atl_dmm4x4xur3_mips.c
来自「基于Blas CLapck的.用过的人知道是干啥的」· C语言 代码 · 共 2,389 行 · 第 1/5 页
C
2,389 行
madd.d rC30, rC30, rz3, rB0 ldc1 rB0, 168(pB0) madd.d rC01, rC01, rz0, rB1 prefA(64(pfA)) madd.d rC11, rC11, rz1, rB1 ldc1 ra1, 176(pA1) madd.d rC21, rC21, rz2, rB1 prefA(92(pfA)) madd.d rC31, rC31, rz3, rB1 ldc1 rB1, 168(pB1) madd.d rC02, rC02, rz0, rB2 prefA(128(pfA)) madd.d rC12, rC12, rz1, rB2 ldc1 ra2, 176(pA2) madd.d rC22, rC22, rz2, rB2 prefA(160(pfA)) madd.d rC32, rC32, rz3, rB2 ldc1 rB2, 168(pB2) madd.d rC03, rC03, rz0, rB3 prefA(160(pfA)) madd.d rC13, rC13, rz1, rB3 ldc1 ra3, 176(pA3) madd.d rC23, rC23, rz2, rB3 prefA(192(pfA)) madd.d rC33, rC33, rz3, rB3 ldc1 rB3, 168(pB3)#endif#if KB > 24 madd.d rC00, rC00, rA0, rB0 daddiu pfA, pfA, 213 madd.d rC10, rC10, rA1, rB0 ldc1 rz0, 184(pA0) madd.d rC20, rC20, rA2, rB0 madd.d rC30, rC30, rA3, rB0 ldc1 rB0, 176(pB0) madd.d rC01, rC01, rA0, rB1 madd.d rC11, rC11, rA1, rB1 ldc1 rz1, 184(pA1) madd.d rC21, rC21, rA2, rB1 madd.d rC31, rC31, rA3, rB1 ldc1 rB1, 176(pB1) madd.d rC02, rC02, rA0, rB2 madd.d rC12, rC12, rA1, rB2 ldc1 rz2, 184(pA2) madd.d rC22, rC22, rA2, rB2 madd.d rC32, rC32, rA3, rB2 ldc1 rB2, 176(pB2) madd.d rC03, rC03, rA0, rB3 madd.d rC13, rC13, rA1, rB3 ldc1 rz3, 184(pA3) madd.d rC23, rC23, rA2, rB3 madd.d rC33, rC33, rA3, rB3 ldc1 rB3, 176(pB3) madd.d rC00, rC00, ra0, rB0 madd.d rC10, rC10, ra1, rB0 ldc1 rA0, 192(pA0) madd.d rC20, rC20, ra2, rB0 madd.d rC30, rC30, ra3, rB0 ldc1 rB0, 184(pB0) madd.d rC01, rC01, ra0, rB1 madd.d rC11, rC11, ra1, rB1 ldc1 rA1, 192(pA1) madd.d rC21, rC21, ra2, rB1 madd.d rC31, rC31, ra3, rB1 ldc1 rB1, 184(pB1) madd.d rC02, rC02, ra0, rB2 madd.d rC12, rC12, ra1, rB2 ldc1 rA2, 192(pA2) madd.d rC22, rC22, ra2, rB2 madd.d rC32, rC32, ra3, rB2 ldc1 rB2, 184(pB2) madd.d rC03, rC03, ra0, rB3 madd.d rC13, rC13, ra1, rB3 ldc1 rA3, 192(pA3) madd.d rC23, rC23, ra2, rB3 madd.d rC33, rC33, ra3, rB3 ldc1 rB3, 184(pB3) madd.d rC00, rC00, rz0, rB0 madd.d rC10, rC10, rz1, rB0 ldc1 ra0, 200(pA0) madd.d rC20, rC20, rz2, rB0 madd.d rC30, rC30, rz3, rB0 ldc1 rB0, 192(pB0) madd.d rC01, rC01, rz0, rB1 madd.d rC11, rC11, rz1, rB1 ldc1 ra1, 200(pA1) madd.d rC21, rC21, rz2, rB1 madd.d rC31, rC31, rz3, rB1 ldc1 rB1, 192(pB1) madd.d rC02, rC02, rz0, rB2 madd.d rC12, rC12, rz1, rB2 ldc1 ra2, 200(pA2) madd.d rC22, rC22, rz2, rB2 madd.d rC32, rC32, rz3, rB2 ldc1 rB2, 