atl_dmm14x1x56_sse2pabc_mn.c

来自「基于Blas CLapck的.用过的人知道是干啥的」· C语言 代码 · 共 2,979 行 · 第 1/5 页

C
2,979
字号
	addpd	rA0, rC2	movapd	16-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	16-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	16-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	16-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	16-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	16-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	16-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	16-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	16-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	16-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	16-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	32-120(pA10,mldab5,2), rA0	movapd	32-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	32-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	32-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	32-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	32-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	32-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	32-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	32-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	32-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	32-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	32-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	32-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	32-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	32-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	48-120(pA10,mldab5,2), rA0	movapd	48-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	48-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	48-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	48-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	48-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	48-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	48-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	48-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	48-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	48-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	48-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	48-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	48-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	48-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	64-120(pA10,mldab5,2), rA0	movapd	64-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	64-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	64-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	64-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	64-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	64-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	64-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	64-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	64-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	64-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	64-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	64-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	64-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	64-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	80-120(pA10,mldab5,2), rA0	movapd	80-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	80-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	80-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	80-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	80-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	80-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	80-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	80-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	80-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	80-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	80-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	80-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	80-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	80-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	96-120(pA10,mldab5,2), rA0	movapd	96-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	96-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	96-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	96-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	96-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	96-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	96-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	96-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	96-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	96-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	96-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	96-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	96-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	96-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	112-120(pA10,mldab5,2), rA0	movapd	112-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	112-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	112-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	112-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	112-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	112-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	112-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	112-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	112-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	112-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	112-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	112-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	112-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	112-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	128-120(pA10,mldab5,2), rA0	movapd	128-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	128-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	128-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	128-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	128-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	128-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	128-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	128-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	128-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	128-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	128-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	128-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	128-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	128-120(pA5,ldab,8), rB0	addpd	rB0, rC13						prefB(128-120(pB0,ldab))						prefB(192-120(pB0,ldab))	movapd	144-120(pA10,mldab5,2), rA0	movapd	144-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	144-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	144-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	144-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	144-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	144-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	144-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	144-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	144-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	144-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	144-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	144-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	144-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	144-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	160-120(pA10,mldab5,2), rA0	movapd	160-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	160-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	160-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	160-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	160-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	160-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	160-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	160-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	160-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	160-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	160-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	160-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	160-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	160-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	176-120(pA10,mldab5,2), rA0	movapd	176-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	176-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	176-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	176-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	176-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	176-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	176-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	176-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	176-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	176-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	176-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	176-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	176-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	176-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	192-120(pA10,mldab5,2), rA0	movapd	192-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	192-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	192-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	192-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	192-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	192-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	192-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	192-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	192-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	192-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	192-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	192-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	192-120(pA10,ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC12	mulpd	192-120(pA5,ldab,8), rB0	addpd	rB0, rC13	movapd	208-120(pA10,mldab5,2), rA0	movapd	208-120(pB0), rB0	mulpd	rB0, rA0			addq	$224, pB0	addpd	rA0, rC0	movapd	208-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	208-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	208-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	208-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	208-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	208-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	208-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	208-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	208-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	208-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	208-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	208-120(pA10,ldab,2), rA0	mulpd	rB0, rA0			addq	$224, pA10	addpd	rA0, rC12	mulpd	208-120(pA5,ldab,8), rB0	addpd	rB0, rC13			addq	$224, pA5/* KLOOP / 2 */	movapd	0-120(pA10,mldab5,2), rA0	movapd	0-120(pB0), rB0	mulpd	rB0, rA0	addpd	rA0, rC0	movapd	0-120(pA5, mldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC1	movapd	0-120(pA10, mldab,8), rA0	mulpd	rB0, rA0	addpd	rA0, rC2	movapd	0-120(pA5, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC3	movapd	0-120(pA5, mldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC4	movapd	0-120(pA5), rA0	mulpd	rB0, rA0	addpd	rA0, rC5	movapd	0-120(pA5, ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC6	movapd	0-120(pA5, ldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC7	movapd	0-120(pA10, mldab,2), rA0	mulpd	rB0, rA0	addpd	rA0, rC8	movapd	0-120(pA5,ldab,4), rA0	mulpd	rB0, rA0	addpd	rA0, rC9	movapd	0-120(pA10), rA0	mulpd	rB0, rA0	addpd	rA0, rC10	movapd	0-120(pA10,ldab), rA0	mulpd	rB0, rA0	addpd	rA0, rC11	movapd	0-120(pA10,ldab,2), rA0	mulpd	rB0, rA0

⌨️ 快捷键说明

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