5caae72d1a
The `test-lower-to-nvvm` pipeline serves as the common and proper pipeline for nvvm+host compilation, and it's used across our CUDA integration tests. This PR updates the `test-lower-to-nvvm` pipeline to `gpu-lower-to-nvvm` and moves it within `InitAllPasses.h`. The aim is to call it from Python, also having a standardize compilation process for nvvm.
31 lines
952 B
MLIR
31 lines
952 B
MLIR
// RUN: mlir-opt %s \
|
|
// RUN: | mlir-opt -gpu-lower-to-nvvm="cubin-format=%gpu_compilation_format" \
|
|
// RUN: | mlir-cpu-runner \
|
|
// RUN: --shared-libs=%mlir_cuda_runtime \
|
|
// RUN: --shared-libs=%mlir_runner_utils \
|
|
// RUN: --entry-point-result=void \
|
|
// RUN: | FileCheck %s
|
|
|
|
// CHECK: Hello from 0, 2, 3.000000
|
|
// CHECK: Hello from 1, 2, 3.000000
|
|
module attributes {gpu.container_module} {
|
|
gpu.module @kernels {
|
|
gpu.func @hello() kernel {
|
|
%0 = gpu.thread_id x
|
|
%csti8 = arith.constant 2 : i8
|
|
%cstf32 = arith.constant 3.0 : f32
|
|
gpu.printf "Hello from %lld, %d, %f\n" %0, %csti8, %cstf32 : index, i8, f32
|
|
gpu.return
|
|
}
|
|
}
|
|
|
|
func.func @main() {
|
|
%c2 = arith.constant 2 : index
|
|
%c1 = arith.constant 1 : index
|
|
gpu.launch_func @kernels::@hello
|
|
blocks in (%c1, %c1, %c1)
|
|
threads in (%c2, %c1, %c1)
|
|
return
|
|
}
|
|
}
|