192(pB2) madd.d rC03, rC03, rz0, rB3 madd.d rC13, rC13, rz1, rB3 ldc1 ra3, 200(pA3) madd.d rC23, rC23, rz2, rB3 madd.d rC33, rC33, rz3, rB3 ldc1 rB3, 192(pB3)#endif#if KB > 27 madd.d rC00, rC00, rA0, rB0 madd.d rC10, rC10, rA1, rB0 ldc1 rz0, 208(pA0) madd.d rC20, rC20, rA2, rB0 madd.d rC30, rC30, rA3, rB0 ldc1 rB0, 200(pB0) madd.d rC01, rC01, rA0, rB1 madd.d rC11, rC11, rA1, rB1 ldc1 rz1, 208(pA1) madd.d rC21, rC21, rA2, rB1 madd.d rC31, rC31, rA3, rB1 ldc1 rB1, 200(pB1) madd.d rC02, rC02, rA0, rB2 madd.d rC12, rC12, rA1, rB2 ldc1 rz2, 208(pA2) madd.d rC22, rC22, rA2, rB2 madd.d rC32, rC32, rA3, rB2 ldc1 rB2, 200(pB2) madd.d rC03, rC03, rA0, rB3 madd.d rC13, rC13, rA1, rB3 ldc1 rz3, 208(pA3) madd.d rC23, rC23, rA2, rB3 madd.d rC33, rC33, rA3, rB3 ldc1 rB3, 200(pB3) madd.d rC00, rC00, ra0, rB0 madd.d rC10, rC10, ra1, rB0 ldc1 rA0, 216(pA0) madd.d rC20, rC20, ra2, rB0 madd.d rC30, rC30, ra3, rB0 ldc1 rB0, 208(pB0) madd.d rC01, rC01, ra0, rB1 madd.d rC11, rC11, ra1, rB1 ldc1 rA1, 216(pA1) madd.d rC21, rC21, ra2, rB1 madd.d rC31, rC31, ra3, rB1 ldc1 rB1, 208(pB1) madd.d rC02, rC02, ra0, rB2 madd.d rC12, rC12, ra1, rB2 ldc1 rA2, 216(pA2) madd.d rC22, rC22, ra2, rB2 madd.d rC32, rC32, ra3, rB2 ldc1 rB2, 208(pB2) madd.d rC03, rC03, ra0, rB3 madd.d rC13, rC13, ra1, rB3 ldc1 rA3, 216(pA3) madd.d rC23, rC23, ra2, rB3 madd.d rC33, rC33, ra3, rB3 ldc1 rB3, 208(pB3) madd.d rC00, rC00, rz0, rB0 madd.d rC10, rC10, rz1, rB0 ldc1 ra0, 224(pA0) madd.d rC20, rC20, rz2, rB0 madd.d rC30, rC30, rz3, rB0 ldc1 rB0, 216(pB0) madd.d rC01, rC01, rz0, rB1 madd.d rC11, rC11, rz1, rB1 ldc1 ra1, 224(pA1) madd.d rC21, rC21, rz2, rB1 madd.d rC31, rC31, rz3, rB1 ldc1 rB1, 216(pB1) madd.d rC02, rC02, rz0, rB2 madd.d rC12, rC12, rz1, rB2 ldc1 ra2, 224(pA2) madd.d rC22, rC22, rz2, rB2 madd.d rC32, rC32, rz3, rB2 ldc1 rB2, 216(pB2) madd.d rC03, rC03, rz0, rB3 madd.d rC13, rC13, rz1, rB3 ldc1 ra3, 224(pA3) madd.d rC23, rC23, rz2, rB3 madd.d rC33, rC33, rz3, rB3 ldc1 rB3, 216(pB3)#endif#if KB > 30 madd.d rC00, rC00, rA0, rB0 madd.d rC10, rC10, rA1, rB0 ldc1 rz0, 232(pA0) madd.d rC20, rC20, rA2, rB0 madd.d rC30, rC30, rA3, rB0 ldc1 rB0, 224(pB0) madd.d rC01, rC01, rA0, rB1 madd.d rC11, rC11, rA1, rB1 ldc1 rz1, 232(pA1) madd.d rC21, rC21, rA2, rB1 madd.d rC31, rC31, rA3, rB1 ldc1 rB1, 224(pB1) madd.d rC02, rC02, rA0, rB2 madd.d rC12, rC12, rA1, rB2 ldc1 rz2, 