hash/crc32: improve asm for ppc64SlicingUpdateBy8

Improvements are made in the assembler code which improves  time and
space by 9-10%.
1. ANDCC, followed by SLD is combined and replaced by CLRLSLDI.
2. MOVWZ can use an indexed load and eliminate an ADD instruction in some cases.
	Example: ADD R7,R10,R7 followed by MOVWZ 0(R7),R5 can be replaced with just MOVWZ (R7)(R10),R5.
3. Optimizations for the block after the "short" label includes the same MOVWZ use of indexed load, as well as other improvements.

The gain from code  changes can be seen as follows, generated by
benchstat:

goos: linux
goarch: ppc64le
pkg: hash/crc32
cpu: POWER10
                                     |  oldCrc.out   |  newCrc.out                     	 |
                                     |    sec/op     |   sec/op     vs base            	 |
CRC32/poly=IEEE/size=15/align=0-12      50.19n ±  1%   39.85n ± 0%  -20.59% (p=0.002 n=6)
CRC32/poly=IEEE/size=15/align=1-12      50.18n ±  1%   39.87n ± 0%  -20.54% (p=0.002 n=6)
CRC32/poly=IEEE/size=40/align=0-12      40.25n ±  0%   36.95n ± 0%   -8.19% (p=0.002 n=6)
CRC32/poly=IEEE/size=40/align=1-12      40.31n ±  0%   36.95n ± 0%   -8.36% (p=0.002 n=6)
CRC32/poly=IEEE/size=512/align=0-12     38.03n ±  0%   38.17n ± 0%   +0.37% (p=0.002 n=6)
CRC32/poly=IEEE/size=512/align=1-12     89.19n ±  1%   73.65n ± 0%  -17.43% (p=0.002 n=6)
CRC32/poly=IEEE/size=1kB/align=0-12     50.73n ±  7%   50.14n ± 0%   -1.18% (p=0.002 n=6)
CRC32/poly=IEEE/size=1kB/align=1-12    101.00n ± 37%   81.58n ± 0%  -19.23% (p=0.002 n=6)
CRC32/poly=IEEE/size=4kB/align=0-12     98.30n ± 45%   93.05n ± 0%   -5.34% (p=0.043 n=6)
CRC32/poly=IEEE/size=4kB/align=1-12     140.8n ±  0%   125.8n ± 0%  -10.65% (p=0.002 n=6)
CRC32/poly=IEEE/size=32kB/align=0-12    525.8n ±  0%   528.5n ± 0%   +0.52% (p=0.011 n=6)
CRC32/poly=IEEE/size=32kB/align=1-12    584.4n ±  1%   576.3n ± 0%   -1.39% (p=0.002 n=6)
geomean                                 90.51n         81.74n        -9.69%

	                             |    oldCrc.out |    newCrc.out           		  |
                                     |      B/s      |     B/s       vs base    	  |
CRC32/poly=IEEE/size=15/align=0-12     285.0Mi ±  1%    359.0Mi ± 0%  +25.94% (p=0.002 n=6)
CRC32/poly=IEEE/size=15/align=1-12     285.1Mi ±  1%    358.8Mi ± 0%  +25.86% (p=0.002 n=6)
CRC32/poly=IEEE/size=40/align=0-12     947.8Mi ±  0%   1032.3Mi ± 0%   +8.91% (p=0.002 n=6)
CRC32/poly=IEEE/size=40/align=1-12     946.2Mi ±  0%   1032.5Mi ± 0%   +9.12% (p=0.002 n=6)
CRC32/poly=IEEE/size=512/align=0-12    12.54Gi ±  0%    12.49Gi ± 0%   -0.37% (p=0.002 n=6)
CRC32/poly=IEEE/size=512/align=1-12    5.346Gi ±  1%    6.475Gi ± 0%  +21.12% (p=0.002 n=6)
CRC32/poly=IEEE/size=1kB/align=0-12    18.80Gi ±  7%    19.02Gi ± 0%   +1.20% (p=0.002 n=6)
CRC32/poly=IEEE/size=1kB/align=1-12    9.454Gi ± 27%   11.690Gi ± 0%  +23.66% (p=0.002 n=6)
CRC32/poly=IEEE/size=4kB/align=0-12    38.86Gi ± 31%    41.00Gi ± 0%   +5.49% (p=0.041 n=6)
CRC32/poly=IEEE/size=4kB/align=1-12    27.10Gi ±  0%    30.32Gi ± 0%  +11.89% (p=0.002 n=6)
CRC32/poly=IEEE/size=32kB/align=0-12   58.05Gi ±  0%    57.74Gi ± 0%   -0.53% (p=0.009 n=6)
CRC32/poly=IEEE/size=32kB/align=1-12   52.22Gi ±  1%    52.95Gi ± 0%   +1.41% (p=0.002 n=6)
geomean                                6.074Gi          6.724Gi       +10.70%

