Skip to content

[NFC][OpenMP][MLIR] Add test for lowering parallel workshare GPU loop #76144

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 22, 2023
Merged

[NFC][OpenMP][MLIR] Add test for lowering parallel workshare GPU loop #76144

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 36 additions & 0 deletions mlir/test/Target/LLVMIR/omptarget-parallel-wsloop.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s

// The aim of the test is to check the GPU LLVM IR codegen
// for nested omp do loop inside omp target region

module attributes {dlti.dl_spec = #dlti.dl_spec<#dlti.dl_entry<"dlti.alloca_memory_space", 5 : ui32>>, llvm.data_layout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-p7:160:256:256:32-p8:128:128-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-G1-ni:7:8", llvm.target_triple = "amdgcn-amd-amdhsa", omp.is_gpu = true, omp.is_target_device = true } {
llvm.func @target_parallel_wsloop(%arg0: !llvm.ptr ){
omp.parallel {
%loop_ub = llvm.mlir.constant(9 : i32) : i32
%loop_lb = llvm.mlir.constant(0 : i32) : i32
%loop_step = llvm.mlir.constant(1 : i32) : i32
omp.wsloop for (%loop_cnt) : i32 = (%loop_lb) to (%loop_ub) inclusive step (%loop_step) {
%gep = llvm.getelementptr %arg0[0, %loop_cnt] : (!llvm.ptr, i32) -> !llvm.ptr, !llvm.array<10 x i32>
llvm.store %loop_cnt, %gep : i32, !llvm.ptr
omp.yield
}
omp.terminator
}

llvm.return
}

}
// CHECK: call void @__kmpc_parallel_51(ptr addrspacecast
// CHECK-SAME: (ptr addrspace(1) @[[GLOB:[0-9]+]] to ptr),
// CHECK-SAME: i32 %[[THREAD_NUM:.*]], i32 1, i32 -1, i32 -1,
// CHECK-SAME: ptr @[[PARALLEL_FUNC:.*]], ptr null, ptr %[[PARALLEL_ARGS:.*]], i64 1)

// CHECK: define internal void @[[PARALLEL_FUNC]]
// CHECK-SAME: (ptr noalias noundef %[[TID_ADDR:.*]], ptr noalias noundef %[[ZERO_ADDR:.*]],
// CHECK-SAME: ptr %[[ARG_PTR:.*]])
// CHECK: call void @__kmpc_for_static_loop_4u(ptr addrspacecast (ptr addrspace(1) @[[GLOB]] to ptr),
// CHECK-SAME: ptr @[[LOOP_BODY_FUNC:.*]], ptr %[[LOO_BODY_FUNC_ARG:.*]], i32 10,
// CHECK-SAME: i32 %[[THREAD_NUM:.*]], i32 0)

// CHECK: define internal void @[[LOOP_BODY_FUNC]](i32 %[[CNT:.*]], ptr %[[LOOP_BODY_ARG_PTR:.*]]) {