RE: Should -mfma/-mavx and -msse5/-msse4a mutually exclusive?

2008-11-18 Thread rajagopal, dwarak
mavx should turn off -msse5/-msse4a and vice versa. > Yes. We can have -mavx turn off -msse5/-msse4a. Thanks, Dwarak > -Original Message- > From: H.J. Lu [mailto:[EMAIL PROTECTED] > Sent: Sunday, November 16, 2008 1:04 PM > To: Uros Bizjak; GCC Development; Ye, Joey; Guo, Xuep

RE: RFC: A new meta intrinsic header file for x86 intrinsics

2008-11-05 Thread rajagopal, dwarak
I agree with Michael on the naming and having separate files for AVX and including all the header files inside x86intrin.h. Also it would be easy for the users if we include all the instruction sets supported by both Intel and AMD in x86intrin.h file so that it is sufficient for the application de

RE: cmov for stores

2006-03-08 Thread rajagopal, dwarak
Behalf Of Steven Bosscher Sent: Thursday, February 09, 2006 1:31 PM To: gcc@gcc.gnu.org Cc: rajagopal, dwarak Subject: Re: cmov for stores On Thursday 09 February 2006 20:04, rajagopal, dwarak wrote: > The fact here is that in this case, A[k] will never trap because the > A[k] is already bee

cmov for stores

2006-02-09 Thread rajagopal, dwarak
int cmov(int* A ,int B ,int C ,int* D ,int* E ,int F ,int g) { int k,f; for (k = 1; k <= 1000; k++) { A[k] = B+C; g = D[k-1] + E[k-1]; if (g > A[k]) A[k]=g; /* This is not converted to cmov*/ f += g; } return f; } In the above code, the if-then statement is not conve