Skip to content

Merge v0.11.x into main #1314

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.

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
Show file tree
Hide file tree
Changes from all commits
Commits
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
12 changes: 6 additions & 6 deletions .github/workflows/reusable_gpu.yml
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,6 @@ jobs:
name: "${{matrix.os}}, ${{matrix.build_type}}, shared=${{matrix.shared_library}}"
env:
VCPKG_PATH: "${{github.workspace}}/build/vcpkg/packages/hwloc_x64-windows;${{github.workspace}}/build/vcpkg/packages/tbb_x64-windows;${{github.workspace}}/build/vcpkg/packages/jemalloc_x64-windows;"
CUDA_PATH: "C:/cuda"
COVERAGE_NAME : "exports-coverage-${{inputs.provider}}-${{inputs.runner}}"
# run only on upstream; forks will not have the HW
if: github.repository == 'oneapi-src/unified-memory-framework'
Expand All @@ -52,13 +51,14 @@ jobs:

runs-on: ["DSS-${{inputs.runner}}", "DSS-${{matrix.os}}"]
steps:
# Set number of processes and compiler based on OS
# Set various build params based on OS
- name: "[Win] Establish build params"
if : ${{ matrix.os == 'Windows' }}
run: |
echo "C_COMPILER=cl" >> $GITHUB_ENV
echo "CXX_COMPILER=cl" >> $GITHUB_ENV
echo "PROCS=$Env:NUMBER_OF_PROCESSORS" >> $GITHUB_ENV
echo "C_COMPILER=cl" >> $env:GITHUB_ENV
echo "CXX_COMPILER=cl" >> $env:GITHUB_ENV
echo "PROCS=$Env:NUMBER_OF_PROCESSORS" >> $env:GITHUB_ENV
echo "EXTRA_CMAKE_PATH=$Env:CUDA_PATH" >> $env:GITHUB_ENV

- name: "[Lin] Establish build params"
if : ${{ matrix.os == 'Ubuntu' }}
Expand Down Expand Up @@ -93,7 +93,7 @@ jobs:
- name: Configure build
run: >
cmake
-DCMAKE_PREFIX_PATH="${{env.VCPKG_PATH}}${{env.CUDA_PATH}}"
-DCMAKE_PREFIX_PATH="${{env.VCPKG_PATH}};${{env.EXTRA_CMAKE_PATH}}"
-B ${{env.BUILD_DIR}}
-DCMAKE_INSTALL_PREFIX="${{env.INSTL_DIR}}"
-DCMAKE_BUILD_TYPE=${{matrix.build_type}}
Expand Down
7 changes: 7 additions & 0 deletions ChangeLog
Original file line number Diff line number Diff line change
@@ -1,3 +1,10 @@
Mon May 12 2025 Łukasz Stolarczuk <lukasz.stolarczuk@intel.com>

* Version 0.11.2

This patch release contains following changes:
- retrieve numanode object by os index instead of logical index (#1309)

Thu May 08 2025 Łukasz Stolarczuk <lukasz.stolarczuk@intel.com>

* Version 0.11.1
Expand Down
10 changes: 4 additions & 6 deletions src/memtargets/memtarget_numa.c
Original file line number Diff line number Diff line change
Expand Up @@ -263,17 +263,15 @@ static umf_result_t query_attribute_value(void *srcMemoryTarget,
return UMF_RESULT_ERROR_NOT_SUPPORTED;
}

hwloc_obj_t srcNumaNode = hwloc_get_obj_by_type(
topology, HWLOC_OBJ_NUMANODE,
((struct numa_memtarget_t *)srcMemoryTarget)->physical_id);
hwloc_obj_t srcNumaNode = hwloc_get_numanode_obj_by_os_index(
topology, ((struct numa_memtarget_t *)srcMemoryTarget)->physical_id);
if (!srcNumaNode) {
LOG_PERR("Getting HWLOC object by type failed");
return UMF_RESULT_ERROR_INVALID_ARGUMENT;
}

hwloc_obj_t dstNumaNode = hwloc_get_obj_by_type(
topology, HWLOC_OBJ_NUMANODE,
((struct numa_memtarget_t *)dstMemoryTarget)->physical_id);
hwloc_obj_t dstNumaNode = hwloc_get_numanode_obj_by_os_index(
topology, ((struct numa_memtarget_t *)dstMemoryTarget)->physical_id);
if (!dstNumaNode) {
LOG_PERR("Getting HWLOC object by type failed");
return UMF_RESULT_ERROR_INVALID_ARGUMENT;
Expand Down
Loading