public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug target/57009] New: Select best typed instruction for scalar bitwise operations
@ 2013-04-19 19:46 glisse at gcc dot gnu.org
2021-12-06 23:52 ` [Bug target/57009] " pinskia at gcc dot gnu.org
0 siblings, 1 reply; 2+ messages in thread
From: glisse at gcc dot gnu.org @ 2013-04-19 19:46 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=57009
Bug #: 57009
Summary: Select best typed instruction for scalar bitwise
operations
Classification: Unclassified
Product: gcc
Version: 4.9.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: enhancement
Priority: P3
Component: target
AssignedTo: unassigned@gcc.gnu.org
ReportedBy: glisse@gcc.gnu.org
Target: x86_64-linux-gnu
Hello,
I purposedly took almost the same title as PR 54716, because this is the same
issue, but for scalars. Consider this code:
union A { double d; unsigned long long i; };
bool f(double a, double b, double c){
A x, y, z;
x.d = a * a;
y.d = b * b;
z.i = x.i & y.i;
return z.d < c;
}
which compiles to:
mulsd %xmm0, %xmm0
mulsd %xmm1, %xmm1
movq %xmm0, %rax
movq %xmm1, %rdx
andq %rdx, %rax
movq %rax, %xmm0
ucomisd %xmm0, %xmm2
seta %al
when using andpd would save 3 movq. Note that for vectors, we get nicer code
thanks to Jakub's patch:
mulpd %xmm1, %xmm1
mulpd %xmm0, %xmm0
andpd %xmm1, %xmm0
cmpltpd %xmm2, %xmm0
It would be nice to extend that code to scalars (including the case where one
of the arguments is a constant).
I hit this while experimenting for PR 56944.
^ permalink raw reply [flat|nested] 2+ messages in thread
* [Bug target/57009] Select best typed instruction for scalar bitwise operations
2013-04-19 19:46 [Bug target/57009] New: Select best typed instruction for scalar bitwise operations glisse at gcc dot gnu.org
@ 2021-12-06 23:52 ` pinskia at gcc dot gnu.org
0 siblings, 0 replies; 2+ messages in thread
From: pinskia at gcc dot gnu.org @ 2021-12-06 23:52 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=57009
--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
(In reply to Marc Glisse from comment #1)
> union A { double d; unsigned long long i; };
> bool f(double x){
> A a; a.d = x;
> unsigned long long inf = 0x7ff0000000000000;
> return (a.i & inf) != inf;
> }
>
> (I use != and not < in the example above because gcc insists on creating a
> new constant inf-1 and replacing <inf with <=inf-1)
I think the above issue is the same issue as mentioned in PR 95740.
I have not looked into the original comments yet but I think there might be a
dup of it somewhere too.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2021-12-06 23:52 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2013-04-19 19:46 [Bug target/57009] New: Select best typed instruction for scalar bitwise operations glisse at gcc dot gnu.org
2021-12-06 23:52 ` [Bug target/57009] " pinskia at gcc dot gnu.org
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).