[Bug target/90991] [9/10 Regression] _mm_loadu_ps instrinsic translates to vmovaps in combination with _mm512_insertf32x4

2019-08-06 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90991 Jakub Jelinek changed: What|Removed |Added Status|ASSIGNED|RESOLVED Resolution|---

[Bug target/90991] [9/10 Regression] _mm_loadu_ps instrinsic translates to vmovaps in combination with _mm512_insertf32x4

2019-08-06 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90991 Jakub Jelinek changed: What|Removed |Added CC||kretz at kde dot org --- Comment #8

[Bug target/90991] [9/10 Regression] _mm_loadu_ps instrinsic translates to vmovaps in combination with _mm512_insertf32x4

2019-06-28 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90991 --- Comment #6 from Jakub Jelinek --- Author: jakub Date: Fri Jun 28 22:56:27 2019 New Revision: 272803 URL: https://gcc.gnu.org/viewcvs?rev=272803=gcc=rev Log: Backported from mainline 2019-06-26 Jakub Jelinek PR

[Bug target/90991] [9/10 Regression] _mm_loadu_ps instrinsic translates to vmovaps in combination with _mm512_insertf32x4

2019-06-27 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90991 --- Comment #5 from Jakub Jelinek --- Author: jakub Date: Thu Jun 27 11:13:10 2019 New Revision: 272745 URL: https://gcc.gnu.org/viewcvs?rev=272745=gcc=rev Log: PR target/90991 * config/i386/sse.md (avx_vec_concat): Use

[Bug target/90991] [9/10 Regression] _mm_loadu_ps instrinsic translates to vmovaps in combination with _mm512_insertf32x4

2019-06-26 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90991 --- Comment #4 from Jakub Jelinek --- Author: jakub Date: Wed Jun 26 08:26:18 2019 New Revision: 272674 URL: https://gcc.gnu.org/viewcvs?rev=272674=gcc=rev Log: PR target/90991 * config/i386/sse.md (*_vinsert_0): Use

[Bug target/90991] [9/10 Regression] _mm_loadu_ps instrinsic translates to vmovaps in combination with _mm512_insertf32x4

2019-06-26 Thread kronbichler.martin at gmail dot com
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90991 --- Comment #3 from Martin Kronbichler --- I can confirm that this patch creates the right instruction on my test case, "vmovups (%rdi,%rax,4), %xmm0", and also in the application code where it originated from.

[Bug target/90991] [9/10 Regression] _mm_loadu_ps instrinsic translates to vmovaps in combination with _mm512_insertf32x4

2019-06-25 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90991 --- Comment #2 from Jakub Jelinek --- Created attachment 46520 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=46520=edit gcc10-pr90991.patch Untested fix.

[Bug target/90991] [9/10 Regression] _mm_loadu_ps instrinsic translates to vmovaps in combination with _mm512_insertf32x4

2019-06-25 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90991 Jakub Jelinek changed: What|Removed |Added Priority|P3 |P2 Status|UNCONFIRMED