hash/crc32: optimize arm64 crc32 implementation

ARMv8 defines crc32 instruction.

Comparing to the original crc32 calculation, this patch makes use of
crc32 instructions to do crc32 calculation instead of the multiple
lookup table algorithms.

ARMv8 provides IEEE and Castagnoli polynomials for crc32 calculation
so that the perfomance of these two types of crc32 get significant
improved.

name                                        old time/op   new time/op    delta
CRC32/poly=IEEE/size=15/align=0-32            117ns ± 0%      38ns ± 0%   -67.44%
CRC32/poly=IEEE/size=15/align=1-32            117ns ± 0%      38ns ± 0%   -67.52%
CRC32/poly=IEEE/size=40/align=0-32            129ns ± 0%      41ns ± 0%   -68.37%
CRC32/poly=IEEE/size=40/align=1-32            129ns ± 0%      41ns ± 0%   -68.29%
CRC32/poly=IEEE/size=512/align=0-32           828ns ± 0%     246ns ± 0%   -70.29%
CRC32/poly=IEEE/size=512/align=1-32           828ns ± 0%     132ns ± 0%   -84.06%
CRC32/poly=IEEE/size=1kB/align=0-32          1.58µs ± 0%    0.46µs ± 0%   -70.98%
CRC32/poly=IEEE/size=1kB/align=1-32          1.58µs ± 0%    0.46µs ± 0%   -70.92%
CRC32/poly=IEEE/size=4kB/align=0-32          6.06µs ± 0%    1.74µs ± 0%   -71.27%
CRC32/poly=IEEE/size=4kB/align=1-32          6.10µs ± 0%    1.74µs ± 0%   -71.44%
CRC32/poly=IEEE/size=32kB/align=0-32         48.3µs ± 0%    13.7µs ± 0%   -71.61%
CRC32/poly=IEEE/size=32kB/align=1-32         48.3µs ± 0%    13.7µs ± 0%   -71.60%
CRC32/poly=Castagnoli/size=15/align=0-32      116ns ± 0%      38ns ± 0%   -67.07%
CRC32/poly=Castagnoli/size=15/align=1-32      116ns ± 0%      38ns ± 0%   -66.90%
CRC32/poly=Castagnoli/size=40/align=0-32      127ns ± 0%      40ns ± 0%   -68.11%
CRC32/poly=Castagnoli/size=40/align=1-32      127ns ± 0%      40ns ± 0%   -68.11%
CRC32/poly=Castagnoli/size=512/align=0-32     828ns ± 0%     132ns ± 0%   -84.06%
CRC32/poly=Castagnoli/size=512/align=1-32     827ns ± 0%     132ns ± 0%   -84.04%
CRC32/poly=Castagnoli/size=1kB/align=0-32    1.59µs ± 0%    0.22µs ± 0%   -85.89%
CRC32/poly=Castagnoli/size=1kB/align=1-32    1.58µs ± 0%    0.22µs ± 0%   -85.79%
CRC32/poly=Castagnoli/size=4kB/align=0-32    6.14µs ± 0%    0.77µs ± 0%   -87.40%
CRC32/poly=Castagnoli/size=4kB/align=1-32    6.06µs ± 0%    0.77µs ± 0%   -87.25%
CRC32/poly=Castagnoli/size=32kB/align=0-32   48.3µs ± 0%     5.9µs ± 0%   -87.71%
CRC32/poly=Castagnoli/size=32kB/align=1-32   48.4µs ± 0%     6.0µs ± 0%   -87.69%
CRC32/poly=Koopman/size=15/align=0-32         104ns ± 0%     104ns ± 0%    +0.00%
CRC32/poly=Koopman/size=15/align=1-32         104ns ± 0%     104ns ± 0%    +0.00%
CRC32/poly=Koopman/size=40/align=0-32         235ns ± 0%     235ns ± 0%    +0.00%
CRC32/poly=Koopman/size=40/align=1-32         235ns ± 0%     235ns ± 0%    +0.00%
CRC32/poly=Koopman/size=512/align=0-32       2.71µs ± 0%    2.71µs ± 0%    -0.07%
CRC32/poly=Koopman/size=512/align=1-32       2.71µs ± 0%    2.71µs ± 0%    -0.04%
CRC32/poly=Koopman/size=1kB/align=0-32       5.40µs ± 0%    5.39µs ± 0%    -0.06%
CRC32/poly=Koopman/size=1kB/align=1-32       5.40µs ± 0%    5.40µs ± 0%    +0.02%
CRC32/poly=Koopman/size=4kB/align=0-32       21.5µs ± 0%    21.5µs ± 0%    -0.16%
CRC32/poly=Koopman/size=4kB/align=1-32       21.5µs ± 0%    21.5µs ± 0%    -0.05%
CRC32/poly=Koopman/size=32kB/align=0-32       172µs ± 0%     172µs ± 0%    -0.07%
CRC32/poly=Koopman/size=32kB/align=1-32       172µs ± 0%     172µs ± 0%    -0.01%

