Skip to content

Fix memory allocation bug to use the correct hipDevice #308

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

Open
nileshnegi wants to merge 3 commits into
base: candidate
Choose a base branch
from
+11 −6
Open

Fix memory allocation bug to use the correct hipDevice #308

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9ed4506
Fix memory allocation bug to use the correct hipDevice
nileshnegi May 19, 2026
625ed6c
Fix NUMA policy leak, redundant hipSetDevice, and device-guard gaps
nileshnegi May 20, 2026
7b8f335
Update bug fix
nileshnegi May 20, 2026
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
17 changes: 11 additions & 6 deletions src/header/TransferBench.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1495,6 +1495,15 @@ namespace {
deviceIdx = GetClosestCpuNumaToGpu(memDevice.memIndex);
}

if (IsCpuMemType(memType)) {
// Set NUMA policy prior to call to hipHostMalloc
numa_set_preferred(deviceIdx);
} else if (IsGpuMemType(memType)) {
Comment on lines +1498 to +1501
// Switch to the appropriate GPU
// IMP: if the remapping above changes, remember to modify this!
ERR_CHECK(hipSetDevice(deviceIdx));
}
Comment thread
nileshnegi marked this conversation as resolved.
Comment on lines +1498 to +1505

// If memHandle is provided, allocate sharable memory
if (memHandle != NULL) {
#ifdef POD_COMM_ENABLED
Expand Down Expand Up @@ -1532,13 +1541,14 @@ namespace {
memset(*memPtr, 0, roundedUpBytes);
// Check that the allocated pages are actually on the correct NUMA node
ERR_CHECK(CheckPages((char*)*memPtr, roundedUpBytes, deviceIdx));
numa_set_preferred(-1);
} else if (IsGpuMemType(memType)) {
ERR_CHECK(hipSetDevice(memDevice.memIndex));
ERR_CHECK(hipMemset(*memPtr, 0, numBytes));
ERR_CHECK(hipDeviceSynchronize());
}
return ERR_NONE;
#else
if (IsCpuMemType(memType)) numa_set_preferred(-1);
return {ERR_FATAL, "Unable to allocate sharable memory if not compiled with pod communication support"};
#endif
} else {
Expand All @@ -1547,9 +1557,6 @@ namespace {

if (IsCpuMemType(memType)) {

// Set NUMA policy prior to call to hipHostMalloc
numa_set_preferred(deviceIdx);

// Allocate host-pinned memory (should respect NUMA mem policy)
int flags = 0;
#if !defined (__NVCC__)
Expand Down Expand Up @@ -1590,8 +1597,6 @@ namespace {
// Reset to default numa mem policy
numa_set_preferred(-1);
} else if (IsGpuMemType(memType)) {
// Switch to the appropriate GPU
ERR_CHECK(hipSetDevice(memDevice.memIndex));

if (memType == MEM_GPU) {
// Allocate GPU memory on appropriate device
Expand Down