From: Cherry Zhang <cherryyz@google.com>
Date: Tue, 20 Mar 2018 00:10:08 +0000 (+0000)
Subject: Revert "bytes: add optimized Compare for arm64"
X-Git-Tag: go1.11beta1~1161
X-Git-Url: http://www.git.cypherpunks.su/?a=commitdiff_plain;h=e22d24131c8075c344fef790a93ec1addc2663e6;p=gostls13.git

Revert "bytes: add optimized Compare for arm64"

This reverts commit bfa8b6f8ffa49b3e5796af45a2f0bf9714a37bb9.

Reason for revert: This depends on another CL which is not yet submitted.

Change-Id: I50e7594f1473c911a2079fe910849a6694ac6c07
Reviewed-on: https://go-review.googlesource.com/101496
Reviewed-by: Cherry Zhang <cherryyz@google.com>
---

diff --git a/src/internal/bytealg/compare_arm64.s b/src/internal/bytealg/compare_arm64.s
index 2bd38064c3..9b6354715a 100644
--- a/src/internal/bytealg/compare_arm64.s
+++ b/src/internal/bytealg/compare_arm64.s
@@ -10,7 +10,7 @@ TEXT ·Compare(SB),NOSPLIT|NOFRAME,$0-56
 	MOVD	a_len+8(FP), R0
 	MOVD	b_base+24(FP), R3
 	MOVD	b_len+32(FP), R1
-	MOVD	$ret+48(FP), R7
+	ADD	$56, RSP, R7
 	B	cmpbody<>(SB)
 
 TEXT bytes·Compare(SB),NOSPLIT|NOFRAME,$0-56
@@ -18,7 +18,7 @@ TEXT bytes·Compare(SB),NOSPLIT|NOFRAME,$0-56
 	MOVD	a_len+8(FP), R0
 	MOVD	b_base+24(FP), R3
 	MOVD	b_len+32(FP), R1
-	MOVD	$ret+48(FP), R7
+	ADD	$56, RSP, R7
 	B	cmpbody<>(SB)
 
 TEXT runtime·cmpstring(SB),NOSPLIT|NOFRAME,$0-40
@@ -26,7 +26,7 @@ TEXT runtime·cmpstring(SB),NOSPLIT|NOFRAME,$0-40
 	MOVD	a_len+8(FP), R0
 	MOVD	b_base+16(FP), R3
 	MOVD	b_len+24(FP), R1
-	MOVD	$ret+32(FP), R7
+	ADD	$40, RSP, R7
 	B	cmpbody<>(SB)
 
 // On entry:
@@ -37,98 +37,30 @@ TEXT runtime·cmpstring(SB),NOSPLIT|NOFRAME,$0-40
 // R7 points to return value (-1/0/1 will be written here)
 //
 // On exit:
-// R4, R5, R6, R8, R9 and R10 are clobbered
+// R4, R5, and R6 are clobbered
 TEXT cmpbody<>(SB),NOSPLIT|NOFRAME,$0-0
 	CMP	R2, R3
-	BEQ	samebytes         // same starting pointers; compare lengths
+	BEQ	samebytes // same starting pointers; compare lengths
 	CMP	R0, R1
-	CSEL	LT, R1, R0, R6    // R6 is min(R0, R1)
+	CSEL    LT, R1, R0, R6 // R6 is min(R0, R1)
 
-	CMP	$0, R6
-	BEQ	samebytes
-	BIC	$0xf, R6, R10
-	CBZ	R10, small        // length < 16
-	ADD	R2, R10           // end of chunk16
-	// length >= 16
-chunk16_loop:
-	LDP.P	16(R2), (R4, R8)
-	LDP.P	16(R3), (R5, R9)
+	ADD	R2, R6	// R2 is current byte in a, R6 is last byte in a to compare
+loop:
+	CMP	R2, R6
+	BEQ	samebytes // all compared bytes were the same; compare lengths
+	MOVBU.P	1(R2), R4
+	MOVBU.P	1(R3), R5
 	CMP	R4, R5
-	BNE	cmp
-	CMP	R8, R9
-	BNE	cmpnext
-	CMP	R10, R2
-	BNE	chunk16_loop
-	AND	$0xf, R6, R6
-	CBZ	R6, samebytes
-	SUBS	$8, R6
-	BLT	tail
-	// the length of tail > 8 bytes
-	MOVD.P	8(R2), R4
-	MOVD.P	8(R3), R5
-	CMP	R4, R5
-	BNE	cmp
-	SUB	$8, R6
-	// compare last 8 bytes
-tail:
-	MOVD	(R2)(R6), R4
-	MOVD	(R3)(R6), R5
-	CMP	R4, R5
-	BEQ	samebytes
-cmp:
-	REV	R4, R4
-	REV	R5, R5
-	CMP	R4, R5
-ret:
+	BEQ	loop
+	// bytes differed
 	MOVD	$1, R4
-	CNEG	HI, R4, R4
+	CSNEG	LT, R4, R4, R4
 	MOVD	R4, (R7)
 	RET
-small:
-	TBZ	$3, R6, lt_8
-	MOVD	(R2), R4
-	MOVD	(R3), R5
-	CMP	R4, R5
-	BNE	cmp
-	SUBS	$8, R6
-	BEQ	samebytes
-	ADD	$8, R2
-	ADD	$8, R3
-	SUB	$8, R6
-	B	tail
-lt_8:
-	TBZ	$2, R6, lt_4
-	MOVWU	(R2), R4
-	MOVWU	(R3), R5
-	CMPW	R4, R5
-	BNE	cmp
-	SUBS	$4, R6
-	BEQ	samebytes
-	ADD	$4, R2
-	ADD	$4, R3
-lt_4:
-	TBZ	$1, R6, lt_2
-	MOVHU	(R2), R4
-	MOVHU	(R3), R5
-	CMPW	R4, R5
-	BNE	cmp
-	ADD	$2, R2
-	ADD	$2, R3
-lt_2:
-	TBZ	$0, R6, samebytes
-one:
-	MOVBU	(R2), R4
-	MOVBU	(R3), R5
-	CMPW	R4, R5
-	BNE	ret
 samebytes:
-	CMP	R1, R0
-	CSET	NE, R4
-	CNEG	LO, R4, R4
+	MOVD	$1, R4
+	CMP	R0, R1
+	CSNEG	LT, R4, R4, R4
+	CSEL	EQ, ZR, R4, R4
 	MOVD	R4, (R7)
 	RET
-cmpnext:
-	REV	R8, R4
-	REV	R9, R5
-	CMP	R4, R5
-	B	ret