atl_dmm8x1x120_sse2.c

来自「基于Blas CLapck的.用过的人知道是干啥的」· C语言 代码 · 共 3,266 行 · 第 1/5 页

C
3,266
字号
	addpd	rA0,rC00	movapd	272-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	272-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	272-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	272-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	272-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	272-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	272-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 36	movapd	288-128(pB0), rB0	movapd	288-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	288-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	288-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	288-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	288-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	288-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	288-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	288-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 38	movapd	304-128(pB0), rB0	movapd	304-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	304-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	304-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	304-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	304-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	304-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	304-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	304-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 40	movapd	320-128(pB0), rB0	movapd	320-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	320-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	320-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	320-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	320-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	320-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	320-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	320-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 42	movapd	336-128(pB0), rB0	movapd	336-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	336-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	336-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	336-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	336-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	336-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	336-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	336-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 44	movapd	352-128(pB0), rB0	movapd	352-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	352-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	352-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	352-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	352-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	352-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	352-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	352-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 46	movapd	368-128(pB0), rB0	movapd	368-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	368-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	368-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	368-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	368-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	368-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	368-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	368-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 48	movapd	384-128(pB0), rB0	movapd	384-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	384-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	384-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	384-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	384-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	384-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	384-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	384-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 50	movapd	400-128(pB0), rB0	movapd	400-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	400-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	400-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	400-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	400-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	400-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	400-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	400-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 52	movapd	416-128(pB0), rB0	movapd	416-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	416-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	416-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	416-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	416-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	416-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	416-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	416-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 54	movapd	432-128(pB0), rB0	movapd	432-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	432-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	432-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	432-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	432-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	432-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	432-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	432-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 56	movapd	448-128(pB0), rB0	movapd	448-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	448-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	448-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	448-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	448-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	448-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	448-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	448-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 58	movapd	464-128(pB0), rB0	movapd	464-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	464-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	464-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	464-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	464-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	464-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	464-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	464-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 60	movapd	480-128(pB0), rB0	movapd	480-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	480-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	480-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	480-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	480-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	480-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	480-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	480-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 62	movapd	496-128(pB0), rB0	movapd	496-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	496-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	496-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	496-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	496-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	496-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	496-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	496-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 64	movapd	512-128(pB0), rB0	movapd	512-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	512-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	512-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	512-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	512-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	512-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	512-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	512-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 66	movapd	528-128(pB0), rB0	movapd	528-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	528-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	528-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	528-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	528-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	528-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	528-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	528-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 68	movapd	544-128(pB0), rB0	movapd	544-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	544-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	544-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	544-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	544-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	544-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	544-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	544-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 70	movapd	560-128(pB0), rB0	movapd	560-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	560-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	560-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	560-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	560-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	560-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	560-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	560-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 72	movapd	576-128(pB0), rB0	movapd	576-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	576-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	576-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	576-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	576-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	576-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	576-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	576-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 74	movapd	592-128(pB0), rB0	movapd	592-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	592-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	592-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	592-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	592-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	592-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	592-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	592-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 76	movapd	608-128(pB0), rB0	movapd	608-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	608-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	608-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	608-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	608-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	608-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	608-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	608-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 78	movapd	624-128(pB0), rB0	movapd	624-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	624-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	624-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	624-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	624-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	624-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	624-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	624-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 80	movapd	640-128(pB0), rB0	movapd	640-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	640-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	640-128(pA0,lda,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC02	movapd	640-128(pA0,lda3), rA0	mulpd	rB0,rA0	addpd	rA0,rC03	movapd	640-128(pA0,lda,4), rA0	mulpd	rB0,rA0	addpd	rA0,rC04	movapd	640-128(pA0,lda5), rA0	mulpd	rB0,rA0	addpd	rA0,rC05	movapd	640-128(pA0,lda3,2), rA0	mulpd	rB0,rA0	addpd	rA0,rC06	mulpd	640-128(pA0,lda7), rB0	addpd	rB0,rC07#endif#if KB > 82	movapd	656-128(pB0), rB0	movapd	656-128(pA0), rA0	mulpd	rB0,rA0	addpd	rA0,rC00	movapd	656-128(pA0,lda), rA0	mulpd	rB0,rA0	addpd	rA0,rC01	movapd	656-128(pA0,lda,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?