232(pA2) madd.d rC22, rC22, rA2, rB2 madd.d rC32, rC32, rA3, rB2 ldc1 rB2, 224(pB2) madd.d rC03, rC03, rA0, rB3 madd.d rC13, rC13, rA1, rB3 ldc1 rz3, 232(pA3) madd.d rC23, rC23, rA2, rB3 madd.d rC33, rC33, rA3, rB3 ldc1 rB3, 224(pB3) madd.d rC00, rC00, ra0, rB0 madd.d rC10, rC10, ra1, rB0 ldc1 rA0, 240(pA0) madd.d rC20, rC20, ra2, rB0 madd.d rC30, rC30, ra3, rB0 ldc1 rB0, 232(pB0) madd.d rC01, rC01, ra0, rB1 madd.d rC11, rC11, ra1, rB1 ldc1 rA1, 240(pA1) madd.d rC21, rC21, ra2, rB1 madd.d rC31, rC31, ra3, rB1 ldc1 rB1, 232(pB1) madd.d rC02, rC02, ra0, rB2 madd.d rC12, rC12, ra1, rB2 ldc1 rA2, 240(pA2) madd.d rC22, rC22, ra2, rB2 madd.d rC32, rC32, ra3, rB2 ldc1 rB2, 232(pB2) madd.d rC03, rC03, ra0, rB3 madd.d rC13, rC13, ra1, rB3 ldc1 rA3, 240(pA3) madd.d rC23, rC23, ra2, rB3 madd.d rC33, rC33, ra3, rB3 ldc1 rB3, 232(pB3) madd.d rC00, rC00, rz0, rB0 madd.d rC10, rC10, rz1, rB0 ldc1 ra0, 248(pA0) madd.d rC20, rC20, rz2, rB0 madd.d rC30, rC30, rz3, rB0 ldc1 rB0, 240(pB0) madd.d rC01, rC01, rz0, rB1 madd.d rC11, rC11, rz1, rB1 ldc1 ra1, 248(pA1) madd.d rC21, rC21, rz2, rB1 madd.d rC31, rC31, rz3, rB1 ldc1 rB1, 240(pB1) madd.d rC02, rC02, rz0, rB2 madd.d rC12, rC12, rz1, rB2 ldc1 ra2, 248(pA2) madd.d rC22, rC22, rz2, rB2 madd.d rC32, rC32, rz3, rB2 ldc1 rB2, 240(pB2) madd.d rC03, rC03, rz0, rB3 madd.d rC13, rC13, rz1, rB3 ldc1 ra3, 248(pA3) madd.d rC23, rC23, rz2, rB3 madd.d rC33, rC33, rz3, rB3 ldc1 rB3, 240(pB3)#endif#if KB > 33 madd.d rC00, rC00, rA0, rB0 madd.d rC10, rC10, rA1, rB0 ldc1 rz0, 256(pA0) madd.d rC20, rC20, rA2, rB0 madd.d rC30, rC30, rA3, rB0 ldc1 rB0, 248(pB0) madd.d rC01, rC01, rA0, rB1 madd.d rC11, rC11, rA1, rB1 ldc1 rz1, 256(pA1) madd.d rC21, rC21, rA2, rB1 madd.d rC31, rC31, rA3, rB1 ldc1 rB1, 248(pB1) madd.d rC02, rC02, rA0, rB2 madd.d rC12, rC12, rA1, rB2 ldc1 rz2, 256(pA2) madd.d rC22, rC22, rA2, rB2 madd.d rC32, rC32, rA3, rB2 ldc1 rB2, 248(pB2) madd.d rC03, rC03, rA0, rB3 madd.d rC13, rC13, rA1, rB3 ldc1 rz3, 256(pA3) madd.d rC23, rC23, rA2, rB3 madd.d rC33, rC33, rA3, rB3 ldc1 rB3, 248(pB3) madd.d rC00, rC00, ra0, rB0 madd.d rC10, rC10, ra1, rB0 ldc1 rA0, 264(pA0) madd.d rC20, rC20, ra2, rB0 madd.d rC30, rC30, ra3, rB0 ldc1 rB0, 256(pB0) madd.d rC01, rC01, ra0, rB1 madd.d rC11, rC11, ra1, rB1 ldc1 rA1, 264(pA1) madd.d rC21, rC21, ra2, rB1 madd.d rC31, rC31, ra3, rB1 ldc1 rB1, 256(pB1) madd.d