diff options
author | Meng Zhuo <mzh@golangcn.org> | 2021-06-22 11:20:03 +0000 |
---|---|---|
committer | Meng Zhuo <mzh@golangcn.org> | 2021-08-16 13:50:11 +0000 |
commit | efd206eb40a59e955c12653b1720026244e6c667 (patch) | |
tree | aaed5d70ae2fb0ac1f16a0cfe2f24678a48592f5 /src/cmd/compile/internal/ssa/opGen.go | |
parent | 7b7d7d7818dfc1db22930be9333e8cc9f8c7f68c (diff) | |
download | go-efd206eb40a59e955c12653b1720026244e6c667.tar.gz go-efd206eb40a59e955c12653b1720026244e6c667.zip |
cmd/compile: intrinsify Mul64 on riscv64
According to RISCV instruction set manual v2.2 Sec 6.1
MULHU followed by MUL will be fused into one multiply by microarchitecture
Benchstat on Hifive unmatched:
name old time/op new time/op delta
Hash8Bytes 245ns ± 3% 186ns ± 4% -23.99% (p=0.000 n=10+10)
Hash320Bytes 1.94µs ± 1% 1.31µs ± 1% -32.38% (p=0.000 n=9+10)
Hash1K 5.84µs ± 0% 3.84µs ± 0% -34.20% (p=0.000 n=10+9)
Hash8K 45.3µs ± 0% 29.4µs ± 0% -35.04% (p=0.000 n=10+10)
name old speed new speed delta
Hash8Bytes 32.7MB/s ± 3% 43.0MB/s ± 4% +31.61% (p=0.000 n=10+10)
Hash320Bytes 165MB/s ± 1% 244MB/s ± 1% +47.88% (p=0.000 n=9+10)
Hash1K 175MB/s ± 0% 266MB/s ± 0% +51.98% (p=0.000 n=10+9)
Hash8K 181MB/s ± 0% 279MB/s ± 0% +53.94% (p=0.000 n=10+10)
Change-Id: I3561495d02a4a0ad8578e9b9819bf0a4eaca5d12
Reviewed-on: https://go-review.googlesource.com/c/go/+/329970
Reviewed-by: Joel Sing <joel@sing.id.au>
Run-TryBot: Joel Sing <joel@sing.id.au>
TryBot-Result: Go Bot <gobot@golang.org>
Trust: Meng Zhuo <mzh@golangcn.org>
Diffstat (limited to 'src/cmd/compile/internal/ssa/opGen.go')
-rw-r--r-- | src/cmd/compile/internal/ssa/opGen.go | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/src/cmd/compile/internal/ssa/opGen.go b/src/cmd/compile/internal/ssa/opGen.go index df15c2edda..7893ce837e 100644 --- a/src/cmd/compile/internal/ssa/opGen.go +++ b/src/cmd/compile/internal/ssa/opGen.go @@ -2069,6 +2069,7 @@ const ( OpRISCV64MULW OpRISCV64MULH OpRISCV64MULHU + OpRISCV64LoweredMuluhilo OpRISCV64DIV OpRISCV64DIVU OpRISCV64DIVW @@ -27604,6 +27605,21 @@ var opcodeTable = [...]opInfo{ }, }, { + name: "LoweredMuluhilo", + argLen: 2, + resultNotInArgs: true, + reg: regInfo{ + inputs: []inputInfo{ + {0, 1006632948}, // X3 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14 X15 X16 X17 X18 X19 X20 X21 X22 X23 X24 X25 X26 X28 X29 X30 + {1, 1006632948}, // X3 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14 X15 X16 X17 X18 X19 X20 X21 X22 X23 X24 X25 X26 X28 X29 X30 + }, + outputs: []outputInfo{ + {0, 1006632948}, // X3 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14 X15 X16 X17 X18 X19 X20 X21 X22 X23 X24 X25 X26 X28 X29 X30 + {1, 1006632948}, // X3 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14 X15 X16 X17 X18 X19 X20 X21 X22 X23 X24 X25 X26 X28 X29 X30 + }, + }, + }, + { name: "DIV", argLen: 2, asm: riscv.ADIV, |