Change-Id: I378c0e84e798656384a8009f4ac48b51614489b2
Cq-Include-Trybots: luci.golang.try:gotip-linux-ppc64_power10,gotip-linux-ppc64_power8,gotip-linux-ppc64le_power8,gotip-linux-ppc64le_power9,gotip-linux-ppc64le_power10
Reviewed-on: https://go-review.googlesource.com/c/go/+/582395
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: David Chase <drchase@google.com>
Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com>
Reviewed-by: Eli Bendersky <eliben@google.com>

1 files changed, 21 insertions, 32 deletions

diff --git a/src/hash/crc32/crc32_ppc64le.s b/src/hash/crc32/crc32_ppc64le.s
index 84ef213312..fb7c783f93 100644
--- a/src/hash/crc32/crc32_ppc64le.s
+++ b/src/hash/crc32/crc32_ppc64le.s
@@ -63,67 +63,56 @@ loop:
 	RLDICL	$40,R9,$56,R17	// p[7]
 	SLD	$2,R17,R17	// p[7]*4
 	RLDICL	$40,R7,$56,R8	// crc>>24
-	ADD	R17,R10,R17	// &tab[0][p[7]]
 	SLD	$2,R8,R8	// crc>>24*4
 	RLDICL	$48,R9,$56,R18	// p[6]
 	SLD	$2,R18,R18	// p[6]*4
+	MOVWZ	(R10)(R17),R21	// tab[0][p[7]]
 	ADD	$1024,R10,R10	// tab[1]
-	MOVWZ	0(R17),R21	// tab[0][p[7]]
 	RLDICL	$56,R9,$56,R19	// p[5]
-	ADD	R10,R18,R18	// &tab[1][p[6]]
 	SLD	$2,R19,R19	// p[5]*4:1
-	MOVWZ	0(R18),R22	// tab[1][p[6]]
+	MOVWZ	(R10)(R18),R22	// tab[1][p[6]]
 	ADD	$1024,R10,R10	// tab[2]
 	XOR	R21,R22,R21	// xor done R22
-	ADD	R19,R10,R19	// &tab[2][p[5]]
-	ANDCC	$255,R9,R20	// p[4] ??
-	SLD	$2,R20,R20	// p[4]*4
-	MOVWZ	0(R19),R23	// tab[2][p[5]]
+	CLRLSLDI $56,R9,$2,R20
+	MOVWZ	(R10)(R19),R23	// tab[2][p[5]]
 	ADD	$1024,R10,R10	// &tab[3]
-	ADD	R20,R10,R20	// tab[3][p[4]]
 	XOR	R21,R23,R21	// xor done R23
-	ADD	$1024,R10,R10	// &tab[4]
-	MOVWZ	0(R20),R24	// tab[3][p[4]]
-	ADD	R10,R8,R23	// &tab[4][crc>>24]
+	MOVWZ	(R10)(R20),R24	// tab[3][p[4]]
+	ADD 	$1024,R10,R10   // &tab[4]
 	XOR	R21,R24,R21	// xor done R24
-	MOVWZ	0(R23),R25	// tab[4][crc>>24]
+	MOVWZ	(R10)(R8),R25	// tab[4][crc>>24]
 	RLDICL	$48,R7,$56,R24	// crc>>16&0xFF
 	XOR	R21,R25,R21	// xor done R25
