generated from mlcommons/mlperf_inference_submissions
-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
b37d72e
commit d43776c
Showing
23 changed files
with
16,603 additions
and
0 deletions.
There are no files selected for viewing
37 changes: 37 additions & 0 deletions
37
closed/MLCommons/systems/mlc-server-reference-gpu-pytorch_v2.4.0-cu124.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,37 @@ | ||
| { | ||
| "accelerator_frequency": "1980000 MHz", | ||
| "accelerator_host_interconnect": "N/A", | ||
| "accelerator_interconnect": "N/A", | ||
| "accelerator_interconnect_topology": "", | ||
| "accelerator_memory_capacity": "79.09661865234375 GB", | ||
| "accelerator_memory_configuration": "N/A", | ||
| "accelerator_model_name": "NVIDIA H100 80GB HBM3", | ||
| "accelerator_on-chip_memories": "", | ||
| "accelerators_per_node": 8, | ||
| "cooling": "air", | ||
| "division": "closed", | ||
| "framework": "pytorch v2.4.0", | ||
| "host_memory_capacity": "2.1T", | ||
| "host_memory_configuration": "undefined", | ||
| "host_network_card_count": "1", | ||
| "host_networking": "Gig Ethernet", | ||
| "host_networking_topology": "N/A", | ||
| "host_processor_caches": "L1d cache: 5.3 MiB (112 instances), L1i cache: 3.5 MiB (112 instances), L2 cache: 224 MiB (112 instances), L3 cache: 210 MiB (2 instances)", | ||
| "host_processor_core_count": "56", | ||
| "host_processor_frequency": "2001.0000", | ||
| "host_processor_interconnect": "", | ||
| "host_processor_model_name": "Intel(R) Xeon(R) Platinum 8480+", | ||
| "host_processors_per_node": "2", | ||
| "host_storage_capacity": "19T", | ||
| "host_storage_type": "SSD", | ||
| "hw_notes": "", | ||
| "number_of_nodes": "1", | ||
| "operating_system": "Ubuntu 22.04 (linux-5.15.0-113-generic-glibc2.35)", | ||
| "other_software_stack": "Python: 3.10.12, LLVM-15.0.6 , CUDA 12.4", | ||
| "status": "available", | ||
| "submitter": "MLCommons", | ||
| "sw_notes": "", | ||
| "system_name": "5234c0b61ae3", | ||
| "system_type": "datacenter", | ||
| "system_type_detail": "edge server" | ||
| } |
55 changes: 55 additions & 0 deletions
55
...asurements/mlc-server-reference-gpu-pytorch_v2.4.0-cu124/rgat/offline/README.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,55 @@ | ||
| *Check [CM MLPerf docs](https://docs.mlcommons.org/inference) for more details.* | ||
|
|
||
| ## Host platform | ||
|
|
||
| * OS version: Linux-5.15.0-113-generic-x86_64-with-glibc2.35 | ||
| * CPU version: x86_64 | ||
| * Python version: 3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0] | ||
| * MLCommons CM version: 3.5.2 | ||
|
|
||
| ## CM Run Command | ||
|
|
||
| See [CM installation guide](https://docs.mlcommons.org/inference/install/). | ||
|
|
||
| ```bash | ||
| pip install -U cmind | ||
|
|
||
| cm rm cache -f | ||
|
|
||
| cm pull repo mlcommons@mlperf-automations --checkout=86f785f2f02ddcbfb4ab4d997ea914e516cc94aa | ||
|
|
||
| cm run script \ | ||
| --tags=run-mlperf,inference,_r5.0-dev,_full \ | ||
| --model=rgat \ | ||
| --implementation=reference \ | ||
| --framework=pytorch \ | ||
| --category=datacenter \ | ||
| --scenario=Offline \ | ||
| --execution_mode=valid \ | ||
| --device=cuda \ | ||
| --quiet \ | ||
| --threads=2 \ | ||
| --batch_size=2048 \ | ||
| --division=closed | ||
| ``` | ||
| *Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf (CM scripts), | ||
| you should simply reload mlcommons@mlperf-automations without checkout and clean CM cache as follows:* | ||
|
|
||
| ```bash | ||
| cm rm repo mlcommons@mlperf-automations | ||
| cm pull repo mlcommons@mlperf-automations | ||
| cm rm cache -f | ||
|
|
||
| ``` | ||
|
|
||
| ## Results | ||
|
|
||
| Platform: mlc-server-reference-gpu-pytorch_v2.4.0-cu124 | ||
|
|
||
| Model Precision: fp32 | ||
|
|
||
| ### Accuracy Results | ||
| `acc`: `72.813`, Required accuracy for closed division `>= 0.72131` | ||
|
|
||
| ### Performance Results | ||
| `Samples per second`: `316.253` |
10 changes: 10 additions & 0 deletions
10
...surements/mlc-server-reference-gpu-pytorch_v2.4.0-cu124/rgat/offline/accuracy_console.out
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,10 @@ | ||
