runtime: improve memmove for amd64

    Use AVX if available on 4th generation of Intel(TM) Core(TM) processors.

    (collected on E5 2609v3 @1.9GHz)
    name                        old speed      new speed       delta
    Memmove/1-6                  158MB/s ± 0%    172MB/s ± 0%    +9.09% (p=0.000 n=16+16)
    Memmove/2-6                  316MB/s ± 0%    345MB/s ± 0%    +9.09% (p=0.000 n=18+16)
    Memmove/3-6                  517MB/s ± 0%    517MB/s ± 0%      ~ (p=0.445 n=16+16)
    Memmove/4-6                  687MB/s ± 1%    690MB/s ± 0%    +0.35% (p=0.000 n=20+17)
    Memmove/5-6                  729MB/s ± 0%    729MB/s ± 0%    +0.01% (p=0.000 n=16+18)
    Memmove/6-6                  875MB/s ± 0%    875MB/s ± 0%    +0.01% (p=0.000 n=18+18)
    Memmove/7-6                 1.02GB/s ± 0%   1.02GB/s ± 1%      ~ (p=0.139 n=19+20)
    Memmove/8-6                 1.26GB/s ± 0%   1.26GB/s ± 0%    +0.00% (p=0.000 n=18+18)
    Memmove/9-6                 1.42GB/s ± 0%   1.42GB/s ± 0%    +0.00% (p=0.000 n=17+18)
    Memmove/10-6                1.58GB/s ± 0%   1.58GB/s ± 0%    +0.00% (p=0.000 n=19+19)
    Memmove/11-6                1.74GB/s ± 0%   1.74GB/s ± 0%    +0.00% (p=0.001 n=18+17)
    Memmove/12-6                1.90GB/s ± 0%   1.90GB/s ± 0%    +0.00% (p=0.000 n=19+19)
    Memmove/13-6                2.05GB/s ± 0%   2.05GB/s ± 0%    +0.00% (p=0.000 n=18+19)
    Memmove/14-6                2.21GB/s ± 0%   2.21GB/s ± 0%    +0.00% (p=0.000 n=16+20)
    Memmove/15-6                2.37GB/s ± 0%   2.37GB/s ± 0%    +0.00% (p=0.004 n=19+20)
    Memmove/16-6                2.53GB/s ± 0%   2.53GB/s ± 0%    +0.00% (p=0.000 n=16+16)
    Memmove/32-6                4.67GB/s ± 0%   4.67GB/s ± 0%    +0.00% (p=0.000 n=17+17)
    Memmove/64-6                8.67GB/s ± 0%   8.64GB/s ± 0%    -0.33% (p=0.000 n=18+17)
    Memmove/128-6               12.6GB/s ± 0%   11.6GB/s ± 0%    -8.05% (p=0.000 n=16+19)
    Memmove/256-6               16.3GB/s ± 0%   16.6GB/s ± 0%    +1.66% (p=0.000 n=20+18)
    Memmove/512-6               21.5GB/s ± 0%   24.4GB/s ± 0%   +13.35% (p=0.000 n=18+17)
    Memmove/1024-6              24.7GB/s ± 0%   33.7GB/s ± 0%   +36.12% (p=0.000 n=18+18)
    Memmove/2048-6              27.3GB/s ± 0%   43.3GB/s ± 0%   +58.77% (p=0.000 n=19+17)
    Memmove/4096-6              37.5GB/s ± 0%   50.5GB/s ± 0%   +34.56% (p=0.000 n=19+19)
    MemmoveUnalignedDst/1-6      135MB/s ± 0%    146MB/s ± 0%    +7.69% (p=0.000 n=16+14)
    MemmoveUnalignedDst/2-6      271MB/s ± 0%    292MB/s ± 0%    +7.69% (p=0.000 n=18+18)
    MemmoveUnalignedDst/3-6      438MB/s ± 0%    438MB/s ± 0%      ~ (p=0.352 n=16+19)
    MemmoveUnalignedDst/4-6      584MB/s ± 0%    584MB/s ± 0%      ~ (p=0.876 n=17+17)
    MemmoveUnalignedDst/5-6      631MB/s ± 1%    632MB/s ± 0%    +0.25% (p=0.000 n=20+17)
    MemmoveUnalignedDst/6-6      759MB/s ± 0%    759MB/s ± 0%    +0.00% (p=0.000 n=19+16)
    MemmoveUnalignedDst/7-6      885MB/s ± 0%    883MB/s ± 1%      ~ (p=0.647 n=18+20)
    MemmoveUnalignedDst/8-6     1.08GB/s ± 0%   1.08GB/s ± 0%    +0.00% (p=0.035 n=19+18)
    MemmoveUnalignedDst/9-6     1.22GB/s ± 0%   1.22GB/s ± 0%      ~ (p=0.251 n=18+17)
    MemmoveUnalignedDst/10-6    1.35GB/s ± 0%   1.35GB/s ± 0%      ~ (p=0.327 n=17+18)
    MemmoveUnalignedDst/11-6    1.49GB/s ± 0%   1.49GB/s ± 0%      ~ (p=0.531 n=18+19)
