summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/AMDGPU/amdgpu-inline.ll
Commit message (Collapse)AuthorAgeFilesLines
* [AMDGPU] Tune inlining parameters for AMDGPU target (part 2)dfukalov2019-11-191-0/+7
| | | | | | | | | | | | | | | | | Summary: Most of IR instructions got better code size estimations after commit 47a5c36b. So default parameters values should be updated to improve inlining and unrolling for the target. Reviewers: rampitec, arsenm Reviewed By: rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, zzheng, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70391
* [AMDGPU] Tune inlining parameters for AMDGPU targetDaniil Fukalov2019-07-171-7/+0
| | | | | | | | | | | | | | | | | | | 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: Enable function calls by defaultMatt Arsenault2019-02-281-2/+2
| | | | | | | Fixes some crashes on illegal call situations which are unfortunately still valid IR. llvm-svn: 355051
* [AMDGPU] Switch to the new addr space mapping by defaultYaxun Liu2018-02-021-51/+51
| | | | | | | | This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
* [AMDGPU] Port of HSAIL inlinerStanislav Mekhanoshin2017-09-201-0/+152
Differential Revision: https://reviews.llvm.org/D36849 llvm-svn: 313714
OpenPOWER on IntegriCloud