Forums before death by AOL, social media and spammers... "We can't have nice things"
|    comp.lang.asm.x86    |    Ahh, the lost art of x86 assembly    |    4,675 messages    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
|    Message 3,961 of 4,675    |
|    Bonita Montero to All    |
|    Re: FMA4 on Matisse?    |
|    20 Oct 19 20:55:35    |
      From: Bonita.Montero@nospicedham.gmail.com              > FMA4 works on my 2700X. Question is: is that supported       > still on Zen2?       > Instructions are not reported at all by cpuid but works.       > I had some nice speedup with FMA4 on Zen.       > I don't know why FMA3 won when FMA4 is clearly superior?              When dealing with floating-point-operations you have a lot of       instructions with long latencies. Even if you have parallel chains       of instructions that could be pipelined, there are mostly oppurtu-       nities to hide movs that might be necessary to prevent overwriting       registers. And often their value isn't needed to be remembered. So       your speedup could be only slightly and sometimes there's nothing       at all.              --- SoupGate-Win32 v1.05        * Origin: you cannot sedate... all the things you hate (1:229/2)    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
(c) 1994, bbs@darkrealms.ca