AMDGPU: Use more accurate IR type for block handle

[arsenm]

Summary

The device library uses this as a struct with a pointer sized integer
and 2 ints.

[arsenm]

47554a0c73ee703362d913d3a149f104819c8365

llvm/lib/Target/AMDGPU/AMDGPUOpenCLEnqueuedBlockLowering.cpp

 
 ModulePass* llvm::createAMDGPUOpenCLEnqueuedBlockLoweringPass() {
   return new AMDGPUOpenCLEnqueuedBlockLowering();
 }
 
 bool AMDGPUOpenCLEnqueuedBlockLowering::runOnModule(Module &M) {
   auto &C = M.getContext();
   bool Changed = false;
+
+  // ptr kernel_object, i32 private_segment_size, i32 group_segment_size
+  StructType *HandleTy = nullptr;
+
   for (auto &F : M.functions()) {
     if (F.hasFnAttribute("enqueued-block")) {
       if (!F.hasName()) {
         SmallString<64> Name;
         Mangler::getNameWithPrefix(Name, "__amdgpu_enqueued_kernel",
                                    M.getDataLayout());
         F.setName(Name);
       }
       LLVM_DEBUG(dbgs() << "found enqueued kernel: " << F.getName() << '\n');
       auto RuntimeHandle = (F.getName() + ".runtime_handle").str();
-      auto T = ArrayType::get(Type::getInt64Ty(C), 2);
+      if (!HandleTy) {
+        Type *Int32 = Type::getInt32Ty(C);
+        HandleTy = StructType::create(
+            C, {Type::getInt8Ty(C)->getPointerTo(0), Int32, Int32},
+            "block.runtime.handle.t");
+      }
+
       auto *GV = new GlobalVariable(
-          M, T,
+          M, HandleTy,
           /*isConstant=*/false, GlobalValue::ExternalLinkage,
-          /*Initializer=*/Constant::getNullValue(T), RuntimeHandle,
+          /*Initializer=*/Constant::getNullValue(HandleTy), RuntimeHandle,
           /*InsertBefore=*/nullptr, GlobalValue::NotThreadLocal,
           AMDGPUAS::GLOBAL_ADDRESS,
           /*isExternallyInitialized=*/false);
       LLVM_DEBUG(dbgs() << "runtime handle created: " << *GV << '\n');
 
       F.replaceAllUsesWith(ConstantExpr::getAddrSpaceCast(GV, F.getType()));
       F.addFnAttr("runtime-handle", RuntimeHandle);
       F.setLinkage(GlobalValue::ExternalLinkage);
       Changed = true;
     }
   }
 
   return Changed;
 }

llvm/test/CodeGen/AMDGPU/enqueue-kernel.ll

 
 define internal amdgpu_kernel void @1(<{ i32, i32, ptr addrspace(1), i8 }> %arg) #0 {
   ret void
 }
 
 attributes #0 = { "enqueued-block" }
 ;.
 ; CHECK: @[[KERNEL_ADDRESS_USER:[a-zA-Z0-9_$"\\.-]+]] = global [1 x ptr] [ptr addrspacecast (ptr addrspace(1) @block_has_used_kernel_address.runtime_handle to ptr)]
-; CHECK: @[[__TEST_BLOCK_INVOKE_KERNEL_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [2 x i64] zeroinitializer
-; CHECK: @[[__TEST_BLOCK_INVOKE_2_KERNEL_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [2 x i64] zeroinitializer
-; CHECK: @[[BLOCK_HAS_USED_KERNEL_ADDRESS_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [2 x i64] zeroinitializer
-; CHECK: @[[__AMDGPU_ENQUEUED_KERNEL_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [2 x i64] zeroinitializer
-; CHECK: @[[__AMDGPU_ENQUEUED_KERNEL_1_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [2 x i64] zeroinitializer
+; CHECK: @[[__TEST_BLOCK_INVOKE_KERNEL_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
+; CHECK: @[[__TEST_BLOCK_INVOKE_2_KERNEL_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
+; CHECK: @[[BLOCK_HAS_USED_KERNEL_ADDRESS_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
+; CHECK: @[[__AMDGPU_ENQUEUED_KERNEL_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
+; CHECK: @[[__AMDGPU_ENQUEUED_KERNEL_1_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) global [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
 ;.
 ; CHECK-LABEL: define {{[^@]+}}@non_caller
 ; CHECK-SAME: (ptr addrspace(1) [[A:%.*]], i8 [[B:%.*]], ptr addrspace(1) [[C:%.*]], i64 [[D:%.*]]) {
 ; CHECK-NEXT:    ret void
 ;
 ;
 ; CHECK-LABEL: define {{[^@]+}}@caller_indirect
 ; CHECK-SAME: (ptr addrspace(1) [[A:%.*]], i8 [[B:%.*]], ptr addrspace(1) [[C:%.*]], i64 [[D:%.*]]) {