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
55 lines
4.4 KiB
MLIR
55 lines
4.4 KiB
MLIR
// RUN: mlir-opt --pass-pipeline="builtin.module(func.func(sharding-propagation))" %s | FileCheck %s
|
|
|
|
shard.grid @grid4x4(shape = 4x4)
|
|
|
|
// CHECK-LABEL: func.func @test_shard_constant() -> tensor<1024x1024xf32> attributes {llvm.emit_c_interface} {
|
|
// CHECK-NEXT: [[vcst:%.*]] = arith.constant dense<0.000000e+00> : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded:%.*]] = shard.shard [[vcst]] to [[vsharding]] : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vcst_0:%.*]] = arith.constant 4.340000e+01 : f32
|
|
// CHECK-NEXT: [[v0:%.*]] = tensor.empty() : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding_1:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded_2:%.*]] = shard.shard [[v0]] to [[vsharding_1]] : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding_3:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded_4:%.*]] = shard.shard [[vsharded]] to [[vsharding_3]] annotate_for_users : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding_5:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded_6:%.*]] = shard.shard [[vsharded_2]] to [[vsharding_5]] annotate_for_users : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[v1:%.*]] = linalg.add ins([[vsharded_4]], [[vcst_0]] : tensor<1024x1024xf32>, f32) outs([[vsharded_6]] : tensor<1024x1024xf32>) -> tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding_7:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded_8:%.*]] = shard.shard [[v1]] to [[vsharding_7]] : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: return [[vsharded_8]] : tensor<1024x1024xf32>
|
|
func.func @test_shard_constant() -> (tensor<1024x1024xf32>) attributes {llvm.emit_c_interface} {
|
|
%cst_1 = arith.constant dense<0.000000e+00> : tensor<1024x1024xf32>
|
|
%sharding_1 = shard.sharding @grid4x4 split_axes = [[0]] : !shard.sharding
|
|
%sharded_1 = shard.shard %cst_1 to %sharding_1 : tensor<1024x1024xf32>
|
|
%ci = arith.constant 43.4e+00 : f32
|
|
%o1 = tensor.empty() : tensor<1024x1024xf32>
|
|
%res = linalg.add ins(%sharded_1, %ci : tensor<1024x1024xf32>, f32) outs(%o1 : tensor<1024x1024xf32>) -> tensor<1024x1024xf32>
|
|
return %res : tensor<1024x1024xf32>
|
|
}
|
|
|
|
// CHECK-LABEL: func.func @test_shard_constant_back() -> tensor<1024x1024xf32> attributes {llvm.emit_c_interface} {
|
|
// CHECK-NEXT: [[vcst:%.*]] = arith.constant dense<0.000000e+00> : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded:%.*]] = shard.shard [[vcst]] to [[vsharding]] : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vcst_0:%.*]] = arith.constant 4.340000e+01 : f32
|
|
// CHECK-NEXT: [[v0:%.*]] = tensor.empty() : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding_1:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded_2:%.*]] = shard.shard [[v0]] to [[vsharding_1]] : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding_3:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded_4:%.*]] = shard.shard [[vsharded]] to [[vsharding_3]] annotate_for_users : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding_5:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded_6:%.*]] = shard.shard [[vsharded_2]] to [[vsharding_5]] annotate_for_users : tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[v1:%.*]] = linalg.add ins([[vsharded_4]], [[vcst_0]] : tensor<1024x1024xf32>, f32) outs([[vsharded_6]] : tensor<1024x1024xf32>) -> tensor<1024x1024xf32>
|
|
// CHECK-NEXT: [[vsharding_7:%.*]] = shard.sharding @grid4x4 split_axes = {{\[\[}}0]] : !shard.sharding
|
|
// CHECK-NEXT: [[vsharded_8:%.*]] = shard.shard [[v1]] to [[vsharding_7]] : tensor<1024x1024xf32>
|
|
func.func @test_shard_constant_back() -> (tensor<1024x1024xf32>) attributes {llvm.emit_c_interface} {
|
|
%cst_1 = arith.constant dense<0.000000e+00> : tensor<1024x1024xf32>
|
|
%ci = arith.constant 43.4e+00 : f32
|
|
%o1 = tensor.empty() : tensor<1024x1024xf32>
|
|
%res = linalg.add ins(%cst_1, %ci : tensor<1024x1024xf32>, f32) outs(%o1 : tensor<1024x1024xf32>) -> tensor<1024x1024xf32>
|
|
%sharding_1 = shard.sharding @grid4x4 split_axes = [[0]] : !shard.sharding
|
|
%sharded_1 = shard.shard %res to %sharding_1 : tensor<1024x1024xf32>
|
|
return %sharded_1 : tensor<1024x1024xf32>
|
|
}
|