bytes: add optimized countByte for amd64
Use SSE/AVX2 when counting a single byte.
Inspired from runtime indexbyte implementation.
Benchmark against previous implementation, where
1 byte in every 8 is the one we are looking for:
* On a machine without AVX2
name old time/op new time/op delta
CountSingle/10-4 61.8ns ±10% 15.6ns ±11% -74.83% (p=0.000 n=10+10)
CountSingle/32-4 100ns ± 4% 17ns ±10% -82.54% (p=0.000 n=10+9)
CountSingle/4K-4 9.66µs ± 3% 0.37µs ± 6% -96.21% (p=0.000 n=10+10)
CountSingle/4M-4 11.0ms ± 6% 0.4ms ± 4% -96.04% (p=0.000 n=10+10)
CountSingle/64M-4 194ms ± 8% 8ms ± 2% -95.64% (p=0.000 n=10+10)
name old speed new speed delta
CountSingle/10-4 162MB/s ±10% 645MB/s ±10% +297.00% (p=0.000 n=10+10)
CountSingle/32-4 321MB/s ± 5% 1844MB/s ± 9% +474.79% (p=0.000 n=10+9)
CountSingle/4K-4 424MB/s ± 3% 11169MB/s ± 6% +2533.10% (p=0.000 n=10+10)
CountSingle/4M-4 381MB/s ± 7% 9609MB/s ± 4% +2421.88% (p=0.000 n=10+10)
CountSingle/64M-4 346MB/s ± 7% 7924MB/s ± 2% +2188.78% (p=0.000 n=10+10)
* On a machine with AVX2
name old time/op new time/op delta
CountSingle/10-8 37.1ns ± 3% 8.2ns ± 1% -77.80% (p=0.000 n=10+10)
CountSingle/32-8 66.1ns ± 3% 9.8ns ± 2% -85.23% (p=0.000 n=10+10)
CountSingle/4K-8 7.36µs ± 3% 0.11µs ± 1% -98.54% (p=0.000 n=10+10)
CountSingle/4M-8 7.46ms ± 2% 0.15ms ± 2% -97.95% (p=0.000 n=10+9)
CountSingle/64M-8 124ms ± 2% 6ms ± 4% -95.09% (p=0.000 n=10+10)
name old speed new speed delta
CountSingle/10-8 269MB/s ± 3% 1213MB/s ± 1% +350.32% (p=0.000 n=10+10)
CountSingle/32-8 484MB/s ± 4% 3277MB/s ± 2% +576.66% (p=0.000 n=10+10)
CountSingle/4K-8 556MB/s ± 3% 37933MB/s ± 1% +6718.36% (p=0.000 n=10+10)
CountSingle/4M-8 562MB/s ± 2% 27444MB/s ± 3% +4783.43% (p=0.000 n=10+9)
CountSingle/64M-8 543MB/s ± 2% 11054MB/s ± 3% +1935.81% (p=0.000 n=10+10)
Fixes #19411
Change-Id: Ieaf20b1fabccabe767c55c66e242e86f3617f883
Reviewed-on: https://go-review.googlesource.com/38258
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
diff --git a/src/bytes/bytes_amd64.go b/src/bytes/bytes_amd64.go
index 6affff6..5b42f27 100644
--- a/src/bytes/bytes_amd64.go
+++ b/src/bytes/bytes_amd64.go
@@ -10,6 +10,7 @@
// indexShortStr requires 2 <= len(c) <= shortStringLen
func indexShortStr(s, c []byte) int // ../runtime/asm_$GOARCH.s
func supportAVX2() bool // ../runtime/asm_$GOARCH.s
+func supportPOPCNT() bool // ../runtime/asm_$GOARCH.s
var shortStringLen int
@@ -94,6 +95,18 @@
return -1
}
+// Special case for when we must count occurences of a single byte.
+func countByte(s []byte, c byte) int
+
+// Count counts the number of non-overlapping instances of sep in s.
+// If sep is an empty slice, Count returns 1 + the number of Unicode code points in s.
+func Count(s, sep []byte) int {
+ if len(sep) == 1 && supportPOPCNT() {
+ return countByte(s, sep[0])
+ }
+ return countGeneric(s, sep)
+}
+
// primeRK is the prime base used in Rabin-Karp algorithm.
const primeRK = 16777619
