter entirely. Likewise the arithmetic right shift rules produce sequences that check if the shift amount exceeds 64 and if so, ensures that the lower six bits of the shift are all ones. When the shift amount is a constant we can precompute the shift value. Arithmetic right shift sequences like: 117fc: 00100513 li a0,1 11800: 04053593 sltiu a1,a0,64 11804: fff58593 addi a1,a1,-1 11808: 0015e593 ori a1,a1,1 1180c: 40b45433 sra s0,s0,a1 Are now a single srai instruction: 117fc: 40145413 srai s0,s0,0x1 Likewise for logical left shift (and logical right shift): 1d560: 01100413 li s0,17 1d564: 04043413 sltiu s0,s0,64 1d568: 40800433 neg s0,s0 1d56c: 01131493 slli s1,t1,0x11 1d570: 0084f433 and s0,s1,s0 Which are now a single slli (or srli) instruction: 1d120: 01131413 slli s0,t1,0x11 This removes more than 30,000 instructions from the Go binary and should improve performance in a variety of areas - of note runtime.makemap_small drops from 48 to 36 instructions. Similar gains exist in at least other parts of runtime and math/bits. Change-Id: I33f6f3d1fd36d9ff1bda706997162bfe4bb859b6 Reviewed-on: https://go-review.googlesource.com/c/go/+/350689 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2021-09-17 00:53:11 -06:00
// riscv64:"SLLI",-"AND",-"SLTIU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v << uint64(33)
}
func rshConst64Ux64(v uint64) uint64 {
cmd/compile: optimise immediate operands with constants on riscv64 Instructions with immediates can be precomputed when operating on a constant - do so for SLTI/SLTIU, SLLI/SRLI/SRAI, NEG/NEGW, ANDI, ORI and ADDI. Additionally, optimise ANDI and ORI when the immediate is all ones or all zeroes. In particular, the RISCV64 logical left and right shift rules (Lsh*x*/Rsh*Ux*) produce sequences that check if the shift amount exceeds 64 and if so returns zero. When the shift amount is a constant we can precompute and eliminate the filter entirely. Likewise the arithmetic right shift rules produce sequences that check if the shift amount exceeds 64 and if so, ensures that the lower six bits of the shift are all ones. When the shift amount is a constant we can precompute the shift value. Arithmetic right shift sequences like: 117fc: 00100513 li a0,1 11800: 04053593 sltiu a1,a0,64 11804: fff58593 addi a1,a1,-1 11808: 0015e593 ori a1,a1,1 1180c: 40b45433 sra s0,s0,a1 Are now a single srai instruction: 117fc: 40145413 srai s0,s0,0x1 Likewise for logical left shift (and logical right shift): 1d560: 01100413 li s0,17 1d564: 04043413 sltiu s0,s0,64 1d568: 40800433 neg s0,s0 1d56c: 01131493 slli s1,t1,0x11 1d570: 0084f433 and s0,s1,s0 Which are now a single slli (or srli) instruction: 1d120: 01131413 slli s0,t1,0x11 This removes more than 30,000 instructions from the Go binary and should improve performance in a variety of areas - of note runtime.makemap_small drops from 48 to 36 instructions. Similar gains exist in at least other parts of runtime and math/bits. Change-Id: I33f6f3d1fd36d9ff1bda706997162bfe4bb859b6 Reviewed-on: https://go-review.googlesource.com/c/go/+/350689 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2021-09-17 00:53:11 -06:00
// riscv64:"SRLI",-"AND",-"SLTIU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v >> uint64(33)
}
func rshConst64x64(v int64) int64 {
cmd/compile: optimise immediate operands with constants on riscv64 Instructions with immediates can be precomputed when operating on a constant - do so for SLTI/SLTIU, SLLI/SRLI/SRAI, NEG/NEGW, ANDI, ORI and ADDI. Additionally, optimise ANDI and ORI when the immediate is all ones or all zeroes. In particular, the RISCV64 logical left and right shift rules (Lsh*x*/Rsh*Ux*) produce sequences that check if the shift amount exceeds 64 and if so returns zero. When the shift amount is a constant we can precompute and eliminate the filter entirely. Likewise the arithmetic right shift rules produce sequences that check if the shift amount exceeds 64 and if so, ensures that the lower six bits of the shift are all ones. When the shift amount is a constant we can precompute the shift value. Arithmetic right shift sequences like: 117fc: 00100513 li a0,1 11800: 04053593 sltiu a1,a0,64 11804: fff58593 addi a1,a1,-1 11808: 0015e593 ori a1,a1,1 1180c: 40b45433 sra s0,s0,a1 Are now a single srai instruction: 117fc: 40145413 srai s0,s0,0x1 Likewise for logical left shift (and logical right shift): 1d560: 01100413 li s0,17 1d564: 04043413 sltiu s0,s0,64 1d568: 40800433 neg s0,s0 1d56c: 01131493 slli s1,t1,0x11 1d570: 0084f433 and s0,s1,s0 Which are now a single slli (or srli) instruction: 1d120: 01131413 slli s0,t1,0x11 This removes more than 30,000 instructions from the Go binary and should improve performance in a variety of areas - of note runtime.makemap_small drops from 48 to 36 instructions. Similar gains exist in at least other parts of runtime and math/bits. Change-Id: I33f6f3d1fd36d9ff1bda706997162bfe4bb859b6 Reviewed-on: https://go-review.googlesource.com/c/go/+/350689 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2021-09-17 00:53:11 -06:00
// riscv64:"SRAI",-"OR",-"SLTIU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v >> uint64(33)
}
func lshConst32x64(v int32) int32 {
cmd/compile: optimise immediate operands with constants on riscv64 Instructions with immediates can be precomputed when operating on a constant - do so for SLTI/SLTIU, SLLI/SRLI/SRAI, NEG/NEGW, ANDI, ORI and ADDI. Additionally, optimise ANDI and ORI when the immediate is all ones or all zeroes. In particular, the RISCV64 logical left and right shift rules (Lsh*x*/Rsh*Ux*) produce sequences that check if the shift amount exceeds 64 and if so returns zero. When the shift amount is a constant we can precompute and eliminate the filter entirely. Likewise the arithmetic right shift rules produce sequences that check if the shift amount exceeds 64 and if so, ensures that the lower six bits of the shift are all ones. When the shift amount is a constant we can precompute the shift value. Arithmetic right shift sequences like: 117fc: 00100513 li a0,1 11800: 04053593 sltiu a1,a0,64 11804: fff58593 addi a1,a1,-1 11808: 0015e593 ori a1,a1,1 1180c: 40b45433 sra s0,s0,a1 Are now a single srai instruction: 117fc: 40145413 srai s0,s0,0x1 Likewise for logical left shift (and logical right shift): 1d560: 01100413 li s0,17 1d564: 04043413 sltiu s0,s0,64 1d568: 40800433 neg s0,s0 1d56c: 01131493 slli s1,t1,0x11 1d570: 0084f433 and s0,s1,s0 Which are now a single slli (or srli) instruction: 1d120: 01131413 slli s0,t1,0x11 This removes more than 30,000 instructions from the Go binary and should improve performance in a variety of areas - of note runtime.makemap_small drops from 48 to 36 instructions. Similar gains exist in at least other parts of runtime and math/bits. Change-Id: I33f6f3d1fd36d9ff1bda706997162bfe4bb859b6 Reviewed-on: https://go-review.googlesource.com/c/go/+/350689 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2021-09-17 00:53:11 -06:00
// riscv64:"SLLI",-"AND",-"SLTIU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v << uint64(29)
}
func rshConst32Ux64(v uint32) uint32 {