name                                        old speed     new speed      delta
CRC32/poly=IEEE/size=15/align=0-32          128MB/s ± 0%   394MB/s ± 0%  +207.95%
CRC32/poly=IEEE/size=15/align=1-32          128MB/s ± 0%   394MB/s ± 0%  +208.09%
CRC32/poly=IEEE/size=40/align=0-32          310MB/s ± 0%   979MB/s ± 0%  +216.07%
CRC32/poly=IEEE/size=40/align=1-32          310MB/s ± 0%   979MB/s ± 0%  +216.16%
CRC32/poly=IEEE/size=512/align=0-32         618MB/s ± 0%  2074MB/s ± 0%  +235.72%
CRC32/poly=IEEE/size=512/align=1-32         618MB/s ± 0%  3852MB/s ± 0%  +523.55%
CRC32/poly=IEEE/size=1kB/align=0-32         646MB/s ± 0%  2225MB/s ± 0%  +244.57%
CRC32/poly=IEEE/size=1kB/align=1-32         647MB/s ± 0%  2225MB/s ± 0%  +243.87%
CRC32/poly=IEEE/size=4kB/align=0-32         676MB/s ± 0%  2352MB/s ± 0%  +248.02%
CRC32/poly=IEEE/size=4kB/align=1-32         672MB/s ± 0%  2352MB/s ± 0%  +250.15%
CRC32/poly=IEEE/size=32kB/align=0-32        678MB/s ± 0%  2387MB/s ± 0%  +252.17%
CRC32/poly=IEEE/size=32kB/align=1-32        678MB/s ± 0%  2388MB/s ± 0%  +252.11%
CRC32/poly=Castagnoli/size=15/align=0-32    129MB/s ± 0%   393MB/s ± 0%  +205.51%
CRC32/poly=Castagnoli/size=15/align=1-32    129MB/s ± 0%   390MB/s ± 0%  +203.41%
CRC32/poly=Castagnoli/size=40/align=0-32    314MB/s ± 0%   988MB/s ± 0%  +215.04%
CRC32/poly=Castagnoli/size=40/align=1-32    314MB/s ± 0%   987MB/s ± 0%  +214.68%
CRC32/poly=Castagnoli/size=512/align=0-32   618MB/s ± 0%  3860MB/s ± 0%  +524.32%
CRC32/poly=Castagnoli/size=512/align=1-32   619MB/s ± 0%  3859MB/s ± 0%  +523.66%
CRC32/poly=Castagnoli/size=1kB/align=0-32   645MB/s ± 0%  4568MB/s ± 0%  +608.56%
CRC32/poly=Castagnoli/size=1kB/align=1-32   650MB/s ± 0%  4567MB/s ± 0%  +602.94%
CRC32/poly=Castagnoli/size=4kB/align=0-32   667MB/s ± 0%  5297MB/s ± 0%  +693.81%
CRC32/poly=Castagnoli/size=4kB/align=1-32   676MB/s ± 0%  5297MB/s ± 0%  +684.00%
CRC32/poly=Castagnoli/size=32kB/align=0-32  678MB/s ± 0%  5519MB/s ± 0%  +713.83%
CRC32/poly=Castagnoli/size=32kB/align=1-32  677MB/s ± 0%  5497MB/s ± 0%  +712.04%
CRC32/poly=Koopman/size=15/align=0-32       143MB/s ± 0%   144MB/s ± 0%    +0.27%
CRC32/poly=Koopman/size=15/align=1-32       143MB/s ± 0%   144MB/s ± 0%    +0.33%
CRC32/poly=Koopman/size=40/align=0-32       169MB/s ± 0%   170MB/s ± 0%    +0.12%
CRC32/poly=Koopman/size=40/align=1-32       170MB/s ± 0%   170MB/s ± 0%    +0.08%
CRC32/poly=Koopman/size=512/align=0-32      189MB/s ± 0%   189MB/s ± 0%    +0.07%
CRC32/poly=Koopman/size=512/align=1-32      189MB/s ± 0%   189MB/s ± 0%    +0.04%
CRC32/poly=Koopman/size=1kB/align=0-32      190MB/s ± 0%   190MB/s ± 0%    +0.05%
CRC32/poly=Koopman/size=1kB/align=1-32      190MB/s ± 0%   190MB/s ± 0%    -0.01%
CRC32/poly=Koopman/size=4kB/align=0-32      190MB/s ± 0%   190MB/s ± 0%    +0.15%
CRC32/poly=Koopman/size=4kB/align=1-32      190MB/s ± 0%   191MB/s ± 0%    +0.05%
CRC32/poly=Koopman/size=32kB/align=0-32     191MB/s ± 0%   191MB/s ± 0%    +0.06%
CRC32/poly=Koopman/size=32kB/align=1-32     191MB/s ± 0%   191MB/s ± 0%    +0.02%

Also fix a bug of arm64 assembler

The optimization is mainly contributed by Fangming.Fang <fangming.fang@arm.com>

Change-Id: I900678c2e445d7e8ad9e2a9ab3305d649230905f
Reviewed-on: https://go-review.googlesource.com/40074
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>

1 files changed, 7 insertions, 0 deletions

diff --git a/src/runtime/os_linux_arm64.go b/src/runtime/os_linux_arm64.go
index bdc341d962..f2a2916c37 100644
--- a/src/runtime/os_linux_arm64.go
+++ b/src/runtime/os_linux_arm64.go
@@ -4,7 +4,12 @@
 
 package runtime
 
+const (
+        _ARM64_FEATURE_HAS_CRC32 = 0x80
+)
+
 var randomNumber uint32
+var supportCRC32 bool
 
 func archauxv(tag, val uintptr) {
 	switch tag {
@@ -14,6 +19,8 @@ func archauxv(tag, val uintptr) {
 		// it as a byte array.
 		randomNumber = uint32(startupRandomData[4]) | uint32(startupRandomData[5])<<8 |
 			uint32(startupRandomData[6])<<16 | uint32(startupRandomData[7])<<24
+        case _AT_HWCAP:
+                supportCRC32 = val & _ARM64_FEATURE_HAS_CRC32 != 0
 	}
 }