// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --check-attributes --check-globals all --include-generated-funcs --prefix-filecheck-ir-name VAR --version 5
// RUN: %clang_cc1 -cl-std=CL2.0 -O0 -disable-llvm-passes -fno-ident -emit-llvm -o - -triple amdgcn-amd-amdhsa %s -fdenormal-fp-math-f32=preserve-sign | FileCheck %s --check-prefixes=CHECK,NOCPU

// // Check no-optnone and target-cpu behavior
// RUN: %clang_cc1 -cl-std=CL2.0 -O1 -disable-llvm-passes -fno-ident -emit-llvm -o - -triple amdgcn-amd-amdhsa -target-cpu gfx900 -target-feature -sram-ecc -fdenormal-fp-math-f32=preserve-sign %s | FileCheck %s --check-prefixes=CHECK,GFX900


typedef struct {int a;} ndrange_t;

void callee(long id, global long *out) {
  out[id] = id;
}

kernel void test(global char *a, char b, global long *c, long d) {
  queue_t default_queue;
  unsigned flags = 0;
  ndrange_t ndrange;

  enqueue_kernel(default_queue, flags, ndrange,
                 ^(void) {
                 a[0] = b;
                 });

  enqueue_kernel(default_queue, flags, ndrange,
                 ^(void) {
                 a[0] = b;
                 c[0] = d;
                 });
  enqueue_kernel(default_queue, flags, ndrange,
                 ^(local void *lp) {
                 a[0] = b;
                 c[0] = d;
                 ((local int*)lp)[0] = 1;
                 }, 100);

  void (^block)(void) = ^{
    callee(d, c);
  };

  enqueue_kernel(default_queue, flags, ndrange, block);
}

// The target attribute from the caller is not propagated to the block.

// FIXME: Something is broken and inconsistent. Either the builtin use in the
// block should be rejected, or the target attribute needs to apply to the block
// as well.
// https://github.com/llvm/llvm-project/issues/60005
__attribute__((target("s-memtime-inst")))
kernel void test_target_features_kernel(global int *i) {
  queue_t default_queue;
  unsigned flags = 0;
  ndrange_t ndrange;

  __builtin_amdgcn_s_memtime();

  enqueue_kernel(default_queue, flags, ndrange,
                 ^(void) {
                   __builtin_amdgcn_s_memtime();
                 });
}

//.
// CHECK: @__test_block_invoke_kernel.runtime.handle = internal addrspace(1) externally_initialized constant %block.runtime.handle.t zeroinitializer, section ".amdgpu.kernel.runtime.handle"
// CHECK: @__test_block_invoke_2_kernel.runtime.handle = internal addrspace(1) externally_initialized constant %block.runtime.handle.t.0 zeroinitializer, section ".amdgpu.kernel.runtime.handle"
// CHECK: @__test_block_invoke_3_kernel.runtime.handle = internal addrspace(1) externally_initialized constant %block.runtime.handle.t.1 zeroinitializer, section ".amdgpu.kernel.runtime.handle"
// CHECK: @__test_block_invoke_4_kernel.runtime.handle = internal addrspace(1) externally_initialized constant %block.runtime.handle.t.2 zeroinitializer, section ".amdgpu.kernel.runtime.handle"
// CHECK: @__block_literal_global = internal addrspace(1) constant { i32, i32, ptr } { i32 16, i32 8, ptr @__test_target_features_kernel_block_invoke }, align 8 #0
// CHECK: @__test_target_features_kernel_block_invoke_kernel.runtime.handle = internal addrspace(1) externally_initialized constant %block.runtime.handle.t.3 zeroinitializer, section ".amdgpu.kernel.runtime.handle"
// CHECK: @llvm.used = appending addrspace(1) global [10 x ptr] [ptr @__test_block_invoke_kernel, ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_kernel.runtime.handle to ptr), ptr @__test_block_invoke_2_kernel, ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_2_kernel.runtime.handle to ptr), ptr @__test_block_invoke_3_kernel, ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_3_kernel.runtime.handle to ptr), ptr @__test_block_invoke_4_kernel, ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_4_kernel.runtime.handle to ptr), ptr @__test_target_features_kernel_block_invoke_kernel, ptr addrspacecast (ptr addrspace(1) @__test_target_features_kernel_block_invoke_kernel.runtime.handle to ptr)], section "llvm.metadata"
//.
// NOCPU: Function Attrs: convergent noinline norecurse nounwind optnone
// NOCPU-LABEL: define dso_local void @callee(
// NOCPU-SAME: i64 noundef [[ID:%.*]], ptr addrspace(1) noundef [[OUT:%.*]]) #[[ATTR1:[0-9]+]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[ID_ADDR:%.*]] = alloca i64, align 8, addrspace(5)
// NOCPU-NEXT:    [[OUT_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// NOCPU-NEXT:    [[ID_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[ID_ADDR]] to ptr
// NOCPU-NEXT:    [[OUT_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[OUT_ADDR]] to ptr
// NOCPU-NEXT:    store i64 [[ID]], ptr [[ID_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr addrspace(1) [[OUT]], ptr [[OUT_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP0:%.*]] = load i64, ptr [[ID_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[OUT_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP2:%.*]] = load i64, ptr [[ID_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr addrspace(1) [[TMP1]], i64 [[TMP2]]
// NOCPU-NEXT:    store i64 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 8
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent noinline norecurse nounwind optnone
// NOCPU-LABEL: define dso_local amdgpu_kernel void @test(
// NOCPU-SAME: ptr addrspace(1) noundef align 1 [[A:%.*]], i8 noundef [[B:%.*]], ptr addrspace(1) noundef align 8 [[C:%.*]], i64 noundef [[D:%.*]]) #[[ATTR2:[0-9]+]] !kernel_arg_addr_space [[META3:![0-9]+]] !kernel_arg_access_qual [[META4:![0-9]+]] !kernel_arg_type [[META5:![0-9]+]] !kernel_arg_base_type [[META5]] !kernel_arg_type_qual [[META6:![0-9]+]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// NOCPU-NEXT:    [[B_ADDR:%.*]] = alloca i8, align 1, addrspace(5)
// NOCPU-NEXT:    [[C_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// NOCPU-NEXT:    [[D_ADDR:%.*]] = alloca i64, align 8, addrspace(5)
// NOCPU-NEXT:    [[A_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[A_ADDR]] to ptr
// NOCPU-NEXT:    [[B_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[B_ADDR]] to ptr
// NOCPU-NEXT:    [[C_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[C_ADDR]] to ptr
// NOCPU-NEXT:    [[D_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[D_ADDR]] to ptr
// NOCPU-NEXT:    store ptr addrspace(1) [[A]], ptr [[A_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store i8 [[B]], ptr [[B_ADDR_ASCAST]], align 1
// NOCPU-NEXT:    store ptr addrspace(1) [[C]], ptr [[C_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store i64 [[D]], ptr [[D_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr [[A_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP1:%.*]] = load i8, ptr [[B_ADDR_ASCAST]], align 1
// NOCPU-NEXT:    [[TMP2:%.*]] = load ptr addrspace(1), ptr [[C_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP3:%.*]] = load i64, ptr [[D_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    call void @__clang_ocl_kern_imp_test(ptr addrspace(1) noundef align 1 [[TMP0]], i8 noundef signext [[TMP1]], ptr addrspace(1) noundef align 8 [[TMP2]], i64 noundef [[TMP3]]) #[[ATTR10:[0-9]+]]
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent noinline norecurse nounwind optnone
// NOCPU-LABEL: define dso_local void @__clang_ocl_kern_imp_test(
// NOCPU-SAME: ptr addrspace(1) noundef align 1 [[A:%.*]], i8 noundef signext [[B:%.*]], ptr addrspace(1) noundef align 8 [[C:%.*]], i64 noundef [[D:%.*]]) #[[ATTR3:[0-9]+]] !kernel_arg_addr_space [[META3]] !kernel_arg_access_qual [[META4]] !kernel_arg_type [[META5]] !kernel_arg_base_type [[META5]] !kernel_arg_type_qual [[META6]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// NOCPU-NEXT:    [[B_ADDR:%.*]] = alloca i8, align 1, addrspace(5)
// NOCPU-NEXT:    [[C_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// NOCPU-NEXT:    [[D_ADDR:%.*]] = alloca i64, align 8, addrspace(5)
// NOCPU-NEXT:    [[DEFAULT_QUEUE:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// NOCPU-NEXT:    [[FLAGS:%.*]] = alloca i32, align 4, addrspace(5)
// NOCPU-NEXT:    [[NDRANGE:%.*]] = alloca [[STRUCT_NDRANGE_T:%.*]], align 4, addrspace(5)
// NOCPU-NEXT:    [[TMP:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// NOCPU-NEXT:    [[BLOCK:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), i8 }>, align 8, addrspace(5)
