⭐ 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

📄 gemv_t.s

📁 Optimized GotoBLAS libraries
💻 S
📖 第 1 页 / 共 4 页
字号:
	FMADD	y07, a7, b7, y07	LFD	a7, 16 * SIZE(AO7)	FMADD	y08, a8, b7, y08	LFD	a8, 16 * SIZE(AO8)	FMADD	y09, a1, b8, y09	LFD	a1, 17 * SIZE(AO1)	FMADD	y10, a2, b8, y10	LFD	a2, 17 * SIZE(AO2)	FMADD	y11, a3, b8, y11	LFD	a3, 17 * SIZE(AO3)	FMADD	y12, a4, b8, y12	LFD	a4, 17 * SIZE(AO4)	addi	AO1, AO1, 16 * SIZE	addi	AO2, AO2, 16 * SIZE	addi	AO3, AO3, 16 * SIZE	addi	AO4, AO4, 16 * SIZE	FMADD	y13, a5, b8, y13	LFD	a5, 17 * SIZE(AO5)	FMADD	y14, a6, b8, y14	LFD	a6, 17 * SIZE(AO6)	FMADD	y15, a7, b8, y15	LFD	a7, 17 * SIZE(AO7)	FMADD	y16, a8, b8, y16	LFD	a8, 17 * SIZE(AO8)	LFD	b5, 21 * SIZE(BO)	LFD	b6, 22 * SIZE(BO)	LFD	b7, 23 * SIZE(BO)	LFD	b8, 24 * SIZE(BO)	addi	AO5, AO5, 16 * SIZE	addi	AO6, AO6, 16 * SIZE	PREFETCH_A5	PREFETCH_A6	addi	AO7, AO7, 16 * SIZE	addi	AO8, AO8, 16 * SIZE	PREFETCH_A7	PREFETCH_A8	addi	BO,  BO,  16 * SIZE 	bdnz	LL(12)	.align 4	LL(13):	FMADD	y01, a1, b1, y01	LFD	a1,  2 * SIZE(AO1)	FMADD	y02, a2, b1, y02	LFD	a2,  2 * SIZE(AO2)	FMADD	y03, a3, b1, y03	LFD	a3,  2 * SIZE(AO3)	FMADD	y04, a4, b1, y04	LFD	a4,  2 * SIZE(AO4)	FMADD	y05, a5, b1, y05	LFD	a5,  2 * SIZE(AO5)	FMADD	y06, a6, b1, y06	LFD	a6,  2 * SIZE(AO6)	FMADD	y07, a7, b1, y07	LFD	a7,  2 * SIZE(AO7)	FMADD	y08, a8, b1, y08	LFD	a8,  2 * SIZE(AO8)	FMADD	y09, a1, b2, y09	LFD	a1,  3 * SIZE(AO1)	FMADD	y10, a2, b2, y10	LFD	a2,  3 * SIZE(AO2)	FMADD	y11, a3, b2, y11	LFD	a3,  3 * SIZE(AO3)	FMADD	y12, a4, b2, y12	LFD	a4,  3 * SIZE(AO4)	FMADD	y13, a5, b2, y13	LFD	a5,  3 * SIZE(AO5)	FMADD	y14, a6, b2, y14	LFD	a6,  3 * SIZE(AO6)	FMADD	y15, a7, b2, y15	LFD	a7,  3 * SIZE(AO7)	FMADD	y16, a8, b2, y16	LFD	a8,  3 * SIZE(AO8)	FMADD	y01, a1, b3, y01	LFD	a1,  4 * SIZE(AO1)	FMADD	y02, a2, b3, y02	LFD	a2,  4 * SIZE(AO2)	FMADD	y03, a3, b3, y03	LFD	a3,  4 * SIZE(AO3)	FMADD	y04, a4, b3, y04	LFD	a4,  4 * SIZE(AO4)	FMADD	y05, a5, b3, y05	LFD	a5,  4 * SIZE(AO5)	FMADD	y06, a6, b3, y06	LFD	a6,  4 * SIZE(AO6)	FMADD	y07, a7, b3, y07	LFD	a7,  4 * SIZE(AO7)	FMADD	y08, a8, b3, y08	