[Bug other/83497] CPU2000 172.mgrid starts failing with r254730
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83497 --- Comment #4 from Pat Haugen --- (In reply to Pat Haugen from comment #0) > mgrid started failing (output miscompare) with r254730. The following > options demonstrate the failure "-O3 -mcpu=power6 -ffast-math". Incomplete option set, -m32 is also required.
[Bug other/83497] CPU2000 172.mgrid starts failing with r254730
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83497 --- Comment #3 from Pat Haugen --- (In reply to Richard Biener from comment #2) > > As far as I see the miscompare is -0.8 vs. 0.18 so it doesn't look like a > precision issue to me. Does it only happen for power6 / bigendian? > Yes, the failure is only for -mcpu=power6. I don't have a copy of CPU2000 that runs on powerpc64le, so can't say for sure if it's a big endian issue only. I will do some further digging on the failure.
[Bug other/83497] CPU2000 172.mgrid starts failing with r254730
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83497 --- Comment #2 from Richard Biener --- The initial bisection rev. is indeed odd. I'm testing a fix for the inliner issue btw, but I've not seen the mgrid fail on any of our x86/ia64 configs. As far as I see the miscompare is -0.8 vs. 0.18 so it doesn't look like a precision issue to me. Does it only happen for power6 / bigendian? Maybe you can narrow down the root-cause somewhat - mgrid is a very small benchmark. power6 always hints at scheduling.
[Bug other/83497] CPU2000 172.mgrid starts failing with r254730
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83497 --- Comment #1 from Andrew Pinski --- I really doubt inlining is causing the miscompiling, only exposing it ... And if I look at the difference, it looks more like a precision issue which -ffast-math exposes.