// NOCPU-NEXT:    [[VARTMP2:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// NOCPU-NEXT:    [[BLOCK3:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
// NOCPU-NEXT:    [[VARTMP11:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// NOCPU-NEXT:    [[BLOCK12:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
// NOCPU-NEXT:    [[BLOCK_SIZES:%.*]] = alloca [1 x i64], align 8, addrspace(5)
// NOCPU-NEXT:    [[BLOCK20:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[BLOCK21:%.*]] = alloca <{ i32, i32, ptr, i64, ptr addrspace(1) }>, align 8, addrspace(5)
// NOCPU-NEXT:    [[VARTMP27:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// NOCPU-NEXT:    [[A_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[A_ADDR]] to ptr
// NOCPU-NEXT:    [[B_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[B_ADDR]] to ptr
// NOCPU-NEXT:    [[C_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[C_ADDR]] to ptr
// NOCPU-NEXT:    [[D_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[D_ADDR]] to ptr
// NOCPU-NEXT:    [[DEFAULT_QUEUE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DEFAULT_QUEUE]] to ptr
// NOCPU-NEXT:    [[FLAGS_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[FLAGS]] to ptr
// NOCPU-NEXT:    [[NDRANGE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[NDRANGE]] to ptr
// NOCPU-NEXT:    [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr
// NOCPU-NEXT:    [[BLOCK_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK]] to ptr
// NOCPU-NEXT:    [[TMP2_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VARTMP2]] to ptr
// NOCPU-NEXT:    [[BLOCK3_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK3]] to ptr
// NOCPU-NEXT:    [[TMP11_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VARTMP11]] to ptr
// NOCPU-NEXT:    [[BLOCK12_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK12]] to ptr
// NOCPU-NEXT:    [[BLOCK_SIZES_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK_SIZES]] to ptr
// NOCPU-NEXT:    [[BLOCK20_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK20]] to ptr
// NOCPU-NEXT:    [[BLOCK21_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK21]] to ptr
// NOCPU-NEXT:    [[TMP27_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VARTMP27]] to ptr
// NOCPU-NEXT:    store ptr addrspace(1) [[A]], ptr [[A_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store i8 [[B]], ptr [[B_ADDR_ASCAST]], align 1
// NOCPU-NEXT:    store ptr addrspace(1) [[C]], ptr [[C_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store i64 [[D]], ptr [[D_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store i32 0, ptr [[FLAGS_ASCAST]], align 4
// NOCPU-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP1:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4
// NOCPU-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false)
// NOCPU-NEXT:    [[BLOCK_SIZE:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 0
// NOCPU-NEXT:    store i32 25, ptr [[BLOCK_SIZE]], align 8
// NOCPU-NEXT:    [[BLOCK_ALIGN:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 1
// NOCPU-NEXT:    store i32 8, ptr [[BLOCK_ALIGN]], align 4
// NOCPU-NEXT:    [[BLOCK_INVOKE:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 2
// NOCPU-NEXT:    store ptr @__test_block_invoke, ptr [[BLOCK_INVOKE]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 3
// NOCPU-NEXT:    [[TMP2:%.*]] = load ptr addrspace(1), ptr [[A_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr addrspace(1) [[TMP2]], ptr [[BLOCK_CAPTURED]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 4
// NOCPU-NEXT:    [[TMP3:%.*]] = load i8, ptr [[B_ADDR_ASCAST]], align 1
// NOCPU-NEXT:    store i8 [[TMP3]], ptr [[BLOCK_CAPTURED1]], align 8
// NOCPU-NEXT:    [[TMP4:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP0]], i32 [[TMP1]], ptr addrspace(5) [[TMP]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_kernel.runtime.handle to ptr), ptr [[BLOCK_ASCAST]])
// NOCPU-NEXT:    [[TMP5:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP6:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4
// NOCPU-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP2_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false)
// NOCPU-NEXT:    [[BLOCK_SIZE4:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 0
// NOCPU-NEXT:    store i32 41, ptr [[BLOCK_SIZE4]], align 8
// NOCPU-NEXT:    [[BLOCK_ALIGN5:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 1
// NOCPU-NEXT:    store i32 8, ptr [[BLOCK_ALIGN5]], align 4
// NOCPU-NEXT:    [[BLOCK_INVOKE6:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 2
// NOCPU-NEXT:    store ptr @__test_block_invoke_2, ptr [[BLOCK_INVOKE6]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED7:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 3
// NOCPU-NEXT:    [[TMP7:%.*]] = load ptr addrspace(1), ptr [[A_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr addrspace(1) [[TMP7]], ptr [[BLOCK_CAPTURED7]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED8:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 6
// NOCPU-NEXT:    [[TMP8:%.*]] = load i8, ptr [[B_ADDR_ASCAST]], align 1
// NOCPU-NEXT:    store i8 [[TMP8]], ptr [[BLOCK_CAPTURED8]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED9:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 4
// NOCPU-NEXT:    [[TMP9:%.*]] = load ptr addrspace(1), ptr [[C_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr addrspace(1) [[TMP9]], ptr [[BLOCK_CAPTURED9]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED10:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 5
// NOCPU-NEXT:    [[TMP10:%.*]] = load i64, ptr [[D_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store i64 [[TMP10]], ptr [[BLOCK_CAPTURED10]], align 8
// NOCPU-NEXT:    [[TMP11:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP5]], i32 [[TMP6]], ptr addrspace(5) [[VARTMP2]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_2_kernel.runtime.handle to ptr), ptr [[BLOCK3_ASCAST]])
// NOCPU-NEXT:    [[TMP12:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP13:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4
// NOCPU-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP11_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false)
// NOCPU-NEXT:    [[BLOCK_SIZE13:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 0
// NOCPU-NEXT:    store i32 41, ptr [[BLOCK_SIZE13]], align 8
// NOCPU-NEXT:    [[BLOCK_ALIGN14:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 1
// NOCPU-NEXT:    store i32 8, ptr [[BLOCK_ALIGN14]], align 4
// NOCPU-NEXT:    [[BLOCK_INVOKE15:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 2
// NOCPU-NEXT:    store ptr @__test_block_invoke_3, ptr [[BLOCK_INVOKE15]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED16:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 3
// NOCPU-NEXT:    [[TMP14:%.*]] = load ptr addrspace(1), ptr [[A_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr addrspace(1) [[TMP14]], ptr [[BLOCK_CAPTURED16]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED17:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 6
// NOCPU-NEXT:    [[TMP15:%.*]] = load i8, ptr [[B_ADDR_ASCAST]], align 1
// NOCPU-NEXT:    store i8 [[TMP15]], ptr [[BLOCK_CAPTURED17]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED18:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 4
// NOCPU-NEXT:    [[TMP16:%.*]] = load ptr addrspace(1), ptr [[C_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr addrspace(1) [[TMP16]], ptr [[BLOCK_CAPTURED18]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED19:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 5
// NOCPU-NEXT:    [[TMP17:%.*]] = load i64, ptr [[D_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store i64 [[TMP17]], ptr [[BLOCK_CAPTURED19]], align 8
// NOCPU-NEXT:    [[TMP18:%.*]] = getelementptr [1 x i64], ptr [[BLOCK_SIZES_ASCAST]], i32 0, i32 0
// NOCPU-NEXT:    store i64 100, ptr [[TMP18]], align 8
// NOCPU-NEXT:    [[TMP19:%.*]] = call i32 @__enqueue_kernel_varargs(ptr addrspace(1) [[TMP12]], i32 [[TMP13]], ptr addrspace(5) [[VARTMP11]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_3_kernel.runtime.handle to ptr), ptr [[BLOCK12_ASCAST]], i32 1, ptr [[TMP18]])
// NOCPU-NEXT:    [[BLOCK_SIZE22:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 0
// NOCPU-NEXT:    store i32 32, ptr [[BLOCK_SIZE22]], align 8