cmd/compile: optimise immediate operands with constants on riscv64 Instructions with immediates can be precomputed when operating on a constant - do so for SLTI/SLTIU, SLLI/SRLI/SRAI, NEG/NEGW, ANDI, ORI and ADDI. Additionally, optimise ANDI and ORI when the immediate is all ones or all zeroes. In particular, the RISCV64 logical left and right shift rules (Lsh*x*/Rsh*Ux*) produce sequences that check if the shift amount exceeds 64 and if so returns zero. When the shift amount is a constant we can precompute and eliminate the filter entirely. Likewise the arithmetic right shift rules produce sequences that check if the shift amount exceeds 64 and if so, ensures that the lower six bits of the shift are all ones. When the shift amount is a constant we can precompute the shift value. Arithmetic right shift sequences like: 117fc: 00100513 li a0,1 11800: 04053593 sltiu a1,a0,64 11804: fff58593 addi a1,a1,-1 11808: 0015e593 ori a1,a1,1 1180c: 40b45433 sra s0,s0,a1 Are now a single srai instruction: 117fc: 40145413 srai s0,s0,0x1 Likewise for logical left shift (and logical right shift): 1d560: 01100413 li s0,17 1d564: 04043413 sltiu s0,s0,64 1d568: 40800433 neg s0,s0 1d56c: 01131493 slli s1,t1,0x11 1d570: 0084f433 and s0,s1,s0 Which are now a single slli (or srli) instruction: 1d120: 01131413 slli s0,t1,0x11 This removes more than 30,000 instructions from the Go binary and should improve performance in a variety of areas - of note runtime.makemap_small drops from 48 to 36 instructions. Similar gains exist in at least other parts of runtime and math/bits. Change-Id: I33f6f3d1fd36d9ff1bda706997162bfe4bb859b6 Reviewed-on: https://go-review.googlesource.com/c/go/+/350689 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2021-09-17 00:53:11 -06:00
// riscv64:"SRLI",-"AND",-"SLTIU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v >> uint64(29)
}
func rshConst32x64(v int32) int32 {
cmd/compile: optimise immediate operands with constants on riscv64 Instructions with immediates can be precomputed when operating on a constant - do so for SLTI/SLTIU, SLLI/SRLI/SRAI, NEG/NEGW, ANDI, ORI and ADDI. Additionally, optimise ANDI and ORI when the immediate is all ones or all zeroes. In particular, the RISCV64 logical left and right shift rules (Lsh*x*/Rsh*Ux*) produce sequences that check if the shift amount exceeds 64 and if so returns zero. When the shift amount is a constant we can precompute and eliminate the filter entirely. Likewise the arithmetic right shift rules produce sequences that check if the shift amount exceeds 64 and if so, ensures that the lower six bits of the shift are all ones. When the shift amount is a constant we can precompute the shift value. Arithmetic right shift sequences like: 117fc: 00100513 li a0,1 11800: 04053593 sltiu a1,a0,64 11804: fff58593 addi a1,a1,-1 11808: 0015e593 ori a1,a1,1 1180c: 40b45433 sra s0,s0,a1 Are now a single srai instruction: 117fc: 40145413 srai s0,s0,0x1 Likewise for logical left shift (and logical right shift): 1d560: 01100413 li s0,17 1d564: 04043413 sltiu s0,s0,64 1d568: 40800433 neg s0,s0 1d56c: 01131493 slli s1,t1,0x11 1d570: 0084f433 and s0,s1,s0 Which are now a single slli (or srli) instruction: 1d120: 01131413 slli s0,t1,0x11 This removes more than 30,000 instructions from the Go binary and should improve performance in a variety of areas - of note runtime.makemap_small drops from 48 to 36 instructions. Similar gains exist in at least other parts of runtime and math/bits. Change-Id: I33f6f3d1fd36d9ff1bda706997162bfe4bb859b6 Reviewed-on: https://go-review.googlesource.com/c/go/+/350689 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2021-09-17 00:53:11 -06:00
// riscv64:"SRAI",-"OR",-"SLTIU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v >> uint64(29)
}
func lshConst64x32(v int64) int64 {
cmd/compile: optimise immediate operands with constants on riscv64 Instructions with immediates can be precomputed when operating on a constant - do so for SLTI/SLTIU, SLLI/SRLI/SRAI, NEG/NEGW, ANDI, ORI and ADDI. Additionally, optimise ANDI and ORI when the immediate is all ones or all zeroes. In particular, the RISCV64 logical left and right shift rules (Lsh*x*/Rsh*Ux*) produce sequences that check if the shift amount exceeds 64 and if so returns zero. When the shift amount is a constant we can precompute and eliminate the filter entirely. Likewise the arithmetic right shift rules produce sequences that check if the shift amount exceeds 64 and if so, ensures that the lower six bits of the shift are all ones. When the shift amount is a constant we can precompute the shift value. Arithmetic right shift sequences like: 117fc: 00100513 li a0,1 11800: 04053593 sltiu a1,a0,64 11804: fff58593 addi a1,a1,-1 11808: 0015e593 ori a1,a1,1 1180c: 40b45433 sra s0,s0,a1 Are now a single srai instruction: 117fc: 40145413 srai s0,s0,0x1 Likewise for logical left shift (and logical right shift): 1d560: 01100413 li s0,17 1d564: 04043413 sltiu s0,s0,64 1d568: 40800433 neg s0,s0 1d56c: 01131493 slli s1,t1,0x11 1d570: 0084f433 and s0,s1,s0 Which are now a single slli (or srli) instruction: 1d120: 01131413 slli s0,t1,0x11 This removes more than 30,000 instructions from the Go binary and should improve performance in a variety of areas - of note runtime.makemap_small drops from 48 to 36 instructions. Similar gains exist in at least other parts of runtime and math/bits. Change-Id: I33f6f3d1fd36d9ff1bda706997162bfe4bb859b6 Reviewed-on: https://go-review.googlesource.com/c/go/+/350689 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2021-09-17 00:53:11 -06:00
// riscv64:"SLLI",-"AND",-"SLTIU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v << uint32(33)
}
func rshConst64Ux32(v uint64) uint64 {
cmd/compile: optimise immediate operands with constants on riscv64 Instructions with immediates can be precomputed when operating on a constant - do so for SLTI/SLTIU, SLLI/SRLI/SRAI, NEG/NEGW, ANDI, ORI and ADDI. Additionally, optimise ANDI and ORI when the immediate is all ones or all zeroes. In particular, the RISCV64 logical left and right shift rules (Lsh*x*/Rsh*Ux*) produce sequences that check if the shift amount exceeds 64 and if so returns zero. When the shift amount is a constant we can precompute and eliminate the filter entirely. Likewise the arithmetic right shift rules produce sequences that check if the shift amount exceeds 64 and if so, ensures that the lower six bits of the shift are all ones. When the shift amount is a constant we can precompute the shift value. Arithmetic right shift sequences like: 117fc: 00100513 li a0,1 11800: 04053593 sltiu a1,a0,64 11804: fff58593 addi a1,a1,-1 11808: 0015e593 ori a1,a1,1 1180c: 40b45433 sra s0,s0,a1 Are now a single srai instruction: 117fc: 40145413 srai s0,s0,0x1 Likewise for logical left shift (and logical right shift): 1d560: 01100413 li s0,17 1d564: 04043413 sltiu s0,s0,64 1d568: 40800433 neg s0,s0 1d56c: 01131493 slli s1,t1,0x11 1d570: 0084f433 and s0,s1,s0 Which are now a single slli (or srli) instruction: 1d120: 01131413 slli s0,t1,0x11 This removes more than 30,000 instructions from the Go binary and should improve performance in a variety of areas - of note runtime.makemap_small drops from 48 to 36 instructions. Similar gains exist in at least other parts of runtime and math/bits. Change-Id: I33f6f3d1fd36d9ff1bda706997162bfe4bb859b6 Reviewed-on: https://go-review.googlesource.com/c/go/+/350689 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2021-09-17 00:53:11 -06:00
// riscv64:"SRLI",-"AND",-"SLTIU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v >> uint32(33)
}
func rshConst64x32(v int64) int64 {
cmd/compile: optimise immediate operands with constants on riscv64 Instructions with immediates can be precomputed when operating on a constant - do so for SLTI/SLTIU, SLLI/SRLI/SRAI, NEG/NEGW, ANDI, ORI and ADDI. Additionally, optimise ANDI and ORI when the immediate is all ones or all zeroes. In particular, the RISCV64 logical left and right shift rules (Lsh*x*/Rsh*Ux*) produce sequences that check if the shift amount exceeds 64 and if so returns zero. When the shift amount is a constant we can precompute and eliminate the filter entirely. Likewise the arithmetic right shift rules produce sequences that check if the shift amount exceeds 64 and if so, ensures that the lower six bits of the shift are all ones. When the shift amount is a constant we can precompute the shift value. Arithmetic right shift sequences like: 117fc: 00100513 li a0,1 11800: 04053593 sltiu a1,a0,64 11804: fff58593 addi a1,a1,-1 11808: 0015e593 ori a1,a1,1 1180c: 40b45433 sra s0,s0,a1 Are now a single srai instruction: 117fc: 40145413 srai s0,s0,0x1 Likewise for logical left shift (and logical right shift): 1d560: 01100413 li s0,17 1d564: 04043413 sltiu s0,s0,64 1d568: 40800433 neg s0,s0 1d56c: 01131493 slli s1,t1,0x11 1d570: 0084f433 and s0,s1,s0 Which are now a single slli (or srli) instruction: 1d120: 01131413 slli s0,t1,0x11 This removes more than 30,000 instructions from the Go binary and should improve performance in a variety of areas - of note runtime.makemap_small drops from 48 to 36 instructions. Similar gains exist in at least other parts of runtime and math/bits. Change-Id: I33f6f3d1fd36d9ff1bda706997162bfe4bb859b6 Reviewed-on: https://go-review.googlesource.com/c/go/+/350689 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com>