LFD	a8,  4 * SIZE(AO8)	FMADD	y09, a1, b4, y09	LFD	a1,  5 * SIZE(AO1)	FMADD	y10, a2, b4, y10	LFD	a2,  5 * SIZE(AO2)	FMADD	y11, a3, b4, y11	LFD	a3,  5 * SIZE(AO3)	FMADD	y12, a4, b4, y12	LFD	a4,  5 * SIZE(AO4)	FMADD	y13, a5, b4, y13	LFD	a5,  5 * SIZE(AO5)	FMADD	y14, a6, b4, y14	LFD	a6,  5 * SIZE(AO6)	FMADD	y15, a7, b4, y15	LFD	a7,  5 * SIZE(AO7)	FMADD	y16, a8, b4, y16	LFD	a8,  5 * SIZE(AO8)	LFD	b1,  9 * SIZE(BO)	LFD	b2, 10 * SIZE(BO)	LFD	b3, 11 * SIZE(BO)	LFD	b4, 12 * SIZE(BO)	FMADD	y01, a1, b5, y01	LFD	a1,  6 * SIZE(AO1)	FMADD	y02, a2, b5, y02	LFD	a2,  6 * SIZE(AO2)	FMADD	y03, a3, b5, y03	LFD	a3,  6 * SIZE(AO3)	FMADD	y04, a4, b5, y04	LFD	a4,  6 * SIZE(AO4)	FMADD	y05, a5, b5, y05	LFD	a5,  6 * SIZE(AO5)	FMADD	y06, a6, b5, y06	LFD	a6,  6 * SIZE(AO6)	FMADD	y07, a7, b5, y07	LFD	a7,  6 * SIZE(AO7)	FMADD	y08, a8, b5, y08	LFD	a8,  6 * SIZE(AO8)	FMADD	y09, a1, b6, y09	LFD	a1,  7 * SIZE(AO1)	FMADD	y10, a2, b6, y10	LFD	a2,  7 * SIZE(AO2)	FMADD	y11, a3, b6, y11	LFD	a3,  7 * SIZE(AO3)	FMADD	y12, a4, b6, y12	LFD	a4,  7 * SIZE(AO4)	FMADD	y13, a5, b6, y13	LFD	a5,  7 * SIZE(AO5)	FMADD	y14, a6, b6, y14	LFD	a6,  7 * SIZE(AO6)	FMADD	y15, a7, b6, y15	LFD	a7,  7 * SIZE(AO7)	FMADD	y16, a8, b6, y16	LFD	a8,  7 * SIZE(AO8)	FMADD	y01, a1, b7, y01	LFD	a1,  8 * SIZE(AO1)	FMADD	y02, a2, b7, y02	LFD	a2,  8 * SIZE(AO2)	FMADD	y03, a3, b7, y03	LFD	a3,  8 * SIZE(AO3)	FMADD	y04, a4, b7, y04	LFD	a4,  8 * SIZE(AO4)	FMADD	y05, a5, b7, y05	LFD	a5,  8 * SIZE(AO5)	FMADD	y06, a6, b7, y06	LFD	a6,  8 * SIZE(AO6)	FMADD	y07, a7, b7, y07	LFD	a7,  8 * SIZE(AO7)	FMADD	y08, a8, b7, y08	LFD	a8,  8 * SIZE(AO8)	FMADD	y09, a1, b8, y09	LFD	a1,  9 * SIZE(AO1)	FMADD	y10, a2, b8, y10	LFD	a2,  9 * SIZE(AO2)	FMADD	y11, a3, b8, y11	LFD	a3,  9 * SIZE(AO3)	FMADD	y12, a4, b8, y12	LFD	a4,  9 * SIZE(AO4)	FMADD	y13, a5, b8, y13	LFD	a5,  9 * SIZE(AO5)	FMADD	y14, a6, b8, y14	LFD	a6,  9 * SIZE(AO6)	FMADD	y15, a7, b8, y15	LFD	a7,  9 * SIZE(AO7)	FMADD	y16, a8, b8, y16	LFD	a8,  9 * SIZE(AO8)	LFD	b5, 13 * SIZE(BO)	LFD	b6, 14 * SIZE(BO)	LFD	b7, 15 * SIZE(BO)	LFD	b8, 16 * SIZE(BO)	