// NOCPU-NEXT:    [[BLOCK_ALIGN23:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 1
// NOCPU-NEXT:    store i32 8, ptr [[BLOCK_ALIGN23]], align 4
// NOCPU-NEXT:    [[BLOCK_INVOKE24:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 2
// NOCPU-NEXT:    store ptr @__test_block_invoke_4, ptr [[BLOCK_INVOKE24]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED25:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 3
// NOCPU-NEXT:    [[TMP20:%.*]] = load i64, ptr [[D_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store i64 [[TMP20]], ptr [[BLOCK_CAPTURED25]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURED26:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 4
// NOCPU-NEXT:    [[TMP21:%.*]] = load ptr addrspace(1), ptr [[C_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr addrspace(1) [[TMP21]], ptr [[BLOCK_CAPTURED26]], align 8
// NOCPU-NEXT:    store ptr [[BLOCK21_ASCAST]], ptr [[BLOCK20_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP22:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP23:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4
// NOCPU-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP27_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false)
// NOCPU-NEXT:    [[TMP24:%.*]] = load ptr, ptr [[BLOCK20_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP25:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP22]], i32 [[TMP23]], ptr addrspace(5) [[VARTMP27]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_4_kernel.runtime.handle to ptr), ptr [[BLOCK21_ASCAST]])
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent noinline norecurse nounwind optnone
// NOCPU-LABEL: define dso_local amdgpu_kernel void @test_target_features_kernel(
// NOCPU-SAME: ptr addrspace(1) noundef align 4 [[I:%.*]]) #[[ATTR4:[0-9]+]] !kernel_arg_addr_space [[META7:![0-9]+]] !kernel_arg_access_qual [[META8:![0-9]+]] !kernel_arg_type [[META9:![0-9]+]] !kernel_arg_base_type [[META9]] !kernel_arg_type_qual [[META10:![0-9]+]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[I_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// NOCPU-NEXT:    [[I_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I_ADDR]] to ptr
// NOCPU-NEXT:    store ptr addrspace(1) [[I]], ptr [[I_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr [[I_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    call void @__clang_ocl_kern_imp_test_target_features_kernel(ptr addrspace(1) noundef align 4 [[TMP0]]) #[[ATTR10]]
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent noinline norecurse nounwind optnone
// NOCPU-LABEL: define dso_local void @__clang_ocl_kern_imp_test_target_features_kernel(
// NOCPU-SAME: ptr addrspace(1) noundef align 4 [[I:%.*]]) #[[ATTR5:[0-9]+]] !kernel_arg_addr_space [[META7]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META9]] !kernel_arg_base_type [[META9]] !kernel_arg_type_qual [[META10]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[I_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// NOCPU-NEXT:    [[DEFAULT_QUEUE:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// NOCPU-NEXT:    [[FLAGS:%.*]] = alloca i32, align 4, addrspace(5)
// NOCPU-NEXT:    [[NDRANGE:%.*]] = alloca [[STRUCT_NDRANGE_T:%.*]], align 4, addrspace(5)
// NOCPU-NEXT:    [[TMP:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// NOCPU-NEXT:    [[I_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I_ADDR]] to ptr
// NOCPU-NEXT:    [[DEFAULT_QUEUE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DEFAULT_QUEUE]] to ptr
// NOCPU-NEXT:    [[FLAGS_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[FLAGS]] to ptr
// NOCPU-NEXT:    [[NDRANGE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[NDRANGE]] to ptr
// NOCPU-NEXT:    [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr
// NOCPU-NEXT:    store ptr addrspace(1) [[I]], ptr [[I_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store i32 0, ptr [[FLAGS_ASCAST]], align 4
// NOCPU-NEXT:    [[TMP0:%.*]] = call i64 @llvm.amdgcn.s.memtime()
// NOCPU-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP2:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4
// NOCPU-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false)
// NOCPU-NEXT:    [[TMP3:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP1]], i32 [[TMP2]], ptr addrspace(5) [[TMP]], ptr addrspacecast (ptr addrspace(1) @__test_target_features_kernel_block_invoke_kernel.runtime.handle to ptr), ptr addrspacecast (ptr addrspace(1) @__block_literal_global to ptr))
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent noinline nounwind optnone
// NOCPU-LABEL: define internal void @__test_block_invoke(
// NOCPU-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR7:[0-9]+]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[BLOCK_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// NOCPU-NEXT:    [[BLOCK_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK_ADDR]] to ptr
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[BLOCK_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// NOCPU-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// NOCPU-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8
// NOCPU-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP1]], i64 0
// NOCPU-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent nounwind
// NOCPU-LABEL: define internal amdgpu_kernel void @__test_block_invoke_kernel(
// NOCPU-SAME: <{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0:%.*]]) #[[ATTR8:[0-9]+]] !associated [[META11:![0-9]+]] !kernel_arg_addr_space [[META12:![0-9]+]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META13:![0-9]+]] !kernel_arg_base_type [[META13]] !kernel_arg_type_qual [[META10]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), i8 }>, align 8, addrspace(5)
// NOCPU-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
// NOCPU-NEXT:    [[TMP2:%.*]] = addrspacecast ptr addrspace(5) [[TMP1]] to ptr
// NOCPU-NEXT:    call void @__test_block_invoke(ptr [[TMP2]])
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent noinline nounwind optnone
// NOCPU-LABEL: define internal void @__test_block_invoke_2(
// NOCPU-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR7]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[BLOCK_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// NOCPU-NEXT:    [[BLOCK_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK_ADDR]] to ptr
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[BLOCK_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 6
// NOCPU-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// NOCPU-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8
// NOCPU-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP1]], i64 0
// NOCPU-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR2:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 5
// NOCPU-NEXT:    [[TMP2:%.*]] = load i64, ptr [[BLOCK_CAPTURE_ADDR2]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR3:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// NOCPU-NEXT:    [[TMP3:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR3]], align 8
// NOCPU-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, ptr addrspace(1) [[TMP3]], i64 0
// NOCPU-NEXT:    store i64 [[TMP2]], ptr addrspace(1) [[ARRAYIDX4]], align 8
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent nounwind
// NOCPU-LABEL: define internal amdgpu_kernel void @__test_block_invoke_2_kernel(
// NOCPU-SAME: <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]]) #[[ATTR8]] !associated [[META14:![0-9]+]] !kernel_arg_addr_space [[META12]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META13]] !kernel_arg_base_type [[META13]] !kernel_arg_type_qual [[META10]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
// NOCPU-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
// NOCPU-NEXT:    [[TMP2:%.*]] = addrspacecast ptr addrspace(5) [[TMP1]] to ptr
// NOCPU-NEXT:    call void @__test_block_invoke_2(ptr [[TMP2]])
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent noinline nounwind optnone
// NOCPU-LABEL: define internal void @__test_block_invoke_3(
// NOCPU-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]], ptr addrspace(3) noundef [[LP:%.*]]) #[[ATTR7]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[LP_ADDR:%.*]] = alloca ptr addrspace(3), align 4, addrspace(5)
