internal/bytealg: add assembly implementation of Count/CountString on arm

Simple single-byte loop count for now, to be further improved in future
CLs.

Benchmark on linux/arm:

name               old time/op    new time/op     delta
CountSingle/10-4      122ns ± 0%       87ns ± 1%  -28.41%  (p=0.000 n=7+10)
CountSingle/32-4      242ns ± 0%      174ns ± 1%  -28.25%  (p=0.000 n=10+10)
CountSingle/4K-4     24.2µs ± 1%     15.6µs ± 1%  -35.42%  (p=0.000 n=10+10)
CountSingle/4M-4     29.6ms ± 1%     21.3ms ± 1%  -28.09%  (p=0.000 n=10+9)
CountSingle/64M-4     562ms ± 0%      414ms ± 1%  -26.23%  (p=0.000 n=8+10)

name               old speed      new speed       delta
CountSingle/10-4   81.7MB/s ± 1%  114.5MB/s ± 1%  +40.07%  (p=0.000 n=10+10)
CountSingle/32-4    132MB/s ± 0%    184MB/s ± 1%  +39.39%  (p=0.000 n=10+9)
CountSingle/4K-4    170MB/s ± 1%    263MB/s ± 1%  +54.86%  (p=0.000 n=10+10)
CountSingle/4M-4    142MB/s ± 1%    197MB/s ± 1%  +39.07%  (p=0.000 n=10+9)
CountSingle/64M-4   119MB/s ± 0%    162MB/s ± 1%  +35.55%  (p=0.000 n=8+10)

Updates #29001

Change-Id: I42a268215a62044286ec32b548d8e4b86b9570ee
Reviewed-on: https://go-review.googlesource.com/c/go/+/168319
Run-TryBot: Tobias Klauser <tobias.klauser@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>

diff --git a/src/internal/bytealg/count_arm.s b/src/internal/bytealg/count_arm.s
new file mode 100644 (file)
index 0000000..f704ea0
--- /dev/null
+++ b/src/internal/bytealg/count_arm.s
@@ -0,0 +1,43 @@
+// Copyright 2019 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.
+
+#include "go_asm.h"
+#include "textflag.h"
+
+TEXT ·Count(SB),NOSPLIT,$0-20
+       MOVW    b_base+0(FP), R0
+       MOVW    b_len+4(FP), R1
+       MOVBU   c+12(FP), R2
+       MOVW    $ret+16(FP), R7
+       B       countbytebody<>(SB)
+
+TEXT ·CountString(SB),NOSPLIT,$0-16
+       MOVW    s_base+0(FP), R0
+       MOVW    s_len+4(FP), R1
+       MOVBU   c+8(FP), R2
+       MOVW    $ret+12(FP), R7
+       B       countbytebody<>(SB)
+
+// Input:
+// R0: data
+// R1: data length
+// R2: byte to find
+// R7: address to put result
+//
+// On exit:
+// R4 and R8 are clobbered
+TEXT countbytebody<>(SB),NOSPLIT,$0
+       MOVW    $0, R8  // R8 = count of byte to search
+       CMP     $0, R1
+       B.EQ    done    // short path to handle 0-byte case
+       ADD     R0, R1  // R1 is the end of the range
+byte_loop:
+       MOVBU.P 1(R0), R4
+       CMP     R4, R2
+       ADD.EQ  $1, R8
+       CMP     R0, R1
+       B.NE    byte_loop
+done:
+       MOVW    R8, (R7)
+       RET

diff --git a/src/internal/bytealg/count_generic.go b/src/internal/bytealg/count_generic.go
index e24b2b7fa076f34ee8f529e0eb8344ef6d677a2e..13759ad496c8d45324cf20ce67e26ad9b3538b41 100644 (file)
--- a/src/internal/bytealg/count_generic.go
+++ b/src/internal/bytealg/count_generic.go
@@ -2,7 +2,7 @@
 // Use of this source code is governed by a BSD-style
 // license that can be found in the LICENSE file.
 
-// +build !amd64,!arm64,!ppc64le,!ppc64
+// +build !amd64,!arm,!arm64,!ppc64le,!ppc64
 
 package bytealg
 

diff --git a/src/internal/bytealg/count_native.go b/src/internal/bytealg/count_native.go
index e6a91b3c0e265a68a73da1c99d19c65221013307..52b2a461a493e9e3ff0a9f45ed21c59ee0aedf05 100644 (file)
--- a/src/internal/bytealg/count_native.go
+++ b/src/internal/bytealg/count_native.go
@@ -2,7 +2,7 @@
 // Use of this source code is governed by a BSD-style
 // license that can be found in the LICENSE file.
 
-// +build amd64 arm64 ppc64le ppc64
+// +build amd64 arm arm64 ppc64le ppc64
 
 package bytealg