2021-09-17 00:53:11 -06:00
// riscv64:"SRAI",-"OR",-"SLTIU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v >> uint32(33)
}
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
// ------------------ //
// masked shifts //
// ------------------ //
func lshMask64x64(v int64, s uint64) int64 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ANDCC",-"ORN",-"ISEL"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ANDCC",-"ORN",-"ISEL"
// riscv64:"SLL","AND","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
test/codegen: gofmt Change-Id: I33f5b5051e5f75aa264ec656926223c5a3c09c1b Reviewed-on: https://go-review.googlesource.com/c/go/+/167498 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Matt Layher <mdlayher@gmail.com>
2019-03-13 14:52:17 -06:00
return v << (s & 63)
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
func rshMask64Ux64(v uint64, s uint64) uint64 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ANDCC",-"ORN",-"ISEL"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ANDCC",-"ORN",-"ISEL"
// riscv64:"SRL","AND","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
test/codegen: gofmt Change-Id: I33f5b5051e5f75aa264ec656926223c5a3c09c1b Reviewed-on: https://go-review.googlesource.com/c/go/+/167498 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Matt Layher <mdlayher@gmail.com>
2019-03-13 14:52:17 -06:00
return v >> (s & 63)
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
func rshMask64x64(v int64, s uint64) int64 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ANDCC",-"ORN",-"ISEL"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ANDCC",-ORN",-"ISEL"
// riscv64:"SRA","OR","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
test/codegen: gofmt Change-Id: I33f5b5051e5f75aa264ec656926223c5a3c09c1b Reviewed-on: https://go-review.googlesource.com/c/go/+/167498 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Matt Layher <mdlayher@gmail.com>
2019-03-13 14:52:17 -06:00
return v >> (s & 63)
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
func lshMask32x64(v int32, s uint64) int32 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ISEL",-"ORN"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ISEL",-"ORN"
// riscv64:"SLL","AND","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
test/codegen: gofmt Change-Id: I33f5b5051e5f75aa264ec656926223c5a3c09c1b Reviewed-on: https://go-review.googlesource.com/c/go/+/167498 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Matt Layher <mdlayher@gmail.com>
2019-03-13 14:52:17 -06:00
return v << (s & 63)
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
func rshMask32Ux64(v uint32, s uint64) uint32 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ISEL",-"ORN"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ISEL",-"ORN"
// riscv64:"SRL","AND","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
test/codegen: gofmt Change-Id: I33f5b5051e5f75aa264ec656926223c5a3c09c1b Reviewed-on: https://go-review.googlesource.com/c/go/+/167498 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Matt Layher <mdlayher@gmail.com>
2019-03-13 14:52:17 -06:00
return v >> (s & 63)
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
func rshMask32x64(v int32, s uint64) int32 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ISEL",-"ORN"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ISEL",-"ORN"
// riscv64:"SRA","OR","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
test/codegen: gofmt Change-Id: I33f5b5051e5f75aa264ec656926223c5a3c09c1b Reviewed-on: https://go-review.googlesource.com/c/go/+/167498 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Matt Layher <mdlayher@gmail.com>
2019-03-13 14:52:17 -06:00
return v >> (s & 63)
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
func lshMask64x32(v int64, s uint32) int64 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ANDCC",-"ORN"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ANDCC",-"ORN"
// riscv64:"SLL","AND","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
test/codegen: gofmt Change-Id: I33f5b5051e5f75aa264ec656926223c5a3c09c1b Reviewed-on: https://go-review.googlesource.com/c/go/+/167498 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Matt Layher <mdlayher@gmail.com>
2019-03-13 14:52:17 -06:00
return v << (s & 63)
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
func rshMask64Ux32(v uint64, s uint32) uint64 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ANDCC",-"ORN"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ANDCC",-"ORN"
// riscv64:"SRL","AND","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
test/codegen: gofmt Change-Id: I33f5b5051e5f75aa264ec656926223c5a3c09c1b Reviewed-on: https://go-review.googlesource.com/c/go/+/167498 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Matt Layher <mdlayher@gmail.com>
2019-03-13 14:52:17 -06:00
return v >> (s & 63)
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
func rshMask64x32(v int64, s uint32) int64 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ANDCC",-"ORN",-"ISEL"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ANDCC",-"ORN",-"ISEL"
// riscv64:"SRA","OR","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
test/codegen: gofmt Change-Id: I33f5b5051e5f75aa264ec656926223c5a3c09c1b Reviewed-on: https://go-review.googlesource.com/c/go/+/167498 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Matt Layher <mdlayher@gmail.com>
2019-03-13 14:52:17 -06:00
return v >> (s & 63)
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
func lshMask64x32Ext(v int64, s int32) int64 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ANDCC",-"ORN",-"ISEL"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ANDCC",-"ORN",-"ISEL"
// riscv64:"SLL","AND","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
return v << uint(s&63)
}
func rshMask64Ux32Ext(v uint64, s int32) uint64 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ANDCC",-"ORN",-"ISEL"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ANDCC",-"ORN",-"ISEL"
// riscv64:"SRL","AND","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
return v >> uint(s&63)
}
func rshMask64x32Ext(v int64, s int32) int64 {
cmd/compile: use isel with variable shifts on ppc64x This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-04-01 08:30:05 -06:00
// ppc64:"ANDCC",-"ORN",-"ISEL"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// ppc64le:"ANDCC",-"ORN",-"ISEL"
// riscv64:"SRA","OR","SLTIU"
// s390x:-"RISBGZ",-"AND",-"LOCGR"
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
return v >> uint(s&63)
}
cmd/compile: don't generate panicshift for masked int shifts We know that a & 31 is non-negative for all a, signed or not. We can avoid checking that and needing to write out an unreachable call to panicshift. Change-Id: I32f32fb2c950d2b2b35ac5c0e99b7b2dbd47f917 Reviewed-on: https://go-review.googlesource.com/c/go/+/167499 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Keith Randall <khr@golang.org>
2019-03-13 14:53:38 -06:00
// --------------- //
// signed shifts //
// --------------- //
// We do want to generate a test + panicshift for these cases.
