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
81 lines
2.5 KiB
MLIR
81 lines
2.5 KiB
MLIR
// RUN: mlir-opt %s -pass-pipeline='builtin.module(func.func(scf-forall-to-parallel))' -split-input-file | FileCheck %s
|
|
|
|
func.func private @callee(%i: index, %j: index)
|
|
|
|
// CHECK-LABEL: @two_iters
|
|
// CHECK-SAME: %[[UB1:.+]]: index, %[[UB2:.+]]: index
|
|
func.func @two_iters(%ub1: index, %ub2: index) {
|
|
scf.forall (%i, %j) in (%ub1, %ub2) {
|
|
func.call @callee(%i, %j) : (index, index) -> ()
|
|
}
|
|
|
|
// CHECK: scf.parallel (%[[IV1:.+]], %[[IV2:.+]]) = (%{{.*}}, %{{.*}}) to (%[[UB1]], %[[UB2]])
|
|
// CHECK: func.call @callee(%[[IV1]], %[[IV2]]) : (index, index) -> ()
|
|
// CHECK: scf.reduce
|
|
return
|
|
}
|
|
|
|
// -----
|
|
|
|
func.func private @callee(%i: index, %j: index)
|
|
|
|
// CHECK-LABEL: @repeated
|
|
// CHECK-SAME: %[[UB1:.+]]: index, %[[UB2:.+]]: index
|
|
func.func @repeated(%ub1: index, %ub2: index) {
|
|
scf.forall (%i, %j) in (%ub1, %ub2) {
|
|
func.call @callee(%i, %j) : (index, index) -> ()
|
|
}
|
|
|
|
// CHECK: scf.parallel (%[[IV1:.+]], %[[IV2:.+]]) = (%{{.*}}, %{{.*}}) to (%[[UB1]], %[[UB2]])
|
|
// CHECK: func.call @callee(%[[IV1]], %[[IV2]]) : (index, index) -> ()
|
|
// CHECK: scf.reduce
|
|
scf.forall (%i, %j) in (%ub1, %ub2) {
|
|
func.call @callee(%i, %j) : (index, index) -> ()
|
|
}
|
|
|
|
// CHECK: scf.parallel (%[[IV3:.+]], %[[IV4:.+]]) = (%{{.*}}, %{{.*}}) to (%[[UB1]], %[[UB2]])
|
|
// CHECK: func.call @callee(%[[IV3]], %[[IV4]])
|
|
// CHECK: scf.reduce
|
|
return
|
|
}
|
|
|
|
// -----
|
|
|
|
func.func private @callee(%i: index, %j: index, %k: index, %l: index)
|
|
|
|
// CHECK-LABEL: @nested
|
|
// CHECK-SAME: %[[UB1:.+]]: index, %[[UB2:.+]]: index, %[[UB3:.+]]: index, %[[UB4:.+]]: index
|
|
func.func @nested(%ub1: index, %ub2: index, %ub3: index, %ub4: index) {
|
|
// CHECK: scf.parallel (%[[IV1:.+]], %[[IV2:.+]]) = (%{{.*}}, %{{.*}}) to (%[[UB1]], %[[UB2]]) step (%{{.*}}, %{{.*}}) {
|
|
// CHECK: scf.parallel (%[[IV3:.+]], %[[IV4:.+]]) = (%{{.*}}, %{{.*}}) to (%[[UB3]], %[[UB4]]) step (%{{.*}}, %{{.*}}) {
|
|
// CHECK: func.call @callee(%[[IV1]], %[[IV2]], %[[IV3]], %[[IV4]])
|
|
// CHECK: scf.reduce
|
|
// CHECK: }
|
|
// CHECK: scf.reduce
|
|
// CHECK: }
|
|
scf.forall (%i, %j) in (%ub1, %ub2) {
|
|
scf.forall (%k, %l) in (%ub3, %ub4) {
|
|
func.call @callee(%i, %j, %k, %l) : (index, index, index, index) -> ()
|
|
}
|
|
}
|
|
return
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: @mapping_attr
|
|
func.func @mapping_attr() -> () {
|
|
// CHECK: scf.parallel
|
|
// CHECK: scf.reduce
|
|
// CHECK: {mapping = [#gpu.thread<x>]}
|
|
|
|
%num_threads = arith.constant 100 : index
|
|
|
|
scf.forall (%thread_idx) in (%num_threads) {
|
|
scf.forall.in_parallel {
|
|
}
|
|
} {mapping = [#gpu.thread<x>]}
|
|
return
|
|
|
|
}
|