// Copyright 2012 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 !purego

#include "textflag.h"

// func encryptBlockAsm(nr int, xk *uint32, dst, src *byte)
TEXT ·encryptBlockAsm(SB),NOSPLIT,$0
	MOVQ nr+0(FP), CX
	MOVQ xk+8(FP), AX
	MOVQ dst+16(FP), DX
	MOVQ src+24(FP), BX
	MOVUPS 0(AX), X1
	MOVUPS 0(BX), X0
	ADDQ $16, AX

#define ZER   V26
#define SEL1  V27
#define CAR1  V28
#define CAR2  V29
/*
 * http://www.hyperelliptic.org/EFD/g1p/auto-shortw-jacobian-3.html#doubling-dbl-2004-hmv
 * Cost: 4M + 4S + 1*half + 5add + 2*2 + 1*3.
 * Source: 2004 Hankerson–Menezes–Vanstone, page 91.
 * 	A  = 3(X₁-Z₁²)×(X₁+Z₁²)
 * 	B  = 2Y₁
 * 	Z₃ = B×Z₁
 * 	C  = B²
 * 	D  = C×X₁
 * 	X₃ = A²-2D
 * 	Y₃ = (D-X₃)×A-C²/2
 *

// Copyright 2011 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.

#include "go_asm.h"
#include "go_tls.h"
#include "textflag.h"
#include "time_windows.h"
#include "cgo/abi_amd64.h"

// Offsets into Thread Environment Block (pointer in GS)
#define TEB_TlsSlots 0x1480
#define TEB_ArbitraryPtr 0x28

// Copyright 2013 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 !purego

#include "textflag.h"

// SHA256 block routine. See sha256block.go for Go equivalent.
//
// The algorithm is detailed in FIPS 180-4:
//
//  https://csrc.nist.gov/publications/fips/fips180-4/fips-180-4.pdf

// Wt = Mt; for 0 <= t <= 15

// Copyright 2013 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 !math_big_pure_go

#include "textflag.h"

// This file provides fast assembly versions for the elementary
// arithmetic operations on vectors implemented in arith.go.

// TODO: Consider re-implementing using Advanced SIMD
// once the assembler supports those instructions.

// 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 ppc64 || ppc64le

#include "go_asm.h"
#include "go_tls.h"
#include "funcdata.h"
#include "textflag.h"
#include "asm_ppc64x.h"

#ifdef GOOS_aix
#define cgoCalleeStackSize 48
#else
#define cgoCalleeStackSize 32
#endif

TEXT runtime·rt0_go(SB),NOSPLIT|TOPFRAME,$0

#define ZER   V26
#define SEL1  V27
#define CAR1  V28
#define CAR2  V29
/*
 * https://www.hyperelliptic.org/EFD/g1p/auto-shortw-jacobian-3.html#doubling-dbl-2004-hmv
 * Cost: 4M + 4S + 1*half + 5add + 2*2 + 1*3.
 * Source: 2004 Hankerson–Menezes–Vanstone, page 91.
 * 	A  = 3(X₁-Z₁²)×(X₁+Z₁²)
 * 	B  = 2Y₁
 * 	Z₃ = B×Z₁
 * 	C  = B²
 * 	D  = C×X₁
 * 	X₃ = A²-2D
 * 	Y₃ = (D-X₃)×A-C²/2
 *

// Copyright 2015 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 !linux

#include "textflag.h"

// TODO(minux): this is only valid for ARMv6+
// bool armcas(int32 *val, int32 old, int32 new)
// Atomically:
//	if(*val == old){
//		*val = new;
//		return 1;
//	}else
//		return 0;
TEXT	·Cas(SB),NOSPLIT,$0
	JMP	·armcas(SB)

// Copyright 2012 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.

#include "textflag.h"

// Set the x_crosscall2_ptr C function pointer variable point to crosscall2.
// It's such a pointer chain: _crosscall2_ptr -> x_crosscall2_ptr -> crosscall2
// Use a local trampoline, to avoid taking the address of a dynamically exported
// function.

// Copyright 2015 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.

#include "textflag.h"

// Linux/ARM atomic operations.

// Because there is so much variation in ARM devices,
// the Linux kernel provides an appropriate compare-and-swap
// implementation at address 0xffff0fc0.  Caller sets:
//	R0 = old value
//	R1 = new value
//	R2 = addr