func lshSigned(v8 int8, v16 int16, v32 int32, v64 int64, x int) {
// amd64:"TESTB"
_ = x << v8
// amd64:"TESTW"
_ = x << v16
// amd64:"TESTL"
_ = x << v32
// amd64:"TESTQ"
_ = x << v64
}
// We want to avoid generating a test + panicshift for these cases.
func lshSignedMasked(v8 int8, v16 int16, v32 int32, v64 int64, x int) {
// amd64:-"TESTB"
_ = x << (v8 & 7)
// amd64:-"TESTW"
_ = x << (v16 & 15)
// amd64:-"TESTL"
_ = x << (v32 & 31)
// amd64:-"TESTQ"
_ = x << (v64 & 63)
}
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
// ------------------ //
// bounded shifts //
// ------------------ //
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
func lshGuarded64(v int64, s uint) int64 {
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
if s < 64 {
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// riscv64:"SLL","AND","SLTIU"
cmd/compile: optimize shift pairs and masks on s390x Optimize combinations of left and right shifts by a constant value into a 'rotate then insert selected bits [into zero]' instruction. Use the same instruction for contiguous masks since it has some benefits over 'and immediate' (not restricted to 32-bits, does not overwrite source register). To keep the complexity of this change under control I've only implemented 64 bit operations for now. There are a lot more optimizations that can be done with this instruction family. However, since their function overlaps with other instructions we need to be somewhat careful not to break existing optimization rules by creating optimization dead ends. This is particularly true of the load/store merging rules which contain lots of zero extensions and shifts. This CL does interfere with the store merging rules when an operand is shifted left before it is stored: binary.BigEndian.PutUint64(b, x << 1) This is unfortunate but it's not critical and somewhat complex so I plan to fix that in a follow up CL. file before after Δ % addr2line 4117446 4117282 -164 -0.004% api 4945184 4942752 -2432 -0.049% asm 4998079 4991891 -6188 -0.124% buildid 2685158 2684074 -1084 -0.040% cgo 4553732 4553394 -338 -0.007% compile 19294446 19245070 -49376 -0.256% cover 4897105 4891319 -5786 -0.118% dist 3544389 3542785 -1604 -0.045% doc 3926795 3927617 +822 +0.021% fix 3302958 3293868 -9090 -0.275% link 6546274 6543456 -2818 -0.043% nm 4102021 4100825 -1196 -0.029% objdump 4542431 4548483 +6052 +0.133% pack 2482465 2416389 -66076 -2.662% pprof 13366541 13363915 -2626 -0.020% test2json 2829007 2761515 -67492 -2.386% trace 10216164 10219684 +3520 +0.034% vet 6773956 6773572 -384 -0.006% total 107124151 106917891 -206260 -0.193% Change-Id: I7591cce41e06867ba10a745daae9333513062746 Reviewed-on: https://go-review.googlesource.com/c/go/+/233317 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Trust: Michael Munday <mike.munday@ibm.com>
2020-05-11 10:44:48 -06:00
// s390x:-"RISBGZ",-"AND",-"LOCGR"
// wasm:-"Select",-".*LtU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v << s
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
panic("shift too large")
}
func rshGuarded64U(v uint64, s uint) uint64 {
if s < 64 {
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// riscv64:"SRL","AND","SLTIU"
cmd/compile: optimize shift pairs and masks on s390x Optimize combinations of left and right shifts by a constant value into a 'rotate then insert selected bits [into zero]' instruction. Use the same instruction for contiguous masks since it has some benefits over 'and immediate' (not restricted to 32-bits, does not overwrite source register). To keep the complexity of this change under control I've only implemented 64 bit operations for now. There are a lot more optimizations that can be done with this instruction family. However, since their function overlaps with other instructions we need to be somewhat careful not to break existing optimization rules by creating optimization dead ends. This is particularly true of the load/store merging rules which contain lots of zero extensions and shifts. This CL does interfere with the store merging rules when an operand is shifted left before it is stored: binary.BigEndian.PutUint64(b, x << 1) This is unfortunate but it's not critical and somewhat complex so I plan to fix that in a follow up CL. file before after Δ % addr2line 4117446 4117282 -164 -0.004% api 4945184 4942752 -2432 -0.049% asm 4998079 4991891 -6188 -0.124% buildid 2685158 2684074 -1084 -0.040% cgo 4553732 4553394 -338 -0.007% compile 19294446 19245070 -49376 -0.256% cover 4897105 4891319 -5786 -0.118% dist 3544389 3542785 -1604 -0.045% doc 3926795 3927617 +822 +0.021% fix 3302958 3293868 -9090 -0.275% link 6546274 6543456 -2818 -0.043% nm 4102021 4100825 -1196 -0.029% objdump 4542431 4548483 +6052 +0.133% pack 2482465 2416389 -66076 -2.662% pprof 13366541 13363915 -2626 -0.020% test2json 2829007 2761515 -67492 -2.386% trace 10216164 10219684 +3520 +0.034% vet 6773956 6773572 -384 -0.006% total 107124151 106917891 -206260 -0.193% Change-Id: I7591cce41e06867ba10a745daae9333513062746 Reviewed-on: https://go-review.googlesource.com/c/go/+/233317 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Trust: Michael Munday <mike.munday@ibm.com>
2020-05-11 10:44:48 -06:00
// s390x:-"RISBGZ",-"AND",-"LOCGR"
// wasm:-"Select",-".*LtU"
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
return v >> s
}
panic("shift too large")
}
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
func rshGuarded64(v int64, s uint) int64 {
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
if s < 64 {
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
// riscv64:"SRA","OR","SLTIU"
cmd/compile: optimize shift pairs and masks on s390x Optimize combinations of left and right shifts by a constant value into a 'rotate then insert selected bits [into zero]' instruction. Use the same instruction for contiguous masks since it has some benefits over 'and immediate' (not restricted to 32-bits, does not overwrite source register). To keep the complexity of this change under control I've only implemented 64 bit operations for now. There are a lot more optimizations that can be done with this instruction family. However, since their function overlaps with other instructions we need to be somewhat careful not to break existing optimization rules by creating optimization dead ends. This is particularly true of the load/store merging rules which contain lots of zero extensions and shifts. This CL does interfere with the store merging rules when an operand is shifted left before it is stored: binary.BigEndian.PutUint64(b, x << 1) This is unfortunate but it's not critical and somewhat complex so I plan to fix that in a follow up CL. file before after Δ % addr2line 4117446 4117282 -164 -0.004% api 4945184 4942752 -2432 -0.049% asm 4998079 4991891 -6188 -0.124% buildid 2685158 2684074 -1084 -0.040% cgo 4553732 4553394 -338 -0.007% compile 19294446 19245070 -49376 -0.256% cover 4897105 4891319 -5786 -0.118% dist 3544389 3542785 -1604 -0.045% doc 3926795 3927617 +822 +0.021% fix 3302958 3293868 -9090 -0.275% link 6546274 6543456 -2818 -0.043% nm 4102021 4100825 -1196 -0.029% objdump 4542431 4548483 +6052 +0.133% pack 2482465 2416389 -66076 -2.662% pprof 13366541 13363915 -2626 -0.020% test2json 2829007 2761515 -67492 -2.386% trace 10216164 10219684 +3520 +0.034% vet 6773956 6773572 -384 -0.006% total 107124151 106917891 -206260 -0.193% Change-Id: I7591cce41e06867ba10a745daae9333513062746 Reviewed-on: https://go-review.googlesource.com/c/go/+/233317 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Trust: Michael Munday <mike.munday@ibm.com>
