[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-24 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 Jakub Jelinek changed: What|Removed |Added Status|NEW |RESOLVED Resolution|---

[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-24 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 --- Comment #9 from Jakub Jelinek --- Author: jakub Date: Sun Feb 24 19:23:51 2019 New Revision: 269176 URL: https://gcc.gnu.org/viewcvs?rev=269176&root=gcc&view=rev Log: PR rtl-optimization/89445 * simplify-rtx.c (simplify_terna

[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-22 Thread thiago at kde dot org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 --- Comment #8 from Thiago Macieira --- Sorry, in editing I ended up removing an important point: GCC 8 also generates the move *from* OpMask when I put it in the benchmark loop. So that's not a regression, per se.

[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-22 Thread thiago at kde dot org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 --- Comment #7 from Thiago Macieira --- Comment on attachment 45800 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=45800 gcc9-pr89445.patch Tested and works on my machine. The movzbl that GCC 8 generated is also gone, but it inserted move

[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-22 Thread thiago at kde dot org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 --- Comment #6 from Thiago Macieira --- (In reply to Jakub Jelinek from comment #4) > vmovupd (%rsi,%rax), %zmm1{%k1}{z} > addq%rdx, %rax > vmovupd (%rax), %zmm2{%k1}{z} > vfmadd132pd %zmm0, %zmm2, %zmm1 >

[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-22 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 --- Comment #5 from Jakub Jelinek --- Created attachment 45800 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=45800&action=edit gcc9-pr89445.patch Full untested fix.

[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-22 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 --- Comment #4 from Jakub Jelinek --- vmovupd (%rsi,%rax), %zmm1{%k1}{z} addq%rdx, %rax vmovupd (%rax), %zmm2{%k1}{z} vfmadd132pd %zmm0, %zmm2, %zmm1 vmovupd %zmm1, (%rax){%k1} isn't optimal btw, it

[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-22 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 --- Comment #3 from Jakub Jelinek --- Something like: --- gcc/simplify-rtx.c.jj 2019-01-10 11:43:14.390377646 +0100 +++ gcc/simplify-rtx.c 2019-02-22 17:54:36.633829649 +0100 @@ -6073,8 +6073,10 @@ simplify_ternary_operation (enum rtx_cod

[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-22 Thread jakub at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 Jakub Jelinek changed: What|Removed |Added Status|UNCONFIRMED |NEW Last reconfirmed|

[Bug rtl-optimization/89445] [9 regression] _mm512_maskz_loadu_pd "forgets" to use the mask

2019-02-21 Thread rguenth at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89445 Richard Biener changed: What|Removed |Added Keywords||wrong-code Target|