rC02, rC02, ra0, rB2 madd.d rC12, rC12, ra1, rB2 ldc1 rA2, 264(pA2) madd.d rC22, rC22, ra2, rB2 madd.d rC32, rC32, ra3, rB2 ldc1 rB2, 256(pB2) madd.d rC03, rC03, ra0, rB3 madd.d rC13, rC13, ra1, rB3 ldc1 rA3, 264(pA3) madd.d rC23, rC23, ra2, rB3 madd.d rC33, rC33, ra3, rB3 ldc1 rB3, 256(pB3) madd.d rC00, rC00, rz0, rB0 madd.d rC10, rC10, rz1, rB0 ldc1 ra0, 272(pA0) madd.d rC20, rC20, rz2, rB0 madd.d rC30, rC30, rz3, rB0 ldc1 rB0, 264(pB0) madd.d rC01, rC01, rz0, rB1 madd.d rC11, rC11, rz1, rB1 ldc1 ra1, 272(pA1) madd.d rC21, rC21, rz2, rB1 madd.d rC31, rC31, rz3, rB1 ldc1 rB1, 264(pB1) madd.d rC02, rC02, rz0, rB2 madd.d rC12, rC12, rz1, rB2 ldc1 ra2, 272(pA2) madd.d rC22, rC22, rz2, rB2 madd.d rC32, rC32, rz3, rB2 ldc1 rB2, 264(pB2) madd.d rC03, rC03, rz0, rB3 madd.d rC13, rC13, rz1, rB3 ldc1 ra3, 272(pA3) madd.d rC23, rC23, rz2, rB3 madd.d rC33, rC33, rz3, rB3 ldc1 rB3, 264(pB3)#endif#if KB > 36 madd.d rC00, rC00, rA0, rB0 madd.d rC10, rC10, rA1, rB0 ldc1 rz0, 280(pA0) madd.d rC20, rC20, rA2, rB0 madd.d rC30, rC30, rA3, rB0 ldc1 rB0, 272(pB0) madd.d rC01, rC01, rA0, rB1 madd.d rC11, rC11, rA1, rB1 ldc1 rz1, 280(pA1) madd.d rC21, rC21, rA2, rB1 madd.d rC31, rC31, rA3, rB1 ldc1 rB1, 272(pB1) madd.d rC02, rC02, rA0, rB2 madd.d rC12, rC12, rA1, rB2 ldc1 rz2, 280(pA2) madd.d rC22, rC22, rA2, rB2 madd.d rC32, rC32, rA3, rB2 ldc1 rB2, 272(pB2) madd.d rC03, rC03, rA0, rB3 madd.d rC13, rC13, rA1, rB3 ldc1 rz3, 280(pA3) madd.d rC23, rC23, rA2, rB3 madd.d rC33, rC33, rA3, rB3 ldc1 rB3, 272(pB3) madd.d rC00, rC00, ra0, rB0 madd.d rC10, rC10, ra1, rB0 ldc1 rA0, 288(pA0) madd.d rC20, rC20, ra2, rB0 madd.d rC30, rC30, ra3, rB0 ldc1 rB0, 280(pB0) madd.d rC01, rC01, ra0, rB1 madd.d rC11, rC11, ra1, rB1 ldc1 rA1, 288(pA1) madd.d rC21, rC21, ra2, rB1 madd.d rC31, rC31, ra3, rB1 ldc1 rB1, 280(pB1) madd.d rC02, rC02, ra0, rB2 madd.d rC12, rC12, ra1, rB2 ldc1 rA2, 288(pA2) madd.d rC22, rC22, ra2, rB2 madd.d rC32, rC32, ra3, rB2 ldc1 rB2, 280(pB2) madd.d rC03, rC03, ra0, rB3 madd.d rC13, rC13, ra1, rB3 ldc1 rA3, 288(pA3) madd.d rC23, rC23, ra2, rB3 madd.d rC33, rC33, ra3, rB3 ldc1 rB3, 280(pB3) madd.d rC00, rC00, rz0, rB0 madd.d rC10, rC10, rz1, rB0 ldc1 ra0, 296(pA0) madd.d rC20, rC20, rz2, rB0 madd.d rC30, rC30, rz3, rB0 ldc1 rB0, 288(pB0) madd.d rC01, rC01, rz0, rB1 madd.d rC11, rC11, rz1, rB1 ldc1 ra1, 296(pA1) madd.d rC21, rC21, rz2, rB1 madd.d