derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
79 lines
4.8 KiB
MLIR
79 lines
4.8 KiB
MLIR
// RUN: mlir-opt %s -convert-gpu-to-rocdl='runtime=HIP' -split-input-file | FileCheck %s
|
|
|
|
// CHECK-LABEL: gpu.module @test_module
|
|
gpu.module @test_module {
|
|
// CHECK-DAG: llvm.mlir.global internal constant @[[$PRINT_GLOBAL0:[A-Za-z0-9_]+]]("Hello, world\0A\00")
|
|
// CHECK-DAG: llvm.mlir.global internal constant @[[$PRINT_GLOBAL1:[A-Za-z0-9_]+]]("Hello: %d\0A\00")
|
|
// CHECK-DAG: llvm.func @__ockl_printf_append_args(i64, i32, i64, i64, i64, i64, i64, i64, i64, i32) -> i64
|
|
// CHECK-DAG: llvm.func @__ockl_printf_append_string_n(i64, !llvm.ptr, i64, i32) -> i64
|
|
// CHECK-DAG: llvm.func @__ockl_printf_begin(i64) -> i64
|
|
|
|
// CHECK-LABEL: func @test_const_printf
|
|
gpu.func @test_const_printf() {
|
|
// CHECK: %[[CST0:.*]] = llvm.mlir.constant(0 : i64) : i64
|
|
// CHECK-NEXT: %[[DESC0:.*]] = llvm.call @__ockl_printf_begin(%0) : (i64) -> i64
|
|
// CHECK-NEXT: %[[FORMATSTR:.*]] = llvm.mlir.addressof @[[$PRINT_GLOBAL0]] : !llvm.ptr
|
|
// CHECK-NEXT: %[[FORMATSTART:.*]] = llvm.getelementptr %[[FORMATSTR]][0, 0] : (!llvm.ptr) -> !llvm.ptr, !llvm.array<14 x i8>
|
|
// CHECK-NEXT: %[[FORMATLEN:.*]] = llvm.mlir.constant(14 : i64) : i64
|
|
// CHECK-NEXT: %[[ISLAST:.*]] = llvm.mlir.constant(1 : i32) : i32
|
|
// CHECK-NEXT: %[[ISNTLAST:.*]] = llvm.mlir.constant(0 : i32) : i32
|
|
// CHECK-NEXT: %{{.*}} = llvm.call @__ockl_printf_append_string_n(%[[DESC0]], %[[FORMATSTART]], %[[FORMATLEN]], %[[ISLAST]]) : (i64, !llvm.ptr, i64, i32) -> i64
|
|
gpu.printf "Hello, world\n"
|
|
gpu.return
|
|
}
|
|
|
|
|
|
// CHECK-LABEL: func @test_printf
|
|
// CHECK: (%[[ARG0:.*]]: i32)
|
|
gpu.func @test_printf(%arg0: i32) {
|
|
// CHECK: %[[CST0:.*]] = llvm.mlir.constant(0 : i64) : i64
|
|
// CHECK-NEXT: %[[DESC0:.*]] = llvm.call @__ockl_printf_begin(%0) : (i64) -> i64
|
|
// CHECK-NEXT: %[[FORMATSTR:.*]] = llvm.mlir.addressof @[[$PRINT_GLOBAL1]] : !llvm.ptr
|
|
// CHECK-NEXT: %[[FORMATSTART:.*]] = llvm.getelementptr %[[FORMATSTR]][0, 0] : (!llvm.ptr) -> !llvm.ptr, !llvm.array<11 x i8>
|
|
// CHECK-NEXT: %[[FORMATLEN:.*]] = llvm.mlir.constant(11 : i64) : i64
|
|
// CHECK-NEXT: %[[ISLAST:.*]] = llvm.mlir.constant(1 : i32) : i32
|
|
// CHECK-NEXT: %[[ISNTLAST:.*]] = llvm.mlir.constant(0 : i32) : i32
|
|
// CHECK-NEXT: %[[DESC1:.*]] = llvm.call @__ockl_printf_append_string_n(%[[DESC0]], %[[FORMATSTART]], %[[FORMATLEN]], %[[ISNTLAST]]) : (i64, !llvm.ptr, i64, i32) -> i64
|
|
// CHECK-NEXT: %[[NARGS1:.*]] = llvm.mlir.constant(1 : i32) : i32
|
|
// CHECK-NEXT: %[[ARG0_64:.*]] = llvm.zext %[[ARG0]] : i32 to i64
|
|
// CHECK-NEXT: %{{.*}} = llvm.call @__ockl_printf_append_args(%[[DESC1]], %[[NARGS1]], %[[ARG0_64]], %[[CST0]], %[[CST0]], %[[CST0]], %[[CST0]], %[[CST0]], %[[CST0]], %[[ISLAST]]) : (i64, i32, i64, i64, i64, i64, i64, i64, i64, i32) -> i64
|
|
gpu.printf "Hello: %d\n", %arg0 : i32
|
|
gpu.return
|
|
}
|
|
}
|
|
|
|
// -----
|
|
|
|
// The bulitin.module we're targetting is wrapped in a fake gpu.module
|
|
// because the convert-gpu-to-rocdl pass only runs an `gpu.module` ops,
|
|
// even though the printf patterns could run in other contexts.
