Skip to content
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

Jump to bottom

replaced numa with py-libnuma to work w python 3.11 #900

Merged
merged 2 commits into from
Sep 16, 2024
Merged

replaced numa with py-libnuma to work w python 3.11 #900

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c9eafb6
replaced numa with py-libnuma to work w python 3.11
rbrugaro Sep 13, 2024
200df00
update Dockerfile dependencies
rbrugaro Sep 13, 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
4 changes: 1 addition & 3 deletions docker/Dockerfile.intel
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,8 +27,6 @@ RUN --mount=type=cache,id=apt-dev,target=/var/cache/apt \
libpng-dev \
python3 \
python3-pip \
python3-dev \
libnuma-dev \
&& rm -rf /var/lib/apt/lists/*"
RUN /usr/sbin/update-ccache-symlinks
RUN mkdir /opt/ccache && ccache --set-config=cache_dir=/opt/ccache
Expand All @@ -46,7 +44,7 @@ RUN python3 -m pip install --no-cache-dir \
-f https://download.pytorch.org/whl/torch_stable.html && \
python3 -m pip install intel-extension-for-pytorch==$IPEX_VERSION && \
python3 -m pip install oneccl_bind_pt --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/ && \
python3 -m pip install --no-cache-dir numa
python3 -m pip install --no-cache-dir py-libnuma

ARG KMP_BLOCKTIME=1
ENV KMP_BLOCKTIME=${KMP_BLOCKTIME}
Expand Down
2 changes: 1 addition & 1 deletion optimum/intel/utils/import_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,7 @@

if _numa_available:
try:
importlib_metadata.version("numa")
importlib_metadata.version("py-libnuma")
except importlib_metadata.PackageNotFoundError:
_numa_available = False

Expand Down
16 changes: 8 additions & 8 deletions optimum/intel/utils/modeling_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,7 @@ def bind_cores_for_best_perf():
raise OSError("bind_cores_for_best_perf: OS not supported, this function can only be run on Linux systems.")
if not is_numa_available():
logger.error("'numa' module not found")
raise ImportError("'numa' module not found, install with 'pip install numa'")
raise ImportError("'numa' module not found, install with 'pip install py-libnuma'")
import numa

local_size = get_int_from_env(
Expand All @@ -201,7 +201,7 @@ def bind_cores_for_best_perf():
rank_id = get_int_from_env(
["LOCAL_RANK", "MPI_LOCALRANKID", "OMPI_COMM_WORLD_LOCAL_RANK", "MV2_COMM_WORLD_LOCAL_RANK"], 0
)
nodes = numa.get_max_node() + 1
nodes = numa.info.get_max_node() + 1
rank_per_node = math.ceil(local_size / nodes)
num_cpus_per_nodes = int(psutil.cpu_count(logical=False) / nodes)
node_id = int(rank_id / rank_per_node)
Expand All @@ -212,17 +212,17 @@ def bind_cores_for_best_perf():
else:
num_cpus_per_rank = int(os.getenv("OMP_NUM_THREADS"))
logger.info(f"OMP_NUM_THREADS already set to {num_cpus_per_rank}")
if len(numa.get_membind()) == nodes:
if len(numa.memory.get_membind_nodes()) == nodes:
# if numa memory binding is not set, set it to the node where the rank is running
numa.set_membind([node_id])
numa.memory.set_membind_nodes((node_id))

torch.set_num_threads(num_cpus_per_rank)

if len(numa.get_affinity(0)) == psutil.cpu_count(logical=True):
if len(numa.schedule.get_affinitive_cpus(0)) == psutil.cpu_count(logical=True):
# if numa affinity is unset (default value is set to all logical cores) set it to the physical cores assigned to the rank
cpu_start = num_cpus_per_rank * rank_offset_per_node
numa.set_affinity(
numa.schedule.run_on_cpus(
0,
list(numa.node_to_cpus(node_id))[cpu_start : cpu_start + num_cpus_per_rank],
*(numa.info.node_to_cpus(node_id)[cpu_start : cpu_start + num_cpus_per_rank]),
)
logger.info(f"affinity={numa.get_affinity(0)}, membind = {numa.get_membind()}")
logger.info(f"affinity={numa.schedule.get_affinitive_cpus(0)}, membind = {numa.memory.get_membind_nodes()}")
Loading