2020-05-11 10:44:48 -06:00
// s390x:-"RISBGZ",-"AND",-"LOCGR"
// wasm:-"Select",-".*LtU"
test/codegen: add shift tests for RISCV64 Add tests for shift by constant, masked shifts and bounded shifts. While here, sort tests by architecture and keep order of tests consistent (lsh, rshU, rsh). Change-Id: I512d64196f34df9cb2884e8c0f6adcf9dd88b0fc Reviewed-on: https://go-review.googlesource.com/c/go/+/351289 Trust: Joel Sing <joel@sing.id.au> Reviewed-by: Michael Munday <mike.munday@lowrisc.org> Reviewed-by: Cherry Mui <cherryyz@google.com> Run-TryBot: Cherry Mui <cherryyz@google.com>
2021-09-21 10:46:00 -06:00
return v >> s
cmd/compile: simplify shift lowering on s390x Use conditional moves instead of subtractions with borrow to handle saturation cases. This allows us to delete the SUBE/SUBEW ops and associated rules from the SSA backend. Using conditional moves also means we can detect when shift values are masked so I've added some new rules to constant fold the relevant comparisons and masking ops. Also use the new shiftIsBounded() function to avoid generating code to handle saturation cases where possible. Updates #25167 for s390x. Change-Id: Ief9991c91267c9151ce4c5ec07642abb4dcc1c0d Reviewed-on: https://go-review.googlesource.com/110070 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
2018-04-30 06:27:50 -06:00
}
panic("shift too large")
}
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
func checkUnneededTrunc(tab *[100000]uint32, d uint64, v uint32, h uint16, b byte) (uint32, uint64) {
// ppc64le:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
// ppc64:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
f := tab[byte(v)^b]
// ppc64le:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
// ppc64:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
f += tab[byte(v)&b]
// ppc64le:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
// ppc64:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
f += tab[byte(v)|b]
// ppc64le:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
// ppc64:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
f += tab[uint16(v)&h]
// ppc64le:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
// ppc64:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
f += tab[uint16(v)^h]
// ppc64le:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
// ppc64:-".*RLWINM",-".*RLDICR",".*CLRLSLDI"
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
f += tab[uint16(v)|h]
// ppc64le:-".*AND",-"RLDICR",".*CLRLSLDI"
// ppc64:-".*AND",-"RLDICR",".*CLRLSLDI"
f += tab[v&0xff]
// ppc64le:-".*AND",".*CLRLSLWI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
// ppc64:-".*AND",".*CLRLSLWI"
f += 2 * uint32(uint16(d))
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
// ppc64le:-".*AND",-"RLDICR",".*CLRLSLDI"
// ppc64:-".*AND",-"RLDICR",".*CLRLSLDI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
g := 2 * uint64(uint32(d))
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
return f, g
}
cmd/asm,cmd/compile,cmd/internal/obj/ppc64: add extswsli support on power9 This adds support for the extswsli instruction which combines extsw followed by a shift. New benchmark demonstrates the improvement: name old time/op new time/op delta ExtShift 1.34µs ± 0% 1.30µs ± 0% -3.15% (p=0.057 n=4+3) Change-Id: I21b410676fdf15d20e0cbbaa75d7c6dcd3bbb7b0 Reviewed-on: https://go-review.googlesource.com/c/go/+/257017 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <carlos.seo@gmail.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-09-23 09:06:39 -06:00
func checkCombinedShifts(v8 uint8, v16 uint16, v32 uint32, x32 int32, v64 uint64) (uint8, uint16, uint32, uint64, int64) {
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
// ppc64le:-"AND","CLRLSLWI"
// ppc64:-"AND","CLRLSLWI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
f := (v8 & 0xF) << 2
cmd/compile,cmd/internal/obj/ppc64: fix some shift rules due to a regression A recent change to improve shifts was generating some invalid cases when the rule was based on an AND. The extended mnemonics CLRLSLDI and CLRLSLWI only allow certain values for the operands and in the mask case those values were not being checked properly. This adds a check to those rules to verify that the 'b' and 'n' values used when an AND was part of the rule have correct values. There was a bug in some diag messages in asm9. The message expected 3 values but only provided 2. Those are corrected here also. The test/codegen/shift.go was updated to add a few more cases to check for the case mentioned here. Some of the comments that mention the order of operands in these extended mnemonics were wrong and those have been corrected. Fixes #41683. Change-Id: If5bb860acaa5051b9e0cd80784b2868b85898c31 Reviewed-on: https://go-review.googlesource.com/c/go/+/258138 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Paul Murphy <murp@ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-09-28 16:20:12 -06:00
// ppc64le:"CLRLSLWI"
// ppc64:"CLRLSLWI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
f += byte(v16) << 3
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
// ppc64le:-"AND","CLRLSLWI"
// ppc64:-"AND","CLRLSLWI"
g := (v16 & 0xFF) << 3
// ppc64le:-"AND","CLRLSLWI"
// ppc64:-"AND","CLRLSLWI"
h := (v32 & 0xFFFFF) << 2
