This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [patch] require sse3 for fisttp

Andrew Pinski wrote:
On Sat, 2006-09-16 at 22:10 -0700, Eric Christopher wrote:
You still haven't addressed the issue of "it is considered an sse3 instruction in that the processor will fault". Until you do, please refrain from arguing this more. 

I did, did you see how I said it was Intel's fault for renaming PNI to
SSE3 without considering there some PNIs did not effect SSE registers.
Until you realize that -msse3 should only effect instructions that
effect SSE registers, then please refrain from arguing this more.


Your opinion on a "fault" of intel is irrelevant to a technical discussion. Whether you like it or not the instruction is considered SSE3 and therefore falls under the SSE3 instruction set and should fall under the effect of the flag.

-eric

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]