atl_mm6x8x8_1p.c

来自「基于Blas CLapck的.用过的人知道是干啥的」· C语言 代码 · 共 1,986 行 · 第 1/5 页

C
1,986
字号
         rC3_0 += rA3 * rB0;         rC4_0 += rA4 * rB0; rb0 = *pB0++;         rC5_0 += rA5 * rB0;         rC0_1 += rA0 * rB1;         rC1_1 += rA1 * rB1; ra0 = *pA0++;         rC2_1 += rA2 * rB1;         rC3_1 += rA3 * rB1;         rC4_1 += rA4 * rB1; ra1 = *pA1++;         rC5_1 += rA5 * rB1;         rC0_2 += rA0 * rB2;         rC1_2 += rA1 * rB2; ra2 = *pA2++;         rC2_2 += rA2 * rB2;         rC3_2 += rA3 * rB2;         rC4_2 += rA4 * rB2; ra3 = *pA3++;         rC5_2 += rA5 * rB2;         rC0_3 += rA0 * rB3;         rC1_3 += rA1 * rB3; ra4 = *pA4++;         rC2_3 += rA2 * rB3;         rC3_3 += rA3 * rB3;         rC4_3 += rA4 * rB3; ra5 = *pA5++;         rC5_3 += rA5 * rB3;         rC0_4 += rA0 * rB4;         rC1_4 += rA1 * rB4; rb1 = *pB1++;         rC2_4 += rA2 * rB4;         rC3_4 += rA3 * rB4;         rC4_4 += rA4 * rB4; rb2 = *pB2++;         rC5_4 += rA5 * rB4;         rC0_5 += rA0 * rB5;         rC1_5 += rA1 * rB5; rb3 = *pB3++;         rC2_5 += rA2 * rB5;         rC3_5 += rA3 * rB5; ATL_pfl1R(pA1+PFD-2);         rC4_5 += rA4 * rB5; rb4 = *pB4++;         rC5_5 += rA5 * rB5;         rC0_6 += rA0 * rB6;         rC1_6 += rA1 * rB6; rb5 = *pB5++;         rC2_6 += rA2 * rB6;         rC3_6 += rA3 * rB6;         rC4_6 += rA4 * rB6; rb6 = *pB6++;         rC5_6 += rA5 * rB6;         rC0_7 += rA0 * rB7;         rC1_7 += rA1 * rB7; rb7 = *pB7++;         rC2_7 += rA2 * rB7;         rC3_7 += rA3 * rB7;         rC4_7 += rA4 * rB7; rB0 = *pB0++;         rC5_7 += rA5 * rB7;         rC0_0 += ra0 * rb0;         rC1_0 += ra1 * rb0; rA0 = *pA0++;         rC2_0 += ra2 * rb0;         rC3_0 += ra3 * rb0;         rC4_0 += ra4 * rb0; rA1 = *pA1++;         rC5_0 += ra5 * rb0;         rC0_1 += ra0 * rb1;         rC1_1 += ra1 * rb1; rA2 = *pA2++;         rC2_1 += ra2 * rb1;         rC3_1 += ra3 * rb1;         rC4_1 += ra4 * rb1; rA3 = *pA3++;         rC5_1 += ra5 * rb1;         rC0_2 += ra0 * rb2;         rC1_2 += ra1 * rb2; rA4 = *pA4++;         rC2_2 += ra2 * rb2;         rC3_2 += ra3 * rb2;         rC4_2 += ra4 * rb2; rA5 = *pA5++;         rC5_2 += ra5 * rb2;         rC0_3 += ra0 * rb3;         rC1_3 += ra1 * rb3; rB1 = *pB1++;         rC2_3 += ra2 * rb3;         rC3_3 += ra3 * rb3;         rC4_3 += ra4 * rb3; rB2 = *pB2++;         rC5_3 += ra5 * rb3;         rC0_4 += ra0 * rb4;         rC1_4 += ra1 * rb4; rB3 = *pB3++;         rC2_4 += ra2 * rb4;         rC3_4 += ra3 * rb4;         rC4_4 += ra4 * rb4; rB4 = *pB4++;         rC5_4 += ra5 * rb4;         rC0_5 += ra0 * rb5;         rC1_5 += ra1 * rb5; rB5 = *pB5++;         rC2_5 += ra2 * rb5;         rC3_5 += ra3 * rb5;         rC4_5 += ra4 * rb5; rB6 = *pB6++;         rC5_5 += ra5 * rb5;         rC0_6 += ra0 * rb6;         rC1_6 += ra1 * rb6;         rC2_6 += ra2 * rb6; rB7 = *pB7++;         rC3_6 += ra3 * rb6;         rC4_6 += ra4 * rb6;         rC5_6 += ra5 * rb6;         rC0_7 += ra0 * rb7;         rC1_7 += ra1 * rb7;         rC2_7 += ra2 * rb7;         rC3_7 += ra3 * rb7;         rC4_7 += ra4 * rb7;         rC5_7 += ra5 * rb7;         rC0_0 += rA0 * rB0; ATL_pfl1R(pA2+PFD-3);         rC1_0 += rA1 * rB0;         rC2_0 += rA2 * rB0;         rC3_0 += rA3 * rB0;         rC4_0 += rA4 * rB0; rb0 = *pB0++;         rC5_0 += rA5 * rB0;         rC0_1 += rA0 * rB1;         rC1_1 += rA1 * rB1; ra0 = *pA0++;         rC2_1 += rA2 * rB1;         rC3_1 += rA3 * rB1;         rC4_1 += rA4 * rB1; ra1 = *pA1++;         rC5_1 += rA5 * rB1;         rC0_2 += rA0 * rB2;         rC1_2 += rA1 * rB2; ra2 = *pA2++;         rC2_2 += rA2 * rB2;         rC3_2 += rA3 * rB2;         rC4_2 += rA4 * rB2; ra3 = *pA3++;         rC5_2 += rA5 * rB2;         rC0_3 += rA0 * rB3;         rC1_3 += rA1 * rB3; ra4 = *pA4++;         rC2_3 += rA2 * rB3;         rC3_3 += rA3 * rB3;         rC4_3 += rA4 * rB3; ra5 = *pA5++;         rC5_3 += rA5 * rB3;         rC0_4 += rA0 * rB4;         rC1_4 += rA1 * rB4; rb1 = *pB1++;         rC2_4 += rA2 * rB4;         rC3_4 += rA3 * rB4;         rC4_4 += rA4 * rB4; rb2 = *pB2++;         rC5_4 += rA5 * rB4;         rC0_5 += rA0 * rB5;         rC1_5 += rA1 * rB5; rb3 = *pB3++;         rC2_5 += rA2 * rB5; ATL_pfl1R(pA3+PFD-3);         rC3_5 += rA3 * rB5;         rC4_5 += rA4 * rB5; rb4 = *pB4++;         rC5_5 += rA5 * rB5;         rC0_6 += rA0 * rB6;         rC1_6 += rA1 * rB6; rb5 = *pB5++;         rC2_6 += rA2 * rB6;         rC3_6 += rA3 * rB6;         rC4_6 += rA4 * rB6; rb6 = *pB6++;         rC5_6 += rA5 * rB6;         rC0_7 += rA0 * rB7;         rC1_7 += rA1 * rB7; rb7 = *pB7++;         rC2_7 += rA2 * rB7;         rC3_7 += rA3 * rB7;         rC4_7 += rA4 * rB7; rB0 = *pB0++;         rC5_7 += rA5 * rB7;         rC0_0 += ra0 * rb0;         rC1_0 += ra1 * rb0; rA0 = *pA0++;         rC2_0 += ra2 * rb0;         rC3_0 += ra3 * rb0;         rC4_0 += ra4 * rb0; rA1 = *pA1++;         rC5_0 += ra5 * rb0;         rC0_1 += ra0 * rb1;         rC1_1 += ra1 * rb1; rA2 = *pA2++;         rC2_1 += ra2 * rb1;         rC3_1 += ra3 * rb1;         rC4_1 += ra4 * rb1; rA3 = *pA3++;         rC5_1 += ra5 * rb1;         rC0_2 += ra0 * rb2;         rC1_2 += ra1 * rb2; rA4 = *pA4++;         