Skip to content

Fix for multinode #65

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 11, 2024
Merged

Fix for multinode #65

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ed14d41
fix for multinode
Sep 26, 2024
924ad64
one more fix
Oct 11, 2024
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
22 changes: 18 additions & 4 deletions plugin/sycl/device_manager.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,18 +20,25 @@ ::sycl::device DeviceManager::GetDevice(const DeviceOrd& device_spec) const {
(collective::IsDistributed());
if (not_use_default_selector) {
DeviceRegister& device_register = GetDevicesRegister();
const int device_idx =
collective::IsDistributed() ? collective::GetRank() : device_spec.ordinal;
if (device_spec.IsSyclDefault()) {
auto& devices = device_register.devices;
const int device_idx = collective::IsDistributed()
? collective::GetRank() % devices.size()
: device_spec.ordinal;
CHECK_LT(device_idx, devices.size());
return devices[device_idx];
} else if (device_spec.IsSyclCPU()) {
auto& cpu_devices = device_register.cpu_devices;
const int device_idx = collective::IsDistributed()
? collective::GetRank() % cpu_devices.size()
: device_spec.ordinal;
CHECK_LT(device_idx, cpu_devices.size());
return cpu_devices[device_idx];
} else {
auto& gpu_devices = device_register.gpu_devices;
const int device_idx = collective::IsDistributed()
? collective::GetRank() % gpu_devices.size()
: device_spec.ordinal;
CHECK_LT(device_idx, gpu_devices.size());
return gpu_devices[device_idx];
}
Expand Down Expand Up @@ -63,18 +70,25 @@ ::sycl::queue DeviceManager::GetQueue(const DeviceOrd& device_spec) const {
std::lock_guard<std::mutex> guard(queue_registering_mutex);
if (not_use_default_selector) {
DeviceRegister& device_register = GetDevicesRegister();
const int device_idx =
collective::IsDistributed() ? collective::GetRank() : device_spec.ordinal;
if (device_spec.IsSyclDefault()) {
auto& devices = device_register.devices;
const int device_idx = collective::IsDistributed()
? collective::GetRank() % devices.size()
: device_spec.ordinal;
CHECK_LT(device_idx, devices.size());
queue_register[device_spec.Name()] = ::sycl::queue(devices[device_idx]);
} else if (device_spec.IsSyclCPU()) {
auto& cpu_devices = device_register.cpu_devices;
const int device_idx = collective::IsDistributed()
? collective::GetRank() % cpu_devices.size()
: device_spec.ordinal;
CHECK_LT(device_idx, cpu_devices.size());
queue_register[device_spec.Name()] = ::sycl::queue(cpu_devices[device_idx]);
} else if (device_spec.IsSyclGPU()) {
auto& gpu_devices = device_register.gpu_devices;
const int device_idx = collective::IsDistributed()
? collective::GetRank() % gpu_devices.size()
: device_spec.ordinal;
CHECK_LT(device_idx, gpu_devices.size());
queue_register[device_spec.Name()] = ::sycl::queue(gpu_devices[device_idx]);
}
Expand Down
Loading