⭐ 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

📄 zsymv_u.s

📁 Optimized GotoBLAS libraries
💻 S
📖 第 1 页 / 共 3 页
字号:
	LFD	xtemp2,  9 * SIZE(XX)	FNMSUB	y07, atemp2, a4, y07	NOP2	FMADD2	xsum4, xtemp1, a6,  xsum4	LFD	xtemp1,  8 * SIZE(XX)	FMADD	y08, atemp1, a4, y08	NOP2	FMADD	xsum1, xtemp3, a3,  xsum1	LFD	y03, 10 * SIZE(YY)	FMADD	y05, atemp3, a5, y05	NOP2	FMADD	xsum2, xtemp4, a3,  xsum2	LFD	a3, 10 * SIZE(AO1)	FMADD	y06, atemp4, a5, y06	LFD	a5,  8 * SIZE(AO2)	FMADD	xsum3, xtemp3, a7,  xsum3	LFD	y04, 11 * SIZE(YY)	FMADD	y07, atemp3, a7, y07	NOP2	FMADD	xsum4, xtemp4, a7,  xsum4	NOP1	FMADD	y08, atemp4, a7, y08	LFD	a7, 10 * SIZE(AO2)	FMADD1	xsum1, xtemp4, a4,  xsum1	NOP1	FNMSUB	y05, atemp4, a6, y05	NOP2	FMADD2	xsum2, xtemp3, a4,  xsum2	LFD	a4, 11 * SIZE(AO1)	FMADD	y06, atemp3, a6, y06	LFD	a6,  9 * SIZE(AO2)	FMADD1	xsum3, xtemp4, a8,  xsum3	LFD	xtemp4, 11 * SIZE(XX)	FNMSUB	y07, atemp4, a8, y07	bdz	LL(13)	.align 4LL(12):	FMADD2	xsum4, xtemp3, a8,  xsum4	LFD	xtemp3, 10 * SIZE(XX)	FMADD	y08, atemp3, a8, y08	LFD	a8, 11 * SIZE(AO2)	FMADD	xsum1, xtemp1, a1,  xsum1	STFD	y05,  4 * SIZE(YY)	FMADD	y01, atemp1, a1, y01	PREFETCH_A2	FMADD	xsum2, xtemp2, a1,  xsum2	STFD	y06,  5 * SIZE(YY)	FMADD	y02, atemp2, a1, y02	LFD	a1, 12 * SIZE(AO1)	FMADD	xsum3, xtemp1, a5,  xsum3	STFD	y07,  6 * SIZE(YY)	FMADD	y03, atemp1, a3, y03	NOP2	FMADD	xsum4, xtemp2, a5,  xsum4	STFD	y08,  7 * SIZE(YY)	FMADD	y04, atemp2, a3, y04	NOP2	FMADD1	xsum1, xtemp2, a2,  xsum1	LFD	y05, 12 * SIZE(YY)	FNMSUB	y01, atemp2, a2, y01	NOP2	FMADD2	xsum2, xtemp1, a2,  xsum2	LFD	y06, 13 * SIZE(YY)	FMADD	y02, atemp1, a2, y02	LFD	a2, 13 * SIZE(AO1)	FMADD1	xsum3, xtemp2, a6,  xsum3	LFD	xtemp2, 13 * SIZE(XX)	FNMSUB	y03, atemp2, a4, y03	NOP2	FMADD2	xsum4, xtemp1, a6,  xsum4	LFD	xtemp1, 12 * SIZE(XX)	FMADD	y04, atemp1, a4, y04	NOP2	FMADD	xsum1, xtemp3, a3,  xsum1	LFD	y07, 14 * SIZE(YY)	FMADD	y01, atemp3, a5, y01	NOP2	FMADD	xsum2, xtemp4, a3,  xsum2	LFD	a3, 14 * SIZE(AO1)	FMADD	y02, atemp4, a5, y02	LFD	a5, 12 * SIZE(AO2)	FMADD	xsum3, xtemp3, a7,  xsum3	LFD	y08, 15 * SIZE(YY)	FMADD	y03, atemp3, a7, y03	NOP2	FMADD	