[Bug target/106471] Strange code generation for __builtin_ctzl()

2022-07-29 Thread rguenth at gcc dot gnu.org via Gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106471 Richard Biener changed: What|Removed |Added Target||x86_64-*-* Keywords|

[Bug target/106471] Strange code generation for __builtin_ctzl()

2022-07-28 Thread torvalds--- via Gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106471 --- Comment #6 from Linus Torvalds --- Ahh, crossed comments. (In reply to Andrew Pinski from comment #3) > The xor is due to X86_TUNE_AVOID_FALSE_DEP_FOR_BMI setting: > > /* X86_TUNE_AVOID_FALSE_DEP_FOR_BMI: Avoid false dependency >for bi

[Bug target/106471] Strange code generation for __builtin_ctzl()

2022-07-28 Thread torvalds--- via Gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106471 --- Comment #5 from Linus Torvalds --- (In reply to Andrew Pinski from comment #2) > The xor is needed because of an errata in some Intel cores. The only errata I'm aware of is that tzcnt can act as tzcnt even when cpuid doesn't enumerate it (s

[Bug target/106471] Strange code generation for __builtin_ctzl()

2022-07-28 Thread pinskia at gcc dot gnu.org via Gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106471 --- Comment #4 from Andrew Pinski --- https://gcc.gnu.org/pipermail/gcc-patches/2022-July/598930.html

[Bug target/106471] Strange code generation for __builtin_ctzl()

2022-07-28 Thread pinskia at gcc dot gnu.org via Gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106471 --- Comment #3 from Andrew Pinski --- The xor is due to X86_TUNE_AVOID_FALSE_DEP_FOR_BMI setting: /* X86_TUNE_AVOID_FALSE_DEP_FOR_BMI: Avoid false dependency for bit-manipulation instructions. */ DEF_TUNE (X86_TUNE_AVOID_FALSE_DEP_FOR_BMI,

[Bug target/106471] Strange code generation for __builtin_ctzl()

2022-07-28 Thread pinskia at gcc dot gnu.org via Gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106471 Andrew Pinski changed: What|Removed |Added Component|c |target --- Comment #2 from Andrew Pinsk