    MemmoveUnalignedDst/12-6    1.63GB/s ± 0%   1.63GB/s ± 0%      ~ (p=0.886 n=19+18)
    MemmoveUnalignedDst/13-6    1.76GB/s ± 0%   1.76GB/s ± 1%    -0.24% (p=0.006 n=18+20)
    MemmoveUnalignedDst/14-6    1.90GB/s ± 0%   1.90GB/s ± 0%      ~ (p=0.818 n=20+19)
    MemmoveUnalignedDst/15-6    2.03GB/s ± 0%   2.03GB/s ± 0%      ~ (p=0.294 n=17+16)
    MemmoveUnalignedDst/16-6    2.17GB/s ± 0%   2.17GB/s ± 0%      ~ (p=0.602 n=16+18)
    MemmoveUnalignedDst/32-6    4.05GB/s ± 0%   4.05GB/s ± 0%    +0.00% (p=0.010 n=18+17)
    MemmoveUnalignedDst/64-6    7.59GB/s ± 0%   7.59GB/s ± 0%    +0.00% (p=0.022 n=18+16)
    MemmoveUnalignedDst/128-6   11.1GB/s ± 0%   11.4GB/s ± 0%    +2.79% (p=0.000 n=18+17)
    MemmoveUnalignedDst/256-6   16.4GB/s ± 0%   16.7GB/s ± 0%    +1.59% (p=0.000 n=20+17)
    MemmoveUnalignedDst/512-6   15.7GB/s ± 0%   21.3GB/s ± 0%   +35.87% (p=0.000 n=18+20)
    MemmoveUnalignedDst/1024-6  16.0GB/s ±20%   31.5GB/s ± 0%   +96.93% (p=0.000 n=20+14)
    MemmoveUnalignedDst/2048-6  19.6GB/s ± 0%   42.1GB/s ± 0%  +115.16% (p=0.000 n=17+18)
    MemmoveUnalignedDst/4096-6  6.41GB/s ± 0%  33.18GB/s ± 0%  +417.56% (p=0.000 n=17+18)
    MemmoveUnalignedSrc/1-6      171MB/s ± 0%    166MB/s ± 0%    -3.33% (p=0.000 n=19+16)
    MemmoveUnalignedSrc/2-6      343MB/s ± 0%    342MB/s ± 1%    -0.41% (p=0.000 n=17+20)
    MemmoveUnalignedSrc/3-6      508MB/s ± 0%    493MB/s ± 1%    -2.90% (p=0.000 n=17+17)
    MemmoveUnalignedSrc/4-6      677MB/s ± 0%    660MB/s ± 2%    -2.55% (p=0.000 n=17+20)
    MemmoveUnalignedSrc/5-6      790MB/s ± 0%    790MB/s ± 0%      ~ (p=0.139 n=17+17)
    MemmoveUnalignedSrc/6-6      948MB/s ± 0%    946MB/s ± 1%      ~ (p=0.330 n=17+19)
    MemmoveUnalignedSrc/7-6     1.11GB/s ± 0%   1.11GB/s ± 0%    -0.05% (p=0.026 n=17+17)
    MemmoveUnalignedSrc/8-6     1.38GB/s ± 0%   1.38GB/s ± 0%      ~ (p=0.091 n=18+16)
    MemmoveUnalignedSrc/9-6     1.42GB/s ± 0%   1.40GB/s ± 1%    -1.04% (p=0.000 n=19+20)
    MemmoveUnalignedSrc/10-6    1.58GB/s ± 0%   1.56GB/s ± 1%    -1.15% (p=0.000 n=18+19)
    MemmoveUnalignedSrc/11-6    1.73GB/s ± 0%   1.71GB/s ± 1%    -1.30% (p=0.000 n=20+20)
    MemmoveUnalignedSrc/12-6    1.89GB/s ± 0%   1.87GB/s ± 1%    -1.18% (p=0.000 n=17+20)
    MemmoveUnalignedSrc/13-6    2.05GB/s ± 0%   2.02GB/s ± 1%    -1.18% (p=0.000 n=17+20)
    MemmoveUnalignedSrc/14-6    2.21GB/s ± 0%   2.18GB/s ± 1%    -1.14% (p=0.000 n=17+20)
    MemmoveUnalignedSrc/15-6    2.36GB/s ± 0%   2.34GB/s ± 1%    -1.04% (p=0.000 n=17+20)
    MemmoveUnalignedSrc/16-6    2.52GB/s ± 0%   2.49GB/s ± 1%    -1.26% (p=0.000 n=19+20)
    MemmoveUnalignedSrc/32-6    4.82GB/s ± 0%   4.61GB/s ± 0%    -4.40% (p=0.000 n=19+20)
    MemmoveUnalignedSrc/64-6    5.03GB/s ± 4%   7.97GB/s ± 0%   +58.55% (p=0.000 n=20+16)
    MemmoveUnalignedSrc/128-6   11.1GB/s ± 0%   11.2GB/s ± 0%    +0.52% (p=0.000 n=17+18)
    MemmoveUnalignedSrc/256-6   16.5GB/s ± 0%   16.4GB/s ± 0%    -0.10% (p=0.000 n=20+18)
    MemmoveUnalignedSrc/512-6   21.0GB/s ± 0%   22.1GB/s ± 0%    +5.48% (p=0.000 n=14+17)
    MemmoveUnalignedSrc/1024-6  24.9GB/s ± 0%   31.9GB/s ± 0%   +28.20% (p=0.000 n=19+20)
    MemmoveUnalignedSrc/2048-6  23.3GB/s ± 0%   33.8GB/s ± 0%   +45.22% (p=0.000 n=17+19)
    MemmoveUnalignedSrc/4096-6  37.3GB/s ± 0%   42.7GB/s ± 0%   +14.30% (p=0.000 n=17+17)

