Question/Advice on PERMD and PERMPS..

Question/Advice on PERMD and PERMPS..

perfwise的头像

Intel, the instructions above take the form:

PERMD XDEST, XSRC1, XSRC2

the mask containing the indexes is stored in XSRC1 and the bytes to be permuted are in XSRC2.  Why is the mask not in XSRC2 and viceversa.  The PERMILPS and other instructions have used the implicit mask as the last SRC.  Is there a reason you changed this?  I just ask because the x86 instruction set is complicated as it is.. and now to have some forms of PERM instructions in one orientation and others in the opposite.. it's just confusing.  

Also, why don't you provide a similar implicit form for PERMQ and PERMPD?  There it's only encoded with immediates.

I wanted to offer some advice and suggest keeping the format uniform, as much as possible. 

Perfwise

1 条帖子 / 0 new
如需更全面地了解编译器优化,请参阅优化注意事项