diff options
| author | Farzon Lotfi <1802579+farzonl@users.noreply.github.com> | 2024-06-27 12:15:13 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-27 15:15:13 -0400 |
| commit | 918313d17d38d8723d5d81fef008538677abf9cc (patch) | |
| tree | e55581ef9bf218bd8a62674c3c48cfebbc46932a /llvm/lib/Analysis/ValueTracking.cpp | |
| parent | aa8409fdca5e738c30a4ab70a3dc809bb4e9160d (diff) | |
| download | llvm-918313d17d38d8723d5d81fef008538677abf9cc.zip llvm-918313d17d38d8723d5d81fef008538677abf9cc.tar.gz llvm-918313d17d38d8723d5d81fef008538677abf9cc.tar.bz2 | |
[SLPVectorizer] Support SLPVectorizer cases of tan across all backends (#95517)
This PR is intended to address the limited SLPVectorizer support of tan
raised in the comments of this PR:
https://github.com/llvm/llvm-project/pull/94559.
Right now emitting the tan intrinsisic allows you to vectorize tan, but
emitting the libfunc does not. to address this the libcall needs to be
mapped to the intrinsic. and the libcall and function name need to be
marked approriately so they can be optimized or defined as a call
lowering.
Diffstat (limited to 'llvm/lib/Analysis/ValueTracking.cpp')
| -rw-r--r-- | llvm/lib/Analysis/ValueTracking.cpp | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp index d0d9caa..44ac0db 100644 --- a/llvm/lib/Analysis/ValueTracking.cpp +++ b/llvm/lib/Analysis/ValueTracking.cpp @@ -3994,6 +3994,10 @@ Intrinsic::ID llvm::getIntrinsicForCallSite(const CallBase &CB, case LibFunc_cosf: case LibFunc_cosl: return Intrinsic::cos; + case LibFunc_tan: + case LibFunc_tanf: + case LibFunc_tanl: + return Intrinsic::tan; case LibFunc_exp: case LibFunc_expf: case LibFunc_expl: |