cmd/compile,cmd/internal/obj/ppc64: fix some shift rules due to a regression A recent change to improve shifts was generating some invalid cases when the rule was based on an AND. The extended mnemonics CLRLSLDI and CLRLSLWI only allow certain values for the operands and in the mask case those values were not being checked properly. This adds a check to those rules to verify that the 'b' and 'n' values used when an AND was part of the rule have correct values. There was a bug in some diag messages in asm9. The message expected 3 values but only provided 2. Those are corrected here also. The test/codegen/shift.go was updated to add a few more cases to check for the case mentioned here. Some of the comments that mention the order of operands in these extended mnemonics were wrong and those have been corrected. Fixes #41683. Change-Id: If5bb860acaa5051b9e0cd80784b2868b85898c31 Reviewed-on: https://go-review.googlesource.com/c/go/+/258138 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Paul Murphy <murp@ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-09-28 16:20:12 -06:00
// ppc64le:"CLRLSLDI"
// ppc64:"CLRLSLDI"
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
i := (v64 & 0xFFFFFFFF) << 5
cmd/compile,cmd/internal/obj/ppc64: fix some shift rules due to a regression A recent change to improve shifts was generating some invalid cases when the rule was based on an AND. The extended mnemonics CLRLSLDI and CLRLSLWI only allow certain values for the operands and in the mask case those values were not being checked properly. This adds a check to those rules to verify that the 'b' and 'n' values used when an AND was part of the rule have correct values. There was a bug in some diag messages in asm9. The message expected 3 values but only provided 2. Those are corrected here also. The test/codegen/shift.go was updated to add a few more cases to check for the case mentioned here. Some of the comments that mention the order of operands in these extended mnemonics were wrong and those have been corrected. Fixes #41683. Change-Id: If5bb860acaa5051b9e0cd80784b2868b85898c31 Reviewed-on: https://go-review.googlesource.com/c/go/+/258138 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Paul Murphy <murp@ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-09-28 16:20:12 -06:00
// ppc64le:-"CLRLSLDI"
// ppc64:-"CLRLSLDI"
i += (v64 & 0xFFFFFFF) << 38
// ppc64le/power9:-"CLRLSLDI"
// ppc64/power9:-"CLRLSLDI"
i += (v64 & 0xFFFF00) << 10
cmd/asm,cmd/compile,cmd/internal/obj/ppc64: add extswsli support on power9 This adds support for the extswsli instruction which combines extsw followed by a shift. New benchmark demonstrates the improvement: name old time/op new time/op delta ExtShift 1.34µs ± 0% 1.30µs ± 0% -3.15% (p=0.057 n=4+3) Change-Id: I21b410676fdf15d20e0cbbaa75d7c6dcd3bbb7b0 Reviewed-on: https://go-review.googlesource.com/c/go/+/257017 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <carlos.seo@gmail.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-09-23 09:06:39 -06:00
// ppc64le/power9:-"SLD","EXTSWSLI"
// ppc64/power9:-"SLD","EXTSWSLI"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
j := int64(x32+32) * 8
cmd/asm,cmd/compile,cmd/internal/obj/ppc64: add extswsli support on power9 This adds support for the extswsli instruction which combines extsw followed by a shift. New benchmark demonstrates the improvement: name old time/op new time/op delta ExtShift 1.34µs ± 0% 1.30µs ± 0% -3.15% (p=0.057 n=4+3) Change-Id: I21b410676fdf15d20e0cbbaa75d7c6dcd3bbb7b0 Reviewed-on: https://go-review.googlesource.com/c/go/+/257017 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <carlos.seo@gmail.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-09-23 09:06:39 -06:00
return f, g, h, i, j
cmd/compile: use combined shifts to improve array addressing on ppc64x This change adds rules to find pairs of instructions that can be combined into a single shifts. These instruction sequences are common in array addressing within loops. Improvements can be seen in many crypto packages and the hash packages. These are based on the extended mnemonics found in the ISA sections C.8.1 and C.8.2. Some rules in PPC64.rules were moved because the ordering prevented some matching. The following results were generated on power9. hash/crc32: CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41% CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50% CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46% CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80% CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27% CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15% CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22% CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79% CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56% CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53% crypto/rc4: RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1) RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1) RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1) crypto/sha1: Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1) Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1) Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1) Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1) There are other improvements found in golang.org/x/crypto which are all in the range of 5-15%. Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c Reviewed-on: https://go-review.googlesource.com/c/go/+/252097 Trust: Lynn Boger <laboger@linux.vnet.ibm.com> Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
2020-08-31 07:43:40 -06:00
}
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
func checkWidenAfterShift(v int64, u uint64) (int64, uint64) {
// ppc64le:-".*MOVW"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
f := int32(v >> 32)
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
// ppc64le:".*MOVW"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
f += int32(v >> 31)
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
// ppc64le:-".*MOVH"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
g := int16(v >> 48)
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
// ppc64le:".*MOVH"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
g += int16(v >> 30)
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
// ppc64le:-".*MOVH"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
g += int16(f >> 16)
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
// ppc64le:-".*MOVB"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
h := int8(v >> 56)
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
// ppc64le:".*MOVB"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
h += int8(v >> 28)
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
// ppc64le:-".*MOVB"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
h += int8(f >> 24)
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
// ppc64le:".*MOVB"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
h += int8(f >> 16)
return int64(h), uint64(g)
}
func checkShiftAndMask32(v []uint32) {
i := 0
