diff options
| author | Amy Kwan <amy.kwan1@ibm.com> | 2021-08-13 11:22:38 -0500 |
|---|---|---|
| committer | Amy Kwan <amy.kwan1@ibm.com> | 2021-08-13 12:27:24 -0500 |
| commit | 581a80304c671b6cb2b1b1f87feb9fbe14875f2a (patch) | |
| tree | 07d28b677eb6fd6d6dba04e553a23ef813ab8521 /llvm/lib/Transforms/Utils/InlineFunction.cpp | |
| parent | 571b0d84d2071f403980823989fdb90288bca972 (diff) | |
| download | llvm-581a80304c671b6cb2b1b1f87feb9fbe14875f2a.zip llvm-581a80304c671b6cb2b1b1f87feb9fbe14875f2a.tar.gz llvm-581a80304c671b6cb2b1b1f87feb9fbe14875f2a.tar.bz2 | |
[PowerPC] Disable CTR Loop generate for fma with the PPC double double type.
It is possible to generate the llvm.fmuladd.ppcf128 intrinsic, and there is no actual
FMA instruction that corresponds to this intrinsic call for ppcf128. Thus, this
intrinsic needs to remain as a call as it cannot be lowered to any instruction, which
also means we need to disable CTR loop generation for fma involving the ppcf128 type.
This patch accomplishes this behaviour.
Differential Revision: https://reviews.llvm.org/D107914
Diffstat (limited to 'llvm/lib/Transforms/Utils/InlineFunction.cpp')
0 files changed, 0 insertions, 0 deletions