https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
Martin Liška changed:
What|Removed |Added
CC||jbeulich at suse dot com,
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
Jakub Jelinek changed:
What|Removed |Added
Assignee|unassigned at gcc dot gnu.org |jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #3 from H.J. Lu ---
Created attachment 48126
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=48126&action=edit
A patch
Jakub, this is what I have. Feel free to ignore it.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #4 from Jakub Jelinek ---
I was thinking about
--- gcc/config/i386/sse.md.jj 2020-03-06 11:35:46.284074858 +0100
+++ gcc/config/i386/sse.md 2020-03-26 17:35:23.690515228 +0100
@@ -12800,10 +12800,18 @@
(xor:VI (match_op
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #5 from Jakub Jelinek ---
Created attachment 48127
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=48127&action=edit
gcc10-pr94343.patch
That of course doesn't work if the input operand is memory. This should.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #6 from H.J. Lu ---
(In reply to Jakub Jelinek from comment #5)
> Created attachment 48127 [details]
> gcc10-pr94343.patch
>
> That of course doesn't work if the input operand is memory. This should.
LGTM. Thanks.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #7 from Jakub Jelinek ---
Though, there are other issues. There is only vpternlog{d,q}, so for
V*[QH]Imode we shouldn't pretend we have masking support.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
Jakub Jelinek changed:
What|Removed |Added
Attachment #48127|0 |1
is obsolete|
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #9 from Matthias Kretz (Vir) ---
(In reply to Jakub Jelinek from comment #8)
> Created attachment 48128 [details]
> gcc10-pr94343.patch
The avx512vl-pr94343.c test should ideally fail because `_mm_andnot_si128
((__m128i) (~v ^ a), (_
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #10 from Jakub Jelinek ---
--- gcc/testsuite/gcc.target/i386/avx512f-pr94343.c.jj 2020-03-26
17:47:40.008654504 +0100
+++ gcc/testsuite/gcc.target/i386/avx512f-pr94343.c 2020-03-26
17:48:37.169811375 +0100
@@ -0,0 +1,12 @@
+/* PR
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #11 from jbeulich at suse dot com ---
(In reply to Jakub Jelinek from comment #7)
> Though, there are other issues. There is only vpternlog{d,q}, so for
> V*[QH]Imode we shouldn't pretend we have masking support.
Why would this be? T
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #12 from jbeulich at suse dot com ---
(In reply to Jakub Jelinek from comment #8)
> Created attachment 48128 [details]
> gcc10-pr94343.patch
>
> Updated patch. A variant to that would be 4 separate patterns I guess, not
> sure if tha
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #13 from jbeulich at suse dot com ---
As to using 512-bit operations even on more narrow input types - is this
correct when e.g. subsequently source code upcasts the vector? I.e. would such
an upcast be carried out by emitting an insn
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #14 from Jakub Jelinek ---
(In reply to jbeulich from comment #13)
> As to using 512-bit operations even on more narrow input types - is this
> correct when e.g. subsequently source code upcasts the vector? I.e. would
> such an upcast
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #15 from Jakub Jelinek ---
(In reply to jbeulich from comment #11)
> (In reply to Jakub Jelinek from comment #7)
> > Though, there are other issues. There is only vpternlog{d,q}, so for
> > V*[QH]Imode we shouldn't pretend we have ma
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #16 from jbeulich at suse dot com ---
Oh, right - I didn't pay attention to the insn permitting masking to be used.
Then still non-masked uses ought to be permitted, perhaps by having a
VI48_AVX512VL one permitting masking and a VI12_A
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #17 from Jakub Jelinek ---
The patch I've posted -
https://gcc.gnu.org/pipermail/gcc-patches/2020-March/542774.html - solves it by
disabling the problematic masked cases in the condition. Or we could just
disable the masking on the i
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
--- Comment #18 from CVS Commits ---
The master branch has been updated by Jakub Jelinek :
https://gcc.gnu.org/g:5abbfd3cd36342df530410033844584d8b85e187
commit r10-7460-g5abbfd3cd36342df530410033844584d8b85e187
Author: Jakub Jelinek
Date: M
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94343
Jakub Jelinek changed:
What|Removed |Added
Status|ASSIGNED|RESOLVED
Resolution|---
19 matches
Mail list logo