// NOCPU-NEXT:    [[BLOCK_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// NOCPU-NEXT:    [[LP_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[LP_ADDR]] to ptr
// NOCPU-NEXT:    [[BLOCK_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK_ADDR]] to ptr
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr addrspace(3) [[LP]], ptr [[LP_ADDR_ASCAST]], align 4
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[BLOCK_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 6
// NOCPU-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// NOCPU-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8
// NOCPU-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP1]], i64 0
// NOCPU-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR2:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 5
// NOCPU-NEXT:    [[TMP2:%.*]] = load i64, ptr [[BLOCK_CAPTURE_ADDR2]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR3:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// NOCPU-NEXT:    [[TMP3:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR3]], align 8
// NOCPU-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, ptr addrspace(1) [[TMP3]], i64 0
// NOCPU-NEXT:    store i64 [[TMP2]], ptr addrspace(1) [[ARRAYIDX4]], align 8
// NOCPU-NEXT:    [[TMP4:%.*]] = load ptr addrspace(3), ptr [[LP_ADDR_ASCAST]], align 4
// NOCPU-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, ptr addrspace(3) [[TMP4]], i64 0
// NOCPU-NEXT:    store i32 1, ptr addrspace(3) [[ARRAYIDX5]], align 4
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent nounwind
// NOCPU-LABEL: define internal amdgpu_kernel void @__test_block_invoke_3_kernel(
// NOCPU-SAME: <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]], ptr addrspace(3) [[TMP1:%.*]]) #[[ATTR8]] !associated [[META15:![0-9]+]] !kernel_arg_addr_space [[META16:![0-9]+]] !kernel_arg_access_qual [[META17:![0-9]+]] !kernel_arg_type [[META18:![0-9]+]] !kernel_arg_base_type [[META18]] !kernel_arg_type_qual [[META19:![0-9]+]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[TMP2:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
// NOCPU-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0]], ptr addrspace(5) [[TMP2]], align 8
// NOCPU-NEXT:    [[TMP3:%.*]] = addrspacecast ptr addrspace(5) [[TMP2]] to ptr
// NOCPU-NEXT:    call void @__test_block_invoke_3(ptr [[TMP3]], ptr addrspace(3) [[TMP1]])
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent noinline nounwind optnone
// NOCPU-LABEL: define internal void @__test_block_invoke_4(
// NOCPU-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR7]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[BLOCK_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// NOCPU-NEXT:    [[BLOCK_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK_ADDR]] to ptr
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[BLOCK_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// NOCPU-NEXT:    [[TMP0:%.*]] = load i64, ptr [[BLOCK_CAPTURE_ADDR]], align 8
// NOCPU-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// NOCPU-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8
// NOCPU-NEXT:    call void @callee(i64 noundef [[TMP0]], ptr addrspace(1) noundef [[TMP1]]) #[[ATTR10]]
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent nounwind
// NOCPU-LABEL: define internal amdgpu_kernel void @__test_block_invoke_4_kernel(
// NOCPU-SAME: <{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0:%.*]]) #[[ATTR8]] !associated [[META20:![0-9]+]] !kernel_arg_addr_space [[META12]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META13]] !kernel_arg_base_type [[META13]] !kernel_arg_type_qual [[META10]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, i64, ptr addrspace(1) }>, align 8, addrspace(5)
// NOCPU-NEXT:    store <{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
// NOCPU-NEXT:    [[TMP2:%.*]] = addrspacecast ptr addrspace(5) [[TMP1]] to ptr
// NOCPU-NEXT:    call void @__test_block_invoke_4(ptr [[TMP2]])
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent noinline nounwind optnone
// NOCPU-LABEL: define internal void @__test_target_features_kernel_block_invoke(
// NOCPU-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR7]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[BLOCK_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// NOCPU-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// NOCPU-NEXT:    [[BLOCK_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK_ADDR]] to ptr
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[BLOCK_ADDR_ASCAST]], align 8
// NOCPU-NEXT:    [[TMP0:%.*]] = call i64 @llvm.amdgcn.s.memtime()
// NOCPU-NEXT:    ret void
//
//
// NOCPU: Function Attrs: convergent nounwind
// NOCPU-LABEL: define internal amdgpu_kernel void @__test_target_features_kernel_block_invoke_kernel(
// NOCPU-SAME: { i32, i32, ptr } [[TMP0:%.*]]) #[[ATTR8]] !associated [[META21:![0-9]+]] !kernel_arg_addr_space [[META12]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META13]] !kernel_arg_base_type [[META13]] !kernel_arg_type_qual [[META10]] {
// NOCPU-NEXT:  [[ENTRY:.*:]]
// NOCPU-NEXT:    [[TMP1:%.*]] = alloca { i32, i32, ptr }, align 8, addrspace(5)
// NOCPU-NEXT:    store { i32, i32, ptr } [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
// NOCPU-NEXT:    [[TMP2:%.*]] = addrspacecast ptr addrspace(5) [[TMP1]] to ptr
// NOCPU-NEXT:    call void @__test_target_features_kernel_block_invoke(ptr [[TMP2]])
// NOCPU-NEXT:    ret void
//
//
//
//
//
//
//
//
//
//
//
//
//
//
//
//
//
// GFX900: Function Attrs: convergent norecurse nounwind
// GFX900-LABEL: define dso_local void @callee(
// GFX900-SAME: i64 noundef [[ID:%.*]], ptr addrspace(1) noundef [[OUT:%.*]]) #[[ATTR1:[0-9]+]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[ID_ADDR:%.*]] = alloca i64, align 8, addrspace(5)
// GFX900-NEXT:    [[OUT_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// GFX900-NEXT:    [[ID_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[ID_ADDR]] to ptr
// GFX900-NEXT:    [[OUT_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[OUT_ADDR]] to ptr
// GFX900-NEXT:    store i64 [[ID]], ptr [[ID_ADDR_ASCAST]], align 8, !tbaa [[TBAA3:![0-9]+]]
// GFX900-NEXT:    store ptr addrspace(1) [[OUT]], ptr [[OUT_ADDR_ASCAST]], align 8, !tbaa [[TBAA7:![0-9]+]]
// GFX900-NEXT:    [[TMP0:%.*]] = load i64, ptr [[ID_ADDR_ASCAST]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[OUT_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    [[TMP2:%.*]] = load i64, ptr [[ID_ADDR_ASCAST]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr addrspace(1) [[TMP1]], i64 [[TMP2]]
// GFX900-NEXT:    store i64 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent norecurse nounwind
// GFX900-LABEL: define dso_local amdgpu_kernel void @test(
// GFX900-SAME: ptr addrspace(1) noundef align 1 [[A:%.*]], i8 noundef [[B:%.*]], ptr addrspace(1) noundef align 8 [[C:%.*]], i64 noundef [[D:%.*]]) #[[ATTR2:[0-9]+]] !kernel_arg_addr_space [[META10:![0-9]+]] !kernel_arg_access_qual [[META11:![0-9]+]] !kernel_arg_type [[META12:![0-9]+]] !kernel_arg_base_type [[META12]] !kernel_arg_type_qual [[META13:![0-9]+]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// GFX900-NEXT:    [[B_ADDR:%.*]] = alloca i8, align 1, addrspace(5)
// GFX900-NEXT:    [[C_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// GFX900-NEXT:    [[D_ADDR:%.*]] = alloca i64, align 8, addrspace(5)
// GFX900-NEXT:    [[A_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[A_ADDR]] to ptr
// GFX900-NEXT:    [[B_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[B_ADDR]] to ptr
// GFX900-NEXT:    [[C_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[C_ADDR]] to ptr
// GFX900-NEXT:    [[D_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[D_ADDR]] to ptr
// GFX900-NEXT:    store ptr addrspace(1) [[A]], ptr [[A_ADDR_ASCAST]], align 8, !tbaa [[TBAA14:![0-9]+]]
// GFX900-NEXT:    store i8 [[B]], ptr [[B_ADDR_ASCAST]], align 1, !tbaa [[TBAA16:![0-9]+]]