rC2_2 += ra2 * rb2;         rC3_2 += ra3 * rb2; ATL_pfl1R(pA4+PFD-4);         rC4_2 += ra4 * rb2; rA5 = *pA5++;         rC5_2 += ra5 * rb2;         rC0_3 += ra0 * rb3;         rC1_3 += ra1 * rb3; rB1 = *pB1++;         rC2_3 += ra2 * rb3;         rC3_3 += ra3 * rb3;         rC4_3 += ra4 * rb3; rB2 = *pB2++;         rC5_3 += ra5 * rb3;         rC0_4 += ra0 * rb4;         rC1_4 += ra1 * rb4; rB3 = *pB3++;         rC2_4 += ra2 * rb4;         rC3_4 += ra3 * rb4;         rC4_4 += ra4 * rb4; rB4 = *pB4++;         rC5_4 += ra5 * rb4;         rC0_5 += ra0 * rb5;         rC1_5 += ra1 * rb5; rB5 = *pB5++;         rC2_5 += ra2 * rb5;         rC3_5 += ra3 * rb5;         rC4_5 += ra4 * rb5; rB6 = *pB6++;         rC5_5 += ra5 * rb5;         rC0_6 += ra0 * rb6;         rC1_6 += ra1 * rb6;         rC2_6 += ra2 * rb6; rB7 = *pB7++;         rC3_6 += ra3 * rb6;         rC4_6 += ra4 * rb6;         rC5_6 += ra5 * rb6;         rC0_7 += ra0 * rb7;         rC1_7 += ra1 * rb7;         rC2_7 += ra2 * rb7;         rC3_7 += ra3 * rb7;         rC4_7 += ra4 * rb7;         rC5_7 += ra5 * rb7; ATL_pfl1R(pA5+PFD-4);         rC0_0 += rA0 * rB0;         rC1_0 += rA1 * rB0;         rC2_0 += rA2 * rB0;         rC3_0 += rA3 * rB0;         rC4_0 += rA4 * rB0; rb0 = *pB0++;         rC5_0 += rA5 * rB0;         rC0_1 += rA0 * rB1;         rC1_1 += rA1 * rB1; ra0 = *pA0++;         rC2_1 += rA2 * rB1;         rC3_1 += rA3 * rB1;         rC4_1 += rA4 * rB1; ra1 = *pA1++;         rC5_1 += rA5 * rB1;         rC0_2 += rA0 * rB2;         rC1_2 += rA1 * rB2; ra2 = *pA2++;         rC2_2 += rA2 * rB2;         rC3_2 += rA3 * rB2;         rC4_2 += rA4 * rB2; ra3 = *pA3++;         rC5_2 += rA5 * rB2;         rC0_3 += rA0 * rB3;         rC1_3 += rA1 * rB3; ra4 = *pA4++;         rC2_3 += rA2 * rB3;         rC3_3 += rA3 * rB3;         rC4_3 += rA4 * rB3; ra5 = *pA5++;         rC5_3 += rA5 * rB3; ATL_pfl1R(pB0+PFB-4);         rC0_4 += rA0 * rB4;         rC1_4 += rA1 * rB4; rb1 = *pB1++;         rC2_4 += rA2 * rB4;         rC3_4 += rA3 * rB4;         rC4_4 += rA4 * rB4; rb2 = *pB2++;         rC5_4 += rA5 * rB4;         rC0_5 += rA0 * rB5;         rC1_5 += rA1 * rB5; rb3 = *pB3++;         rC2_5 += rA2 * rB5;         rC3_5 += rA3 * rB5;         rC4_5 += rA4 * rB5; rb4 = *pB4++;         rC5_5 += rA5 * rB5;         rC0_6 += rA0 * rB6;         rC1_6 += rA1 * rB6; rb5 = *pB5++;         rC2_6 += rA2 * rB6;         rC3_6 += rA3 * rB6;         rC4_6 += rA4 * rB6; rb6 = *pB6++;         rC5_6 += rA5 * rB6;         rC0_7 += rA0 * rB7;         rC1_7 += rA1 * rB7; rb7 = *pB7++;         rC2_7 += rA2 * rB7;         