]>
Cypherpunks repositories - gostls13.git/commit
cmd/compile: Implement LoweredZeroLoop with LSX Instruction on loong64
goos: linux
goarch: loong64
pkg: runtime
cpu: Loongson-3A6000 @ 2500.00MHz
| old.txt | new.txt |
| sec/op | sec/op vs base |
ClearFat256 6.406n ± 0% 3.329n ± 1% -48.03% (p=0.000 n=10)
ClearFat512 12.810n ± 0% 7.607n ± 0% -40.62% (p=0.000 n=10)
ClearFat1024 25.62n ± 0% 14.01n ± 0% -45.32% (p=0.000 n=10)
ClearFat1032 26.02n ± 0% 14.28n ± 0% -45.14% (p=0.000 n=10)
ClearFat1040 26.02n ± 0% 14.41n ± 0% -44.62% (p=0.000 n=10)
MemclrKnownSize192 4.804n ± 0% 2.827n ± 0% -41.15% (p=0.000 n=10)
MemclrKnownSize248 6.561n ± 0% 4.371n ± 0% -33.38% (p=0.000 n=10)
MemclrKnownSize256 6.406n ± 0% 3.335n ± 0% -47.94% (p=0.000 n=10)
geomean 11.41n 6.453n -43.45%
goos: linux
goarch: loong64
pkg: runtime
cpu: Loongson-3C5000 @ 2200.00MHz
| old.txt | new.txt |
| sec/op | sec/op vs base |
ClearFat256 14.570n ± 0% 7.284n ± 0% -50.01% (p=0.000 n=10)
ClearFat512 29.13n ± 0% 14.57n ± 0% -49.98% (p=0.000 n=10)
ClearFat1024 58.26n ± 0% 29.15n ± 0% -49.97% (p=0.000 n=10)
ClearFat1032 58.73n ± 0% 29.15n ± 0% -50.36% (p=0.000 n=10)
ClearFat1040 59.18n ± 0% 29.26n ± 0% -50.56% (p=0.000 n=10)
MemclrKnownSize192 10.930n ± 0% 5.466n ± 0% -49.99% (p=0.000 n=10)
MemclrKnownSize248 14.110n ± 0% 6.772n ± 0% -52.01% (p=0.000 n=10)
MemclrKnownSize256 14.570n ± 0% 7.285n ± 0% -50.00% (p=0.000 n=10)
geomean 25.75n 12.78n -50.36%
Change-Id: I88d7b6ae2f6fc3f095979f24fb83ff42a9d2d42e
Reviewed-on: https://go-review.googlesource.com/c/go/+/720940
Reviewed-by: Meidan Li <limeidan@loongson.cn>
Reviewed-by: Mark Freeman <markfreeman@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: sophie zhao <zhaoxiaolin@loongson.cn>
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Keith Randall <khr@google.com>