FMADD	y01, a1, b1, y01	LFD	a1, 10 * SIZE(AO1)	FMADD	y02, a2, b1, y02	LFD	a2, 10 * SIZE(AO2)	FMADD	y03, a3, b1, y03	LFD	a3, 10 * SIZE(AO3)	FMADD	y04, a4, b1, y04	LFD	a4, 10 * SIZE(AO4)	FMADD	y05, a5, b1, y05	LFD	a5, 10 * SIZE(AO5)	FMADD	y06, a6, b1, y06	LFD	a6, 10 * SIZE(AO6)	FMADD	y07, a7, b1, y07	LFD	a7, 10 * SIZE(AO7)	FMADD	y08, a8, b1, y08	LFD	a8, 10 * SIZE(AO8)	FMADD	y09, a1, b2, y09	LFD	a1, 11 * SIZE(AO1)	FMADD	y10, a2, b2, y10	LFD	a2, 11 * SIZE(AO2)	FMADD	y11, a3, b2, y11	LFD	a3, 11 * SIZE(AO3)	FMADD	y12, a4, b2, y12	LFD	a4, 11 * SIZE(AO4)	FMADD	y13, a5, b2, y13	LFD	a5, 11 * SIZE(AO5)	FMADD	y14, a6, b2, y14	LFD	a6, 11 * SIZE(AO6)	FMADD	y15, a7, b2, y15	LFD	a7, 11 * SIZE(AO7)	FMADD	y16, a8, b2, y16	LFD	a8, 11 * SIZE(AO8)	FMADD	y01, a1, b3, y01	LFD	a1, 12 * SIZE(AO1)	FMADD	y02, a2, b3, y02	LFD	a2, 12 * SIZE(AO2)	FMADD	y03, a3, b3, y03	LFD	a3, 12 * SIZE(AO3)	FMADD	y04, a4, b3, y04	LFD	a4, 12 * SIZE(AO4)	FMADD	y05, a5, b3, y05	LFD	a5, 12 * SIZE(AO5)	FMADD	y06, a6, b3, y06	LFD	a6, 12 * SIZE(AO6)	FMADD	y07, a7, b3, y07	LFD	a7, 12 * SIZE(AO7)	FMADD	y08, a8, b3, y08	LFD	a8, 12 * SIZE(AO8)	FMADD	y09, a1, b4, y09	LFD	a1, 13 * SIZE(AO1)	FMADD	y10, a2, b4, y10	LFD	a2, 13 * SIZE(AO2)	FMADD	y11, a3, b4, y11	LFD	a3, 13 * SIZE(AO3)	FMADD	y12, a4, b4, y12	LFD	a4, 13 * SIZE(AO4)	FMADD	y13, a5, b4, y13	LFD	a5, 13 * SIZE(AO5)	FMADD	y14, a6, b4, y14	LFD	a6, 13 * SIZE(AO6)	FMADD	y15, a7, b4, y15	LFD	a7, 13 * SIZE(AO7)	FMADD	y16, a8, b4, y16	LFD	a8, 13 * SIZE(AO8)	FMADD	y01, a1, b5, y01	LFD	a1, 14 * SIZE(AO1)	FMADD	y02, a2, b5, y02	LFD	a2, 14 * SIZE(AO2)	FMADD	y03, a3, b5, y03	LFD	a3, 14 * SIZE(AO3)	FMADD	y04, a4, b5, y04	LFD	a4, 14 * SIZE(AO4)	FMADD	y05, a5, b5, y05	LFD	a5, 14 * SIZE(AO5)	FMADD	y06, a6, b5, y06	LFD	a6, 14 * SIZE(AO6)	FMADD	y07, a7, b5, y07	LFD	a7, 14 * SIZE(AO7)	FMADD	y08, a8, b5, y08	LFD	a8, 14 * SIZE(AO8)	FMADD	y09, a1, b6, y09	LFD	a1, 15 * SIZE(AO1)	FMADD	y10, a2, b6, y10	LFD	a2, 15 * SIZE(AO2)	FMADD	y11, a3, b6, y11	LFD	a3, 15 * SIZE(AO3)	FMADD	y12, a4, b6, y12	LFD	a4, 15 * SIZE(AO4)	FMADD	y13, a5, b6, y13	LFD	