145 lines
12 KiB
Plaintext
145 lines
12 KiB
Plaintext
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --check-globals --global-value-regex ".offloading.entry.*" "managed.*"
|
|
// RUN: %clang_cc1 -std=c++11 -triple x86_64-unknown-linux-gnu -fgpu-rdc \
|
|
// RUN: --offload-new-driver -emit-llvm -o - -x cuda %s | FileCheck \
|
|
// RUN: --check-prefix=CUDA %s
|
|
// RUN: %clang_cc1 -std=c++11 -triple x86_64-unknown-linux-gnu -fgpu-rdc \
|
|
// RUN: --offload-new-driver -emit-llvm -o - -x hip %s | FileCheck \
|
|
// RUN: --check-prefix=HIP %s
|
|
// RUN: %clang_cc1 -std=c++11 -triple x86_64-unknown-windows-gnu -fgpu-rdc \
|
|
// RUN: --offload-new-driver -emit-llvm -o - -x cuda %s | FileCheck \
|
|
// RUN: --check-prefix=CUDA-COFF %s
|
|
// RUN: %clang_cc1 -std=c++11 -triple x86_64-unknown-windows-gnu -fgpu-rdc \
|
|
// RUN: --offload-new-driver -emit-llvm -o - -x hip %s | FileCheck \
|
|
// RUN: --check-prefix=HIP-COFF %s
|
|
|
|
#include "Inputs/cuda.h"
|
|
|
|
#define __managed__ __attribute__((managed))
|
|
|
|
//.
|
|
// CUDA: @managed = global i32 undef, align 4
|
|
// CUDA: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
|
|
// CUDA: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z18__device_stub__foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
|
|
// CUDA: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
|
|
// CUDA: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z21__device_stub__kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
|
|
// CUDA: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
|
|
// CUDA: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
|
// CUDA: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
|
|
// CUDA: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @managed, ptr @.offloading.entry_name.3, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
|
// CUDA: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
|
|
// CUDA: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
|
|
// CUDA: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
|
|
// CUDA: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 35, ptr @tex, ptr @.offloading.entry_name.5, i64 1, i64 1, ptr null }, section "llvm_offload_entries"
|
|
//.
|
|
// HIP: @managed.managed = global i32 0, align 4
|
|
// HIP: @managed = externally_initialized global ptr null
|
|
// HIP: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
|
|
// HIP: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
|
|
// HIP: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
|
|
// HIP: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
|
|
// HIP: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
|
|
// HIP: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
|
|
// HIP: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
|
|
// HIP: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "llvm_offload_entries"
|
|
// HIP: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
|
|
// HIP: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
|
|
// HIP: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
|
|
// HIP: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 35, ptr @tex, ptr @.offloading.entry_name.5, i64 1, i64 1, ptr null }, section "llvm_offload_entries"
|
|
//.
|
|
// CUDA-COFF: @managed = dso_local global i32 undef, align 4
|
|
// CUDA-COFF: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
|
|
// CUDA-COFF: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z18__device_stub__foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
|
// CUDA-COFF: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
|
|
// CUDA-COFF: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @_Z21__device_stub__kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
|
// CUDA-COFF: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
|
|
// CUDA-COFF: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
|
// CUDA-COFF: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
|
|
// CUDA-COFF: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 0, ptr @managed, ptr @.offloading.entry_name.3, i64 4, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
|
// CUDA-COFF: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
|
|
// CUDA-COFF: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
|
|
// CUDA-COFF: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
|
|
// CUDA-COFF: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 2, i32 35, ptr @tex, ptr @.offloading.entry_name.5, i64 1, i64 1, ptr null }, section "llvm_offload_entries$OE"
|
|
//.
|
|
// HIP-COFF: @managed.managed = dso_local global i32 0, align 4
|
|
// HIP-COFF: @managed = dso_local externally_initialized global ptr null
|
|
// HIP-COFF: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
|
|
// HIP-COFF: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
|
// HIP-COFF: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
|
|
// HIP-COFF: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
|
// HIP-COFF: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
|
|
// HIP-COFF: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries$OE"
|
|
// HIP-COFF: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
|
|
// HIP-COFF: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "llvm_offload_entries$OE"
|
|
// HIP-COFF: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
|
|
// HIP-COFF: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
|
|
// HIP-COFF: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
|
|
// HIP-COFF: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 35, ptr @tex, ptr @.offloading.entry_name.5, i64 1, i64 1, ptr null }, section "llvm_offload_entries$OE"
|
|
//.
