flat assembler
Message board for the users of flat assembler.
![]() |
Author |
|
cod3b453 02 Jan 2014, 15:55
SSE always uses registers since it doesn't use the stack mechanism that the FPU uses. Note also that you can incur precision losses due to the float format.
SSE provides both floating point and integer operations; without more details on what you're doing I can only suggest using (v)pmul(u)dq for full precision or another pmul variant for optimisation unless you do actually want to represent very large numbers. However if you're only performing scalar multiplication it may be better to use the normal mul instruction. |
|||
![]() |
|
< Last Thread | Next Thread > |
Forum Rules:
|
Copyright © 1999-2025, Tomasz Grysztar. Also on GitHub, YouTube.
Website powered by rwasa.