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
	fmul	%st(1), %st	 /* st = rA0*rB0, rB0, rC3, rC1, rC0, rC2 */	faddp	%st, %st(4)	 /* st = rB0, rC3, rC1, rC0+, rC2 */	fldl	152-128(pA0,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	152-128(pA0,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	152-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 20	fldl	160-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	160-128(pA0)	 /* 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	160-128(pA0,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	160-128(pA0,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	160-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 21	fldl	168-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	168-128(pA0)	 /* 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	168-128(pA0,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	168-128(pA0,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	168-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 22	fldl	176-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	176-128(pA0)	 /* 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	176-128(pA0,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	176-128(pA0,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	176-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 23	fldl	184-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	184-128(pA0)	 /* 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	184-128(pA0,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	184-128(pA0,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	184-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 24	fldl	192-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	192-128(pA0)	 /* 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	192-128(pA0,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	192-128(pA0,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	192-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 25	fldl	200-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	200-128(pA0)	 /* 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	200-128(pA0,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	200-128(pA0,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	200-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 26	fldl	208-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	208-128(pA0)	 /* 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	208-128(pA0,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	208-128(pA0,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	208-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 27	fldl	216-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	216-128(pA0)	 /* 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	216-128(pA0,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	216-128(pA0,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	216-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 28	fldl	224-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	224-128(pA0)	 /* 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	224-128(pA0,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	224-128(pA0,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	224-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 29	fldl	232-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	232-128(pA0)	 /* 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	232-128(pA0,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	232-128(pA0,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	232-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 30	fldl	240-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	240-128(pA0)	 /* 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	240-128(pA0,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	240-128(pA0,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	240-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 31	fldl	248-128(pB0)	 /* st = rB0, rC3, rC1, rC0, rC2 */#if KB > 32 && defined(ATL_GAS_x8632)        addl    $KB*8-128, pB0#endif	fldl	248-128(pA0)	 /* 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	248-128(pA0,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	248-128(pA0,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	248-128(pA0,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */#if KB > 32 && defined(ATL_GAS_x8632)        addl    $KB*8-128, pA0#endif	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if (KB > 32)   #ifdef ATL_GAS_x8632ALIGN8   #endif	fldl	8*(32-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(32-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*(32-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*(32-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*(32-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 33	fldl	8*(33-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(33-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*(33-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*(33-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*(33-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 34	fldl	8*(34-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(34-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*(34-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*(34-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*(34-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 35	fldl	8*(35-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(35-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*(35-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*(35-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*(35-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 36	fldl	8*(36-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(36-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*(36-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*(36-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*(36-KB)(pAE,lda3)	 /* st = rA3*rB0, rC3, rC1+, rC0+, rC2+ */	faddp	%st, %st(1)	 /* st = rC3+, rC1+, rC0+, rC2+ */#endif#if KB > 37	fldl	8*(37-KB)(pBE)	 /* st = rB0, rC3, rC1, rC0, rC2 */	fldl	8*(37-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*(37-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?