Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

retry GPU memory allocation if fragmented #16194

Merged
merged 1 commit into from
Sep 18, 2019
Merged

retry GPU memory allocation if fragmented #16194

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 20 additions & 4 deletions src/storage/pooled_storage_manager.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,8 +153,16 @@ void GPUPooledStorageManager::Alloc(Storage::Handle* handle) {

void* ret = nullptr;
cudaError_t e = cudaMalloc(&ret, size);
if (e != cudaSuccess && e != cudaErrorCudartUnloading) {
LOG(FATAL) << "cudaMalloc failed: " << cudaGetErrorString(e);
if (e != cudaSuccess) {
if (e == cudaErrorMemoryAllocation) {
ReleaseAll();
e = cudaMalloc(&ret, size);
if (e != cudaSuccess && e != cudaErrorCudartUnloading) {
LOG(FATAL) << "cudaMalloc retry failed: " << cudaGetErrorString(e);
}
} else if (e != cudaErrorCudartUnloading) {
LOG(FATAL) << "cudaMalloc failed: " << cudaGetErrorString(e);
}
}
used_memory_ += size;
handle->dptr = ret;
Expand Down Expand Up @@ -328,8 +336,16 @@ void GPUPooledRoundedStorageManager::Alloc(Storage::Handle* handle) {

void* ret = nullptr;
cudaError_t e = cudaMalloc(&ret, size);
if (e != cudaSuccess && e != cudaErrorCudartUnloading) {
LOG(FATAL) << "cudaMalloc failed: " << cudaGetErrorString(e);
if (e != cudaSuccess) {
if (e == cudaErrorMemoryAllocation) {
ReleaseAll();
e = cudaMalloc(&ret, size);
if (e != cudaSuccess && e != cudaErrorCudartUnloading) {
LOG(FATAL) << "cudaMalloc retry failed: " << cudaGetErrorString(e);
}
} else if (e != cudaErrorCudartUnloading) {
LOG(FATAL) << "cudaMalloc failed: " << cudaGetErrorString(e);
}
}
used_memory_ += size;
handle->dptr = ret;
Expand Down