rC31, rC31, rz3, rB1 ldc1 rB1, 288(pB1) madd.d rC02, rC02, rz0, rB2 madd.d rC12, rC12, rz1, rB2 ldc1 ra2, 296(pA2) madd.d rC22, rC22, rz2, rB2 madd.d rC32, rC32, rz3, rB2 ldc1 rB2, 288(pB2) madd.d rC03, rC03, rz0, rB3 madd.d rC13, rC13, rz1, rB3 ldc1 ra3, 296(pA3) madd.d rC23, rC23, rz2, rB3 madd.d rC33, rC33, rz3, rB3 ldc1 rB3, 288(pB3)#endif#if KB > 39 madd.d rC00, rC00, rA0, rB0 madd.d rC10, rC10, rA1, rB0 ldc1 rz0, 304(pA0) madd.d rC20, rC20, rA2, rB0 madd.d rC30, rC30, rA3, rB0 ldc1 rB0, 296(pB0) madd.d rC01, rC01, rA0, rB1 madd.d rC11, rC11, rA1, rB1 ldc1 rz1, 304(pA1) madd.d rC21, rC21, rA2, rB1 madd.d rC31, rC31, rA3, rB1 ldc1 rB1, 296(pB1) madd.d rC02, rC02, rA0, rB2 madd.d rC12, rC12, rA1, rB2 ldc1 rz2, 304(pA2) madd.d rC22, rC22, rA2, rB2 madd.d rC32, rC32, rA3, rB2 ldc1 rB2, 296(pB2) madd.d rC03, rC03, rA0, rB3 madd.d rC13, rC13, rA1, rB3 ldc1 rz3, 304(pA3) madd.d rC23, rC23, rA2, rB3 madd.d rC33, rC33, rA3, rB3 ldc1 rB3, 296(pB3) madd.d rC00, rC00, ra0, rB0 madd.d rC10, rC10, ra1, rB0 ldc1 rA0, 312(pA0) madd.d rC20, rC20, ra2, rB0 madd.d rC30, rC30, ra3, rB0 ldc1 rB0, 304(pB0) madd.d rC01, rC01, ra0, rB1 madd.d rC11, rC11, ra1, rB1 ldc1 rA1, 312(pA1) madd.d rC21, rC21, ra2, rB1 madd.d rC31, rC31, ra3, rB1 ldc1 rB1, 304(pB1) madd.d rC02, rC02, ra0, rB2 madd.d rC12, rC12, ra1, rB2 ldc1 rA2, 312(pA2) madd.d rC22, rC22, ra2, rB2 madd.d rC32, rC32, ra3, rB2 ldc1 rB2, 304(pB2) madd.d rC03, rC03, ra0, rB3 madd.d rC13, rC13, ra1, rB3 ldc1 rA3, 312(pA3) madd.d rC23, rC23, ra2, rB3 madd.d rC33, rC33, ra3, rB3 ldc1 rB3, 304(pB3) madd.d rC00, rC00, rz0, rB0 madd.d rC10, rC10, rz1, rB0 ldc1 ra0, 320(pA0) madd.d rC20, rC20, rz2, rB0 madd.d rC30, rC30, rz3, rB0 ldc1 rB0, 312(pB0) madd.d rC01, rC01, rz0, rB1 madd.d rC11, rC11, rz1, rB1 ldc1 ra1, 320(pA1) madd.d rC21, rC21, rz2, rB1 madd.d rC31, rC31, rz3, rB1 ldc1 rB1, 312(pB1) madd.d rC02, rC02, rz0, rB2 madd.d rC12, rC12, rz1, rB2 ldc1 ra2, 320(pA2) madd.d rC22, rC22, rz2, rB2 madd.d rC32, rC32, rz3, rB2 ldc1 rB2, 312(pB2) madd.d rC03, rC03, rz0, rB3 madd.d rC13, rC13, rz1, rB3 ldc1 ra3, 320(pA3) madd.d rC23, rC23, rz2, rB3 madd.d rC33, rC33, rz3, rB3 ldc1 rB3, 312(pB3)#endif#if KB > 42 madd.d rC00, rC00, rA0, rB0 madd.d rC10, rC10, rA1, rB0 ldc1 rz0, 328(pA0) madd.d rC20, rC20, rA2, rB0 madd.d rC30, rC30, rA3, rB0
⌨️ 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?