[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread hjl.tools at gmail dot com
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 H.J. Lu hjl.tools at gmail dot com changed: What|Removed |Added Status|UNCONFIRMED |WAITING Last

[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread dushistov at mail dot ru
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 --- Comment #3 from Evgeniy Dushistov dushistov at mail dot ru --- So step to reproduce: 1)Download attachment 2)Extract tar xvf dummy_hash.tar 3)Build cd dummy_hash make 4)Run ./thash

[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread pinskia at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 Andrew Pinski pinskia at gcc dot gnu.org changed: What|Removed |Added Status|WAITING |RESOLVED

[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread dushistov at mail dot ru
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 --- Comment #2 from Evgeniy Dushistov dushistov at mail dot ru --- (In reply to H.J. Lu from comment #1) Which gcc did you use? Please provide a run-time test. I try gcc 4.6.4, 4.7.4, 4.9.2, 5.1.0. If you compile attachment on linux/amd64 and

[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread trippels at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 Markus Trippelsdorf trippels at gcc dot gnu.org changed: What|Removed |Added CC|

[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread dushistov at mail dot ru
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 --- Comment #6 from Evgeniy Dushistov dushistov at mail dot ru --- (In reply to Andrew Pinski from comment #5) C standard says this is undefined code. Where? there is two issues aliasing (but I use -fno-strict-aliasing), and alignment, c99 of

[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread trippels at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 --- Comment #7 from Markus Trippelsdorf trippels at gcc dot gnu.org --- 6.3.2.3 p7: »A pointer to an object type may be converted to a pointer to a different object type. If the resulting pointer is not correctly aligned for the referenced type,

[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread pinskia at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 --- Comment #9 from Andrew Pinski pinskia at gcc dot gnu.org --- (In reply to Evgeniy Dushistov from comment #8) (In reply to Markus Trippelsdorf from comment #7) 6.3.2.3 p7: »A pointer to an object type may be converted to a pointer to a

[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread dushistov at mail dot ru
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 --- Comment #8 from Evgeniy Dushistov dushistov at mail dot ru --- (In reply to Markus Trippelsdorf from comment #7) 6.3.2.3 p7: »A pointer to an object type may be converted to a pointer to a different object type. If the resulting pointer is

[Bug c/66194] emit vectorization instruction for not aligned data(amd64), -fno-strict-aliasing not help

2015-05-18 Thread dushistov at mail dot ru
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66194 --- Comment #10 from Evgeniy Dushistov dushistov at mail dot ru --- ABI requirements are not C requirements always. This paragraph is talking about memory accesses but really it did not take into account other requirements of C correctly. But