Change-Id: Id66aa3e499ccfb117cb99d623ef326b50d057b64
Reviewed-on: https://go-review.googlesource.com/29590
Run-TryBot: Denis Nagorny <denis.nagorny@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>

1 files changed, 75 insertions, 0 deletions

diff --git a/src/runtime/cpuflags_amd64.go b/src/runtime/cpuflags_amd64.go
new file mode 100644
index 0000000000..026f0cd88e
--- /dev/null
+++ b/src/runtime/cpuflags_amd64.go
@@ -0,0 +1,75 @@
+// Copyright 2015 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 runtime
+
+var vendorStringBytes [12]byte
+var maxInputValue uint32
+var featureFlags uint32
+var processorVersionInfo uint32
+
+var useRepMovs = true
+
+func hasFeature(feature uint32) bool {
+	return (featureFlags & feature) != 0
+}
+
+func cpuid_low(arg1, arg2 uint32) (eax, ebx, ecx, edx uint32) // implemented in cpuidlow_amd64.s
+func xgetbv_low(arg1 uint32) (eax, edx uint32)                // implemented in cpuidlow_amd64.s
+
+func init() {
+	const cfOSXSAVE uint32 = 1 << 27
+	const cfAVX uint32 = 1 << 28
+
+	leaf0()
+	leaf1()
+
+	enabledAVX := false
+	// Let's check if OS has set CR4.OSXSAVE[bit 18]
+	// to enable XGETBV instruction.
+	if hasFeature(cfOSXSAVE) {
+		eax, _ := xgetbv_low(0)
+		// Let's check that XCR0[2:1] = ‘11b’
+		// i.e. XMM state and YMM state are enabled by OS.
+		enabledAVX = (eax & 0x6) == 0x6
+	}
+
+	isIntelBridgeFamily := (processorVersionInfo == 0x206A0 ||
+		processorVersionInfo == 0x206D0 ||
+		processorVersionInfo == 0x306A0 ||
+		processorVersionInfo == 0x306E0) &&
+		isIntel()
+
+	useRepMovs = !(hasFeature(cfAVX) && enabledAVX) || isIntelBridgeFamily
+}
+
+func leaf0() {
+	eax, ebx, ecx, edx := cpuid_low(0, 0)
+	maxInputValue = eax
+	int32ToBytes(ebx, vendorStringBytes[0:4])
+	int32ToBytes(edx, vendorStringBytes[4:8])
+	int32ToBytes(ecx, vendorStringBytes[8:12])
+}
+
+func leaf1() {
+	if maxInputValue < 1 {
+		return
+	}
+	eax, _, ecx, _ := cpuid_low(1, 0)
+	// Let's remove stepping and reserved fields
+	processorVersionInfo = eax & 0x0FFF3FF0
+	featureFlags = ecx
+}
+
+func int32ToBytes(arg uint32, buffer []byte) {
+	buffer[3] = byte(arg >> 24)
+	buffer[2] = byte(arg >> 16)
+	buffer[1] = byte(arg >> 8)
+	buffer[0] = byte(arg)
+}
+
+func isIntel() bool {
+	intelSignature := [12]byte{'G', 'e', 'n', 'u', 'i', 'n', 'e', 'I', 'n', 't', 'e', 'l'}
+	return vendorStringBytes == intelSignature
+}