rC3_7 += rA3 * rB7;         rC4_7 += rA4 * rB7; rB0 = *pB0++;         rC5_7 += rA5 * rB7; ATL_pfl1R(pB1+PFB-4);         rC0_0 += ra0 * rb0;         rC1_0 += ra1 * rb0; rA0 = *pA0++;         rC2_0 += ra2 * rb0;         rC3_0 += ra3 * rb0;         rC4_0 += ra4 * rb0; rA1 = *pA1++;         rC5_0 += ra5 * rb0;         rC0_1 += ra0 * rb1;         rC1_1 += ra1 * rb1; rA2 = *pA2++;         rC2_1 += ra2 * rb1;         rC3_1 += ra3 * rb1;         rC4_1 += ra4 * rb1; rA3 = *pA3++;         rC5_1 += ra5 * rb1;         rC0_2 += ra0 * rb2;         rC1_2 += ra1 * rb2; rA4 = *pA4++;         rC2_2 += ra2 * rb2;         rC3_2 += ra3 * rb2;         rC4_2 += ra4 * rb2; rA5 = *pA5++;         rC5_2 += ra5 * rb2;         rC0_3 += ra0 * rb3;         rC1_3 += ra1 * rb3; rB1 = *pB1++;         rC2_3 += ra2 * rb3;         rC3_3 += ra3 * rb3;         rC4_3 += ra4 * rb3; rB2 = *pB2++;         rC5_3 += ra5 * rb3; ATL_pfl1R(pB2+PFB-5);         rC0_4 += ra0 * rb4;         rC1_4 += ra1 * rb4; rB3 = *pB3++;         rC2_4 += ra2 * rb4;         rC3_4 += ra3 * rb4;         rC4_4 += ra4 * rb4; rB4 = *pB4++;         rC5_4 += ra5 * rb4;         rC0_5 += ra0 * rb5;         rC1_5 += ra1 * rb5; rB5 = *pB5++;         rC2_5 += ra2 * rb5;         rC3_5 += ra3 * rb5;         rC4_5 += ra4 * rb5; rB6 = *pB6++;         rC5_5 += ra5 * rb5;         rC0_6 += ra0 * rb6;         rC1_6 += ra1 * rb6;         rC2_6 += ra2 * rb6; rB7 = *pB7++;         rC3_6 += ra3 * rb6;         rC4_6 += ra4 * rb6;         rC5_6 += ra5 * rb6;         rC0_7 += ra0 * rb7;         rC1_7 += ra1 * rb7;         rC2_7 += ra2 * rb7;         rC3_7 += ra3 * rb7;         rC4_7 += ra4 * rb7;         rC5_7 += ra5 * rb7; ATL_pfl1R(pB3+PFB-5);         rC0_0 += rA0 * rB0;         rC1_0 += rA1 * rB0;         rC2_0 += rA2 * rB0;         rC3_0 += rA3 * rB0;         rC4_0 += rA4 * rB0; rb0 = *pB0++;         rC5_0 += rA5 * rB0;         rC0_1 += rA0 * rB1;         rC1_1 += rA1 * rB1; ra0 = *pA0++;         rC2_1 += rA2 * rB1;         rC3_1 += rA3 * rB1;         rC4_1 += rA4 * rB1; ra1 = *pA1++;         rC5_1 += rA5 * rB1;         rC0_2 += rA0 * rB2;         rC1_2 += rA1 * rB2; ra2 = *pA2++;         rC2_2 += rA2 * rB2;         rC3_2 += rA3 * rB2;         rC4_2 += rA4 * rB2; ra3 = *pA3++;         rC5_2 += rA5 * rB2;         rC0_3 += rA0 * rB3;         rC1_3 += rA1 * rB3; ra4 = *pA4++;         rC2_3 += rA2 * rB3;         rC3_3 += rA3 * rB3;         rC4_3 += rA4 * rB3; ra5 = *pA5++;         rC5_3 += rA5 * rB3; ATL_pfl1R(pB4+PFB-6);         rC0_4 += rA0 * rB4;         rC1_4 += rA1 * rB4; rb1 = *pB1++;         rC2_4 += rA2 * rB4;         