| INFO:main:Namespace(dataset='igbh-dgl', dataset_path='/cm-mount/data/common/anandhu/igbh', in_memory=False, layout='COO', profile='rgat-dgl-full', scenario='Offline', max_batchsize=2048, threads=2, accuracy=True, find_peak_performance=False, backend='dgl', model_name='rgat', output='/root/CM/repos/local/cache/e1d5c35e70ca49ae/valid_results/5234c0b61ae3-reference-gpu-pytorch-v2.4.0-cu124/rgat/offline/accuracy', qps=None, model_path='/root/CM/repos/local/cache/26842ad3f07d429f/RGAT/RGAT.pt', dtype='fp32', device='gpu', user_conf='/root/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/780b56120abd46ca9c5312477a2cb8f1.conf', audit_conf='audit.config', time=None, count=None, debug=False, performance_sample_count=5000, max_latency=None, samples_per_query=8) | ||
| /root/CM/repos/local/cache/6793a301c9ee436d/inference/graph/R-GAT/dgl_utilities/feature_fetching.py:231: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:206.) | ||
| return edge, torch.from_numpy( | ||
| /root/CM/repos/local/cache/6793a301c9ee436d/inference/graph/R-GAT/dgl_utilities/feature_fetching.py:312: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. | ||
| torch.load( | ||
| /root/CM/repos/local/cache/6793a301c9ee436d/inference/graph/R-GAT/dgl_utilities/feature_fetching.py:318: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. | ||
| torch.load( | ||
| /root/CM/repos/local/cache/6793a301c9ee436d/inference/graph/R-GAT/backend_dgl.py:70: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. | ||
| ckpt = torch.load(ckpt_path, map_location=self.device) | ||
| INFO:main:starting TestScenario.Offline |
75 changes: 75 additions & 0 deletions
75
...mmons/measurements/mlc-server-reference-gpu-pytorch_v2.4.0-cu124/rgat/offline/cm-deps.mmd
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,75 @@ | ||
| graph TD | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_rgat,_pytorch,_cuda,_valid,_r5.0-dev_default,_offline_) --> detect,os | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_rgat,_pytorch,_cuda,_valid,_r5.0-dev_default,_offline_) --> get,sys-utils-cm | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_rgat,_pytorch,_cuda,_valid,_r5.0-dev_default,_offline_) --> get,python | ||
| get-mlperf-inference-src,4b57186581024797 --> detect,os | ||
| get-mlperf-inference-src,4b57186581024797 --> get,python3 | ||
| get-mlperf-inference-src,4b57186581024797 --> get,git,repo,_branch.master,_repo.https://github.com/mlcommons/inference | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_rgat,_pytorch,_cuda,_valid,_r5.0-dev_default,_offline_) --> get,mlcommons,inference,src | ||
| get-mlperf-inference-src,4b57186581024797 --> detect,os | ||
| get-mlperf-inference-src,4b57186581024797 --> get,python3 | ||
| get-mlperf-inference-src,4b57186581024797 --> get,git,repo,_branch.master,_repo.https://github.com/mlcommons/inference | ||
| get-mlperf-inference-utils,e341e5f86d8342e5 --> get,mlperf,inference,src | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_rgat,_pytorch,_cuda,_valid,_r5.0-dev_default,_offline_) --> get,mlperf,inference,utils | ||
| get-cuda-devices,7a3ede4d3558427a_(_with-pycuda_) --> get,cuda,_toolkit | ||
| get-cuda-devices,7a3ede4d3558427a_(_with-pycuda_) --> get,python3 | ||
| get-generic-python-lib,94b62a682bc44791_(_package.pycuda_) --> get,python3 | ||
| get-cuda-devices,7a3ede4d3558427a_(_with-pycuda_) --> get,generic-python-lib,_package.pycuda | ||
| get-generic-python-lib,94b62a682bc44791_(_package.numpy_) --> get,python3 | ||
| get-cuda-devices,7a3ede4d3558427a_(_with-pycuda_) --> get,generic-python-lib,_package.numpy | ||
| app-mlperf-inference,d775cac873ee4231_(_reference,_rgat,_pytorch,_cuda,_valid,_r5.0-dev_default,_offline_) --> get,cuda-devices,_with-pycuda | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> detect,os | ||
| detect-cpu,586c8a43320142f7 --> detect,os | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> detect,cpu | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,sys-utils-cm | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,python | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,cuda,_cudnn | ||