a5, 15 * SIZE(AO5)	FMADD	y14, a6, b6, y14	LFD	a6, 15 * SIZE(AO6)	FMADD	y15, a7, b6, y15	LFD	a7, 15 * SIZE(AO7)	FMADD	y16, a8, b6, y16	LFD	a8, 15 * SIZE(AO8)	FMADD	y01, a1, b7, y01	LFD	a1, 16 * SIZE(AO1)	FMADD	y02, a2, b7, y02	LFD	a2, 16 * SIZE(AO2)	FMADD	y03, a3, b7, y03	LFD	a3, 16 * SIZE(AO3)	FMADD	y04, a4, b7, y04	LFD	a4, 16 * SIZE(AO4)	FMADD	y05, a5, b7, y05	LFD	a5, 16 * SIZE(AO5)	FMADD	y06, a6, b7, y06	LFD	a6, 16 * SIZE(AO6)	FMADD	y07, a7, b7, y07	LFD	a7, 16 * SIZE(AO7)	FMADD	y08, a8, b7, y08	LFD	a8, 16 * SIZE(AO8)	FMADD	y09, a1, b8, y09	FMADD	y10, a2, b8, y10	FMADD	y11, a3, b8, y11	FMADD	y12, a4, b8, y12	addi	AO1, AO1, 16 * SIZE	addi	AO2, AO2, 16 * SIZE	addi	AO3, AO3, 16 * SIZE	addi	AO4, AO4, 16 * SIZE	FMADD	y13, a5, b8, y13	FMADD	y14, a6, b8, y14	FMADD	y15, a7, b8, y15	FMADD	y16, a8, b8, y16	addi	AO5, AO5, 16 * SIZE	addi	AO6, AO6, 16 * SIZE	addi	AO7, AO7, 16 * SIZE	addi	AO8, AO8, 16 * SIZE	addi	BO,  BO,  16 * SIZE	.align 4LL(14):	andi.	r0, MIN_N, 15	ble	LL(18)	andi.	r0, MIN_N,  8	ble	LL(15)	LFD	a1,  1 * SIZE(AO1)	LFD	b1,  1 * SIZE(BO)	LFD	a2,  1 * SIZE(AO2)	LFD	a3,  1 * SIZE(AO3)	LFD	a4,  1 * SIZE(AO4)	LFD	a5,  1 * SIZE(AO5)	LFD	a6,  1 * SIZE(AO6)	LFD	a7,  1 * SIZE(AO7)	LFD	a8,  1 * SIZE(AO8)	LFD	b2,  2 * SIZE(BO)	LFD	b3,  3 * SIZE(BO)	LFD	b4,  4 * SIZE(BO)	FMADD	y01, a1, b1, y01	LFD	a1,  2 * SIZE(AO1)	FMADD	y02, a2, b1, y02	LFD	a2,  2 * SIZE(AO2)	FMADD	y03, a3, b1, y03	LFD	a3,  2 * SIZE(AO3)	FMADD	y04, a4, b1, y04	LFD	a4,  2 * SIZE(AO4)	FMADD	y05, a5, b1, y05	LFD	a5,  2 * SIZE(AO5)	FMADD	y06, a6, b1, y06	LFD	a6,  2 * SIZE(AO6)	FMADD	y07, a7, b1, y07	LFD	a7,  2 * SIZE(AO7)	FMADD	y08, a8, b1, y08	LFD	a8,  2 * SIZE(AO8)	FMADD	y09, a1, b2, y09	LFD	a1,  3 * SIZE(AO1)	FMADD	y10, a2, b2, y10	LFD	a2,  3 * SIZE(AO2)	FMADD	y11, a3, b2, y11	LFD	a3,  3 * SIZE(AO3)	FMADD	y12, a4, b2, y12	LFD	a4,  3 * SIZE(AO4)	FMADD	y13, a5, b2, y13	LFD	a5,  3 * SIZE(AO5)	FMADD	y14, a6, b2, y14	LFD	a6,  3 * SIZE(AO6)	FMADD	y15, a7, b2, y15	LFD	a7,  3 * SIZE(AO7)	FMADD	y16, a8, b2, y16	LFD	a8,  3 * SIZE(AO8)	LFD	b5,  5 * SIZE(BO)	LFD	