// GFX900-NEXT:    store ptr addrspace(1) [[C]], ptr [[C_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    store i64 [[D]], ptr [[D_ADDR_ASCAST]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr [[A_ADDR_ASCAST]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    [[TMP1:%.*]] = load i8, ptr [[B_ADDR_ASCAST]], align 1, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[TMP2:%.*]] = load ptr addrspace(1), ptr [[C_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    [[TMP3:%.*]] = load i64, ptr [[D_ADDR_ASCAST]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    call void @__clang_ocl_kern_imp_test(ptr addrspace(1) noundef align 1 [[TMP0]], i8 noundef signext [[TMP1]], ptr addrspace(1) noundef align 8 [[TMP2]], i64 noundef [[TMP3]]) #[[ATTR8:[0-9]+]]
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent norecurse nounwind
// GFX900-LABEL: define dso_local void @__clang_ocl_kern_imp_test(
// GFX900-SAME: ptr addrspace(1) noundef align 1 [[A:%.*]], i8 noundef signext [[B:%.*]], ptr addrspace(1) noundef align 8 [[C:%.*]], i64 noundef [[D:%.*]]) #[[ATTR3:[0-9]+]] !kernel_arg_addr_space [[META10]] !kernel_arg_access_qual [[META11]] !kernel_arg_type [[META12]] !kernel_arg_base_type [[META12]] !kernel_arg_type_qual [[META13]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// GFX900-NEXT:    [[B_ADDR:%.*]] = alloca i8, align 1, addrspace(5)
// GFX900-NEXT:    [[C_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// GFX900-NEXT:    [[D_ADDR:%.*]] = alloca i64, align 8, addrspace(5)
// GFX900-NEXT:    [[DEFAULT_QUEUE:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// GFX900-NEXT:    [[FLAGS:%.*]] = alloca i32, align 4, addrspace(5)
// GFX900-NEXT:    [[NDRANGE:%.*]] = alloca [[STRUCT_NDRANGE_T:%.*]], align 4, addrspace(5)
// GFX900-NEXT:    [[TMP:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// GFX900-NEXT:    [[BLOCK:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), i8 }>, align 8, addrspace(5)
// GFX900-NEXT:    [[VARTMP2:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// GFX900-NEXT:    [[BLOCK3:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
// GFX900-NEXT:    [[VARTMP11:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// GFX900-NEXT:    [[BLOCK12:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
// GFX900-NEXT:    [[BLOCK_SIZES:%.*]] = alloca [1 x i64], align 8, addrspace(5)
// GFX900-NEXT:    [[BLOCK20:%.*]] = alloca ptr, align 8, addrspace(5)
// GFX900-NEXT:    [[BLOCK21:%.*]] = alloca <{ i32, i32, ptr, i64, ptr addrspace(1) }>, align 8, addrspace(5)
// GFX900-NEXT:    [[VARTMP27:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// GFX900-NEXT:    [[A_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[A_ADDR]] to ptr
// GFX900-NEXT:    [[B_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[B_ADDR]] to ptr
// GFX900-NEXT:    [[C_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[C_ADDR]] to ptr
// GFX900-NEXT:    [[D_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[D_ADDR]] to ptr
// GFX900-NEXT:    [[DEFAULT_QUEUE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DEFAULT_QUEUE]] to ptr
// GFX900-NEXT:    [[FLAGS_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[FLAGS]] to ptr
// GFX900-NEXT:    [[NDRANGE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[NDRANGE]] to ptr
// GFX900-NEXT:    [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr
// GFX900-NEXT:    [[BLOCK_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK]] to ptr
// GFX900-NEXT:    [[TMP2_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VARTMP2]] to ptr
// GFX900-NEXT:    [[BLOCK3_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK3]] to ptr
// GFX900-NEXT:    [[TMP11_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VARTMP11]] to ptr
// GFX900-NEXT:    [[BLOCK12_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK12]] to ptr
// GFX900-NEXT:    [[BLOCK_SIZES_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK_SIZES]] to ptr
// GFX900-NEXT:    [[BLOCK20_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK20]] to ptr
// GFX900-NEXT:    [[BLOCK21_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK21]] to ptr
// GFX900-NEXT:    [[TMP27_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VARTMP27]] to ptr
// GFX900-NEXT:    store ptr addrspace(1) [[A]], ptr [[A_ADDR_ASCAST]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    store i8 [[B]], ptr [[B_ADDR_ASCAST]], align 1, !tbaa [[TBAA16]]
// GFX900-NEXT:    store ptr addrspace(1) [[C]], ptr [[C_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    store i64 [[D]], ptr [[D_ADDR_ASCAST]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[DEFAULT_QUEUE]]) #[[ATTR9:[0-9]+]]
// GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[FLAGS]]) #[[ATTR9]]
// GFX900-NEXT:    store i32 0, ptr [[FLAGS_ASCAST]], align 4, !tbaa [[TBAA17:![0-9]+]]
// GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[NDRANGE]]) #[[ATTR9]]
// GFX900-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8, !tbaa [[TBAA19:![0-9]+]]
// GFX900-NEXT:    [[TMP1:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4, !tbaa [[TBAA17]]
// GFX900-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21:![0-9]+]]
// GFX900-NEXT:    [[BLOCK_SIZE:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 0
// GFX900-NEXT:    store i32 25, ptr [[BLOCK_SIZE]], align 8
// GFX900-NEXT:    [[BLOCK_ALIGN:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 1
// GFX900-NEXT:    store i32 8, ptr [[BLOCK_ALIGN]], align 4
// GFX900-NEXT:    [[BLOCK_INVOKE:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 2
// GFX900-NEXT:    store ptr @__test_block_invoke, ptr [[BLOCK_INVOKE]], align 8
// GFX900-NEXT:    [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 3
// GFX900-NEXT:    [[TMP2:%.*]] = load ptr addrspace(1), ptr [[A_ADDR_ASCAST]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    store ptr addrspace(1) [[TMP2]], ptr [[BLOCK_CAPTURED]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    [[BLOCK_CAPTURED1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[BLOCK_ASCAST]], i32 0, i32 4
// GFX900-NEXT:    [[TMP3:%.*]] = load i8, ptr [[B_ADDR_ASCAST]], align 1, !tbaa [[TBAA16]]
// GFX900-NEXT:    store i8 [[TMP3]], ptr [[BLOCK_CAPTURED1]], align 8, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[TMP4:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP0]], i32 [[TMP1]], ptr addrspace(5) [[TMP]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_kernel.runtime.handle to ptr), ptr [[BLOCK_ASCAST]])
// GFX900-NEXT:    [[TMP5:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8, !tbaa [[TBAA19]]
// GFX900-NEXT:    [[TMP6:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4, !tbaa [[TBAA17]]
// GFX900-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP2_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21]]
// GFX900-NEXT:    [[BLOCK_SIZE4:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 0
// GFX900-NEXT:    store i32 41, ptr [[BLOCK_SIZE4]], align 8
// GFX900-NEXT:    [[BLOCK_ALIGN5:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 1
// GFX900-NEXT:    store i32 8, ptr [[BLOCK_ALIGN5]], align 4
// GFX900-NEXT:    [[BLOCK_INVOKE6:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 2
// GFX900-NEXT:    store ptr @__test_block_invoke_2, ptr [[BLOCK_INVOKE6]], align 8
// GFX900-NEXT:    [[BLOCK_CAPTURED7:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 3
// GFX900-NEXT:    [[TMP7:%.*]] = load ptr addrspace(1), ptr [[A_ADDR_ASCAST]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    store ptr addrspace(1) [[TMP7]], ptr [[BLOCK_CAPTURED7]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    [[BLOCK_CAPTURED8:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 6
// GFX900-NEXT:    [[TMP8:%.*]] = load i8, ptr [[B_ADDR_ASCAST]], align 1, !tbaa [[TBAA16]]
// GFX900-NEXT:    store i8 [[TMP8]], ptr [[BLOCK_CAPTURED8]], align 8, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[BLOCK_CAPTURED9:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 4
// GFX900-NEXT:    [[TMP9:%.*]] = load ptr addrspace(1), ptr [[C_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    store ptr addrspace(1) [[TMP9]], ptr [[BLOCK_CAPTURED9]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    [[BLOCK_CAPTURED10:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK3_ASCAST]], i32 0, i32 5
// GFX900-NEXT:    [[TMP10:%.*]] = load i64, ptr [[D_ADDR_ASCAST]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    store i64 [[TMP10]], ptr [[BLOCK_CAPTURED10]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    [[TMP11:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP5]], i32 [[TMP6]], ptr addrspace(5) [[VARTMP2]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_2_kernel.runtime.handle to ptr), ptr [[BLOCK3_ASCAST]])
