使用Visual Studio 2015,Win 7 64位模式,我找到了erf()中使用的一些路径的以下代码(并非显示所有路径)。 每个路径涉及从内存中读取的最多8个(可能更多用于其他路径)常量,因此保存寄存器的单个存储/加载似乎不太可能导致Linux和Windows之间的3倍速差。 至于保存/恢复,此示例保存并恢复xmm6和xmm7。 至于时间,原始帖子中的程序在Intel 3770K(3.5ghz cpu)(VS2015 / Win 7 64 bit)上大约需要0.86秒。 更新 - 我后来确定,在程序10 ^ 8循环(每个循环约3纳秒)的情况下,保存和恢复xmm寄存器的开销约为0.03秒。
000007FEEE25CF90 mov rax,rsp
000007FEEE25CF93 movss dword ptr [rax+8],xmm0
000007FEEE25CF98 sub rsp,48h
000007FEEE25CF9C movaps xmmword ptr [rax-18h],xmm6
000007FEEE25CFA0 lea rcx,[rax+8]
000007FEEE25CFA4 movaps xmmword ptr [rax-28h],xmm7
000007FEEE25CFA8 movaps xmm6,xmm0
000007FEEE25CFAB call 000007FEEE266370
000007FEEE25CFB0 movsx ecx,ax
000007FEEE25CFB3 test ecx,ecx
000007FEEE25CFB5 je 000007FEEE25D0AF
000007FEEE25CFBB sub ecx,1
000007FEEE25CFBE je 000007FEEE25D08F
000007FEEE25CFC4 cmp ecx,1
000007FEEE25CFC7 je 000007FEEE25D0AF
000007FEEE25CFCD xorps xmm7,xmm7
000007FEEE25CFD0 movaps xmm2,xmm6
000007FEEE25CFD3 comiss xmm7,xmm6
000007FEEE25CFD6 jbe 000007FEEE25CFDF
000007FEEE25CFD8 xorps xmm2,xmmword ptr [7FEEE2991E0h]
000007FEEE25CFDF movss xmm0,dword ptr [7FEEE298E50h]
000007FEEE25CFE7 comiss xmm0,xmm2
000007FEEE25CFEA jbe 000007FEEE25D053
000007FEEE25CFEC movaps xmm2,xmm6
000007FEEE25CFEF mulss xmm2,xmm6
000007FEEE25CFF3 movaps xmm0,xmm2
000007FEEE25CFF6 movaps xmm1,xmm2
000007FEEE25CFF9 mulss xmm0,dword ptr [7FEEE298B34h]
000007FEEE25D001 mulss xmm1,dword ptr [7FEEE298B5Ch]
000007FEEE25D009 addss xmm0,dword ptr [7FEEE298B8Ch]
000007FEEE25D011 addss xmm1,dword ptr [7FEEE298B9Ch]
000007FEEE25D019 mulss xmm0,xmm2
000007FEEE25D01D mulss xmm1,xmm2
000007FEEE25D021 addss xmm0,dword ptr [7FEEE298BB8h]
000007FEEE25D029 addss xmm1,dword ptr [7FEEE298C88h]
000007FEEE25D031 mulss xmm0,xmm2
000007FEEE25D035 mulss xmm1,xmm2
000007FEEE25D039 addss xmm0,dword ptr [7FEEE298DC8h]
000007FEEE25D041 addss xmm1,dword ptr [7FEEE298D8Ch]
000007FEEE25D049 divss xmm0,xmm1
000007FEEE25D04D mulss xmm0,xmm6
000007FEEE25D051 jmp 000007FEEE25D0B2
000007FEEE25D053 movss xmm1,dword ptr [7FEEE299028h]
000007FEEE25D05B comiss xmm1,xmm2
000007FEEE25D05E jbe 000007FEEE25D076
000007FEEE25D060 movaps xmm0,xmm2
000007FEEE25D063 call 000007FEEE25CF04
000007FEEE25D068 movss xmm1,dword ptr [7FEEE298D8Ch]
000007FEEE25D070 subss xmm1,xmm0
000007FEEE25D074 jmp 000007FEEE25D07E
000007FEEE25D076 movss xmm1,dword ptr [7FEEE298D8Ch]
000007FEEE25D07E comiss xmm7,xmm6
000007FEEE25D081 jbe 000007FEEE25D08A
000007FEEE25D083 xorps xmm1,xmmword ptr [7FEEE2991E0h]
000007FEEE25D08A movaps xmm0,xmm1
000007FEEE25D08D jmp 000007FEEE25D0B2
000007FEEE25D08F mov eax,8000h
000007FEEE25D094 test word ptr [rsp+52h],ax
000007FEEE25D099 je 000007FEEE25D0A5
000007FEEE25D09B movss xmm0,dword ptr [7FEEE2990DCh]
000007FEEE25D0A3 jmp 000007FEEE25D0B2
000007FEEE25D0A5 movss xmm0,dword ptr [7FEEE298D8Ch]
000007FEEE25D0AD jmp 000007FEEE25D0B2
000007FEEE25D0AF movaps xmm0,xmm6
000007FEEE25D0B2 movaps xmm6,xmmword ptr [rsp+30h]
000007FEEE25D0B7 movaps xmm7,xmmword ptr [rsp+20h]
000007FEEE25D0BC add rsp,48h
000007FEEE25D0C0 ret