subject:"\[Bug target\/69299\] \[6 Regression\] \-mavx performance degradation with r232088"

[Bug target/69299] [6 Regression] -mavx performance degradation with r232088

2016-01-29 Thread law at redhat dot com

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69299 Jeffrey A. Law changed: What|Removed |Added Status|NEW |RESOLVED CC|

[Bug target/69299] [6 Regression] -mavx performance degradation with r232088

2016-01-29 Thread vmakarov at gcc dot gnu.org

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69299 --- Comment #8 from Vladimir Makarov --- Author: vmakarov Date: Fri Jan 29 18:47:17 2016 New Revision: 232993 URL: https://gcc.gnu.org/viewcvs?rev=232993&root=gcc&view=rev Log: 2016-01-29 Vladimir Makarov PR target/69299 * co

[Bug target/69299] [6 Regression] -mavx performance degradation with r232088

2016-01-26 Thread vmakarov at gcc dot gnu.org

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69299 --- Comment #7 from Vladimir Makarov --- (In reply to Jakub Jelinek from comment #3) > Maybe we really need to have two types of memory > constraints, ones which can be worst case always satisfied by reloading > their address into an address regi

[Bug target/69299] [6 Regression] -mavx performance degradation with r232088

2016-01-16 Thread hjl.tools at gmail dot com

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69299 --- Comment #6 from H.J. Lu --- Created attachment 37378 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=37378&action=edit A followup patch to call constraint_satisfied_p to check memory operand

[Bug target/69299] [6 Regression] -mavx performance degradation with r232088

2016-01-16 Thread hjl.tools at gmail dot com

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69299 H.J. Lu changed: What|Removed |Added Attachment #37364|0 |1 is obsolete|

[Bug target/69299] [6 Regression] -mavx performance degradation with r232088

2016-01-15 Thread hjl.tools at gmail dot com

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69299 --- Comment #4 from H.J. Lu --- Created attachment 37364 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=37364&action=edit A patch Does it make sense?

[Bug target/69299] [6 Regression] -mavx performance degradation with r232088

2016-01-15 Thread rguenth at gcc dot gnu.org

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69299 Richard Biener changed: What|Removed |Added Priority|P3 |P1 CC|

[Bug target/69299] [6 Regression] -mavx performance degradation with r232088

2016-01-15 Thread jakub at gcc dot gnu.org

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69299 --- Comment #3 from Jakub Jelinek --- Maybe we really need to have two types of memory constraints, ones which can be worst case always satisfied by reloading their address into an address register and another ones which can be worst case always

[Bug target/69299] [6 Regression] -mavx performance degradation with r232088

2016-01-15 Thread hjl.tools at gmail dot com

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69299 --- Comment #2 from H.J. Lu --- The related LRA code is case CT_MEMORY: if (MEM_P (op) && satisfies_memory_constraint_p (op, cn)) win = true;