[Bug rtl-optimization/46391] false dependencies are computed after vectorization (#2)

2021-09-08 Thread rguenth at gcc dot gnu.org via Gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46391 Richard Biener changed: What|Removed |Added Status|UNCONFIRMED |RESOLVED Known to work|

[Bug rtl-optimization/46391] false dependencies are computed after vectorization (#2)

2021-08-15 Thread pinskia at gcc dot gnu.org via Gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46391 Andrew Pinski changed: What|Removed |Added Keywords||alias, missed-optimization

[Bug rtl-optimization/46391] false dependencies are computed after vectorization (#2)

2010-11-11 Thread roy.1rosen at gmail dot com
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46391 --- Comment #3 from Roy Rosen roy.1rosen at gmail dot com 2010-11-11 08:03:57 UTC --- It happens also on i386 with ./cc1 -O3 a.c -fdump-rtl-all -funroll-loops -fsched-verbose=8 -fschedule-insns: In asmcons: (insn 16 15 17 4 a.c:5 (set (reg:SI

[Bug rtl-optimization/46391] false dependencies are computed after vectorization (#2)

2010-11-09 Thread rguenth at gcc dot gnu.org
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46391 --- Comment #1 from Richard Guenther rguenth at gcc dot gnu.org 2010-11-09 13:18:47 UTC --- On x86_64 restrict information is there (-fdump-tree-optimized-alias): bb 5: # PT = nonlocal { PARM_RESTRICT.0 } (restr) vect_p.27_71 = c_8(D) +

[Bug rtl-optimization/46391] false dependencies are computed after vectorization (#2)

2010-11-09 Thread roy.1rosen at gmail dot com
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46391 --- Comment #2 from Roy Rosen roy.1rosen at gmail dot com 2010-11-09 13:48:15 UTC --- Seems to me that also on ia64 it is there but the dependecies are still wrong: ;; Function nor (nor) nor (char * restrict c, char * restrict d) { long