From ccd992355df7192993c666236047820244914598 Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel.baumann@progress-linux.org>
Date: Tue, 16 Apr 2024 21:19:13 +0200
Subject: Adding upstream version 1.21.8.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
---
 src/runtime/memclr_386.s | 137 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 137 insertions(+)
 create mode 100644 src/runtime/memclr_386.s

(limited to 'src/runtime/memclr_386.s')

diff --git a/src/runtime/memclr_386.s b/src/runtime/memclr_386.s
new file mode 100644
index 0000000..a72e5f2
--- /dev/null
+++ b/src/runtime/memclr_386.s
@@ -0,0 +1,137 @@
+// Copyright 2014 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.
+
+//go:build !plan9
+
+#include "go_asm.h"
+#include "textflag.h"
+
+// See memclrNoHeapPointers Go doc for important implementation constraints.
+
+// func memclrNoHeapPointers(ptr unsafe.Pointer, n uintptr)
+TEXT runtime·memclrNoHeapPointers(SB), NOSPLIT, $0-8
+	MOVL	ptr+0(FP), DI
+	MOVL	n+4(FP), BX
+	XORL	AX, AX
+
+	// MOVOU seems always faster than REP STOSL.
+tail:
+	// BSR+branch table make almost all memmove/memclr benchmarks worse. Not worth doing.
+	TESTL	BX, BX
+	JEQ	_0
+	CMPL	BX, $2
+	JBE	_1or2
+	CMPL	BX, $4
+	JB	_3
+	JE	_4
+	CMPL	BX, $8
+	JBE	_5through8
+	CMPL	BX, $16
+	JBE	_9through16
+#ifdef GO386_softfloat
+	JMP	nosse2
+#endif
+	PXOR	X0, X0
+	CMPL	BX, $32
+	JBE	_17through32
+	CMPL	BX, $64
+	JBE	_33through64
+	CMPL	BX, $128
+	JBE	_65through128
+	CMPL	BX, $256
+	JBE	_129through256
+
+loop:
+	MOVOU	X0, 0(DI)
+	MOVOU	X0, 16(DI)
+	MOVOU	X0, 32(DI)
+	MOVOU	X0, 48(DI)
+	MOVOU	X0, 64(DI)
+	MOVOU	X0, 80(DI)
+	MOVOU	X0, 96(DI)
+	MOVOU	X0, 112(DI)
+	MOVOU	X0, 128(DI)
+	MOVOU	X0, 144(DI)
+	MOVOU	X0, 160(DI)
+	MOVOU	X0, 176(DI)
+	MOVOU	X0, 192(DI)
+	MOVOU	X0, 208(DI)
+	MOVOU	X0, 224(DI)
+	MOVOU	X0, 240(DI)
+	SUBL	$256, BX
+	ADDL	$256, DI
+	CMPL	BX, $256
+	JAE	loop
+	JMP	tail
+
+_1or2:
+	MOVB	AX, (DI)
+	MOVB	AX, -1(DI)(BX*1)
+	RET
+_0:
+	RET
+_3:
+	MOVW	AX, (DI)
+	MOVB	AX, 2(DI)
+	RET
+_4:
+	// We need a separate case for 4 to make sure we clear pointers atomically.
+	MOVL	AX, (DI)
+	RET
+_5through8:
+	MOVL	AX, (DI)
+	MOVL	AX, -4(DI)(BX*1)
+	RET
+_9through16:
+	MOVL	AX, (DI)
+	MOVL	AX, 4(DI)
+	MOVL	AX, -8(DI)(BX*1)
+	MOVL	AX, -4(DI)(BX*1)
+	RET
+_17through32:
+	MOVOU	X0, (DI)
+	MOVOU	X0, -16(DI)(BX*1)
+	RET
+_33through64:
+	MOVOU	X0, (DI)
+	MOVOU	X0, 16(DI)
+	MOVOU	X0, -32(DI)(BX*1)
+	MOVOU	X0, -16(DI)(BX*1)
+	RET
+_65through128:
+	MOVOU	X0, (DI)
+	MOVOU	X0, 16(DI)
+	MOVOU	X0, 32(DI)
+	MOVOU	X0, 48(DI)
+	MOVOU	X0, -64(DI)(BX*1)
+	MOVOU	X0, -48(DI)(BX*1)
+	MOVOU	X0, -32(DI)(BX*1)
+	MOVOU	X0, -16(DI)(BX*1)
+	RET
+_129through256:
+	MOVOU	X0, (DI)
+	MOVOU	X0, 16(DI)
+	MOVOU	X0, 32(DI)
+	MOVOU	X0, 48(DI)
+	MOVOU	X0, 64(DI)
+	MOVOU	X0, 80(DI)
+	MOVOU	X0, 96(DI)
+	MOVOU	X0, 112(DI)
+	MOVOU	X0, -128(DI)(BX*1)
+	MOVOU	X0, -112(DI)(BX*1)
+	MOVOU	X0, -96(DI)(BX*1)
+	MOVOU	X0, -80(DI)(BX*1)
+	MOVOU	X0, -64(DI)(BX*1)
+	MOVOU	X0, -48(DI)(BX*1)
+	MOVOU	X0, -32(DI)(BX*1)
+	MOVOU	X0, -16(DI)(BX*1)
+	RET
+nosse2:
+	MOVL	BX, CX
+	SHRL	$2, CX
+	REP
+	STOSL
+	ANDL	$3, BX
+	JNE	tail
+	RET
-- 
cgit v1.2.3