| get-generic-python-lib,94b62a682bc44791_(_torch_cuda_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_torch_cuda | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,ml-model,rgat | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,dataset,mlperf,inference,igbh,_full | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> detect,os | ||
| detect-cpu,586c8a43320142f7 --> detect,os | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> detect,cpu | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> get,python | ||
| get-mlperf-inference-src,4b57186581024797 --> detect,os | ||
| get-mlperf-inference-src,4b57186581024797 --> get,python3 | ||
| get-mlperf-inference-src,4b57186581024797 --> get,git,repo,_branch.master,_repo.https://github.com/mlcommons/inference | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> get,mlcommons,inference,src | ||
| get-mlperf-inference-sut-configs,c2fbf72009e2445b --> get,cache,dir,_name.mlperf-inference-sut-configs | ||
| generate-mlperf-inference-user-conf,3af4475745964b93 --> get,sut,configs | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> generate,user-conf,mlperf,inference | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,loadgen | ||
| get-mlperf-inference-src,4b57186581024797 --> detect,os | ||
| get-mlperf-inference-src,4b57186581024797 --> get,python3 | ||
| get-mlperf-inference-src,4b57186581024797 --> get,git,repo,_branch.master,_repo.https://github.com/mlcommons/inference | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,mlcommons,inference,src | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,mlcommons,inference,src | ||
| get-generic-python-lib,94b62a682bc44791_(_package.psutil_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.psutil | ||
| get-generic-python-lib,94b62a682bc44791_(_package.colorama_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.colorama | ||
| get-generic-python-lib,94b62a682bc44791_(_package.tqdm_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.tqdm | ||
| get-generic-python-lib,94b62a682bc44791_(_package.requests_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.requests | ||
| get-generic-python-lib,94b62a682bc44791_(_package.torchdata_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.torchdata | ||
| get-generic-python-lib,94b62a682bc44791_(_package.pybind11_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.pybind11 | ||
| get-generic-python-lib,94b62a682bc44791_(_package.PyYAML_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.PyYAML | ||
| get-generic-python-lib,94b62a682bc44791_(_package.numpy_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.numpy | ||
| get-generic-python-lib,94b62a682bc44791_(_package.pydantic_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.pydantic | ||
| get-generic-python-lib,94b62a682bc44791_(_package.igb,_url.git+https://github.com/IllinoisGraphBenchmark/IGB-Datasets.git_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.igb,_url.git+https://github.com/IllinoisGraphBenchmark/IGB-Datasets.git | ||
| get-generic-python-lib,94b62a682bc44791_(_package.torch-geometric,_find_links_url.https://data.pyg.org/whl/torch-2.4.0.html_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.torch-geometric,_find_links_url.https://data.pyg.org/whl/torch-2.4.0.html | ||
| get-generic-python-lib,94b62a682bc44791_(_package.torch-scatter,_find_links_url.https://data.pyg.org/whl/torch-2.4.0.html_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.torch-scatter,_find_links_url.https://data.pyg.org/whl/torch-2.4.0.html | ||
| get-generic-python-lib,94b62a682bc44791_(_package.torch-sparse,_find_links_url.https://data.pyg.org/whl/torch-2.4.0.html_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.torch-sparse,_find_links_url.https://data.pyg.org/whl/torch-2.4.0.html | ||
| get-generic-python-lib,94b62a682bc44791_(_package.dgl,_find_links_url.https://data.dgl.ai/wheels/torch-2.4/cu121/repo.html_) --> get,python3 | ||
| app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_batch_size.2048,_pytorch,_cuda,_offline,_rgat,_fp32_) --> get,generic-python-lib,_package.dgl,_find_links_url.https://data.dgl.ai/wheels/torch-2.4/cu121/repo.html |
Binary file added
BIN
+4.58 MB
...urements/mlc-server-reference-gpu-pytorch_v2.4.0-cu124/rgat/offline/cm-deps.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Oops, something went wrong.