[Bug target/62054] New: fabsf uses constant pool and andps (x86-64) - use pabsd instead?

[Bug target/62054] New: fabsf uses constant pool and andps (x86-64) - use pabsd instead?

[spatel at rotateright dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62054

            Bug ID: 62054
           Summary: fabsf uses constant pool and andps (x86-64) - use
                    pabsd instead?
           Product: gcc
           Version: 4.9.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: spatel at rotateright dot com

$ cat fabs.c 
#include <math.h>
float foo(float a) {
    return fabsf(a);
}

$ gcc49 -O1 fabs.c -S -o -
    .text
    .globl _foo
_foo:
LFB19:
    movss    LC0(%rip), %xmm1
    andps    %xmm1, %xmm0
    ret
LFE19:
    .literal16
    .align 4
LC0:
    .long    2147483647
    .long    0
    .long    0
    .long    0

----------------------------------------------------

I think we can save 16-bytes of constant pool data and a load instruction by
generating:

   pabsd %xmm0, %xmm0


If this was part of a larger floating point chain of ops and depending on CPU,
there may be some speed penalty for intermingling integer and FP ops on data in
an xmm reg, but the size savings should outweigh that?

[Bug target/62054] fabsf uses constant pool and andps (x86-64) - use pabsd instead?

[glisse at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62054

--- Comment #1 from Marc Glisse <glisse at gcc dot gnu.org> ---
Did you try it? It doesn't compute the same thing at all...

[Bug target/62054] fabsf uses constant pool and andps (x86-64) - use pabsd instead?

[spatel at rotateright dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=62054

--- Comment #3 from Sanjay Patel <spatel at rotateright dot com> ---
I think there's still an optimization possible here regarding the constant pool
data - see bug 62055. Hopefully, I didn't mess that one up. :)