⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 zscal_hummer.s

📁 Optimized GotoBLAS libraries
💻 S
字号:
/*********************************************************************//*                                                                   *//*             Optimized BLAS libraries                              *//*                     By Kazushige Goto <kgoto@tacc.utexas.edu>     *//*                                                                   *//* Copyright (c) The University of Texas, 2005. All rights reserved. *//* UNIVERSITY EXPRESSLY DISCLAIMS ANY AND ALL WARRANTIES CONCERNING  *//* THIS SOFTWARE AND DOCUMENTATION, INCLUDING ANY WARRANTIES OF      *//* MERCHANTABILITY, FITNESS FOR ANY PARTICULAR PURPOSE,              *//* NON-INFRINGEMENT AND WARRANTIES OF PERFORMANCE, AND ANY WARRANTY  *//* THAT MIGHT OTHERWISE ARISE FROM COURSE OF DEALING OR USAGE OF     *//* TRADE. NO WARRANTY IS EITHER EXPRESS OR IMPLIED WITH RESPECT TO   *//* THE USE OF THE SOFTWARE OR DOCUMENTATION.                         *//* Under no circumstances shall University be liable for incidental, *//* special, indirect, direct or consequential damages or loss of     *//* profits, interruption of business, or related expenses which may  *//* arise from use of Software or Documentation, including but not    *//* limited to those resulting from defects in Software and/or        *//* Documentation, or loss or inaccuracy of data of any kind.         *//*********************************************************************/#define ASSEMBLER#include "common.h"		#define N	r3#define X	r6#define INCX	r7	#define INCX2	r4#define XX	r5#define Y	r8#define YY	r9#define ALPHA	f1#define ALPHA_I	f2#define A1	f0#define A2	f16#define A3	f17#define A4	f3#define A5	f4#define A6	f5#define A7	f6#define A8	f7#define B1	f8#define B2	f9#define B3	f10#define B4	f11#define B5	f12#define B6	f13#define B7	f14#define B8	f15	PROLOGUE	PROFCODE	li	r10, -16	stfpdux	f14, SP, r10	stfpdux	f15, SP, r10	stfpdux	f16, SP, r10	stfpdux	f17, SP, r10		li	r10,   0	stwu	r10,   -4(SP)	stwu	r10,   -4(SP)	stwu	r10,   -4(SP)	stwu	r10,   -4(SP)	lfpdx	A1, SP, r10		# Zero clear	fsmfp	ALPHA, ALPHA_I	slwi	INCX,  INCX, BASE_SHIFT	add	INCX2, INCX, INCX	cmpwi	cr0, N, 0	ble	LL(999)	cmpwi	cr0, INCX, SIZE	bne	LL(100)	fcmpu	cr7, ALPHA, A1	bne	cr7, LL(50)	fscmp	cr7, ALPHA, A1	bne	cr7, LL(50)	andi.	r0, X, 2 * SIZE - 1	bne	LL(20)	sub	X,  X, INCX2	srawi.	