b6,  6 * SIZE(BO)	LFD	b7,  7 * SIZE(BO)	LFD	b8,  8 * SIZE(BO)	FMADD	y01, a1, b3, y01	LFD	a1,  4 * SIZE(AO1)	FMADD	y02, a2, b3, y02	LFD	a2,  4 * SIZE(AO2)	FMADD	y03, a3, b3, y03	LFD	a3,  4 * SIZE(AO3)	FMADD	y04, a4, b3, y04	LFD	a4,  4 * SIZE(AO4)	FMADD	y05, a5, b3, y05	LFD	a5,  4 * SIZE(AO5)	FMADD	y06, a6, b3, y06	LFD	a6,  4 * SIZE(AO6)	FMADD	y07, a7, b3, y07	LFD	a7,  4 * SIZE(AO7)	FMADD	y08, a8, b3, y08	LFD	a8,  4 * SIZE(AO8)	FMADD	y09, a1, b4, y09	LFD	a1,  5 * SIZE(AO1)	FMADD	y10, a2, b4, y10	LFD	a2,  5 * SIZE(AO2)	FMADD	y11, a3, b4, y11	LFD	a3,  5 * SIZE(AO3)	FMADD	y12, a4, b4, y12	LFD	a4,  5 * SIZE(AO4)	FMADD	y13, a5, b4, y13	LFD	a5,  5 * SIZE(AO5)	FMADD	y14, a6, b4, y14	LFD	a6,  5 * SIZE(AO6)	FMADD	y15, a7, b4, y15	LFD	a7,  5 * SIZE(AO7)	FMADD	y16, a8, b4, y16	LFD	a8,  5 * SIZE(AO8)	FMADD	y01, a1, b5, y01	LFD	a1,  6 * SIZE(AO1)	FMADD	y02, a2, b5, y02	LFD	a2,  6 * SIZE(AO2)	FMADD	y03, a3, b5, y03	LFD	a3,  6 * SIZE(AO3)	FMADD	y04, a4, b5, y04	LFD	a4,  6 * SIZE(AO4)	FMADD	y05, a5, b5, y05	LFD	a5,  6 * SIZE(AO5)	FMADD	y06, a6, b5, y06	LFD	a6,  6 * SIZE(AO6)	FMADD	y07, a7, b5, y07	LFD	a7,  6 * SIZE(AO7)	FMADD	y08, a8, b5, y08	LFD	a8,  6 * SIZE(AO8)	FMADD	y09, a1, b6, y09	LFD	a1,  7 * SIZE(AO1)	FMADD	y10, a2, b6, y10	LFD	a2,  7 * SIZE(AO2)	FMADD	y11, a3, b6, y11	LFD	a3,  7 * SIZE(AO3)	FMADD	y12, a4, b6, y12	LFD	a4,  7 * SIZE(AO4)	FMADD	y13, a5, b6, y13	LFD	a5,  7 * SIZE(AO5)	FMADD	y14, a6, b6, y14	LFD	a6,  7 * SIZE(AO6)	FMADD	y15, a7, b6, y15	LFD	a7,  7 * SIZE(AO7)	FMADD	y16, a8, b6, y16	LFD	a8,  7 * SIZE(AO8)	FMADD	y01, a1, b7, y01	LFD	a1,  8 * SIZE(AO1)	FMADD	y02, a2, b7, y02	LFD	a2,  8 * SIZE(AO2)	FMADD	y03, a3, b7, y03	LFD	a3,  8 * SIZE(AO3)	FMADD	y04, a4, b7, y04	LFD	a4,  8 * SIZE(AO4)	FMADD	y05, a5, b7, y05	LFD	a5,  8 * SIZE(AO5)	FMADD	y06, a6, b7, y06	LFD	a6,  8 * SIZE(AO6)	FMADD	y07, a7, b7, y07	LFD	a7,  8 * SIZE(AO7)	FMADD	y08, a8, b7, y08	LFD	a8,  8 * SIZE(AO8)	FMADD	y09, a1, b8, y09	addi	AO1, AO1, 8 * SIZE	FMADD	y10, a2, b8, y10	addi	AO2, AO2, 8 * SIZE	FMADD	y11, a3, b8, y11	addi	AO3, AO3, 8 * SIZE	FMADD	