|
|
|
|
// CHECK-LABEL: gpu.module @fake_gpu_module_for_test
|
|
// CHECK-LABEL: builtin.module @test_module
|
|
gpu.module @fake_gpu_module_for_test {
|
|
builtin.module @test_module {
|
|
// CHECK-DAG: llvm.mlir.global internal constant @[[$PRINT_GLOBAL1:[A-Za-z0-9_]+]]("Hello: %d\0A\00")
|
|
// CHECK-DAG: llvm.func @__ockl_printf_append_args(i64, i32, i64, i64, i64, i64, i64, i64, i64, i32) -> i64
|
|
// CHECK-DAG: llvm.func @__ockl_printf_append_string_n(i64, !llvm.ptr, i64, i32) -> i64
|
|
// CHECK-DAG: llvm.func @__ockl_printf_begin(i64) -> i64
|
|
|
|
// CHECK-LABEL: llvm.func @test_printf
|
|
// CHECK: (%[[ARG0:.*]]: i32)
|
|
llvm.func @test_printf(%arg0: i32) {
|
|
// CHECK: %[[CST0:.*]] = llvm.mlir.constant(0 : i64) : i64
|
|
// CHECK-NEXT: %[[DESC0:.*]] = llvm.call @__ockl_printf_begin(%0) : (i64) -> i64
|
|
// CHECK-NEXT: %[[FORMATSTR:.*]] = llvm.mlir.addressof @[[$PRINT_GLOBAL1]] : !llvm.ptr
|
|
// CHECK-NEXT: %[[FORMATSTART:.*]] = llvm.getelementptr %[[FORMATSTR]][0, 0] : (!llvm.ptr) -> !llvm.ptr, !llvm.array<11 x i8>
|
|
// CHECK-NEXT: %[[FORMATLEN:.*]] = llvm.mlir.constant(11 : i64) : i64
|
|
// CHECK-NEXT: %[[ISLAST:.*]] = llvm.mlir.constant(1 : i32) : i32
|
|
// CHECK-NEXT: %[[ISNTLAST:.*]] = llvm.mlir.constant(0 : i32) : i32
|
|
// CHECK-NEXT: %[[DESC1:.*]] = llvm.call @__ockl_printf_append_string_n(%[[DESC0]], %[[FORMATSTART]], %[[FORMATLEN]], %[[ISNTLAST]]) : (i64, !llvm.ptr, i64, i32) -> i64
|
|
// CHECK-NEXT: %[[NARGS1:.*]] = llvm.mlir.constant(1 : i32) : i32
|
|
// CHECK-NEXT: %[[ARG0_64:.*]] = llvm.zext %[[ARG0]] : i32 to i64
|
|
// CHECK-NEXT: %{{.*}} = llvm.call @__ockl_printf_append_args(%[[DESC1]], %[[NARGS1]], %[[ARG0_64]], %[[CST0]], %[[CST0]], %[[CST0]], %[[CST0]], %[[CST0]], %[[CST0]], %[[ISLAST]]) : (i64, i32, i64, i64, i64, i64, i64, i64, i64, i32) -> i64
|
|
gpu.printf "Hello: %d\n", %arg0 : i32
|
|
llvm.return
|
|
}
|
|
}
|
|
}
|