r0, N, 2	mtspr	CTR,  r0	beq-	LL(15)	.align 4LL(12):	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	bdnz	LL(12)	.align 4LL(15):	andi.	r0,  N, 3	beq	LL(999)	andi.	r0,  N, 2	beq	LL(17)	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	.align 4LL(17):	andi.	r0,  N, 1	beq	LL(999)	STFPDUX	A1,   X, INCX2	b	LL(999)	.align 4LL(20):	sub	X,  X, INCX2	STFDX	A1, X, INCX2	addi	X, X, SIZE	addi	N, N, -1	cmpwi	cr0, N, 0	ble	LL(29)	srawi.	r0, N, 2	mtspr	CTR,  r0	beq-	LL(25)	.align 4LL(22):	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	bdnz	LL(22)	.align 4LL(25):	andi.	r0,  N, 3	beq	LL(29)	andi.	r0,  N, 2	beq	LL(27)	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	.align 4LL(27):	andi.	r0,  N, 1	beq	LL(29)	STFPDUX	A1,   X, INCX2	.align 4LL(29):	STFDX	A1,   X, INCX2	b	LL(999)	.align 4LL(50):	sub	Y,  X, INCX2	sub	X,  X, INCX2	andi.	r0, X, 2 * SIZE - 1	bne	LL(60)	srawi.	r0, N, 3	mtspr	CTR,  r0	beq-	LL(55)	LFPDUX	A1,  X,  INCX2	LFPDUX	A2,  X,  INCX2	LFPDUX	A3,  X,  INCX2	LFPDUX	A4,  X,  INCX2	LFPDUX	A5,  X,  INCX2	fxpmul	B1,  ALPHA, A1	LFPDUX	A6,  X,  INCX2	fxpmul	B2,  ALPHA, A2	LFPDUX	A7,  X,  INCX2	fxpmul	B3,  ALPHA, A3	LFPDUX	A8,  X,  INCX2	fxpmul	B4,  ALPHA, A4 	fxpmul	B5,  ALPHA, A5	fxcxnpma B1, ALPHA, A1, B1	fxcxnpma B2, ALPHA, A2, B2	bdz	LL(53)	.align 4LL(52):	fxcxnpma B3, ALPHA, A3, B3	LFPDUX	A1,  X,  INCX2	fxpmul	B6,  ALPHA, A6	STFPDUX	B1,   Y,  INCX2	fxcxnpma B4, ALPHA, A4, B4	LFPDUX	A2,  X,  INCX2	fxpmul	B7,  ALPHA, A7	STFPDUX	B2,   Y,  INCX2	fxcxnpma B5, ALPHA, A5, B5	LFPDUX	A3,  X,  INCX2	fxpmul	B8,  ALPHA, A8	STFPDUX	B3,   Y,  INCX2	fxcxnpma B6, ALPHA, A6, B6	LFPDUX	A4,  X,  INCX2	fxpmul	B1,  ALPHA, A1	STFPDUX	B4,   Y,  INCX2	fxcxnpma B7, ALPHA, A7, B7 	LFPDUX	A5,  X,  INCX2	fxpmul	B2,  ALPHA, A2	STFPDUX	B5,   Y,  INCX2	fxcxnpma B8, ALPHA, A8, B8	LFPDUX	A6,  X,  INCX2	fxpmul	B3,  ALPHA, A3	STFPDUX	B6,   Y,  INCX2	fxcxnpma B1, ALPHA, A1, B1	LFPDUX	A7,  X,  INCX2	fxpmul	B4,  ALPHA, A4	STFPDUX	B7,   Y,  INCX2	fxcxnpma B2, ALPHA, A2, B2	LFPDUX	A8,  X,  INCX2	fxpmul	B5,  ALPHA, A5	STFPDUX	B8,   Y,  INCX2	bdnz	LL(52)	.align 4LL(53):	fxcxnpma B3, ALPHA, A3, B3	fxpmul	B6,  ALPHA, A6	STFPDUX	B1,   Y,  INCX2	fxcxnpma B4, ALPHA, A4, B4	fxpmul	B7,  ALPHA, A7	STFPDUX	B2,   Y,  INCX2	fxcxnpma B5, ALPHA, A5, B5	fxpmul	B8,  ALPHA, A8	