y12, a4, b8, y12	addi	AO4, AO4, 8 * SIZE	FMADD	y13, a5, b8, y13	addi	AO5, AO5, 8 * SIZE	FMADD	y14, a6, b8, y14	addi	AO6, AO6, 8 * SIZE	FMADD	y15, a7, b8, y15	addi	AO7, AO7, 8 * SIZE	FMADD	y16, a8, b8, y16	addi	AO8, AO8, 8 * SIZE	addi	BO,  BO,  8 * SIZE	.align 4LL(15):	andi.	r0, MIN_N,  4	ble	LL(16)	LFD	a1,  1 * SIZE(AO1)	LFD	b1,  1 * SIZE(BO)	LFD	a2,  1 * SIZE(AO2)	LFD	a3,  1 * SIZE(AO3)	LFD	a4,  1 * SIZE(AO4)	LFD	a5,  1 * SIZE(AO5)	LFD	a6,  1 * SIZE(AO6)	LFD	a7,  1 * SIZE(AO7)	LFD	a8,  1 * SIZE(AO8)	LFD	b2,  2 * SIZE(BO)	LFD	b3,  3 * SIZE(BO)	LFD	b4,  4 * SIZE(BO)	FMADD	y01, a1, b1, y01	LFD	a1,  2 * SIZE(AO1)	FMADD	y02, a2, b1, y02	LFD	a2,  2 * SIZE(AO2)	FMADD	y03, a3, b1, y03	LFD	a3,  2 * SIZE(AO3)	FMADD	y04, a4, b1, y04	LFD	a4,  2 * SIZE(AO4)	FMADD	y05, a5, b1, y05	LFD	a5,  2 * SIZE(AO5)	FMADD	y06, a6, b1, y06	LFD	a6,  2 * SIZE(AO6)	FMADD	y07, a7, b1, y07	LFD	a7,  2 * SIZE(AO7)	FMADD	y08, a8, b1, y08	LFD	a8,  2 * SIZE(AO8)	FMADD	y09, a1, b2, y09	LFD	a1,  3 * SIZE(AO1)	FMADD	y10, a2, b2, y10	LFD	a2,  3 * SIZE(AO2)	FMADD	y11, a3, b2, y11	LFD	a3,  3 * SIZE(AO3)	FMADD	y12, a4, b2, y12	LFD	a4,  3 * SIZE(AO4)	FMADD	y13, a5, b2, y13	LFD	a5,  3 * SIZE(AO5)	FMADD	y14, a6, b2, y14	LFD	a6,  3 * SIZE(AO6)	FMADD	y15, a7, b2, y15	LFD	a7,  3 * SIZE(AO7)	FMADD	y16, a8, b2, y16	LFD	a8,  3 * SIZE(AO8)	FMADD	y01, a1, b3, y01	LFD	a1,  4 * SIZE(AO1)	FMADD	y02, a2, b3, y02	LFD	a2,  4 * SIZE(AO2)	FMADD	y03, a3, b3, y03	LFD	a3,  4 * SIZE(AO3)	FMADD	y04, a4, b3, y04	LFD	a4,  4 * SIZE(AO4)	FMADD	y05, a5, b3, y05	LFD	a5,  4 * SIZE(AO5)	FMADD	y06, a6, b3, y06	LFD	a6,  4 * SIZE(AO6)	FMADD	y07, a7, b3, y07	LFD	a7,  4 * SIZE(AO7)	FMADD	y08, a8, b3, y08	LFD	a8,  4 * SIZE(AO8)	FMADD	y09, a1, b4, y09	addi	AO1, AO1, 4 * SIZE	FMADD	y10, a2, b4, y10	addi	AO2, AO2, 4 * SIZE	FMADD	y11, a3, b4, y11	addi	AO3, AO3, 4 * SIZE	FMADD	y12, a4, b4, y12	addi	AO4, AO4, 4 * SIZE	FMADD	y13, a5, b4, y13	addi	AO5, AO5, 4 * SIZE	FMADD	y14, a6, b4, y14	addi	AO6, AO6, 4 * SIZE	FMADD	y15, a7, b4, y15	addi	AO7, AO7, 4 * SIZE	FMADD	y16, a8, b4, y16	addi	AO8, AO8, 4 * SIZE	addi	BO,  BO,  4 * SIZE	.align 4LL(16):	andi.	r0, MIN_N,  2	ble	LL(17)	LFD	a1,  1 * SIZE(AO1)	LFD	b1,  1 * SIZE(BO)	LFD	a2,  1 * SIZE(AO2)	LFD	a3,  1 * SIZE(AO3)	LFD	a4,  1 * SIZE(AO4)	LFD	a5,  1 * SIZE(AO5)	LFD	a6,  1 * SIZE(AO6)	LFD	a7,  1 * SIZE(AO7)	LFD	a8,  1 * SIZE(AO8)	LFD	b2,  2 * SIZE(BO)	FMADD	y01, a1, b1, y01	LFD	a1,  2 * SIZE(AO1)	FMADD	y02, a2, b1, y02	LFD	a2,  2 * SIZE(AO2)	FMADD	y03, a3, b1, y03	LFD	a3,  2 * SIZE(AO3)	FMADD	y04, a4, b1, y04	LFD	a4,  2 * SIZE(AO4)	FMADD	y05, a5, b1, y05	LFD	a5,  2 * SIZE(AO5)	FMADD	y06, a6, b1, y06	LFD	a6,  2 * SIZE(AO6)	FMADD	y07, a7, b1, y07	LFD	a7,  2 * SIZE(AO7)	FMADD	y08, a8, b1, y08	LFD	a8,  2 * SIZE(AO8)	FMADD	y09, a1, b2, y09	addi	AO1, AO1, 2 * SIZE	addi	AO2, AO2, 2 * SIZE	FMADD	y10, a2, b2, y10	addi	AO3, AO3, 2 * SIZE	addi	AO4, AO4, 2 * SIZE	FMADD	y11, a3, b2, y11	FMADD	y12, a4, b2, y12	addi	AO5, AO5, 2 * SIZE	addi	AO6, AO6, 2 * SIZE	FMADD	y13, a5, b2, y13	FMADD	y14, a6, b2, y14	addi	AO7, AO7, 2 * SIZE	addi	AO8, AO8, 2 * SIZE	FMADD	y15, a7, b2, y15	FMADD	y16, a8, b2, y16	addi	BO,  BO,  2 * SIZE	.align 4LL(17):	andi.	r0, MIN_N,  1	ble	LL(18)	LFD	a1,  1 * SIZE(AO1)	LFD	b1,  1 * SIZE(BO)	LFD	a2,  1 * SIZE(AO2)	LFD	a3,  1 * SIZE(AO3)	LFD	a4,  1 * SIZE(AO4)	LFD	a5,  1 * SIZE(AO5)	LFD	a6,  1 * SIZE(AO6)	LFD	a7,  1 * SIZE(AO7)	LFD	a8,  1 * SIZE(AO8)	FMADD	y01, a1, b1, y01	FMADD	y02, a2, b1, y02	FMADD	y03, a3, b1, y03	FMADD	y04, a4, b1, y04	FMADD	y05, a5, b1, y05	FMADD	y06, a6, b1, y06	FMADD	y07, a7, b1, y07	FMADD	y08, a8, b1, y08	.align 4LL(18):	mr	BO, CO	lfd	alpha, ALPHA	cmpi	cr0, 0, INCY, SIZE	bne	LL(19)	LFD	a1,  1 * SIZE(CO)	LFD	a2,  2 * SIZE(CO)	LFD	a3,  3 * SIZE(CO)	LFD	a4,  4 * SIZE(CO)	LFD	a5,  5 * SIZE(CO)	LFD	a6,  6 * SIZE(CO)	LFD	a7,  7 * SIZE(CO)	LFD	a8,  8 * SIZE(CO)	FADD	y01, y09, y01	FADD	y02, y10, y02	FADD	y03, y11, y03	FADD	y04, y12, y04	FADD	y05, y13, y05	FADD	y06, y14, y06	FADD	y07, y15, y07	FADD	y08, y16, y08	FMADD	a1, alpha, y01, a1	FMADD	a2, alpha, y02, a2	FMADD	a3, alpha, y03, a3

⌨️ 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 + -