cmd/asm,cmd/compile: support 5 operand RLWNM/RLWMI on ppc64 These instructions are actually 5 argument opcodes as specified by the ISA. Prior to this patch, the MB and ME arguments were merged into a single bitmask operand to workaround the limitations of the ppc64 assembler backend. This limitation no longer exists. Thus, we can pass operands for these opcodes without having to merge the MB and ME arguments in the assembler frontend or compiler backend. Likewise, support for 4 operand variants is unchanged. Change-Id: Ib086774f3581edeaadfd2190d652aaaa8a90daeb Reviewed-on: https://go-review.googlesource.com/c/go/+/298750 Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Carlos Eduardo Seo <carlos.seo@linaro.org>
2021-01-05 15:44:43 -07:00
// ppc64le: "RLWNM\t[$]24, R[0-9]+, [$]12, [$]19, R[0-9]+"
// ppc64: "RLWNM\t[$]24, R[0-9]+, [$]12, [$]19, R[0-9]+"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
v[i] = (v[i] & 0xFF00000) >> 8
i++
cmd/asm,cmd/compile: support 5 operand RLWNM/RLWMI on ppc64 These instructions are actually 5 argument opcodes as specified by the ISA. Prior to this patch, the MB and ME arguments were merged into a single bitmask operand to workaround the limitations of the ppc64 assembler backend. This limitation no longer exists. Thus, we can pass operands for these opcodes without having to merge the MB and ME arguments in the assembler frontend or compiler backend. Likewise, support for 4 operand variants is unchanged. Change-Id: Ib086774f3581edeaadfd2190d652aaaa8a90daeb Reviewed-on: https://go-review.googlesource.com/c/go/+/298750 Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Carlos Eduardo Seo <carlos.seo@linaro.org>
2021-01-05 15:44:43 -07:00
// ppc64le: "RLWNM\t[$]26, R[0-9]+, [$]22, [$]29, R[0-9]+"
// ppc64: "RLWNM\t[$]26, R[0-9]+, [$]22, [$]29, R[0-9]+"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
v[i] = (v[i] & 0xFF00) >> 6
i++
// ppc64le: "MOVW\tR0"
// ppc64: "MOVW\tR0"
v[i] = (v[i] & 0xFF) >> 8
i++
// ppc64le: "MOVW\tR0"
// ppc64: "MOVW\tR0"
v[i] = (v[i] & 0xF000000) >> 28
i++
cmd/asm,cmd/compile: support 5 operand RLWNM/RLWMI on ppc64 These instructions are actually 5 argument opcodes as specified by the ISA. Prior to this patch, the MB and ME arguments were merged into a single bitmask operand to workaround the limitations of the ppc64 assembler backend. This limitation no longer exists. Thus, we can pass operands for these opcodes without having to merge the MB and ME arguments in the assembler frontend or compiler backend. Likewise, support for 4 operand variants is unchanged. Change-Id: Ib086774f3581edeaadfd2190d652aaaa8a90daeb Reviewed-on: https://go-review.googlesource.com/c/go/+/298750 Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Carlos Eduardo Seo <carlos.seo@linaro.org>
2021-01-05 15:44:43 -07:00
// ppc64le: "RLWNM\t[$]26, R[0-9]+, [$]24, [$]31, R[0-9]+"
// ppc64: "RLWNM\t[$]26, R[0-9]+, [$]24, [$]31, R[0-9]+"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
v[i] = (v[i] >> 6) & 0xFF
i++
cmd/asm,cmd/compile: support 5 operand RLWNM/RLWMI on ppc64 These instructions are actually 5 argument opcodes as specified by the ISA. Prior to this patch, the MB and ME arguments were merged into a single bitmask operand to workaround the limitations of the ppc64 assembler backend. This limitation no longer exists. Thus, we can pass operands for these opcodes without having to merge the MB and ME arguments in the assembler frontend or compiler backend. Likewise, support for 4 operand variants is unchanged. Change-Id: Ib086774f3581edeaadfd2190d652aaaa8a90daeb Reviewed-on: https://go-review.googlesource.com/c/go/+/298750 Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Carlos Eduardo Seo <carlos.seo@linaro.org>
2021-01-05 15:44:43 -07:00
// ppc64le: "RLWNM\t[$]26, R[0-9]+, [$]12, [$]19, R[0-9]+"
// ppc64: "RLWNM\t[$]26, R[0-9]+, [$]12, [$]19, R[0-9]+"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
v[i] = (v[i] >> 6) & 0xFF000
i++
// ppc64le: "MOVW\tR0"
// ppc64: "MOVW\tR0"
v[i] = (v[i] >> 20) & 0xFF000
i++
// ppc64le: "MOVW\tR0"
// ppc64: "MOVW\tR0"
v[i] = (v[i] >> 24) & 0xFF00
i++
}
func checkMergedShifts32(a [256]uint32, b [256]uint64, u uint32, v uint32) {
cmd/asm,cmd/compile: support 5 operand RLWNM/RLWMI on ppc64 These instructions are actually 5 argument opcodes as specified by the ISA. Prior to this patch, the MB and ME arguments were merged into a single bitmask operand to workaround the limitations of the ppc64 assembler backend. This limitation no longer exists. Thus, we can pass operands for these opcodes without having to merge the MB and ME arguments in the assembler frontend or compiler backend. Likewise, support for 4 operand variants is unchanged. Change-Id: Ib086774f3581edeaadfd2190d652aaaa8a90daeb Reviewed-on: https://go-review.googlesource.com/c/go/+/298750 Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Carlos Eduardo Seo <carlos.seo@linaro.org>
2021-01-05 15:44:43 -07:00
//ppc64le: -"CLRLSLDI", "RLWNM\t[$]10, R[0-9]+, [$]22, [$]29, R[0-9]+"
//ppc64: -"CLRLSLDI", "RLWNM\t[$]10, R[0-9]+, [$]22, [$]29, R[0-9]+"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
a[0] = a[uint8(v>>24)]
cmd/asm,cmd/compile: support 5 operand RLWNM/RLWMI on ppc64 These instructions are actually 5 argument opcodes as specified by the ISA. Prior to this patch, the MB and ME arguments were merged into a single bitmask operand to workaround the limitations of the ppc64 assembler backend. This limitation no longer exists. Thus, we can pass operands for these opcodes without having to merge the MB and ME arguments in the assembler frontend or compiler backend. Likewise, support for 4 operand variants is unchanged. Change-Id: Ib086774f3581edeaadfd2190d652aaaa8a90daeb Reviewed-on: https://go-review.googlesource.com/c/go/+/298750 Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Carlos Eduardo Seo <carlos.seo@linaro.org>
2021-01-05 15:44:43 -07:00
//ppc64le: -"CLRLSLDI", "RLWNM\t[$]11, R[0-9]+, [$]21, [$]28, R[0-9]+"
//ppc64: -"CLRLSLDI", "RLWNM\t[$]11, R[0-9]+, [$]21, [$]28, R[0-9]+"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
b[0] = b[uint8(v>>24)]
cmd/asm,cmd/compile: support 5 operand RLWNM/RLWMI on ppc64 These instructions are actually 5 argument opcodes as specified by the ISA. Prior to this patch, the MB and ME arguments were merged into a single bitmask operand to workaround the limitations of the ppc64 assembler backend. This limitation no longer exists. Thus, we can pass operands for these opcodes without having to merge the MB and ME arguments in the assembler frontend or compiler backend. Likewise, support for 4 operand variants is unchanged. Change-Id: Ib086774f3581edeaadfd2190d652aaaa8a90daeb Reviewed-on: https://go-review.googlesource.com/c/go/+/298750 Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Carlos Eduardo Seo <carlos.seo@linaro.org>