// GFX900-NEXT:    [[TMP12:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8, !tbaa [[TBAA19]]
// GFX900-NEXT:    [[TMP13:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4, !tbaa [[TBAA17]]
// GFX900-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP11_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21]]
// GFX900-NEXT:    [[BLOCK_SIZE13:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 0
// GFX900-NEXT:    store i32 41, ptr [[BLOCK_SIZE13]], align 8
// GFX900-NEXT:    [[BLOCK_ALIGN14:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 1
// GFX900-NEXT:    store i32 8, ptr [[BLOCK_ALIGN14]], align 4
// GFX900-NEXT:    [[BLOCK_INVOKE15:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 2
// GFX900-NEXT:    store ptr @__test_block_invoke_3, ptr [[BLOCK_INVOKE15]], align 8
// GFX900-NEXT:    [[BLOCK_CAPTURED16:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 3
// GFX900-NEXT:    [[TMP14:%.*]] = load ptr addrspace(1), ptr [[A_ADDR_ASCAST]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    store ptr addrspace(1) [[TMP14]], ptr [[BLOCK_CAPTURED16]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    [[BLOCK_CAPTURED17:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 6
// GFX900-NEXT:    [[TMP15:%.*]] = load i8, ptr [[B_ADDR_ASCAST]], align 1, !tbaa [[TBAA16]]
// GFX900-NEXT:    store i8 [[TMP15]], ptr [[BLOCK_CAPTURED17]], align 8, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[BLOCK_CAPTURED18:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 4
// GFX900-NEXT:    [[TMP16:%.*]] = load ptr addrspace(1), ptr [[C_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    store ptr addrspace(1) [[TMP16]], ptr [[BLOCK_CAPTURED18]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    [[BLOCK_CAPTURED19:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[BLOCK12_ASCAST]], i32 0, i32 5
// GFX900-NEXT:    [[TMP17:%.*]] = load i64, ptr [[D_ADDR_ASCAST]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    store i64 [[TMP17]], ptr [[BLOCK_CAPTURED19]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[BLOCK_SIZES]]) #[[ATTR9]]
// GFX900-NEXT:    [[TMP18:%.*]] = getelementptr [1 x i64], ptr [[BLOCK_SIZES_ASCAST]], i32 0, i32 0
// GFX900-NEXT:    store i64 100, ptr [[TMP18]], align 8
// GFX900-NEXT:    [[TMP19:%.*]] = call i32 @__enqueue_kernel_varargs(ptr addrspace(1) [[TMP12]], i32 [[TMP13]], ptr addrspace(5) [[VARTMP11]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_3_kernel.runtime.handle to ptr), ptr [[BLOCK12_ASCAST]], i32 1, ptr [[TMP18]])
// GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[BLOCK_SIZES]]) #[[ATTR9]]
// GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[BLOCK20]]) #[[ATTR9]]
// GFX900-NEXT:    [[BLOCK_SIZE22:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 0
// GFX900-NEXT:    store i32 32, ptr [[BLOCK_SIZE22]], align 8
// GFX900-NEXT:    [[BLOCK_ALIGN23:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 1
// GFX900-NEXT:    store i32 8, ptr [[BLOCK_ALIGN23]], align 4
// GFX900-NEXT:    [[BLOCK_INVOKE24:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 2
// GFX900-NEXT:    store ptr @__test_block_invoke_4, ptr [[BLOCK_INVOKE24]], align 8
// GFX900-NEXT:    [[BLOCK_CAPTURED25:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 3
// GFX900-NEXT:    [[TMP20:%.*]] = load i64, ptr [[D_ADDR_ASCAST]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    store i64 [[TMP20]], ptr [[BLOCK_CAPTURED25]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    [[BLOCK_CAPTURED26:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[BLOCK21_ASCAST]], i32 0, i32 4
// GFX900-NEXT:    [[TMP21:%.*]] = load ptr addrspace(1), ptr [[C_ADDR_ASCAST]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    store ptr addrspace(1) [[TMP21]], ptr [[BLOCK_CAPTURED26]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    store ptr [[BLOCK21_ASCAST]], ptr [[BLOCK20_ASCAST]], align 8, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[TMP22:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8, !tbaa [[TBAA19]]
// GFX900-NEXT:    [[TMP23:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4, !tbaa [[TBAA17]]
// GFX900-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP27_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21]]
// GFX900-NEXT:    [[TMP24:%.*]] = load ptr, ptr [[BLOCK20_ASCAST]], align 8, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[TMP25:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP22]], i32 [[TMP23]], ptr addrspace(5) [[VARTMP27]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_4_kernel.runtime.handle to ptr), ptr [[BLOCK21_ASCAST]])
// GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[BLOCK20]]) #[[ATTR9]]
// GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 4, ptr addrspace(5) [[NDRANGE]]) #[[ATTR9]]
// GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 4, ptr addrspace(5) [[FLAGS]]) #[[ATTR9]]
// GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[DEFAULT_QUEUE]]) #[[ATTR9]]
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent norecurse nounwind
// GFX900-LABEL: define dso_local amdgpu_kernel void @test_target_features_kernel(
// GFX900-SAME: ptr addrspace(1) noundef align 4 [[I:%.*]]) #[[ATTR2]] !kernel_arg_addr_space [[META22:![0-9]+]] !kernel_arg_access_qual [[META23:![0-9]+]] !kernel_arg_type [[META24:![0-9]+]] !kernel_arg_base_type [[META24]] !kernel_arg_type_qual [[META25:![0-9]+]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[I_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// GFX900-NEXT:    [[I_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I_ADDR]] to ptr
// GFX900-NEXT:    store ptr addrspace(1) [[I]], ptr [[I_ADDR_ASCAST]], align 8, !tbaa [[TBAA26:![0-9]+]]
// GFX900-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr [[I_ADDR_ASCAST]], align 8, !tbaa [[TBAA26]]
// GFX900-NEXT:    call void @__clang_ocl_kern_imp_test_target_features_kernel(ptr addrspace(1) noundef align 4 [[TMP0]]) #[[ATTR8]]
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent norecurse nounwind
// GFX900-LABEL: define dso_local void @__clang_ocl_kern_imp_test_target_features_kernel(
// GFX900-SAME: ptr addrspace(1) noundef align 4 [[I:%.*]]) #[[ATTR3]] !kernel_arg_addr_space [[META22]] !kernel_arg_access_qual [[META23]] !kernel_arg_type [[META24]] !kernel_arg_base_type [[META24]] !kernel_arg_type_qual [[META25]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[I_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// GFX900-NEXT:    [[DEFAULT_QUEUE:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// GFX900-NEXT:    [[FLAGS:%.*]] = alloca i32, align 4, addrspace(5)
// GFX900-NEXT:    [[NDRANGE:%.*]] = alloca [[STRUCT_NDRANGE_T:%.*]], align 4, addrspace(5)
// GFX900-NEXT:    [[TMP:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
// GFX900-NEXT:    [[I_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I_ADDR]] to ptr
// GFX900-NEXT:    [[DEFAULT_QUEUE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DEFAULT_QUEUE]] to ptr
// GFX900-NEXT:    [[FLAGS_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[FLAGS]] to ptr
// GFX900-NEXT:    [[NDRANGE_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[NDRANGE]] to ptr
// GFX900-NEXT:    [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr
// GFX900-NEXT:    store ptr addrspace(1) [[I]], ptr [[I_ADDR_ASCAST]], align 8, !tbaa [[TBAA26]]
// GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[DEFAULT_QUEUE]]) #[[ATTR9]]
// GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[FLAGS]]) #[[ATTR9]]
// GFX900-NEXT:    store i32 0, ptr [[FLAGS_ASCAST]], align 4, !tbaa [[TBAA17]]
// GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[NDRANGE]]) #[[ATTR9]]
// GFX900-NEXT:    [[TMP0:%.*]] = call i64 @llvm.amdgcn.s.memtime()
// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[DEFAULT_QUEUE_ASCAST]], align 8, !tbaa [[TBAA19]]
// GFX900-NEXT:    [[TMP2:%.*]] = load i32, ptr [[FLAGS_ASCAST]], align 4, !tbaa [[TBAA17]]
// GFX900-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP_ASCAST]], ptr align 4 [[NDRANGE_ASCAST]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21]]
