diff options
| author | Justin Lebar <jlebar@google.com> | 2017-01-31 05:58:22 +0000 |
|---|---|---|
| committer | Justin Lebar <jlebar@google.com> | 2017-01-31 05:58:22 +0000 |
| commit | 1c9692a46fd5650c65da38cb371b8e62a0303cfa (patch) | |
| tree | 16220e7e090164ccb56edf0fea98863ef2fdbff1 /llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp | |
| parent | 93590e09d517f3574a0a9130d1b56440b928933a (diff) | |
| download | llvm-1c9692a46fd5650c65da38cb371b8e62a0303cfa.zip llvm-1c9692a46fd5650c65da38cb371b8e62a0303cfa.tar.gz llvm-1c9692a46fd5650c65da38cb371b8e62a0303cfa.tar.bz2 | |
[NVPTX] Implement NVPTXTargetLowering::getSqrtEstimate.
Summary:
This lets us lower to sqrt.approx and rsqrt.approx under more
circumstances.
* Now we emit sqrt.approx and rsqrt.approx for calls to @llvm.sqrt.f32,
when fast-math is enabled. Previously, we only would emit it for
calls to @llvm.nvvm.sqrt.f. (With this patch we no longer emit
sqrt.approx for calls to @llvm.nvvm.sqrt.f; we rely on intcombine to
simplify llvm.nvvm.sqrt.f into llvm.sqrt.f32.)
* Now we emit the ftz version of rsqrt.approx when ftz is enabled.
Previously, we only emitted rsqrt.approx when ftz was disabled.
Reviewers: hfinkel
Subscribers: llvm-commits, tra, jholewinski
Differential Revision: https://reviews.llvm.org/D28508
llvm-svn: 293605
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp')
0 files changed, 0 insertions, 0 deletions