atl_dmm14x1x56_sse2pabc.c
来自「基于Blas CLapck的.用过的人知道是干啥的」· C语言 代码 · 共 2,893 行 · 第 1/5 页
C
2,893 行
movapd 32-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 32-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 32-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 32-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 32-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 32-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 32-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 32-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 32-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 32-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 32-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 32-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 32-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 32-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 48-120(pA10,mldab5,2), rA0 movapd 48-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 48-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 48-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 48-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 48-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 48-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 48-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 48-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 48-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 48-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 48-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 48-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 48-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 48-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 64-120(pA10,mldab5,2), rA0 movapd 64-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 64-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 64-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 64-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 64-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 64-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 64-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 64-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 64-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 64-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 64-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 64-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 64-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 64-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 80-120(pA10,mldab5,2), rA0 movapd 80-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 80-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 80-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 80-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 80-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 80-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 80-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 80-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 80-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 80-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 80-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 80-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 80-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 80-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 96-120(pA10,mldab5,2), rA0 movapd 96-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 96-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 96-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 96-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 96-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 96-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 96-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 96-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 96-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 96-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 96-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 96-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 96-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 96-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 112-120(pA10,mldab5,2), rA0 movapd 112-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 112-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 112-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 112-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 112-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 112-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 112-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 112-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 112-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 112-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 112-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 112-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 112-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 112-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 128-120(pA10,mldab5,2), rA0 movapd 128-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 128-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 128-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 128-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 128-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 128-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 128-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 128-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 128-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 128-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 128-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 128-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 128-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 128-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 144-120(pA10,mldab5,2), rA0 movapd 144-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 144-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 144-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 144-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 144-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 144-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 144-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 144-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 144-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 144-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 144-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 144-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 144-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 144-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 160-120(pA10,mldab5,2), rA0 movapd 160-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 160-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 160-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 160-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 160-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 160-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 160-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 160-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 160-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 160-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 160-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 160-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 160-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 160-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 176-120(pA10,mldab5,2), rA0 movapd 176-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 176-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 176-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 176-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 176-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 176-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 176-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 176-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 176-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 176-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 176-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 176-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 176-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 176-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 192-120(pA10,mldab5,2), rA0 movapd 192-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 192-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 192-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 192-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 192-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 192-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 192-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 192-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 192-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 192-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 192-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 192-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 192-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 192-120(pA5,ldab,8), rB0 addpd rB0, rC13 movapd 208-120(pA10,mldab5,2), rA0 movapd 208-120(pB0), rB0 mulpd rB0, rA0 addpd rA0, rC0 movapd 208-120(pA5, mldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC1 movapd 208-120(pA10, mldab,8), rA0 mulpd rB0, rA0 addpd rA0, rC2 movapd 208-120(pA5, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC3 movapd 208-120(pA5, mldab), rA0 mulpd rB0, rA0 addpd rA0, rC4 movapd 208-120(pA5), rA0 mulpd rB0, rA0 addpd rA0, rC5 movapd 208-120(pA5, ldab), rA0 mulpd rB0, rA0 addpd rA0, rC6 movapd 208-120(pA5, ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC7 movapd 208-120(pA10, mldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC8 movapd 208-120(pA5,ldab,4), rA0 mulpd rB0, rA0 addpd rA0, rC9 movapd 208-120(pA10), rA0 mulpd rB0, rA0 addpd rA0, rC10 movapd 208-120(pA10,ldab), rA0 mulpd rB0, rA0 addpd rA0, rC11 movapd 208-120(pA10,ldab,2), rA0 mulpd rB0, rA0 addpd rA0, rC12 mulpd 208-120(pA5,ldab,8), rB0 addpd rB0, rC13/* While (pB != stK); *//* *//* cmp pB, stK *//* jne KLOOP *//* * Get these bastard things summed up correctly */ /* rC0 = c0a c0b */ /* rC1 = c1a c1b */ /* rC2 = c2a c2b */ /* rC3 = c3a c3b */ /* rC4 = c4a c4b */ /* rC5 = c5a c5b */ /* rC6 = c6a c6b */ /* rC7 = c7a c7b */ prefC((pC,incCn)) prefC(64(pC, incCn)) movapd rC0, rA0 movapd rC4, rB0 unpcklpd rC1, rC0 /* rC0 = c0a c1a */ unpcklpd rC5, rC4 /* rC4 = c4a c5a */ unpckhpd rC1, rA0 /* rA0 = c0b c1b */ unpckhpd rC5, rB0 /* rB0 = c4b c5b */#ifdef BETAX movapd (pC), rC5 addpd rA0, rC0 /* rC0 = c0ab c1ab */ prefC(128(pC,incCn)) prefC(192(pC, incCn)) addpd rB0, rC4 /* rC4 = c4ab c5ab */ mulpd BOF(%rsp), rC5 movapd rC2, rA0 movapd rC6, rB0 unpcklpd rC3, rC2 /* rC2 = c2a c3a */ addpd rC5, rC0 unpcklpd rC7, rC6 /* rC6 = c6a c7a */ prefB(160-120(pB,ldab)) movapd 16(pC), rC5 unpckhpd rC3, rA0 /* rA0 = c2b c3b */ unpckhpd rC7, rB0 /* rB0 = c6b c7b */ movapd 32(pC), rC7 addpd rA0, rC2 /* rC2 = c2ab c3ab */ mulpd BOF(%rsp), rC5 addpd rB0, rC6 /* rC6 = c6ab c7ab */ /* rC8 = c08a c08b */ /* rC9 = c09a c09b */ /* rC10 = c10a c10b */ /* rC11 = c11a c11b */ /* rC12 = c12a c12b */ /* rC13 = c13a c13b */ movapd rC8, rA0 movapd rC10, rC1 addpd rC5, rC2 mulpd BOF(%rsp), rC7 movapd rC12, rC3 unpcklpd rC9, rC8 /* rC8 = c08a c09a */ movapd 48(pC), rC5 subq $NBNBso-NB14so+224, pA5 unpcklpd rC11, rC10
⌨️ 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?