encounter/llvm-project
0
0
Fork 0
mirror of https://github.com/encounter/llvm-project.git synced 2026-03-30 11:27:19 -07:00
Code Issues Packages Projects Releases Wiki Activity
364,413 Commits 42 Branches 155 Tags
ci
Commit Graph

3 Commits

Author SHA1 Message Date
Wen-Heng (Jack) Chung 061fb8eb2d [mlir][gpu][mlir-cuda-runner] Refactor ConvertKernelFuncToCubin to be generic. 
Make ConvertKernelFuncToCubin pass to be generic:

- Rename to ConvertKernelFuncToBlob.
- Allow specifying triple, target chip, target features.
- Initializing LLVM backend is supplied by a callback function.
- Lowering process from MLIR module to LLVM module is via another callback.
- Change mlir-cuda-runner to adopt the revised pass.
- Add new tests for lowering to ROCm HSA code object (HSACO).
- Tests for CUDA and ROCm are kept in separate directories.

Differential Revision: https://reviews.llvm.org/D80142
 2020-05-28 09:08:28 -05:00
Chris Lattner 42d8f48ccf Fix a warning building on my machine, NFC. warning: unused function 'compilePtxToCubinForTesting' 
Summary: Also eliminate the redunant anon namespace around the already static function.

Reviewers: herhut

Subscribers: hiraditya, steven_wu, dexonsmith, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, csigg, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76627
 2020-03-23 11:16:55 -07:00
River Riddle e8f5c072f6 [mlir] Move the testing pass for GpuKernelToCubin to the test/ directory 
Summary:
This removes the static pass registration, and also cleans up some lingering technical debt.

Differential Revision: https://reviews.llvm.org/D76554
 2020-03-22 03:38:09 -07:00