887c569bcb
HIP is a language similar to CUDA (https://github.com/ROCm-Developer-Tools/HIP/blob/master/docs/markdown/hip_kernel_language.md ). The language syntax is very similar, which allows a hip program to be compiled as a CUDA program by Clang. The main difference is the host API. HIP has a set of vendor neutral host API which can be implemented on different platforms. Currently there is open source implementation of HIP runtime on amdgpu target (https://github.com/ROCm-Developer-Tools/HIP). This patch adds support of input kind and language standard hip. When hip file is compiled, both LangOpts.CUDA and LangOpts.HIP is turned on. This allows compilation of hip program as CUDA in most cases and only special handling of hip program is needed LangOpts.HIP is checked. This patch also adds support of kernel launching of HIP program using HIP host API. When -x hip is not specified, there is no behaviour change for CUDA. Patch by Greg Rodgers. Revised and lit test added by Yaxun Liu. Differential Revision: https://reviews.llvm.org/D44984 llvm-svn: 330790
151 lines
6.6 KiB
Plaintext
151 lines
6.6 KiB
Plaintext
// RUN: echo "GPU binary would be here" > %t
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s \
|
|
// RUN: -fcuda-include-gpubinary %t -o - \
|
|
// RUN: | FileCheck %s --check-prefixes=ALL,NORDC,CUDA
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s \
|
|
// RUN: -fcuda-include-gpubinary %t -o - -DNOGLOBALS \
|
|
// RUN: | FileCheck %s -check-prefix=NOGLOBALS
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s \
|
|
// RUN: -fcuda-rdc -fcuda-include-gpubinary %t -o - \
|
|
// RUN: | FileCheck %s --check-prefixes=ALL,RDC,CUDA
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s -o - \
|
|
// RUN: | FileCheck %s -check-prefix=NOGPUBIN
|
|
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s \
|
|
// RUN: -fcuda-include-gpubinary %t -o - -x hip\
|
|
// RUN: | FileCheck %s --check-prefixes=ALL,NORDC,HIP
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s \
|
|
// RUN: -fcuda-include-gpubinary %t -o - -DNOGLOBALS -x hip \
|
|
// RUN: | FileCheck %s -check-prefix=NOGLOBALS
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s \
|
|
// RUN: -fcuda-rdc -fcuda-include-gpubinary %t -o - -x hip \
|
|
// RUN: | FileCheck %s --check-prefixes=ALL,RDC,HIP
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s -o - -x hip\
|
|
// RUN: | FileCheck %s -check-prefix=NOGPUBIN
|
|
|
|
#include "Inputs/cuda.h"
|
|
|
|
#ifndef NOGLOBALS
|
|
// ALL-DAG: @device_var = internal global i32
|
|
__device__ int device_var;
|
|
|
|
// ALL-DAG: @constant_var = internal global i32
|
|
__constant__ int constant_var;
|
|
|
|
// ALL-DAG: @shared_var = internal global i32
|
|
__shared__ int shared_var;
|
|
|
|
// Make sure host globals don't get internalized...
|
|
// ALL-DAG: @host_var = global i32
|
|
int host_var;
|
|
// ... and that extern vars remain external.
|
|
// ALL-DAG: @ext_host_var = external global i32
|
|
extern int ext_host_var;
|
|
|
|
// Shadows for external device-side variables are *definitions* of
|
|
// those variables.
|
|
// ALL-DAG: @ext_device_var = internal global i32
|
|
extern __device__ int ext_device_var;
|
|
// ALL-DAG: @ext_device_var = internal global i32
|
|
extern __constant__ int ext_constant_var;
|
|
|
|
void use_pointers() {
|
|
int *p;
|
|
p = &device_var;
|
|
p = &constant_var;
|
|
p = &shared_var;
|
|
p = &host_var;
|
|
p = &ext_device_var;
|
|
p = &ext_constant_var;
|
|
p = &ext_host_var;
|
|
}
|
|
|
|
// Make sure that all parts of GPU code init/cleanup are there:
|
|
// * constant unnamed string with the kernel name
|
|
// ALL: private unnamed_addr constant{{.*}}kernelfunc{{.*}}\00"
|
|
// * constant unnamed string with GPU binary
|
|
// ALL: private unnamed_addr constant{{.*GPU binary would be here.*}}\00"
|
|
// NORDC-SAME: section ".nv_fatbin", align 8
|
|
// RDC-SAME: section "__nv_relfatbin", align 8
|
|
// * constant struct that wraps GPU binary
|
|
// CUDA: @__[[PREFIX:cuda]]_fatbin_wrapper = internal constant
|
|
// CUDA-SAME: { i32, i32, i8*, i8* }
|
|
// HIP: @__[[PREFIX:hip]]_fatbin_wrapper = internal constant
|
|
// HIP-SAME: { i32, i32, i8*, i8* }
|
|
// ALL-SAME: { i32 1180844977, i32 1, {{.*}}, i8* null }
|
|
// ALL-SAME: section ".nvFatBinSegment"
|
|
// * variable to save GPU binary handle after initialization
|
|
// NORDC: @__[[PREFIX]]_gpubin_handle = internal global i8** null
|
|
// * constant unnamed string with NVModuleID
|
|
// RDC: [[MODULE_ID_GLOBAL:@.*]] = private unnamed_addr constant
|
|
// RDC-SAME: c"[[MODULE_ID:.+]]\00", section "__nv_module_id", align 32
|
|
// * Make sure our constructor was added to global ctor list.
|
|
// ALL: @llvm.global_ctors = appending global {{.*}}@__[[PREFIX]]_module_ctor
|
|
// * In separate mode we also register a destructor.
|
|
// NORDC: @llvm.global_dtors = appending global {{.*}}@__[[PREFIX]]_module_dtor
|
|
// * Alias to global symbol containing the NVModuleID.
|
|
// RDC: @__fatbinwrap[[MODULE_ID]] = alias { i32, i32, i8*, i8* }
|
|
// RDC-SAME: { i32, i32, i8*, i8* }* @__[[PREFIX]]_fatbin_wrapper
|
|
|
|
// Test that we build the correct number of calls to cudaSetupArgument followed
|
|
// by a call to cudaLaunch.
|
|
|
|
// ALL: define{{.*}}kernelfunc
|
|
// ALL: call{{.*}}[[PREFIX]]SetupArgument
|
|
// ALL: call{{.*}}[[PREFIX]]SetupArgument
|
|
// ALL: call{{.*}}[[PREFIX]]SetupArgument
|
|
// ALL: call{{.*}}[[PREFIX]]Launch
|
|
__global__ void kernelfunc(int i, int j, int k) {}
|
|
|
|
// Test that we've built correct kernel launch sequence.
|
|
// ALL: define{{.*}}hostfunc
|
|
// ALL: call{{.*}}[[PREFIX]]ConfigureCall
|
|
// ALL: call{{.*}}kernelfunc
|
|
void hostfunc(void) { kernelfunc<<<1, 1>>>(1, 1, 1); }
|
|
#endif
|
|
|
|
// Test that we've built a function to register kernels and global vars.
|
|
// ALL: define internal void @__[[PREFIX]]_register_globals
|
|
// ALL: call{{.*}}[[PREFIX]]RegisterFunction(i8** %0, {{.*}}kernelfunc
|
|
// ALL-DAG: call{{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}device_var{{.*}}i32 0, i32 4, i32 0, i32 0
|
|
// ALL-DAG: call{{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}constant_var{{.*}}i32 0, i32 4, i32 1, i32 0
|
|
// ALL-DAG: call{{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}ext_device_var{{.*}}i32 1, i32 4, i32 0, i32 0
|
|
// ALL-DAG: call{{.*}}[[PREFIX]]RegisterVar(i8** %0, {{.*}}ext_constant_var{{.*}}i32 1, i32 4, i32 1, i32 0
|
|
// ALL: ret void
|
|
|
|
// Test that we've built a constructor.
|
|
// ALL: define internal void @__[[PREFIX]]_module_ctor
|
|
|
|
// In separate mode it calls __[[PREFIX]]RegisterFatBinary(&__[[PREFIX]]_fatbin_wrapper)
|
|
// NORDC: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
|
|
// .. stores return value in __[[PREFIX]]_gpubin_handle
|
|
// NORDC-NEXT: store{{.*}}__[[PREFIX]]_gpubin_handle
|
|
// .. and then calls __[[PREFIX]]_register_globals
|
|
// NORDC-NEXT: call void @__[[PREFIX]]_register_globals
|
|
|
|
// With relocatable device code we call __[[PREFIX]]RegisterLinkedBinary%NVModuleID%
|
|
// RDC: call{{.*}}__[[PREFIX]]RegisterLinkedBinary[[MODULE_ID]](
|
|
// RDC-SAME: __[[PREFIX]]_register_globals, {{.*}}__[[PREFIX]]_fatbin_wrapper
|
|
// RDC-SAME: [[MODULE_ID_GLOBAL]]
|
|
|
|
// Test that we've created destructor.
|
|
// NORDC: define internal void @__[[PREFIX]]_module_dtor
|
|
// NORDC: load{{.*}}__[[PREFIX]]_gpubin_handle
|
|
// NORDC-NEXT: call void @__[[PREFIX]]UnregisterFatBinary
|
|
|
|
// There should be no __[[PREFIX]]_register_globals if we have no
|
|
// device-side globals, but we still need to register GPU binary.
|
|
// Skip GPU binary string first.
|
|
// NOGLOBALS: @0 = private unnamed_addr constant{{.*}}
|
|
// NOGLOBALS-NOT: define internal void @__{{.*}}_register_globals
|
|
// NOGLOBALS: define internal void @__[[PREFIX:.*]]_module_ctor
|
|
// NOGLOBALS: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
|
|
// NOGLOBALS-NOT: call void @__[[PREFIX]]_register_globals
|
|
// NOGLOBALS: define internal void @__[[PREFIX]]_module_dtor
|
|
// NOGLOBALS: call void @__[[PREFIX]]UnregisterFatBinary
|
|
|
|
// There should be no constructors/destructors if we have no GPU binary.
|
|
// NOGPUBIN-NOT: define internal void @__[[PREFIX]]_register_globals
|
|
// NOGPUBIN-NOT: define internal void @__[[PREFIX]]_module_ctor
|
|
// NOGPUBIN-NOT: define internal void @__[[PREFIX]]_module_dtor
|