rC3_4 += rA3 * rB4;         rC4_4 += rA4 * rB4; rb2 = *pB2++;         rC5_4 += rA5 * rB4;         rC0_5 += rA0 * rB5;         rC1_5 += rA1 * rB5; rb3 = *pB3++;         rC2_5 += rA2 * rB5;         rC3_5 += rA3 * rB5;         rC4_5 += rA4 * rB5; rb4 = *pB4++;         rC5_5 += rA5 * rB5;         rC0_6 += rA0 * rB6;         rC1_6 += rA1 * rB6; rb5 = *pB5++;         rC2_6 += rA2 * rB6;         rC3_6 += rA3 * rB6;         rC4_6 += rA4 * rB6; rb6 = *pB6++;         rC5_6 += rA5 * rB6;         rC0_7 += rA0 * rB7;         rC1_7 += rA1 * rB7; rb7 = *pB7++;         rC2_7 += rA2 * rB7;         rC3_7 += rA3 * rB7;         rC4_7 += rA4 * rB7; rB0 = *pB0++;         rC5_7 += rA5 * rB7; ATL_pfl1R(pB5+PFB-7);         rC0_0 += ra0 * rb0;         rC1_0 += ra1 * rb0; rA0 = *pA0++;         rC2_0 += ra2 * rb0;         rC3_0 += ra3 * rb0;         rC4_0 += ra4 * rb0; rA1 = *pA1++;         rC5_0 += ra5 * rb0;         rC0_1 += ra0 * rb1;         rC1_1 += ra1 * rb1; rA2 = *pA2++;         rC2_1 += ra2 * rb1;         rC3_1 += ra3 * rb1;         rC4_1 += ra4 * rb1; rA3 = *pA3++;         rC5_1 += ra5 * rb1;         rC0_2 += ra0 * rb2;         rC1_2 += ra1 * rb2; rA4 = *pA4++;         rC2_2 += ra2 * rb2;         rC3_2 += ra3 * rb2;         rC4_2 += ra4 * rb2; rA5 = *pA5++;         rC5_2 += ra5 * rb2;         rC0_3 += ra0 * rb3;         rC1_3 += ra1 * rb3; rB1 = *pB1++;         rC2_3 += ra2 * rb3;         rC3_3 += ra3 * rb3;         rC4_3 += ra4 * rb3; rB2 = *pB2++;         rC5_3 += ra5 * rb3; ATL_pfl1R(pB6+PFB-7);         rC0_4 += ra0 * rb4;         rC1_4 += ra1 * rb4; rB3 = *pB3++;         rC2_4 += ra2 * rb4;         rC3_4 += ra3 * rb4;         rC4_4 += ra4 * rb4; rB4 = *pB4++;         rC5_4 += ra5 * rb4;         rC0_5 += ra0 * rb5;         rC1_5 += ra1 * rb5; rB5 = *pB5++;         rC2_5 += ra2 * rb5;         rC3_5 += ra3 * rb5;         rC4_5 += ra4 * rb5; rB6 = *pB6++;         rC5_5 += ra5 * rb5;         rC0_6 += ra0 * rb6;         rC1_6 += ra1 * rb6;         rC2_6 += ra2 * rb6; rB7 = *pB7++;         rC3_6 += ra3 * rb6;         rC4_6 += ra4 * rb6;         rC5_6 += ra5 * rb6;         rC0_7 += ra0 * rb7;         rC1_7 += ra1 * rb7;         rC2_7 += ra2 * rb7;         rC3_7 += ra3 * rb7;         rC4_7 += ra4 * rb7;         rC5_7 += ra5 * rb7; ATL_pfl1R(pB7+PFB-8);      }      rC0_0 += rA0 * rB0;      rC1_0 += rA1 * rB0;      rC2_0 += rA2 * rB0;      rC3_0 += rA3 * rB0;      rC4_0 += rA4 * rB0; rb0 = *pB0++;      rC5_0 += rA5 * rB0;      rC0_1 += rA0 * rB1;      rC1_1 += rA1 * rB1; ra0 = *pA0++;      rC2_1 += rA2 * rB1;

⌨️ 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?