|
|
// CUDA-LABEL: @_Z18__device_stub__foov(
|
|
// CUDA-NEXT: entry:
|
|
// CUDA-NEXT: [[TMP0:%.*]] = call i32 @cudaLaunch(ptr @_Z18__device_stub__foov)
|
|
// CUDA-NEXT: br label [[SETUP_END:%.*]]
|
|
// CUDA: setup.end:
|
|
// CUDA-NEXT: ret void
|
|
//
|
|
// HIP-LABEL: @_Z18__device_stub__foov(
|
|
// HIP-NEXT: entry:
|
|
// HIP-NEXT: [[TMP0:%.*]] = call i32 @hipLaunchByPtr(ptr @_Z3foov)
|
|
// HIP-NEXT: br label [[SETUP_END:%.*]]
|
|
// HIP: setup.end:
|
|
// HIP-NEXT: ret void
|
|
//
|
|
// CUDA-COFF-LABEL: @_Z18__device_stub__foov(
|
|
// CUDA-COFF-NEXT: entry:
|
|
// CUDA-COFF-NEXT: [[TMP0:%.*]] = call i32 @cudaLaunch(ptr @_Z18__device_stub__foov)
|
|
// CUDA-COFF-NEXT: br label [[SETUP_END:%.*]]
|
|
// CUDA-COFF: setup.end:
|
|
// CUDA-COFF-NEXT: ret void
|
|
//
|
|
// HIP-COFF-LABEL: @_Z18__device_stub__foov(
|
|
// HIP-COFF-NEXT: entry:
|
|
// HIP-COFF-NEXT: [[TMP0:%.*]] = call i32 @hipLaunchByPtr(ptr @_Z3foov)
|
|
// HIP-COFF-NEXT: br label [[SETUP_END:%.*]]
|
|
// HIP-COFF: setup.end:
|
|
// HIP-COFF-NEXT: ret void
|
|
//
|
|
__global__ void foo() {}
|
|
__device__ int var = 1;
|
|
const __device__ int constant = 1;
|
|
extern __device__ int external;
|
|
__device__ __managed__ int managed = 0;
|
|
|
|
// CUDA-LABEL: @_Z21__device_stub__kernelv(
|
|
// CUDA-NEXT: entry:
|
|
// CUDA-NEXT: [[TMP0:%.*]] = call i32 @cudaLaunch(ptr @_Z21__device_stub__kernelv)
|
|
// CUDA-NEXT: br label [[SETUP_END:%.*]]
|
|
// CUDA: setup.end:
|
|
// CUDA-NEXT: ret void
|
|
//
|
|
// HIP-LABEL: @_Z21__device_stub__kernelv(
|
|
// HIP-NEXT: entry:
|
|
// HIP-NEXT: [[TMP0:%.*]] = call i32 @hipLaunchByPtr(ptr @_Z6kernelv)
|
|
// HIP-NEXT: br label [[SETUP_END:%.*]]
|
|
// HIP: setup.end:
|
|
// HIP-NEXT: ret void
|
|
//
|
|
// CUDA-COFF-LABEL: @_Z21__device_stub__kernelv(
|
|
// CUDA-COFF-NEXT: entry:
|
|
// CUDA-COFF-NEXT: [[TMP0:%.*]] = call i32 @cudaLaunch(ptr @_Z21__device_stub__kernelv)
|
|
// CUDA-COFF-NEXT: br label [[SETUP_END:%.*]]
|
|
// CUDA-COFF: setup.end:
|
|
// CUDA-COFF-NEXT: ret void
|
|
//
|
|
// HIP-COFF-LABEL: @_Z21__device_stub__kernelv(
|
|
// HIP-COFF-NEXT: entry:
|
|
// HIP-COFF-NEXT: [[TMP0:%.*]] = call i32 @hipLaunchByPtr(ptr @_Z6kernelv)
|
|
// HIP-COFF-NEXT: br label [[SETUP_END:%.*]]
|
|
// HIP-COFF: setup.end:
|
|
// HIP-COFF-NEXT: ret void
|
|
//
|
|
__global__ void kernel() { external = 1; }
|
|
|
|
surface<void> surf;
|
|
|
|
texture<void, cudaTextureType2D> tex;
|