atl_mm4x4x56_av.c
来自「基于Blas CLapck的.用过的人知道是干啥的」· C语言 代码 · 共 1,129 行 · 第 1/3 页
C
1,129 行
rC3_0 += rA3 * rB0; rB0 = pB0[15]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+15]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+15]; rC0_3 += rA0 * rB3; rA0 = pA0[15]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+15]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+15]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+15]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+15]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[16]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+16]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+16]; rC0_3 += rA0 * rB3; rA0 = pA0[16]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+16]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+16]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+16]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+16]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[17]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+17]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+17]; rC0_3 += rA0 * rB3; rA0 = pA0[17]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+17]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+17]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+17]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+17]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[18]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+18]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+18]; rC0_3 += rA0 * rB3; rA0 = pA0[18]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+18]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+18]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+18]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+18]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[19]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+19]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+19]; rC0_3 += rA0 * rB3; rA0 = pA0[19]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+19]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+19]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+19]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+19]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[20]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+20]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+20]; rC0_3 += rA0 * rB3; rA0 = pA0[20]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+20]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+20]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+20]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+20]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[21]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+21]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+21]; rC0_3 += rA0 * rB3; rA0 = pA0[21]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+21]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+21]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+21]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+21]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[22]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+22]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+22]; rC0_3 += rA0 * rB3; rA0 = pA0[22]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+22]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+22]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+22]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+22]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[23]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+23]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+23]; rC0_3 += rA0 * rB3; rA0 = pA0[23]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+23]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+23]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+23]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+23]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[24]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+24]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+24]; rC0_3 += rA0 * rB3; rA0 = pA0[24]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+24]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+24]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+24]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+24]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[25]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+25]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+25]; rC0_3 += rA0 * rB3; rA0 = pA0[25]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+25]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+25]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+25]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+25]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[26]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+26]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+26]; rC0_3 += rA0 * rB3; rA0 = pA0[26]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+26]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+26]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+26]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+26]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[27]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+27]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+27]; rC0_3 += rA0 * rB3; rA0 = pA0[27]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+27]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+27]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+27]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+27]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[28]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+28]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+28]; rC0_3 += rA0 * rB3; rA0 = pA0[28]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+28]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+28]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+28]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+28]; rC1_0 += rA1 * rB0; pA0 += 28; rC2_0 += rA2 * rB0; pB0 += 28; rC3_0 += rA3 * rB0; rB0 = pB0[1]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+1]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+1]; rC0_3 += rA0 * rB3; rA0 = pA0[1]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+1]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+1]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+1]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+1]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[2]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+2]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+2]; rC0_3 += rA0 * rB3; rA0 = pA0[2]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+2]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+2]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+2]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+2]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[3]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+3]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+3]; rC0_3 += rA0 * rB3; rA0 = pA0[3]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+3]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+3]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+3]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+3]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[4]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+4]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+4]; rC0_3 += rA0 * rB3; rA0 = pA0[4]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+4]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+4]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+4]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+4]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[5]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+5]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+5]; rC0_3 += rA0 * rB3; rA0 = pA0[5]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+5]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+5]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+5]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+5]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[6]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+6]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+6]; rC0_3 += rA0 * rB3; rA0 = pA0[6]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+6]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+6]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+6]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+6]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[7]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+7]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+7]; rC0_3 += rA0 * rB3; rA0 = pA0[7]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+7]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+7]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+7]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+7]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[8]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * rB1; rC2_1 += rA2 * rB1; rC3_1 += rA3 * rB1; rB1 = pB0[KB+8]; rC0_2 += rA0 * rB2; rC1_2 += rA1 * rB2; rC2_2 += rA2 * rB2; rC3_2 += rA3 * rB2; rB2 = pB0[KB2+8]; rC0_3 += rA0 * rB3; rA0 = pA0[8]; rC1_3 += rA1 * rB3; rA1 = pA0[KB+8]; rC2_3 += rA2 * rB3; rA2 = pA0[KB2+8]; rC3_3 += rA3 * rB3; rA3 = pA0[KB3+8]; rC0_0 += rA0 * rB0; rB3 = pB0[KB3+8]; rC1_0 += rA1 * rB0; rC2_0 += rA2 * rB0; rC3_0 += rA3 * rB0; rB0 = pB0[9]; rC0_1 += rA0 * rB1; rC1_1 += rA1 * 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?