xsum4, xtemp4, a7,  xsum4	NOP1	FMADD	y04, atemp4, a7, y04	LFD	a7, 14 * SIZE(AO2)	FMADD1	xsum1, xtemp4, a4,  xsum1	NOP1	FNMSUB	y01, atemp4, a6, y01	PREFETCH_Y	FMADD2	xsum2, xtemp3, a4,  xsum2	LFD	a4, 15 * SIZE(AO1)	FMADD	y02, atemp3, a6, y02	LFD	a6, 13 * SIZE(AO2)	FMADD1	xsum3, xtemp4, a8,  xsum3	LFD	xtemp4, 15 * SIZE(XX)	FNMSUB	y03, atemp4, a8, y03	NOP2	FMADD2	xsum4, xtemp3, a8,  xsum4	LFD	xtemp3, 14 * SIZE(XX)	FMADD	y04, atemp3, a8, y04	LFD	a8, 15 * SIZE(AO2)	FMADD	xsum1, xtemp1, a1,  xsum1	STFD	y01,  8 * SIZE(YY)	FMADD	y05, atemp1, a1, y05	NOP2	FMADD	xsum2, xtemp2, a1,  xsum2	STFD	y02,  9 * SIZE(YY)	FMADD	y06, atemp2, a1, y06	LFD	a1, 16 * SIZE(AO1)	FMADD	xsum3, xtemp1, a5,  xsum3	STFD	y03, 10 * SIZE(YY)	FMADD	y07, atemp1, a3, y07	NOP2	FMADD	xsum4, xtemp2, a5,  xsum4	STFD	y04, 11 * SIZE(YY)	FMADD	y08, atemp2, a3, y08	NOP2	FMADD1	xsum1, xtemp2, a2,  xsum1	LFD	y01, 16 * SIZE(YY)	FNMSUB	y05, atemp2, a2, y05	NOP2	FMADD2	xsum2, xtemp1, a2,  xsum2	LFD	y02, 17 * SIZE(YY)	FMADD	y06, atemp1, a2, y06	LFD	a2, 17 * SIZE(AO1)	FMADD1	xsum3, xtemp2, a6,  xsum3	LFD	xtemp2, 17 * SIZE(XX)	FNMSUB	y07, atemp2, a4, y07	NOP2	FMADD2	xsum4, xtemp1, a6,  xsum4	LFD	xtemp1, 16 * SIZE(XX)	FMADD	y08, atemp1, a4, y08	addi	AO2, AO2, 16 * SIZE	FMADD	xsum1, xtemp3, a3,  xsum1	LFD	y03, 18 * SIZE(YY)	FMADD	y05, atemp3, a5, y05	addi	XX, XX, 16 * SIZE	FMADD	xsum2, xtemp4, a3,  xsum2	LFD	a3, 18 * SIZE(AO1)	FMADD	y06, atemp4, a5, y06	LFD	a5,  0 * SIZE(AO2)	FMADD	xsum3, xtemp3, a7,  xsum3	LFD	y04, 19 * SIZE(YY)	FMADD	y07, atemp3, a7, y07	NOP2	FMADD	xsum4, xtemp4, a7,  xsum4	addi	AO1, AO1, 16 * SIZE	FMADD	y08, atemp4, a7, y08	LFD	a7,  2 * SIZE(AO2)	FMADD1	xsum1, xtemp4, a4,  xsum1	addi	YY, YY, 16 * SIZE	FNMSUB	y05, atemp4, a6, y05	NOP2	FMADD2	xsum2, xtemp3, a4,  xsum2	LFD	a4,  3 * SIZE(AO1)	FMADD	y06, atemp3, a6, y06	LFD	a6,  1 * SIZE(AO2)	FMADD1	xsum3, xtemp4, a8,  xsum3	LFD	xtemp4,  3 * SIZE(XX)	FNMSUB	y07, atemp4, a8, y07	NOP2	FMADD2	xsum4, xtemp3, a8,  xsum4	LFD	xtemp3,  2 * SIZE(XX)	FMADD	y08, atemp3, a8, y08	LFD	a8,  3 * SIZE(AO2)	FMADD	xsum1, xtemp1, a1,  xsum1	STFD	y05, -4 * SIZE(YY)	FMADD	y01, atemp1, a1, y01	PREFETCH_A1	FMADD	xsum2, xtemp2, a1,  xsum2	STFD	y06, -3 * SIZE(YY)	FMADD	y02, atemp2, a1, y02	LFD	a1,  4 * SIZE(AO1)	FMADD	xsum3, xtemp1, a5,  xsum3	STFD	y07, -2 * SIZE(YY)	FMADD	y03, atemp1, a3, y03	NOP2	FMADD	xsum4, xtemp2, a5,  xsum4	STFD	y08, -1 * SIZE(YY)	FMADD	y04, atemp2, a3, y04	NOP2	FMADD1	xsum1, xtemp2, a2,  xsum1	LFD	y05,  4 * SIZE(YY)	FNMSUB	y01, atemp2, a2, y01	NOP2	FMADD2	xsum2, xtemp1, a2,  xsum2	LFD	y06,  5 * SIZE(YY)	FMADD	y02, atemp1, a2, y02	LFD	a2,  5 * SIZE(AO1)	FMADD1	xsum3, xtemp2, a6,  xsum3	LFD	xtemp2,  5 * SIZE(XX)	FNMSUB	y03, atemp2, a4, y03	NOP2	FMADD2	xsum4, xtemp1, a6,  xsum4	LFD	xtemp1,  4 * SIZE(XX)	FMADD	y04, atemp1, a4, y04	NOP2	FMADD	xsum1, xtemp3, a3,  xsum1	LFD	y07,  6 * SIZE(YY)	FMADD	y01, atemp3, a5, y01	NOP2	FMADD	xsum2, xtemp4, a3,  xsum2	LFD	a3,  6 * SIZE(AO1)	FMADD	y02, atemp4, a5, y02	LFD	a5,  4 * SIZE(AO2)	FMADD	xsum3, xtemp3, a7,  xsum3	LFD	y08,  7 * SIZE(YY)	FMADD	y03, atemp3, a7, y03	NOP2	FMADD	xsum4, xtemp4, a7,  xsum4	NOP1	FMADD	y04, atemp4, a7, y04	LFD	a7,  6 * SIZE(AO2)	FMADD1	xsum1, xtemp4, a4,  xsum1	NOP1	FNMSUB	y01, atemp4, a6, y01	PREFETCH_X	FMADD2	xsum2, xtemp3, a4,  xsum2	LFD	a4,  7 * SIZE(AO1)	FMADD	y02, atemp3, a6, y02	LFD	a6,  5 * SIZE(AO2)	FMADD1	xsum3, xtemp4, a8,  xsum3	LFD	xtemp4,  7 * SIZE(XX)	FNMSUB	y03, atemp4, a8, y03	NOP2	FMADD2	xsum4, xtemp3, a8,  xsum4	LFD	xtemp3,  6 * SIZE(XX)	FMADD	y04, atemp3, a8, y04	LFD	a8,  7 * SIZE(AO2)	FMADD	xsum1, xtemp1, a1,  xsum1	STFD	y01,  0 * SIZE(YY)	FMADD	y05, atemp1, a1, y05	NOP2	FMADD	xsum2, xtemp2, a1,  xsum2	STFD	y02,  1 * SIZE(YY)	FMADD	y06, atemp2, a1, y06	LFD	a1,  8 * SIZE(AO1)	FMADD	xsum3, xtemp1, a5,  xsum3	STFD	y03,  2 * SIZE(YY)	FMADD	y07, atemp1, a3, y07	NOP2	FMADD	xsum4, xtemp2, a5,  xsum4	STFD	y04,  3 * SIZE(YY)	FMADD	y08, atemp2, a3, y08	NOP2	FMADD1	xsum1, xtemp2, a2,  xsum1	LFD	y01,  8 * SIZE(YY)	FNMSUB	y05, atemp2, a2, y05	NOP2	FMADD2	xsum2, xtemp1, a2,  xsum2	LFD	y02,  9 * SIZE(YY)	FMADD	y06, atemp1, a2, y06	LFD	a2,  9 * SIZE(AO1)	FMADD1	xsum3, xtemp2, a6,  xsum3	LFD	xtemp2,  9 * SIZE(XX)	FNMSUB	y07, atemp2, a4, y07	NOP2	FMADD2	xsum4, xtemp1, a6,  xsum4	LFD	xtemp1,  8 * SIZE(XX)	FMADD	y08, atemp1, a4, y08	NOP2	FMADD	xsum1, xtemp3, a3,  xsum1	LFD	y03, 10 * SIZE(YY)	FMADD	y05, atemp3, a5, y05	NOP2	FMADD	xsum2, xtemp4, a3,  xsum2	LFD	a3, 10 * SIZE(AO1)	FMADD	y06, atemp4, a5, y06	LFD	a5,  8 * SIZE(AO2)	FMADD	xsum3, xtemp3, a7,  xsum3	LFD	y04, 11 * SIZE(YY)	FMADD	y07, atemp3, a7, y07	NOP2	FMADD	xsum4, xtemp4, a7,  xsum4	NOP1	FMADD	y08, atemp4, a7, y08	LFD	a7, 10 * SIZE(AO2)	FMADD1	xsum1, xtemp4, a4,  xsum1	NOP1	FNMSUB	y05, atemp4, a6, y05	NOP2	FMADD2	xsum2, xtemp3, a4,  xsum2	LFD	a4, 11 * SIZE(AO1)	FMADD	y06, atemp3, a6, y06	LFD	a6,  9 * SIZE(AO2)	FMADD1	xsum3, xtemp4, a8,  xsum3	LFD	xtemp4, 11 * SIZE(XX)	FNMSUB	y07, atemp4, a8, y07	bdnz	LL(12)	.align 4LL(13):	FMADD2	xsum4, xtemp3, a8,  xsum4	LFD	xtemp3, 10 * SIZE(XX)	FMADD	y08, atemp3, a8, y08	LFD	a8, 11 * SIZE(AO2)	FMADD	xsum1, xtemp1, a1,  xsum1	STFD	y05,  4 * SIZE(YY)	FMADD	y01, atemp1, a1, y01	NOP2	FMADD	xsum2, xtemp2, a1,  xsum2	STFD	y06,  5 * SIZE(YY)	FMADD	y02, atemp2, a1, y02	LFD	a1, 12 * SIZE(AO1)	FMADD	xsum3, xtemp1, a5,  xsum3	STFD	y07,  6 * SIZE(YY)	FMADD	y03, atemp1, a3, y03	NOP2	FMADD	xsum4, xtemp2, a5,  xsum4	STFD	y08,  7 * SIZE(YY)	FMADD	y04, atemp2, a3, y04	NOP2	FMADD1	xsum1, xtemp2, a2,  xsum1	LFD	y05, 12 * SIZE(YY)	FNMSUB	y01, atemp2, a2, y01	NOP2	FMADD2	xsum2, xtemp1, a2,  xsum2	LFD	y06, 13 * SIZE(YY)	FMADD	y02, atemp1, a2, y02	LFD	a2, 13 * SIZE(AO1)	FMADD1	xsum3, xtemp2, a6,  xsum3	LFD	xtemp2, 13 * SIZE(XX)	FNMSUB	y03, atemp2, a4, y03	NOP2	FMADD2	xsum4, xtemp1, a6,  xsum4	LFD	xtemp1, 12 * SIZE(XX)	FMADD	y04, atemp1, a4, y04	NOP2	FMADD	xsum1, xtemp3, a3,  xsum1	LFD	y07, 14 * SIZE(YY)	FMADD	y01, atemp3, a5, y01	NOP2	FMADD	xsum2, xtemp4, a3,  xsum2	LFD	a3, 14 * SIZE(AO1)	FMADD	y02, atemp4, a5, y02	LFD	a5, 12 * SIZE(AO2)	FMADD	xsum3, xtemp3, a7,  xsum3	LFD	y08, 15 * SIZE(YY)	FMADD	y03, atemp3, a7, y03	NOP2	FMADD	xsum4, xtemp4, a7,  xsum4	NOP1	FMADD	y04, atemp4, a7, y04	LFD	a7, 14 * SIZE(AO2)	FMADD1	xsum1, xtemp4, a4,  xsum1	NOP1	FNMSUB	y01, atemp4, a6, y01	