STFPDUX	B3,   Y,  INCX2	fxcxnpma B6, ALPHA, A6, B6	STFPDUX	B4,   Y,  INCX2	fxcxnpma B7, ALPHA, A7, B7	STFPDUX	B5,   Y,  INCX2	fxcxnpma B8, ALPHA, A8, B8	STFPDUX	B6,   Y,  INCX2	STFPDUX	B7,   Y,  INCX2	STFPDUX	B8,   Y,  INCX2	.align 4LL(55):	andi.	r0,  N, 7	beq	LL(999)	andi.	r0,  N, 4	beq	LL(56)	LFPDUX	A1,  X,  INCX2	LFPDUX	A2,  X,  INCX2	LFPDUX	A3,  X,  INCX2	LFPDUX	A4,  X,  INCX2	fxpmul	B1,  ALPHA, A1	fxpmul	B2,  ALPHA, A2	fxpmul	B3,  ALPHA, A3	fxpmul	B4,  ALPHA, A4	fxcxnpma B1, ALPHA, A1, B1	fxcxnpma B2, ALPHA, A2, B2	fxcxnpma B3, ALPHA, A3, B3	fxcxnpma B4, ALPHA, A4, B4	STFPDUX	B1,   Y,  INCX2	STFPDUX	B2,   Y,  INCX2	STFPDUX	B3,   Y,  INCX2	STFPDUX	B4,   Y,  INCX2	.align 4LL(56):	andi.	r0,  N, 2	beq	LL(57)	LFPDUX	A1,  X,  INCX2	LFPDUX	A2,  X,  INCX2	fxpmul	B1,  ALPHA, A1	fxpmul	B2,  ALPHA, A2	fxcxnpma B1, ALPHA, A1, B1	fxcxnpma B2, ALPHA, A2, B2	STFPDUX	B1,   Y,  INCX2	STFPDUX	B2,   Y,  INCX2	.align 4LL(57):	andi.	r0,  N, 1	beq	LL(999)	LFPDUX	A1,   X,  INCX2	fxpmul	B1,  ALPHA, A1	fxcxnpma B1, ALPHA, A1, B1	STFPDUX	B1,   Y,  INCX2	b	LL(999)	.align 4LL(60):	addi	XX, X, SIZE	addi	YY, Y, SIZE	srawi.	r0, N, 2	mtspr	CTR,  r0	beq-	LL(65)	LFDUX	A1,  X,  INCX2	LFDUX	A2,  XX, INCX2	LFDUX	A3,  X,  INCX2	LFDUX	A4,  XX, INCX2	LFDUX	A5,  X,  INCX2	fmul	B1, ALPHA,   A1	LFDUX	A6,  XX, INCX2	fmul	B2, ALPHA_I, A1	LFDUX	A7,  X,  INCX2	fmul	B3, ALPHA,   A3	LFDUX	A8,  XX, INCX2	fmul	B4, ALPHA_I, A3	fmul	B5, ALPHA,   A5	fnmsub	B1, ALPHA_I, A2, B1	fmadd	B2, ALPHA  , A2, B2	bdz	LL(63)	.align 4LL(62):	fnmsub	B3, ALPHA_I, A4, B3 	LFDUX	A1,  X,  INCX2	fmul	B6, ALPHA_I, A5	STFDUX	B1,  Y,  INCX2	fmadd	B4, ALPHA  , A4, B4	LFDUX	A2,  XX, INCX2	fmul	B7, ALPHA,   A7	STFDUX	B2,  YY, INCX2	fnmsub	B5, ALPHA_I, A6, B5	LFDUX	A3,  X,  INCX2	fmul	B8, ALPHA_I, A7	STFDUX	B3,  Y,  INCX2	fmadd	B6, ALPHA  , A6, B6	LFDUX	A4,  XX, INCX2	fmul	B1, ALPHA,   A1	STFDUX	B4,  YY, INCX2	fnmsub	B7, ALPHA_I, A8, B7	LFDUX	A5,  X,  INCX2	fmul	B2, ALPHA_I, A1	STFDUX	B5,  Y,  INCX2	fmadd	B8, ALPHA  , A8, B8	LFDUX	A6,  XX, INCX2	fmul	B3, ALPHA,   A3	STFDUX	B6,  YY, INCX2	fnmsub	B1, ALPHA_I, A2, B1	LFDUX	A7,  X,  INCX2	fmul	B4, ALPHA_I, A3	STFDUX	B7,  Y,  INCX2	fmadd	B2, ALPHA  , A2, B2	LFDUX	A8,  XX, INCX2	fmul	B5, ALPHA,   A5	STFDUX	B8,  YY, INCX2	bdnz	LL(62)	.align 4LL(63):	fnmsub	B3, ALPHA_I, A4, B3	fmul	B6, ALPHA_I, A5	STFDUX	B1,  Y,  INCX2	fmadd	B4, ALPHA  , A4, B4	fmul	B7, ALPHA,   A7	STFDUX	B2,  YY, INCX2	fnmsub	B5, ALPHA_I, A6, B5	fmul	B8, ALPHA_I, A7	STFDUX	B3,  Y,  INCX2	fmadd	B6, ALPHA  , A6, B6	STFDUX	B4,  YY, INCX2	fnmsub	B7, ALPHA_I, A8, B7	STFDUX	B5,  Y,  INCX2	fmadd	B8, ALPHA  , A8, B8	STFDUX	B6,  YY, INCX2	STFDUX	B7,  Y,  INCX2	STFDUX	B8,  YY, INCX2	.align 4LL(65):	andi.	r0,  N, 3	beq	LL(999)	andi.	r0,  N, 2	beq	LL(67)	LFDUX	A1,  X,  INCX2	LFDUX	A2,  XX, INCX2	LFDUX	A3,  X,  INCX2	LFDUX	A4,  XX, INCX2	fmul	B1, ALPHA, A1	fmul	B2, ALPHA, A2	fmul	B3, ALPHA, A3	fmul	B4, ALPHA, A4	fnmsub	B1, ALPHA_I, A2, B1	fmadd	B2, ALPHA_I, A1, B2	fnmsub	B3, ALPHA_I, A4, B3	fmadd	B4, ALPHA_I, A3, B4	STFDUX	B1,  Y,  INCX2	STFDUX	B2,  YY, INCX2	STFDUX	B3,  Y,  INCX2	STFDUX	B4,  YY, INCX2	.align 4LL(67):	andi.	r0,  N, 1	beq	LL(999)	LFDUX	A1,   X,  INCX2	LFDUX	A2,   XX, INCX2	fmul	B1, ALPHA, A1	fmul	B2, ALPHA, A2	fnmsub	B1, ALPHA_I, A2, B1	fmadd	B2, ALPHA_I, A1, B2	STFDUX	B1,   Y,  INCX2	STFDUX	B2,   YY, INCX2	b	LL(999)	.align 4LL(100):	fcmpu	cr7, ALPHA, A1	bne	cr7, LL(150)	fscmp	cr7, ALPHA, A1	bne	cr7, LL(150)	andi.	r0, X, 2 * SIZE - 1	bne	LL(120)	sub	X,  X, INCX2	srawi.	r0, N, 2	mtspr	CTR,  r0	beq-	LL(115)	.align 4LL(112):	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	bdnz	LL(112)	.align 4LL(115):	andi.	r0,  N, 3	beq	LL(999)	andi.	r0,  N, 2	beq	LL(117)	STFPDUX	A1,   X, INCX2	STFPDUX	A1,   X, INCX2	.align 4LL(117):	andi.	r0,  N, 1	beq	LL(999)	STFPDUX	A1,   X, INCX2	b	LL(999)	.align 4LL(120):	subi	INCX2, INCX2, SIZE	li	INCX, SIZE	sub	X,  X, INCX2	srawi.	r0, N, 2	mtspr	CTR,  r0	beq-	LL(125)	.align 4LL(122):	STFDUX	A1,   X, INCX2	STFDUX	A1,   X, INCX	STFDUX	A1,   X, INCX2	STFDUX	A1,   X, INCX	STFDUX	A1,   X, INCX2	STFDUX	A1,   X, INCX	STFDUX	A1,   X, INCX2	STFDUX	A1,   X, INCX	bdnz	LL(122)	.align 4LL(125):	andi.	r0,  N, 3	beq	LL(999)	andi.	r0,  N, 2	beq	LL(127)	STFDUX	A1,   X, INCX2	STFDUX	A1,   X, INCX	STFDUX	A1,   X, INCX2	STFDUX	A1,   X, INCX	.align 4LL(127):	andi.	r0,  N, 1	beq	LL(999)	STFDUX	A1,   X, INCX2	STFDUX	A1,   X, INCX	b	LL(999)	.align 4LL(150):	sub	Y,  X, INCX2	sub	X,  X, INCX2	andi.	r0, X, 2 * SIZE - 1	bne	LL(160)	srawi.	