[llvm-branch-commits] [clang] clang/AMDGPU: Emit grid size builtins with range metadata (PR #113038)

[Matt Arsenault via llvm-branch-commits]

https://github.com/arsenm updated https://github.com/llvm/llvm-project/pull/113038

>From 6981d5ad80130130d373b8c879a88b7d727b0115 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Sat, 19 Oct 2024 02:39:06 +0400
Subject: [PATCH] clang/AMDGPU: Emit grid size builtins with range metadata

These cannot be 0.
---
 clang/lib/CodeGen/CGBuiltin.cpp             | 6 ++++++
 clang/test/CodeGenOpenCL/builtins-amdgcn.cl | 3 ++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 34fedd67114751..3e627667cf4da0 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -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;
diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
index 9132cc8a717e0f..3bc6107b7fd40d 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
@@ -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) {
@@ -896,5 +896,6 @@ void test_set_fpenv(unsigned long env) {
   __builtin_amdgcn_set_fpenv(env);
 }
 
+// CHECK-DAG: [[$GRID_RANGE]] = !{i32 1, i32 0}
 // CHECK-DAG: [[$WS_RANGE]] = !{i16 1, i16 1025}
 // CHECK-DAG: attributes #[[$NOUNWIND_READONLY]] = { convergent mustprogress nocallback nofree nounwind willreturn memory(none) }