NOP2	FMADD2	xsum2, xtemp3, a4,  xsum2	LFD	a4, 15 * SIZE(AO1)	FMADD	y02, atemp3, a6, y02	LFD	a6, 13 * SIZE(AO2)	FMADD1	xsum3, xtemp4, a8,  xsum3	LFD	xtemp4, 15 * SIZE(XX)	FNMSUB	y03, atemp4, a8, y03	NOP2	FMADD2	xsum4, xtemp3, a8,  xsum4	LFD	xtemp3, 14 * SIZE(XX)	FMADD	y04, atemp3, a8, y04	LFD	a8, 15 * SIZE(AO2)	FMADD	xsum1, xtemp1, a1,  xsum1	STFD	y01,  8 * SIZE(YY)	FMADD	y05, atemp1, a1, y05	NOP2	FMADD	xsum2, xtemp2, a1,  xsum2	STFD	y02,  9 * SIZE(YY)	FMADD	y06, atemp2, a1, y06	LFD	a1, 16 * SIZE(AO1)	FMADD	xsum3, xtemp1, a5,  xsum3	STFD	y03, 10 * SIZE(YY)	FMADD	y07, atemp1, a3, y07	NOP2	FMADD	xsum4, xtemp2, a5,  xsum4	STFD	y04, 11 * SIZE(YY)	FMADD	y08, atemp2, a3, y08	NOP2	FMADD1	xsum1, xtemp2, a2,  xsum1	LFD	y01, 16 * SIZE(YY)	FNMSUB	y05, atemp2, a2, y05	NOP2	FMADD2	xsum2, xtemp1, a2,  xsum2	LFD	y02, 17 * SIZE(YY)	FMADD	y06, atemp1, a2, y06	LFD	a2, 17 * SIZE(AO1)	FMADD1	xsum3, xtemp2, a6,  xsum3	LFD	xtemp2, 17 * SIZE(XX)	FNMSUB	y07, atemp2, a4, y07	NOP2	FMADD2	xsum4, xtemp1, a6,  xsum4	LFD	xtemp1, 16 * SIZE(XX)	FMADD	y08, atemp1, a4, y08	addi	AO2, AO2, 16 * SIZE	FMADD	xsum1, xtemp3, a3,  xsum1	LFD	y03, 18 * SIZE(YY)	FMADD	y05, atemp3, a5, y05	addi	XX, XX, 16 * SIZE	FMADD	xsum2, xtemp4, a3,  xsum2	LFD	a3, 18 * SIZE(AO1)	FMADD	y06, atemp4, a5, y06	LFD	a5,  0 * SIZE(AO2)	FMADD	xsum3, xtemp3, a7,  xsum3	LFD	y04, 19 * SIZE(YY)	FMADD	y07, atemp3, a7, y07	NOP2	FMADD	xsum4, xtemp4, a7,  xsum4	addi	AO1, AO1, 16 * SIZE	FMADD	y08, atemp4, a7, y08	LFD	a7,  2 * SIZE(AO2)	FMADD1	xsum1, xtemp4, a4,  xsum1	addi	YY, YY, 16 * SIZE	FNMSUB	y05, atemp4, a6, y05	NOP2	FMADD2	xsum2, xtemp3, a4,  xsum2	LFD	a4,  3 * SIZE(AO1)	FMADD	y06, atemp3, a6, y06	LFD	a6,  1 * SIZE(AO2)	FMADD1	xsum3, xtemp4, a8,  xsum3	LFD	xtemp4,  3 * SIZE(XX)	FNMSUB	y07, atemp4, a8, y07	NOP2	FMADD2	xsum4, xtemp3, a8,  xsum4	LFD	xtemp3,  2 * SIZE(XX)	FMADD	y08, atemp3, a8, y08	LFD	a8,  3 * SIZE(AO2)	STFD	y05, -4 * SIZE(YY)	STFD	y06, -3 * SIZE(YY)	STFD	y07, -2 * SIZE(YY)	STFD	y08, -1 * SIZE(YY)	.align 4LL(15):	andi.	r0,  IS, 4	ble	LL(16)

⌨️ 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 + -