 	ADD	$1024,R10,R10	// &tab[5]
 	SLD	$2,R24,R24	// crc>>16&0xFF*4
-	ADD	R24,R10,R24	// &tab[5][crc>>16&0xFF]
-	MOVWZ	0(R24),R26	// tab[5][crc>>16&0xFF]
+	MOVWZ	(R10)(R24),R26	// tab[5][crc>>16&0xFF]
 	XOR	R21,R26,R21	// xor done R26
 	RLDICL	$56,R7,$56,R25	// crc>>8
 	ADD	$1024,R10,R10	// &tab[6]
 	SLD	$2,R25,R25	// crc>>8&FF*2
-	ADD	R25,R10,R25	// &tab[6][crc>>8&0xFF]
 	MOVBZ   R7,R26          // crc&0xFF
-	ADD     $1024,R10,R10   // &tab[7]
-	MOVWZ	0(R25),R27	// tab[6][crc>>8&0xFF]
+	MOVWZ	(R10)(R25),R27	// tab[6][crc>>8&0xFF]
+	ADD 	$1024,R10,R10   // &tab[7]
 	SLD	$2,R26,R26	// crc&0xFF*2
 	XOR	R21,R27,R21	// xor done R27
-	ADD	R26,R10,R26	// &tab[7][crc&0xFF]
 	ADD     $8,R5           // p = p[8:]
-	MOVWZ	0(R26),R28	// tab[7][crc&0xFF]
+	MOVWZ	(R10)(R26),R28	// tab[7][crc&0xFF]
 	XOR	R21,R28,R21	// xor done R28
 	MOVWZ	R21,R7		// crc for next round
-	BC	16,0,loop	// next 8 bytes
+	BDNZ 	loop
 	ANDCC	$7,R6,R8	// any leftover bytes
 	BEQ	done		// none --> done
 	MOVD	R8,CTR		// byte count
 	PCALIGN $16             // align short loop
 short:
-	MOVBZ   0(R5),R8        // get v
-	MOVBZ   R7,R9           // byte(crc) -> R8 BE vs LE?
-	SRD     $8,R7,R14       // crc>>8
-	XOR     R8,R9,R8        // byte(crc)^v -> R8
-	ADD	$1,R5		// ptr to next v
-	SLD     $2,R8           // convert index-> bytes
-	ADD     R8,R4,R9        // &tab[byte(crc)^v]
-	MOVWZ   0(R9),R10       // tab[byte(crc)^v]
-	XOR     R10,R14,R7       // loop crc in R7
-	BC      16,0,short
+	MOVBZ 	0(R5),R8	// get v
+	XOR 	R8,R7,R8	// byte(crc)^v -> R8
+	RLDIC	$2,R8,$54,R8	// rldicl r8,r8,2,22
+	SRD 	$8,R7,R14	// crc>>8
+	MOVWZ	(R4)(R8),R10
+	ADD	$1,R5
+	XOR 	R10,R14,R7	// loop crc in R7
+	BDNZ 	short
 done:
 	NOR     R7,R7,R7        // ^crc
 	MOVW    R7,ret+40(FP)   // return crc
@@ -333,7 +322,7 @@ cool_top:
 	LVX	(R4+off112),V23	// next in buffer
 
 	ADD	$128,R4		// bump up buffer pointer
-	BC	16,0,cool_top	// are we done?
+	BDNZ	cool_top	// are we done?
 
 first_cool_down: