Skip to content

clang/AMDGPU: Emit grid size builtins with range metadata #113038

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
Nov 5, 2024
Merged

clang/AMDGPU: Emit grid size builtins with range metadata #113038

Show file tree
Hide file tree
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
6 changes: 6 additions & 0 deletions clang/lib/CodeGen/CGBuiltin.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18671,6 +18671,12 @@ Value *EmitAMDGPUGridSize(CodeGenFunction &CGF, unsigned Index) {
auto *GEP = CGF.Builder.CreateGEP(CGF.Int8Ty, DP, Offset);
auto *LD = CGF.Builder.CreateLoad(
Address(GEP, CGF.Int32Ty, CharUnits::fromQuantity(4)));

llvm::MDBuilder MDB(CGF.getLLVMContext());

// Known non-zero.
LD->setMetadata(llvm::LLVMContext::MD_range,
MDB.createRange(APInt(32, 1), APInt::getZero(32)));
LD->setMetadata(llvm::LLVMContext::MD_invariant_load,
llvm::MDNode::get(CGF.getLLVMContext(), {}));
return LD;
Expand Down
3 changes: 2 additions & 1 deletion clang/test/CodeGenOpenCL/builtins-amdgcn.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -639,7 +639,7 @@ void test_get_workgroup_size(int d, global int *out)
// CHECK-LABEL: @test_get_grid_size(
// CHECK: {{.*}}call align 4 dereferenceable(64){{.*}} ptr addrspace(4) @llvm.amdgcn.dispatch.ptr()
// CHECK: getelementptr inbounds i8, ptr addrspace(4) %{{.*}}, i64 %{{.+}}
// CHECK: load i32, ptr addrspace(4) %{{.*}}, align 4, !invariant.load
// CHECK: load i32, ptr addrspace(4) %{{.*}}, align 4, !range [[$GRID_RANGE:![0-9]+]], !invariant.load
void test_get_grid_size(int d, global int *out)
{
switch (d) {
Expand Down Expand Up @@ -896,5 +896,6 @@ void test_set_fpenv(unsigned long env) {
__builtin_amdgcn_set_fpenv(env);
}

// CHECK-DAG: [[$GRID_RANGE]] = !{i32 1, i32 0}
Copy link
Contributor

@shiltian shiltian Oct 19, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the upper bound is smaller than the lower bound?

Copy link
Contributor Author

@arsenm arsenm Oct 19, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, this is how you are supposed to represent the wrapped set where the 0 value isn't allowed but the uint32_max is. See ConstantRange

Copy link
Contributor

@shiltian shiltian Oct 19, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

oh I c. range does allow wrap.

// CHECK-DAG: [[$WS_RANGE]] = !{i16 1, i16 1025}
// CHECK-DAG: attributes #[[$NOUNWIND_READONLY]] = { convergent mustprogress nocallback nofree nounwind willreturn memory(none) }
Loading