7efdc117b1
When converting to nvvm lowering gpu.printf to vprintf allows us to support printing when running on cuda. Differential Revision: https://reviews.llvm.org/D141049
32 lines
1.0 KiB
MLIR
32 lines
1.0 KiB
MLIR
// RUN: mlir-opt %s \
|
|
// RUN: | mlir-opt -pass-pipeline='builtin.module(gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin))' \
|
|
// RUN: | mlir-opt -gpu-to-llvm \
|
|
// RUN: | mlir-cpu-runner \
|
|
// RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
|
|
// RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
|
|
// 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
|
|
}
|
|
}
|