Skip to content

Fixing nearest GPU numa detection #305

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
gilbertlee-amd merged 1 commit into from
May 19, 2026
Merged

Fixing nearest GPU numa detection #305

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
28 changes: 13 additions & 15 deletions src/header/TransferBench.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7776,21 +7776,6 @@ static bool IsConfiguredGid(union ibv_gid const& gid)
return HSA_STATUS_SUCCESS;
};

// Index CPU agents
hsa_init();
std::map<int, hsa_agent_t> cpuAgentMap;
hsa_iterate_agents(cpuAgentCallback, &cpuAgentMap);
hsa_shut_down();

cpuAgents.clear();
int numCpus = numa_num_configured_nodes();
cpuAgents.resize(numCpus);
for (int i = 0; i < numCpus; i++) {
if (cpuAgentMap.count(i)) {
cpuAgents[i] = cpuAgentMap[i];
}
}

// Index GPU agents
int numGpus = 0;
hipError_t status = hipGetDeviceCount(&numGpus);
Expand All @@ -7803,6 +7788,19 @@ static bool IsConfiguredGid(union ibv_gid const& gid)
gpuAgents.push_back(info.agentOwner);
DeallocateMemory(MEM_GPU, tempBuffer, 1024);
}

// Index CPU agents (done after HIP initialization)
std::map<int, hsa_agent_t> cpuAgentMap;
hsa_iterate_agents(cpuAgentCallback, &cpuAgentMap);

Comment thread
gilbertlee-amd marked this conversation as resolved.
cpuAgents.clear();
int numCpus = numa_num_configured_nodes();
Comment thread
gilbertlee-amd marked this conversation as resolved.
cpuAgents.resize(numCpus);
for (int i = 0; i < numCpus; i++) {
if (cpuAgentMap.count(i)) {
cpuAgents[i] = cpuAgentMap[i];
}
}
}
#endif

Expand Down