r0, N, 3	mtspr	CTR,  r0	beq-	LL(155)	LFPDUX	A1,  X,  INCX2	LFPDUX	A2,  X,  INCX2	LFPDUX	A3,  X,  INCX2	LFPDUX	A4,  X,  INCX2	LFPDUX	A5,  X,  INCX2	fxpmul	B1,  ALPHA, A1	LFPDUX	A6,  X,  INCX2	fxpmul	B2,  ALPHA, A2	LFPDUX	A7,  X,  INCX2	fxpmul	B3,  ALPHA, A3	LFPDUX	A8,  X,  INCX2	fxpmul	B4,  ALPHA, A4 	fxpmul	B5,  ALPHA, A5	fxcxnpma B1, ALPHA, A1, B1	fxcxnpma B2, ALPHA, A2, B2	bdz	LL(153)	.align 4LL(152):	fxcxnpma B3, ALPHA, A3, B3	LFPDUX	A1,  X,  INCX2	fxpmul	B6,  ALPHA, A6	STFPDUX	B1,   Y,  INCX2	fxcxnpma B4, ALPHA, A4, B4	LFPDUX	A2,  X,  INCX2	fxpmul	B7,  ALPHA, A7	STFPDUX	B2,   Y,  INCX2	fxcxnpma B5, ALPHA, A5, B5	LFPDUX	A3,  X,  INCX2	fxpmul	B8,  ALPHA, A8	STFPDUX	B3,   Y,  INCX2	fxcxnpma B6, ALPHA, A6, B6	LFPDUX	A4,  X,  INCX2	fxpmul	B1,  ALPHA, A1	STFPDUX	B4,   Y,  INCX2	fxcxnpma B7, ALPHA, A7, B7 	LFPDUX	A5,  X,  INCX2	fxpmul	B2,  ALPHA, A2	STFPDUX	B5,   Y,  INCX2	fxcxnpma B8, ALPHA, A8, B8	LFPDUX	A6,  X,  INCX2	fxpmul	B3,  ALPHA, A3	STFPDUX	B6,   Y,  INCX2	fxcxnpma B1, ALPHA, A1, B1	LFPDUX	A7,  X,  INCX2	fxpmul	B4,  ALPHA, A4	STFPDUX	B7,   Y,  INCX2	fxcxnpma B2, ALPHA, A2, B2	LFPDUX	A8,  X,  INCX2	fxpmul	B5,  ALPHA, A5	STFPDUX	B8,   Y,  INCX2	bdnz	LL(152)	.align 4LL(153):	fxcxnpma B3, ALPHA, A3, B3	fxpmul	B6,  ALPHA, A6	STFPDUX	B1,   Y,  INCX2	fxcxnpma B4, ALPHA, A4, B4	fxpmul	B7,  ALPHA, A7	STFPDUX	B2,   Y,  INCX2	fxcxnpma B5, ALPHA, A5, B5	fxpmul	B8,  ALPHA, A8	STFPDUX	B3,   Y,  INCX2	fxcxnpma B6, ALPHA, A6, B6	STFPDUX	B4,   Y,  INCX2	fxcxnpma B7, ALPHA, A7, B7	STFPDUX	B5,   Y,  INCX2	fxcxnpma B8, ALPHA, A8, B8	STFPDUX	B6,   Y,  INCX2	STFPDUX	B7,   Y,  INCX2	STFPDUX	B8,   Y,  INCX2	.align 4LL(155):	andi.	r0,  N, 7	beq	LL(999)	andi.	r0,  N, 4	beq	LL(156)	LFPDUX	A1,  X,  INCX2	LFPDUX	A2,  X,  INCX2	LFPDUX	A3,  X,  INCX2	LFPDUX	A4,  X,  INCX2	fxpmul	B1,  ALPHA, A1	fxpmul	B2,  ALPHA, A2	fxpmul	B3,  ALPHA, A3	fxpmul	B4,  ALPHA, A4	fxcxnpma B1, ALPHA, A1, B1	fxcxnpma B2, ALPHA, A2, B2	fxcxnpma B3, ALPHA, A3, B3	fxcxnpma B4, ALPHA, A4, B4	STFPDUX	B1,   Y,  INCX2	STFPDUX	B2,   Y,  INCX2	STFPDUX	B3,   Y,  INCX2	STFPDUX	B4,   Y,  INCX2	.align 4LL(156):	andi.	r0,  N, 2	beq	LL(157)	LFPDUX	A1,  X,  INCX2	LFPDUX	A2,  X,  INCX2	fxpmul	B1,  ALPHA, A1	fxpmul	B2,  ALPHA, A2	fxcxnpma B1, ALPHA, A1, B1	fxcxnpma B2, ALPHA, A2, B2	STFPDUX	B1,   Y,  INCX2	STFPDUX	B2,   Y,  INCX2	.align 4LL(157):	andi.	r0,  N, 1	beq	LL(999)	LFPDUX	A1,   X,  INCX2	fxpmul	B1,  ALPHA, A1	fxcxnpma B1, ALPHA, A1, B1	STFPDUX	B1,   Y,  INCX2	b	LL(999)	.align 4LL(160):	addi	XX, X, SIZE	addi	YY, Y, SIZE	srawi.	