b68fe8699f
This includes a couple of changes to pass behavior for OpenCL kernels. Vulkan shaders are not impacted by the changes. 1. SPIR-V module is placed inside GPU module. This change is required for gpu-module-to-binary to work correctly as it expects kernel function to be inside the GPU module. 2. A dummy func.func with same kernel name as gpu.func is created. GPU compilation pipeline defers lowering of gpu launch kernel op. Since spirv.func is not directly tied to gpu launch kernel, a dummy func.func is required to avoid legalization issues. 3. Use correct mapping when mapping MemRef memory space to SPIR-V storage class for OpenCL kernels.
68 lines
2.9 KiB
MLIR
68 lines
2.9 KiB
MLIR
// RUN: mlir-opt -allow-unregistered-dialect -convert-gpu-to-spirv="use-64bit-index=true" -verify-diagnostics -split-input-file %s -o - | FileCheck %s
|
|
|
|
module attributes {
|
|
gpu.container_module,
|
|
spirv.target_env = #spirv.target_env<#spirv.vce<v1.0, [Kernel, Addresses], []>, #spirv.resource_limits<>>
|
|
} {
|
|
gpu.module @kernels {
|
|
// CHECK-LABEL: spirv.module @{{.*}} Physical64 OpenCL
|
|
// CHECK: spirv.func
|
|
// CHECK-SAME: {{%.*}}: f32
|
|
// CHECK-NOT: spirv.interface_var_abi
|
|
// CHECK-SAME: {{%.*}}: !spirv.ptr<!spirv.array<12 x f32>, CrossWorkgroup>
|
|
// CHECK-NOT: spirv.interface_var_abi
|
|
// CHECK-SAME: spirv.entry_point_abi = #spirv.entry_point_abi<workgroup_size = [32, 4, 1]>
|
|
// CHECK-LABEL: func.func @basic_module_structure
|
|
// CHECK-SAME: attributes {gpu.kernel}
|
|
gpu.func @basic_module_structure(%arg0 : f32, %arg1 : memref<12xf32, #spirv.storage_class<CrossWorkgroup>>) kernel
|
|
attributes {spirv.entry_point_abi = #spirv.entry_point_abi<workgroup_size = [32, 4, 1]>} {
|
|
gpu.return
|
|
}
|
|
}
|
|
|
|
func.func @main() {
|
|
%0 = "op"() : () -> (f32)
|
|
%1 = "op"() : () -> (memref<12xf32, #spirv.storage_class<CrossWorkgroup>>)
|
|
%cst = arith.constant 1 : index
|
|
gpu.launch_func @kernels::@basic_module_structure
|
|
blocks in (%cst, %cst, %cst) threads in (%cst, %cst, %cst)
|
|
args(%0 : f32, %1 : memref<12xf32, #spirv.storage_class<CrossWorkgroup>>)
|
|
return
|
|
}
|
|
}
|
|
|
|
// -----
|
|
|
|
module attributes {
|
|
gpu.container_module
|
|
} {
|
|
gpu.module @kernels attributes {
|
|
spirv.target_env = #spirv.target_env<#spirv.vce<v1.0, [Kernel, Addresses], []>, #spirv.resource_limits<>>
|
|
} {
|
|
// CHECK-LABEL: spirv.module @{{.*}} Physical64 OpenCL
|
|
// CHECK-SAME: spirv.target_env = #spirv.target_env<#spirv.vce<v1.0, [Kernel, Addresses], []>, #spirv.resource_limits<>>
|
|
// CHECK: spirv.func
|
|
// CHECK-SAME: {{%.*}}: f32
|
|
// CHECK-NOT: spirv.interface_var_abi
|
|
// CHECK-SAME: {{%.*}}: !spirv.ptr<!spirv.array<12 x f32>, CrossWorkgroup>
|
|
// CHECK-NOT: spirv.interface_var_abi
|
|
// CHECK-SAME: spirv.entry_point_abi = #spirv.entry_point_abi<workgroup_size = [32, 4, 1]>
|
|
// CHECK-LABEL: func.func @basic_module_structure
|
|
// CHECK-SAME: attributes {gpu.kernel}
|
|
gpu.func @basic_module_structure(%arg0 : f32, %arg1 : memref<12xf32, #spirv.storage_class<CrossWorkgroup>>) kernel
|
|
attributes {spirv.entry_point_abi = #spirv.entry_point_abi<workgroup_size = [32, 4, 1]>} {
|
|
gpu.return
|
|
}
|
|
}
|
|
|
|
func.func @main() {
|
|
%0 = "op"() : () -> (f32)
|
|
%1 = "op"() : () -> (memref<12xf32, #spirv.storage_class<CrossWorkgroup>>)
|
|
%cst = arith.constant 1 : index
|
|
gpu.launch_func @kernels::@basic_module_structure
|
|
blocks in (%cst, %cst, %cst) threads in (%cst, %cst, %cst)
|
|
args(%0 : f32, %1 : memref<12xf32, #spirv.storage_class<CrossWorkgroup>>)
|
|
return
|
|
}
|
|
}
|