atl_smm14x1x84_sse.c
来自「基于Blas CLapck的.用过的人知道是干啥的」· C语言 代码 · 共 2,566 行 · 第 1/5 页
C
2,566 行
mulps rB0, rA0 addps rA0, rC0 movaps 64-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 64-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 64-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 64-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 64-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 64-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 64-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 64-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 64-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 64-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 64-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 64-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 64-120(pA5,ldab,8), rB0 addps rB0, rC13 movaps 80-120(pA10,mldab5,2), rA0 movaps 80-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 80-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 80-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 80-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 80-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 80-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 80-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 80-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 80-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 80-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 80-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 80-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 80-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 80-120(pA5,ldab,8), rB0 addps rB0, rC13 movaps 96-120(pA10,mldab5,2), rA0 movaps 96-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 96-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 96-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 96-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 96-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 96-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 96-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 96-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 96-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 96-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 96-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 96-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 96-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 96-120(pA5,ldab,8), rB0 addps rB0, rC13 movaps 112-120(pA10,mldab5,2), rA0 movaps 112-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 112-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 112-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 112-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 112-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 112-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 112-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 112-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 112-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 112-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 112-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 112-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 112-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 112-120(pA5,ldab,8), rB0 addps rB0, rC13 movaps 128-120(pA10,mldab5,2), rA0 movaps 128-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 128-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 128-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 128-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 128-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 128-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 128-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 128-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 128-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 128-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 128-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 128-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 128-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 128-120(pA5,ldab,8), rB0 addps rB0, rC13 movaps 144-120(pA10,mldab5,2), rA0 movaps 144-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 144-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 144-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 144-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 144-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 144-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 144-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 144-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 144-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 144-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 144-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 144-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 144-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 144-120(pA5,ldab,8), rB0 addps rB0, rC13 prefB((pB,ldab)) prefB(64(pB,ldab)) movaps 160-120(pA10,mldab5,2), rA0 movaps 160-120(pB0), rB0 mulps rB0, rA0 addq $176, pB0 addps rA0, rC0 movaps 160-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 160-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 160-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 160-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 160-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 160-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 160-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 160-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 160-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 160-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 160-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 160-120(pA10,ldab,2), rA0 mulps rB0, rA0 addq $176, pA10 addps rA0, rC12 mulps 160-120(pA5,ldab,8), rB0 addps rB0, rC13 addq $176, pA5 movaps 0-120(pA10,mldab5,2), rA0 movaps 0-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 0-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 0-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 0-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 0-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 0-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 0-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 0-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 0-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 0-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 0-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 0-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 0-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 0-120(pA5,ldab,8), rB0 addps rB0, rC13 movaps 16-120(pA10,mldab5,2), rA0 movaps 16-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 16-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 16-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 16-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 16-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 16-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 16-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 16-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 16-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 16-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 16-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 16-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 16-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 16-120(pA5,ldab,8), rB0 addps rB0, rC13 movaps 32-120(pA10,mldab5,2), rA0 movaps 32-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 32-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 32-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 32-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 32-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 32-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 32-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 32-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 32-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 32-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 32-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 32-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 32-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 32-120(pA5,ldab,8), rB0 addps rB0, rC13 movaps 48-120(pA10,mldab5,2), rA0 movaps 48-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 48-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 48-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 48-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 48-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 48-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 48-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 48-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 48-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 48-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 48-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 48-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 48-120(pA10,ldab,2), rA0 mulps rB0, rA0 addps rA0, rC12 mulps 48-120(pA5,ldab,8), rB0 addps rB0, rC13 movaps 64-120(pA10,mldab5,2), rA0 movaps 64-120(pB0), rB0 mulps rB0, rA0 addps rA0, rC0 movaps 64-120(pA5, mldab,4), rA0 mulps rB0, rA0 addps rA0, rC1 movaps 64-120(pA10, mldab,8), rA0 mulps rB0, rA0 addps rA0, rC2 movaps 64-120(pA5, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC3 movaps 64-120(pA5, mldab), rA0 mulps rB0, rA0 addps rA0, rC4 movaps 64-120(pA5), rA0 mulps rB0, rA0 addps rA0, rC5 movaps 64-120(pA5, ldab), rA0 mulps rB0, rA0 addps rA0, rC6 movaps 64-120(pA5, ldab,2), rA0 mulps rB0, rA0 addps rA0, rC7 movaps 64-120(pA10, mldab,2), rA0 mulps rB0, rA0 addps rA0, rC8 movaps 64-120(pA5,ldab,4), rA0 mulps rB0, rA0 addps rA0, rC9 movaps 64-120(pA10), rA0 mulps rB0, rA0 addps rA0, rC10 movaps 64-120(pA10,ldab), rA0 mulps rB0, rA0 addps rA0, rC11 movaps 64-120(pA10,ldab,2), 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?