r0, N, 2	mtspr	CTR,  r0	beq-	LL(165)	LFDUX	A1,  X,  INCX2	LFDUX	A2,  XX, INCX2	LFDUX	A3,  X,  INCX2	LFDUX	A4,  XX, INCX2	LFDUX	A5,  X,  INCX2	fmul	B1, ALPHA,   A1	LFDUX	A6,  XX, INCX2	fmul	B2, ALPHA_I, A1	LFDUX	A7,  X,  INCX2	fmul	B3, ALPHA,   A3	LFDUX	A8,  XX, INCX2	fmul	B4, ALPHA_I, A3	fmul	B5, ALPHA,   A5	fnmsub	B1, ALPHA_I, A2, B1	fmadd	B2, ALPHA  , A2, B2	bdz	LL(163)	.align 4LL(162):	fnmsub	B3, ALPHA_I, A4, B3 	LFDUX	A1,  X,  INCX2	fmul	B6, ALPHA_I, A5	STFDUX	B1,  Y,  INCX2	fmadd	B4, ALPHA  , A4, B4	LFDUX	A2,  XX, INCX2	fmul	B7, ALPHA,   A7	STFDUX	B2,  YY, INCX2	fnmsub	B5, ALPHA_I, A6, B5	LFDUX	A3,  X,  INCX2	fmul	B8, ALPHA_I, A7	STFDUX	B3,  Y,  INCX2	fmadd	B6, ALPHA  , A6, B6	LFDUX	A4,  XX, INCX2	fmul	B1, ALPHA,   A1	STFDUX	B4,  YY, INCX2	fnmsub	B7, ALPHA_I, A8, B7	LFDUX	A5,  X,  INCX2	fmul	B2, ALPHA_I, A1	STFDUX	B5,  Y,  INCX2	fmadd	B8, ALPHA  , A8, B8	LFDUX	A6,  XX, INCX2	fmul	B3, ALPHA,   A3	STFDUX	B6,  YY, INCX2	fnmsub	B1, ALPHA_I, A2, B1	LFDUX	A7,  X,  INCX2	fmul	B4, ALPHA_I, A3	STFDUX	B7,  Y,  INCX2	fmadd	B2, ALPHA  , A2, B2	LFDUX	A8,  XX, INCX2	fmul	B5, ALPHA,   A5	STFDUX	B8,  YY, INCX2	bdnz	LL(162)	.align 4LL(163):	fnmsub	B3, ALPHA_I, A4, B3	fmul	B6, ALPHA_I, A5	STFDUX	B1,  Y,  INCX2	fmadd	B4, ALPHA  , A4, B4	fmul	B7, ALPHA,   A7	STFDUX	B2,  YY, INCX2	fnmsub	B5, ALPHA_I, A6, B5	fmul	B8, ALPHA_I, A7	STFDUX	B3,  Y,  INCX2	fmadd	B6, ALPHA  , A6, B6	STFDUX	B4,  YY, INCX2	fnmsub	B7, ALPHA_I, A8, B7	STFDUX	B5,  Y,  INCX2	fmadd	B8, ALPHA  , A8, B8	STFDUX	B6,  YY, INCX2	STFDUX	B7,  Y,  INCX2	STFDUX	B8,  YY, INCX2	.align 4LL(165):	andi.	r0,  N, 3	beq	LL(999)	andi.	r0,  N, 2	beq	LL(167)	LFDUX	A1,  X,  INCX2	LFDUX	A2,  XX, INCX2	LFDUX	A3,  X,  INCX2	LFDUX	A4,  XX, INCX2	fmul	B1, ALPHA, A1	fmul	B2, ALPHA, A2	fmul	B3, ALPHA, A3	fmul	B4, ALPHA, A4	fnmsub	B1, ALPHA_I, A2, B1	fmadd	B2, ALPHA_I, A1, B2	fnmsub	B3, ALPHA_I, A4, B3	fmadd	B4, ALPHA_I, A3, B4	STFDUX	B1,  Y,  INCX2	STFDUX	B2,  YY, INCX2	STFDUX	B3,  Y,  INCX2	STFDUX	B4,  YY, INCX2	.align 4LL(167):	andi.	r0,  N, 1	beq	LL(999)	LFDUX	A1,   X,  INCX2	LFDUX	A2,   XX, INCX2	fmul	B1, ALPHA, A1	fmul	B2, ALPHA, A2	fnmsub	B1, ALPHA_I, A2, B1	fmadd	B2, ALPHA_I, A1, B2	STFDUX	B1,   Y,  INCX2	STFDUX	B2,   YY, INCX2	.align 4LL(999):	li	r10, 16	lfpdux	f17, SP, r10	lfpdux	f16, SP, r10	lfpdux	f15, SP, r10	lfpdux	f14, SP, r10	addi	SP, SP,  16	blr	EPILOGUE

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -