atl_dmm4x1x90_x87.c

来自「基于Blas CLapck的.用过的人知道是干啥的」· C语言 代码 · 共 1,326 行 · 第 1/5 页

C
1,326
字号
	fldl	8*(37-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(37-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 38	fldl	8*(38-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(38-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(38-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(38-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(38-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 39	fldl	8*(39-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(39-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(39-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(39-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(39-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 40	fldl	8*(40-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(40-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(40-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(40-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(40-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 41	fldl	8*(41-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(41-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(41-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(41-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(41-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 42	fldl	8*(42-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(42-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(42-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(42-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(42-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 43	fldl	8*(43-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(43-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(43-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(43-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(43-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 44	fldl	8*(44-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(44-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(44-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(44-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(44-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 45	fldl	8*(45-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(45-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(45-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(45-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(45-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 46	fldl	8*(46-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(46-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(46-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(46-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(46-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 47	fldl	8*(47-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(47-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(47-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(47-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(47-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 48	fldl	8*(48-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(48-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(48-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(48-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(48-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 49	fldl	8*(49-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(49-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(49-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(49-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(49-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 50	fldl	8*(50-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(50-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(50-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(50-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(50-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 51	fldl	8*(51-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(51-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(51-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(51-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(51-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 52	fldl	8*(52-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(52-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(52-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(52-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(52-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 53	fldl	8*(53-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(53-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(53-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(53-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(53-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 54	fldl	8*(54-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(54-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(54-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(54-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(54-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 55	fldl	8*(55-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(55-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(55-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */	fldl	8*(55-KB)(pAE,lda,2) /* st = rA2, rB0, rC3, rC1+, rC0+,rC2 */	fmul	%st(1), %st	 /* st = rA2*rB0, rB0, rC3, rC1+, rC0+, rC2 */	faddp	%st, %st(5)	 /* st = rB0, rC3, rC1+, rC0+, rC2+ */	fmull	8*(55-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 56	fldl	8*(56-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(56-KB)(pAE)	 /* st = rA0, rB0, rC3, rC1, rC0, rC2 */	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	8*(56-KB)(pAE,lda)	 /* st = rA1, rB0, rC3, rC1, rC0+, rC2 */	fmul	%st(1),%st	 /* st = rA1*rB0, rB0, rC3, rC1, rC0+, rC2 */	faddp	%st, %st(3)	 /* st = rA1*rB0, rB0, rC3, rC1+, rC0+, rC2 */

⌨️ 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?