// GFX900-NEXT:    [[TMP3:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP1]], i32 [[TMP2]], ptr addrspace(5) [[TMP]], ptr addrspacecast (ptr addrspace(1) @__test_target_features_kernel_block_invoke_kernel.runtime.handle to ptr), ptr addrspacecast (ptr addrspace(1) @__block_literal_global to ptr))
// GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 4, ptr addrspace(5) [[NDRANGE]]) #[[ATTR9]]
// GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 4, ptr addrspace(5) [[FLAGS]]) #[[ATTR9]]
// GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[DEFAULT_QUEUE]]) #[[ATTR9]]
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal void @__test_block_invoke(
// GFX900-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR6:[0-9]+]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// GFX900-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// GFX900-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP1]], i64 0
// GFX900-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1, !tbaa [[TBAA16]]
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal amdgpu_kernel void @__test_block_invoke_kernel(
// GFX900-SAME: <{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0:%.*]]) #[[ATTR6]] !associated [[META28:![0-9]+]] !kernel_arg_addr_space [[META29:![0-9]+]] !kernel_arg_access_qual [[META23]] !kernel_arg_type [[META30:![0-9]+]] !kernel_arg_base_type [[META30]] !kernel_arg_type_qual [[META25]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), i8 }>, align 8, addrspace(5)
// GFX900-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
// GFX900-NEXT:    [[TMP2:%.*]] = addrspacecast ptr addrspace(5) [[TMP1]] to ptr
// GFX900-NEXT:    call void @__test_block_invoke(ptr [[TMP2]])
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal void @__test_block_invoke_2(
// GFX900-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR6]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// GFX900-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 6
// GFX900-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP1]], i64 0
// GFX900-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR2:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 5
// GFX900-NEXT:    [[TMP2:%.*]] = load i64, ptr [[BLOCK_CAPTURE_ADDR2]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR3:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// GFX900-NEXT:    [[TMP3:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR3]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, ptr addrspace(1) [[TMP3]], i64 0
// GFX900-NEXT:    store i64 [[TMP2]], ptr addrspace(1) [[ARRAYIDX4]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal amdgpu_kernel void @__test_block_invoke_2_kernel(
// GFX900-SAME: <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]]) #[[ATTR6]] !associated [[META31:![0-9]+]] !kernel_arg_addr_space [[META29]] !kernel_arg_access_qual [[META23]] !kernel_arg_type [[META30]] !kernel_arg_base_type [[META30]] !kernel_arg_type_qual [[META25]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
// GFX900-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
// GFX900-NEXT:    [[TMP2:%.*]] = addrspacecast ptr addrspace(5) [[TMP1]] to ptr
// GFX900-NEXT:    call void @__test_block_invoke_2(ptr [[TMP2]])
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal void @__test_block_invoke_3(
// GFX900-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]], ptr addrspace(3) noundef [[LP:%.*]]) #[[ATTR6]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// GFX900-NEXT:    [[LP_ADDR:%.*]] = alloca ptr addrspace(3), align 4, addrspace(5)
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// GFX900-NEXT:    [[LP_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[LP_ADDR]] to ptr
// GFX900-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// GFX900-NEXT:    store ptr addrspace(3) [[LP]], ptr [[LP_ADDR_ASCAST]], align 4, !tbaa [[TBAA32:![0-9]+]]
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 6
// GFX900-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA14]]
// GFX900-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP1]], i64 0
// GFX900-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1, !tbaa [[TBAA16]]
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR2:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 5
// GFX900-NEXT:    [[TMP2:%.*]] = load i64, ptr [[BLOCK_CAPTURE_ADDR2]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR3:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// GFX900-NEXT:    [[TMP3:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR3]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, ptr addrspace(1) [[TMP3]], i64 0
// GFX900-NEXT:    store i64 [[TMP2]], ptr addrspace(1) [[ARRAYIDX4]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    [[TMP4:%.*]] = load ptr addrspace(3), ptr [[LP_ADDR_ASCAST]], align 4, !tbaa [[TBAA32]]
// GFX900-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, ptr addrspace(3) [[TMP4]], i64 0
// GFX900-NEXT:    store i32 1, ptr addrspace(3) [[ARRAYIDX5]], align 4, !tbaa [[TBAA17]]
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal amdgpu_kernel void @__test_block_invoke_3_kernel(
// GFX900-SAME: <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]], ptr addrspace(3) [[TMP1:%.*]]) #[[ATTR6]] !associated [[META33:![0-9]+]] !kernel_arg_addr_space [[META34:![0-9]+]] !kernel_arg_access_qual [[META35:![0-9]+]] !kernel_arg_type [[META36:![0-9]+]] !kernel_arg_base_type [[META36]] !kernel_arg_type_qual [[META37:![0-9]+]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[TMP2:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
// GFX900-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0]], ptr addrspace(5) [[TMP2]], align 8
// GFX900-NEXT:    [[TMP3:%.*]] = addrspacecast ptr addrspace(5) [[TMP2]] to ptr
// GFX900-NEXT:    call void @__test_block_invoke_3(ptr [[TMP3]], ptr addrspace(3) [[TMP1]])
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal void @__test_block_invoke_4(
// GFX900-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR6]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// GFX900-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// GFX900-NEXT:    [[TMP0:%.*]] = load i64, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA3]]
// GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr, i64, ptr addrspace(1) }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA7]]
// GFX900-NEXT:    call void @callee(i64 noundef [[TMP0]], ptr addrspace(1) noundef [[TMP1]]) #[[ATTR8]]
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal amdgpu_kernel void @__test_block_invoke_4_kernel(
// GFX900-SAME: <{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0:%.*]]) #[[ATTR6]] !associated [[META38:![0-9]+]] !kernel_arg_addr_space [[META29]] !kernel_arg_access_qual [[META23]] !kernel_arg_type [[META30]] !kernel_arg_base_type [[META30]] !kernel_arg_type_qual [[META25]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, i64, ptr addrspace(1) }>, align 8, addrspace(5)
// GFX900-NEXT:    store <{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
// GFX900-NEXT:    [[TMP2:%.*]] = addrspacecast ptr addrspace(5) [[TMP1]] to ptr
// GFX900-NEXT:    call void @__test_block_invoke_4(ptr [[TMP2]])
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal void @__test_target_features_kernel_block_invoke(
// GFX900-SAME: ptr noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR6]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]] to ptr
// GFX900-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR_ASCAST]], align 8
// GFX900-NEXT:    [[TMP0:%.*]] = call i64 @llvm.amdgcn.s.memtime()
// GFX900-NEXT:    ret void
//
//
// GFX900: Function Attrs: convergent nounwind
// GFX900-LABEL: define internal amdgpu_kernel void @__test_target_features_kernel_block_invoke_kernel(
// GFX900-SAME: { i32, i32, ptr } [[TMP0:%.*]]) #[[ATTR6]] !associated [[META39:![0-9]+]] !kernel_arg_addr_space [[META29]] !kernel_arg_access_qual [[META23]] !kernel_arg_type [[META30]] !kernel_arg_base_type [[META30]] !kernel_arg_type_qual [[META25]] {
// GFX900-NEXT:  [[ENTRY:.*:]]
// GFX900-NEXT:    [[TMP1:%.*]] = alloca { i32, i32, ptr }, align 8, addrspace(5)
// GFX900-NEXT:    store { i32, i32, ptr } [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
// GFX900-NEXT:    [[TMP2:%.*]] = addrspacecast ptr addrspace(5) [[TMP1]] to ptr
// GFX900-NEXT:    call void @__test_target_features_kernel_block_invoke(ptr [[TMP2]])
// GFX900-NEXT:    ret void
//
//.
