forked from OSchip/llvm-project
d912a9ba9b
Summary: Since the target has no significant advantage of vectorization, vector instructions bous threshold bonus should be optional. amdgpu-inline-arg-alloca-cost parameter default value and the target InliningThresholdMultiplier value tuned then respectively. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, eraman, hiraditya, haicheng, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D64642 llvm-svn: 366348 |
||
|---|---|---|
| .. | ||
| amdgpu-inline-alloca-argument.ll | ||
| inline-amdgpu-dx10-clamp.ll | ||
| inline-amdgpu-ieee.ll | ||
| inline-amdgpu-vecbonus.ll | ||
| inline-hint.ll | ||
| inline-target-cpu.ll | ||
| inline-target-feature-sram-ecc.ll | ||
| inline-target-feature-xnack.ll | ||
| lit.local.cfg | ||