runtime: improve MIPS64x memclr

Using MIPS MSA VLD/VST to improve mips64x large memclr.

name          old time/op    new time/op     delta
Memclr/5        23.2ns ± 0%     21.5ns ± 0%    -7.33%  (p=0.000 n=9+8)
Memclr/16       20.1ns ± 0%     17.1ns ± 0%   -14.93%  (p=0.000 n=10+10)
Memclr/64       27.2ns ± 0%     19.1ns ± 0%   -29.70%  (p=0.000 n=9+9)
Memclr/256      76.8ns ± 0%     24.1ns ± 0%   -68.66%  (p=0.000 n=10+10)
Memclr/4096     1.12µs ± 1%     0.18µs ± 0%   -84.32%  (p=0.000 n=10+8)
Memclr/65536    18.0µs ± 0%      2.8µs ± 0%   -84.29%  (p=0.000 n=10+10)
Memclr/1M        288µs ± 0%       45µs ± 0%   -84.20%  (p=0.000 n=10+10)
Memclr/4M       1.15ms ± 0%     0.18ms ± 0%   -84.21%  (p=0.000 n=9+10)
Memclr/8M       2.34ms ± 0%     1.39ms ± 0%   -40.55%  (p=0.000 n=10+8)
Memclr/16M      4.72ms ± 0%     4.74ms ± 0%    +0.52%  (p=0.000 n=9+10)
Memclr/64M      18.9ms ± 0%     18.9ms ± 0%      ~     (p=0.436 n=10+10)
GoMemclr/5      13.7ns ± 0%     16.9ns ± 0%   +23.36%  (p=0.000 n=10+10)
GoMemclr/16     14.3ns ± 0%      9.0ns ± 0%   -37.27%  (p=0.000 n=10+9)
GoMemclr/64     26.9ns ± 0%     13.7ns ± 0%   -49.07%  (p=0.000 n=10+10)
GoMemclr/256    77.8ns ± 0%     13.0ns ± 0%   -83.24%  (p=0.000 n=9+10)

name          old speed      new speed       delta
Memclr/5       215MB/s ± 0%    232MB/s ± 0%    +7.74%  (p=0.000 n=9+9)
Memclr/16      795MB/s ± 0%    935MB/s ± 0%   +17.60%  (p=0.000 n=10+10)
Memclr/64     2.35GB/s ± 0%   3.35GB/s ± 0%   +42.33%  (p=0.000 n=10+9)
Memclr/256    3.34GB/s ± 0%  10.65GB/s ± 0%  +219.16%  (p=0.000 n=10+10)
Memclr/4096   3.65GB/s ± 1%  23.30GB/s ± 0%  +538.36%  (p=0.000 n=10+10)
Memclr/65536  3.65GB/s ± 0%  23.21GB/s ± 0%  +536.59%  (p=0.000 n=10+10)
Memclr/1M     3.64GB/s ± 0%  23.07GB/s ± 0%  +532.96%  (p=0.000 n=10+10)
Memclr/4M     3.64GB/s ± 0%  23.08GB/s ± 0%  +533.36%  (p=0.000 n=9+10)
Memclr/8M     3.58GB/s ± 0%   6.02GB/s ± 0%   +68.20%  (p=0.000 n=10+8)
Memclr/16M    3.56GB/s ± 0%   3.54GB/s ± 0%    -0.51%  (p=0.000 n=9+10)
Memclr/64M    3.55GB/s ± 0%   3.55GB/s ± 0%      ~     (p=0.436 n=10+10)
GoMemclr/5     364MB/s ± 0%    296MB/s ± 0%   -18.76%  (p=0.000 n=9+10)
GoMemclr/16   1.12GB/s ± 0%   1.78GB/s ± 0%   +58.86%  (p=0.000 n=10+10)
GoMemclr/64   2.38GB/s ± 0%   4.66GB/s ± 0%   +96.27%  (p=0.000 n=10+9)
GoMemclr/256  3.29GB/s ± 0%  19.62GB/s ± 0%  +496.45%  (p=0.000 n=10+9)

Change-Id: I457858368f2875fd66818a41d2f0c190a850e8f1
Reviewed-on: https://go-review.googlesource.com/c/go/+/218177
Run-TryBot: Cherry Zhang <[email protected]>
Reviewed-by: Cherry Zhang <[email protected]>

Author: mengzhuo

src/runtime/cpuflags.go

@@ -17,6 +17,8 @@ const (
 	offsetX86HasSSE2 = unsafe.Offsetof(cpu.X86.HasSSE2)
 
 	offsetARMHasIDIVA = unsafe.Offsetof(cpu.ARM.HasIDIVA)
+
+	offsetMIPS64XHasMSA = unsafe.Offsetof(cpu.MIPS64X.HasMSA)
 )
 
 var (

src/runtime/memclr_mips64x.s

@@ -4,6 +4,7 @@
 
 // +build mips64 mips64le
 
+#include "go_asm.h"
 #include "textflag.h"
 
 // func memclrNoHeapPointers(ptr unsafe.Pointer, n uintptr)
@@ -12,6 +13,60 @@ TEXT runtime·memclrNoHeapPointers(SB),NOSPLIT,$0-16
 	MOVV	n+8(FP), R2
 	ADDV	R1, R2, R4
 
+	// if less than 16 bytes or no MSA, do words check
+	SGTU	$16, R2, R3
+	BNE	R3, no_msa
+	MOVBU	internal∕cpu·MIPS64X+const_offsetMIPS64XHasMSA(SB), R3
+	BEQ	R3, R0, no_msa
+
+	VMOVB	$0, W0
+
+	SGTU	$128, R2, R3
+	BEQ	R3, msa_large
+
+	AND	$15, R2, R5
+	XOR	R2, R5, R6
+	ADDVU	R1, R6
+
+msa_small:
+	VMOVB	W0, (R1)
+	ADDVU	$16, R1
+	SGTU	R6, R1, R3
+	BNE	R3, R0, msa_small
+	BEQ	R5, R0, done
+	VMOVB	W0, -16(R4)
+	JMP	done
+
+msa_large:
+	AND	$127, R2, R5
+	XOR	R2, R5, R6
+	ADDVU	R1, R6
+
+msa_large_loop:
+	VMOVB	W0, (R1)
+	VMOVB	W0, 16(R1)
+	VMOVB	W0, 32(R1)
+	VMOVB	W0, 48(R1)
+	VMOVB	W0, 64(R1)
+	VMOVB	W0, 80(R1)
+	VMOVB	W0, 96(R1)
+	VMOVB	W0, 112(R1)
+
+	ADDVU	$128, R1
+	SGTU	R6, R1, R3
+	BNE	R3, R0, msa_large_loop
+	BEQ	R5, R0, done
+	VMOVB	W0, -128(R4)
+	VMOVB	W0, -112(R4)
+	VMOVB	W0, -96(R4)
+	VMOVB	W0, -80(R4)
+	VMOVB	W0, -64(R4)
+	VMOVB	W0, -48(R4)
+	VMOVB	W0, -32(R4)
+	VMOVB	W0, -16(R4)
+	JMP	done
+
+no_msa:
 	// if less than 8 bytes, do one byte at a time
 	SGTU	$8, R2, R3
 	BNE	R3, out