// NOCPU: attributes #[[ATTR0:[0-9]+]] = { "objc_arc_inert" }
// NOCPU: attributes #[[ATTR1]] = { convergent noinline norecurse nounwind optnone "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// NOCPU: attributes #[[ATTR2]] = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" }
// NOCPU: attributes #[[ATTR3]] = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// NOCPU: attributes #[[ATTR4]] = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+s-memtime-inst" "uniform-work-group-size"="false" }
// NOCPU: attributes #[[ATTR5]] = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+s-memtime-inst" }
// NOCPU: attributes #[[ATTR6:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
// NOCPU: attributes #[[ATTR7]] = { convergent noinline nounwind optnone "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// NOCPU: attributes #[[ATTR8]] = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// NOCPU: attributes #[[ATTR9:[0-9]+]] = { nocallback nofree nosync nounwind willreturn }
// NOCPU: attributes #[[ATTR10]] = { convergent nounwind }
//.
// GFX900: attributes #[[ATTR0:[0-9]+]] = { "objc_arc_inert" }
// GFX900: attributes #[[ATTR1]] = { convergent norecurse nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" }
// GFX900: attributes #[[ATTR2]] = { convergent norecurse nounwind "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" "uniform-work-group-size"="false" }
// GFX900: attributes #[[ATTR3]] = { convergent norecurse nounwind "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" }
// GFX900: attributes #[[ATTR4:[0-9]+]] = { nocallback nofree nosync nounwind willreturn memory(argmem: readwrite) }
// GFX900: attributes #[[ATTR5:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
// GFX900: attributes #[[ATTR6]] = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" }
// GFX900: attributes #[[ATTR7:[0-9]+]] = { nocallback nofree nosync nounwind willreturn }
// GFX900: attributes #[[ATTR8]] = { convergent nounwind }
// GFX900: attributes #[[ATTR9]] = { nounwind }
//.
// NOCPU: [[META0:![0-9]+]] = !{i32 1, !"amdhsa_code_object_version", i32 600}
// NOCPU: [[META1:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
// NOCPU: [[META2:![0-9]+]] = !{i32 2, i32 0}
// NOCPU: [[META3]] = !{i32 1, i32 0, i32 1, i32 0}
// NOCPU: [[META4]] = !{!"none", !"none", !"none", !"none"}
// NOCPU: [[META5]] = !{!"char*", !"char", !"long*", !"long"}
// NOCPU: [[META6]] = !{!"", !"", !"", !""}
// NOCPU: [[META7]] = !{i32 1}
// NOCPU: [[META8]] = !{!"none"}
// NOCPU: [[META9]] = !{!"int*"}
// NOCPU: [[META10]] = !{!""}
// NOCPU: [[META11]] = !{ptr addrspace(1) @__test_block_invoke_kernel.runtime.handle}
// NOCPU: [[META12]] = !{i32 0}
// NOCPU: [[META13]] = !{!"__block_literal"}
// NOCPU: [[META14]] = !{ptr addrspace(1) @__test_block_invoke_2_kernel.runtime.handle}
// NOCPU: [[META15]] = !{ptr addrspace(1) @__test_block_invoke_3_kernel.runtime.handle}
// NOCPU: [[META16]] = !{i32 0, i32 3}
// NOCPU: [[META17]] = !{!"none", !"none"}
// NOCPU: [[META18]] = !{!"__block_literal", !"void*"}
// NOCPU: [[META19]] = !{!"", !""}
// NOCPU: [[META20]] = !{ptr addrspace(1) @__test_block_invoke_4_kernel.runtime.handle}
// NOCPU: [[META21]] = !{ptr addrspace(1) @__test_target_features_kernel_block_invoke_kernel.runtime.handle}
//.
// GFX900: [[META0:![0-9]+]] = !{i32 1, !"amdhsa_code_object_version", i32 600}
// GFX900: [[META1:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
// GFX900: [[META2:![0-9]+]] = !{i32 2, i32 0}
// GFX900: [[TBAA3]] = !{[[META4:![0-9]+]], [[META4]], i64 0}
// GFX900: [[META4]] = !{!"long", [[META5:![0-9]+]], i64 0}
// GFX900: [[META5]] = !{!"omnipotent char", [[META6:![0-9]+]], i64 0}
// GFX900: [[META6]] = !{!"Simple C/C++ TBAA"}
// GFX900: [[TBAA7]] = !{[[META8:![0-9]+]], [[META8]], i64 0}
// GFX900: [[META8]] = !{!"p1 long", [[META9:![0-9]+]], i64 0}
// GFX900: [[META9]] = !{!"any pointer", [[META5]], i64 0}
// GFX900: [[META10]] = !{i32 1, i32 0, i32 1, i32 0}
// GFX900: [[META11]] = !{!"none", !"none", !"none", !"none"}
// GFX900: [[META12]] = !{!"char*", !"char", !"long*", !"long"}
// GFX900: [[META13]] = !{!"", !"", !"", !""}
// GFX900: [[TBAA14]] = !{[[META15:![0-9]+]], [[META15]], i64 0}
// GFX900: [[META15]] = !{!"p1 omnipotent char", [[META9]], i64 0}
// GFX900: [[TBAA16]] = !{[[META5]], [[META5]], i64 0}
// GFX900: [[TBAA17]] = !{[[META18:![0-9]+]], [[META18]], i64 0}
// GFX900: [[META18]] = !{!"int", [[META5]], i64 0}
// GFX900: [[TBAA19]] = !{[[META20:![0-9]+]], [[META20]], i64 0}
// GFX900: [[META20]] = !{!"queue_t", [[META5]], i64 0}
// GFX900: [[TBAA_STRUCT21]] = !{i64 0, i64 4, [[TBAA17]]}
// GFX900: [[META22]] = !{i32 1}
// GFX900: [[META23]] = !{!"none"}
// GFX900: [[META24]] = !{!"int*"}
// GFX900: [[META25]] = !{!""}
// GFX900: [[TBAA26]] = !{[[META27:![0-9]+]], [[META27]], i64 0}
// GFX900: [[META27]] = !{!"p1 int", [[META9]], i64 0}
// GFX900: [[META28]] = !{ptr addrspace(1) @__test_block_invoke_kernel.runtime.handle}
// GFX900: [[META29]] = !{i32 0}
// GFX900: [[META30]] = !{!"__block_literal"}
// GFX900: [[META31]] = !{ptr addrspace(1) @__test_block_invoke_2_kernel.runtime.handle}
// GFX900: [[TBAA32]] = !{[[META9]], [[META9]], i64 0}
// GFX900: [[META33]] = !{ptr addrspace(1) @__test_block_invoke_3_kernel.runtime.handle}
// GFX900: [[META34]] = !{i32 0, i32 3}
// GFX900: [[META35]] = !{!"none", !"none"}
// GFX900: [[META36]] = !{!"__block_literal", !"void*"}
// GFX900: [[META37]] = !{!"", !""}
// GFX900: [[META38]] = !{ptr addrspace(1) @__test_block_invoke_4_kernel.runtime.handle}
// GFX900: [[META39]] = !{ptr addrspace(1) @__test_target_features_kernel_block_invoke_kernel.runtime.handle}
//.
//// NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
// CHECK: {{.*}}