2021-01-05 15:44:43 -07:00
//ppc64le: -"CLRLSLDI", "RLWNM\t[$]15, R[0-9]+, [$]21, [$]28, R[0-9]+"
//ppc64: -"CLRLSLDI", "RLWNM\t[$]15, R[0-9]+, [$]21, [$]28, R[0-9]+"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
b[1] = b[(v>>20)&0xFF]
cmd/asm,cmd/compile: support 5 operand RLWNM/RLWMI on ppc64 These instructions are actually 5 argument opcodes as specified by the ISA. Prior to this patch, the MB and ME arguments were merged into a single bitmask operand to workaround the limitations of the ppc64 assembler backend. This limitation no longer exists. Thus, we can pass operands for these opcodes without having to merge the MB and ME arguments in the assembler frontend or compiler backend. Likewise, support for 4 operand variants is unchanged. Change-Id: Ib086774f3581edeaadfd2190d652aaaa8a90daeb Reviewed-on: https://go-review.googlesource.com/c/go/+/298750 Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Carlos Eduardo Seo <carlos.seo@linaro.org>
2021-01-05 15:44:43 -07:00
//ppc64le: -"SLD", "RLWNM\t[$]10, R[0-9]+, [$]22, [$]28, R[0-9]+"
//ppc64: -"SLD", "RLWNM\t[$]10, R[0-9]+, [$]22, [$]28, R[0-9]+"
cmd/compile: combine more 32 bit shift and mask operations on ppc64 Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
2020-10-23 11:12:34 -06:00
b[2] = b[v>>25]
cmd/compile: add rules to eliminate unnecessary signed shifts This change to the rules removes some unnecessary signed shifts that appear in the math/rand functions. Existing rules did not cover some of the signed cases. A little improvement seen in math/rand due to removing 1 of 2 instructions generated for Int31n, which is inlined quite a bit. Intn1000 46.9ns ± 0% 45.5ns ± 0% -2.99% (p=1.000 n=1+1) Int63n1000 33.5ns ± 0% 32.8ns ± 0% -2.09% (p=1.000 n=1+1) Int31n1000 32.7ns ± 0% 32.6ns ± 0% -0.31% (p=1.000 n=1+1) Float32 32.7ns ± 0% 30.3ns ± 0% -7.34% (p=1.000 n=1+1) Float64 21.7ns ± 0% 20.9ns ± 0% -3.69% (p=1.000 n=1+1) Perm3 205ns ± 0% 202ns ± 0% -1.46% (p=1.000 n=1+1) Perm30 1.71µs ± 0% 1.68µs ± 0% -1.35% (p=1.000 n=1+1) Perm30ViaShuffle 1.65µs ± 0% 1.65µs ± 0% -0.30% (p=1.000 n=1+1) ShuffleOverhead 2.83µs ± 0% 2.83µs ± 0% -0.07% (p=1.000 n=1+1) Read3 18.7ns ± 0% 16.1ns ± 0% -13.90% (p=1.000 n=1+1) Read64 126ns ± 0% 124ns ± 0% -1.59% (p=1.000 n=1+1) Read1000 1.75µs ± 0% 1.63µs ± 0% -7.08% (p=1.000 n=1+1) Change-Id: I11502dfca7d65aafc76749a8d713e9e50c24a858 Reviewed-on: https://go-review.googlesource.com/c/go/+/225917 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Cherry Zhang <cherryyz@google.com>
2020-03-26 14:01:40 -06:00
}
cmd/compile: optimize multi-register shifts on amd64 amd64 can shift in bits from another register instead of filling with 0/1. This pattern is helpful when implementing 128 bit shifts or arbitrary length shifts. In the standard library, it shows up in pure Go math/big. Benchmarks results on amd64 with -tags=math_big_pure_go. name old time/op new time/op delta NonZeroShifts/1/shrVU-8 4.45ns ± 3% 4.39ns ± 1% -1.28% (p=0.000 n=30+27) NonZeroShifts/1/shlVU-8 4.13ns ± 4% 4.10ns ± 2% ~ (p=0.254 n=29+28) NonZeroShifts/2/shrVU-8 5.55ns ± 1% 5.63ns ± 2% +1.42% (p=0.000 n=28+29) NonZeroShifts/2/shlVU-8 5.70ns ± 2% 5.14ns ± 1% -9.82% (p=0.000 n=29+28) NonZeroShifts/3/shrVU-8 6.79ns ± 2% 6.35ns ± 2% -6.46% (p=0.000 n=28+29) NonZeroShifts/3/shlVU-8 6.69ns ± 1% 6.25ns ± 1% -6.60% (p=0.000 n=28+27) NonZeroShifts/4/shrVU-8 7.79ns ± 2% 7.06ns ± 2% -9.48% (p=0.000 n=30+30) NonZeroShifts/4/shlVU-8 7.82ns ± 1% 7.24ns ± 1% -7.37% (p=0.000 n=28+29) NonZeroShifts/5/shrVU-8 8.90ns ± 3% 7.93ns ± 1% -10.84% (p=0.000 n=29+26) NonZeroShifts/5/shlVU-8 8.68ns ± 1% 7.92ns ± 1% -8.76% (p=0.000 n=29+29) NonZeroShifts/10/shrVU-8 14.4ns ± 1% 12.3ns ± 2% -14.79% (p=0.000 n=28+29) NonZeroShifts/10/shlVU-8 14.1ns ± 1% 11.9ns ± 2% -15.55% (p=0.000 n=28+27) NonZeroShifts/100/shrVU-8 118ns ± 1% 96ns ± 3% -18.82% (p=0.000 n=30+29) NonZeroShifts/100/shlVU-8 120ns ± 2% 98ns ± 2% -18.46% (p=0.000 n=29+28) NonZeroShifts/1000/shrVU-8 1.10µs ± 1% 0.88µs ± 2% -19.63% (p=0.000 n=29+30) NonZeroShifts/1000/shlVU-8 1.10µs ± 2% 0.88µs ± 2% -20.28% (p=0.000 n=29+28) NonZeroShifts/10000/shrVU-8 10.9µs ± 1% 8.7µs ± 1% -19.78% (p=0.000 n=28+27) NonZeroShifts/10000/shlVU-8 10.9µs ± 2% 8.7µs ± 1% -19.64% (p=0.000 n=29+27) NonZeroShifts/100000/shrVU-8 111µs ± 2% 90µs ± 2% -19.39% (p=0.000 n=28+29) NonZeroShifts/100000/shlVU-8 113µs ± 2% 90µs ± 2% -20.43% (p=0.000 n=30+27) The assembly version is still faster, unfortunately, but the gap is narrowing. Speedup from pure Go to assembly: name old time/op new time/op delta NonZeroShifts/1/shrVU-8 4.39ns ± 1% 3.45ns ± 2% -21.36% (p=0.000 n=27+29) NonZeroShifts/1/shlVU-8 4.10ns ± 2% 3.47ns ± 3% -15.42% (p=0.000 n=28+30) NonZeroShifts/2/shrVU-8 5.63ns ± 2% 3.97ns ± 0% -29.40% (p=0.000 n=29+25) NonZeroShifts/2/shlVU-8 5.14ns ± 1% 3.77ns ± 2% -26.65% (p=0.000 n=28+26) NonZeroShifts/3/shrVU-8 6.35ns ± 2% 4.79ns ± 2% -24.52% (p=0.000 n=29+29) NonZeroShifts/3/shlVU-8 6.25ns ± 1% 4.42ns ± 1% -29.29% (p=0.000 n=27+26) NonZeroShifts/4/shrVU-8 7.06ns ± 2% 5.64ns ± 1% -20.05% (p=0.000 n=30+29) NonZeroShifts/4/shlVU-8 7.24ns ± 1% 5.34ns ± 2% -26.23% (p=0.000 n=29+29) NonZeroShifts/5/shrVU-8 7.93ns ± 1% 6.56ns ± 2% -17.26% (p=0.000 n=26+30) NonZeroShifts/5/shlVU-8 7.92ns ± 1% 6.27ns ± 1% -20.79% (p=0.000 n=29+25) NonZeroShifts/10/shrVU-8 12.3ns ± 2% 10.2ns ± 2% -17.21% (p=0.000 n=29+29) NonZeroShifts/10/shlVU-8 11.9ns ± 2% 10.5ns ± 2% -12.45% (p=0.000 n=27+29) NonZeroShifts/100/shrVU-8 95.9ns ± 3% 77.7ns ± 1% -19.00% (p=0.000 n=29+30) NonZeroShifts/100/shlVU-8 97.5ns ± 2% 66.8ns ± 2% -31.47% (p=0.000 n=28+30) NonZeroShifts/1000/shrVU-8 884ns ± 2% 705ns ± 1% -20.17% (p=0.000 n=30+28) NonZeroShifts/1000/shlVU-8 880ns ± 2% 590ns ± 1% -32.96% (p=0.000 n=28+25) NonZeroShifts/10000/shrVU-8 8.74µs ± 1% 7.34µs ± 3% -15.94% (p=0.000 n=27+30) NonZeroShifts/10000/shlVU-8 8.73µs ± 1% 6.00µs ± 1% -31.25% (p=0.000 n=27+28) NonZeroShifts/100000/shrVU-8 89.6µs ± 2% 75.5µs ± 2% -15.80% (p=0.000 n=29+29) NonZeroShifts/100000/shlVU-8 89.6µs ± 2% 68.0µs ± 3% -24.09% (p=0.000 n=27+30) Change-Id: I18f58d8f5513d737d9cdf09b8f9d14011ffe3958 Reviewed-on: https://go-review.googlesource.com/c/go/+/297050 Trust: Josh Bleecher Snyder <josharian@gmail.com> Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org>
2021-01-07 20:25:05 -07:00
// 128 bit shifts
func check128bitShifts(x, y uint64, bits uint) (uint64, uint64) {
s := bits & 63
ŝ := (64 - bits) & 63
// check that the shift operation has two commas (three operands)
// amd64:"SHRQ.*,.*,"
shr := x>>s | y<<ŝ
// amd64:"SHLQ.*,.*,"
shl := x<<s | y>>ŝ
return shr, shl
}
Copy Permalink