diff options
| author | Karthik Senthil <karthik.senthil@intel.com> | 2022-11-04 10:33:45 -0400 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2022-11-04 10:39:37 -0400 |
| commit | d9c52c31a0fee22414bb4024ee5b203fe86ef5bb (patch) | |
| tree | 840708bc29242cc7b7fc116bffc782fad98cd4d2 /flang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 710e34e1360710275662ad5b0bdc394570fb26d5 (diff) | |
| download | llvm-d9c52c31a0fee22414bb4024ee5b203fe86ef5bb.zip llvm-d9c52c31a0fee22414bb4024ee5b203fe86ef5bb.tar.gz llvm-d9c52c31a0fee22414bb4024ee5b203fe86ef5bb.tar.bz2 | |
[LV][IVDescriptors] Fix recurrence identity element for FMin and FMax reductions
For a min and max reduction idioms, the identity (i.e. neutral) element
should be datatype's highest and lowest possible values respectively.
Current implementation in IVDescriptors incorrectly returns -Inf for FMin
reduction and +Inf for FMax reduction. This patch fixes this bug which
was causing incorrect reduction computation results in loops vectorized
by LV.
Differential Revision: https://reviews.llvm.org/D137220
Diffstat (limited to 'flang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions