OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity

[OpenMP][CUDA] Keep one kernel list per device, not globally. 

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D86039
This commit is contained in:
Johannes Doerfert 2020-08-16 11:00:33 -05:00
parent aa27cfc1e7
commit 5272d29e2c
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
openmp/libomptarget/plugins/cuda/src/rtl.cpp
View File

@ -89,10 +89,6 @@ struct omptarget_device_environmentTy {
int32_t debug_level;
};
/// List that contains all the kernels.
/// FIXME: we may need this to be per device and per library.
std::list<KernelTy> KernelsList;
namespace {
bool checkResult(CUresult Err, const char *ErrMsg) {
if (Err == CUDA_SUCCESS)
@ -121,7 +117,11 @@ int memcpyDtoD(const void *SrcPtr, void *DstPtr, int64_t Size,
// Structure contains per-device data
struct DeviceDataTy {
/// List that contains all the kernels.
std::list<KernelTy> KernelsList;
std::list<FuncOrGblEntryTy> FuncGblEntries;
CUcontext Context = nullptr;
// Device properties
int ThreadsPerBlock = 0;
@ -568,6 +568,7 @@ public:
const __tgt_offload_entry *HostBegin = Image->EntriesBegin;
const __tgt_offload_entry *HostEnd = Image->EntriesEnd;
std::list<KernelTy> &KernelsList = DeviceData[DeviceId].KernelsList;
for (const __tgt_offload_entry *E = HostBegin; E != HostEnd; ++E) {
if (!E->addr) {
// We return nullptr when something like this happens, the host should