[all-commits] [llvm/llvm-project] 2c48e3: [MLIR] Adding gpu.host_register op and lower it to...

[Christian Sigg via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 2c48e3629cfb25ac1034117fa8945fd0d342f2ae
      https://github.com/llvm/llvm-project/commit/2c48e3629cfb25ac1034117fa8945fd0d342f2ae
  Author: Christian Sigg <csigg at google.com>
  Date:   2020-08-10 (Mon, 10 Aug 2020)

  Changed paths:
    M mlir/include/mlir/Conversion/StandardToLLVM/ConvertStandardToLLVM.h
    M mlir/include/mlir/Dialect/GPU/GPUOps.td
    M mlir/lib/Conversion/GPUCommon/ConvertLaunchFuncToRuntimeCalls.cpp
    M mlir/lib/Conversion/StandardToLLVM/StandardToLLVM.cpp
    M mlir/test/mlir-cuda-runner/all-reduce-and.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-max.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-min.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-op.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-or.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-region.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-xor.mlir
    M mlir/test/mlir-cuda-runner/gpu-to-cubin.mlir
    M mlir/test/mlir-cuda-runner/multiple-all-reduce.mlir
    M mlir/test/mlir-cuda-runner/shuffle.mlir
    M mlir/test/mlir-cuda-runner/two-modules.mlir
    M mlir/test/mlir-rocm-runner/gpu-to-hsaco.mlir
    M mlir/test/mlir-rocm-runner/two-modules.mlir
    M mlir/test/mlir-rocm-runner/vecadd.mlir
    M mlir/test/mlir-rocm-runner/vector-transferops.mlir
    M mlir/tools/mlir-cuda-runner/cuda-runtime-wrappers.cpp
    M mlir/tools/mlir-rocm-runner/rocm-runtime-wrappers.cpp

  Log Message:
  -----------
  [MLIR] Adding gpu.host_register op and lower it to a runtime call.

Reviewed By: herhut

Differential Revision: https://reviews.llvm.org/D85631