summaryrefslogtreecommitdiffstats
path: root/mlir/test/Conversion/GPUToCUDA
Commit message (Expand)AuthorAgeFilesLines
* Plug gpu.func into the GPU lowering pipelinesAlex Zinenko2019-12-161-2/+3
* Introduce Linkage attribute to the LLVM dialectAlex Zinenko2019-12-021-2/+2
* Use LLVM_Type instead of AnyType in the definition of LLVM_CallOpAlex Zinenko2019-10-211-2/+2
* Use llvm.func to define functions with wrapped LLVM IR function typeAlex Zinenko2019-10-102-7/+8
* GPUToCUDA: attach CUBIN to the nested module rather than to the functionAlex Zinenko2019-10-082-5/+4
* GPUToCUDA: emit addressof directly instead of wrapping it into a getter functionAlex Zinenko2019-10-081-12/+8
* Fuse GenerateCubinAccessors pass into LaunchFunctToCudaAlex Zinenko2019-10-082-24/+10
* Use named modules for gpu.launch_funcAlex Zinenko2019-10-082-26/+33
* Outline GPU kernel function into a nested module.Christian Sigg2019-09-232-10/+33
* Automated rollback of commit 5684a12434f923d03b6870f2aa16226bfb0b38b6George Karpenkov2019-09-192-33/+10
* Outline GPU kernel function into a nested module.MLIR Team2019-09-192-10/+33
* LLVM dialect: prefix auxiliary operations with "mlir."Alex Zinenko2019-09-032-4/+4
* ConvertLaunchFuncToCudaCalls: use LLVM dialect globalsAlex Zinenko2019-08-201-8/+10
* GenerateCubinAccessors: use LLVM dialect constantsAlex Zinenko2019-08-131-26/+9
* Add an mlir-cuda-runner tool.Stephan Herhut2019-07-041-3/+3
* Add a pass that inserts getters for all cubins found via nvvm.cubinStephan Herhut2019-06-261-0/+31
* Make GPU to CUDA transformations independent of CUDA runtime.Stephan Herhut2019-06-263-0/+35
OpenPOWER on IntegriCloud