aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/CodeGen/TargetLoweringObjectFileImpl.cpp
diff options
context:
space:
mode:
authorFabian Mora <fmora.dev@gmail.com>2023-09-14 18:00:27 -0400
committerGitHub <noreply@github.com>2023-09-14 18:00:27 -0400
commit5093413a5007b017a530edbeed42d32bfd18b126 (patch)
treef5e8406133c831911222cd1759a1ae2b46705235 /llvm/lib/CodeGen/TargetLoweringObjectFileImpl.cpp
parent6f4a5286981dd57826751834f7a434be1a463339 (diff)
downloadllvm-5093413a5007b017a530edbeed42d32bfd18b126.zip
llvm-5093413a5007b017a530edbeed42d32bfd18b126.tar.gz
llvm-5093413a5007b017a530edbeed42d32bfd18b126.tar.bz2
[mlir][gpu][NVPTX] Enable NVIDIA GPU JIT compilation path (#66220)
This patch adds an NVPTX compilation path that enables JIT compilation on NVIDIA targets. The following modifications were performed: 1. Adding a format field to the GPU object attribute, allowing the translation attribute to use the correct runtime function to load the module. Likewise, a dictionary attribute was added to add any possible extra options. 2. Adding the `createObject` method to `GPUTargetAttrInterface`; this method returns a GPU object from a binary string. 3. Adding the function `mgpuModuleLoadJIT`, which is only available for NVIDIA GPUs, as there is no equivalent for AMD. 4. Adding the CMake flag `MLIR_GPU_COMPILATION_TEST_FORMAT` to specify the format to use during testing.
Diffstat (limited to 'llvm/lib/CodeGen/TargetLoweringObjectFileImpl.cpp')
0 files changed, 0 insertions, 0 deletions