Results from GH action on NVIDIA_RTX4090x1

closed/MLCommons/code/retinanet/README.md

@@ -0,0 +1 @@
+TBD

closed/MLCommons/systems/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config.json

@@ -1,9 +1,9 @@
 {
-  "accelerator_frequency": "2610000 MHz",
+  "accelerator_frequency": "2520000 MHz",
   "accelerator_host_interconnect": "N/A",
   "accelerator_interconnect": "N/A",
   "accelerator_interconnect_topology": "",
-  "accelerator_memory_capacity": "23.54595947265625 GB",
+  "accelerator_memory_capacity": "23.64971923828125 GB",
   "accelerator_memory_configuration": "N/A",
   "accelerator_model_name": "NVIDIA GeForce RTX 4090",
   "accelerator_on-chip_memories": "",
@@ -16,17 +16,17 @@
   "host_network_card_count": "1",
   "host_networking": "Gig Ethernet",
   "host_networking_topology": "N/A",
-  "host_processor_caches": "L1d cache: 512 KiB, L1i cache: 512 KiB, L2 cache: 16 MiB, L3 cache: 64 MiB",
-  "host_processor_core_count": "16",
-  "host_processor_frequency": "5881.0000",
+  "host_processor_caches": "L1d cache: 576 KiB, L1i cache: 384 KiB, L2 cache: 24 MiB, L3 cache:  ",
+  "host_processor_core_count": "24",
+  "host_processor_frequency": "5800.0000",
   "host_processor_interconnect": "",
-  "host_processor_model_name": "AMD Ryzen 9 7950X 16-Core Processor",
+  "host_processor_model_name": "13th Gen Intel(R) Core(TM) i9-13900K",
   "host_processors_per_node": "1",
-  "host_storage_capacity": "6.8T",
+  "host_storage_capacity": "9.4T",
   "host_storage_type": "SSD",
   "hw_notes": "",
   "number_of_nodes": "1",
-  "operating_system": "Ubuntu 20.04 (linux-6.8.0-51-generic-glibc2.31)",
+  "operating_system": "Ubuntu 20.04 (linux-6.8.0-49-generic-glibc2.31)",
   "other_software_stack": "Python: 3.8.10, GCC-9.4.0, Using Docker  , CUDA 12.2",
   "status": "available",
   "submitter": "MLCommons",

open/MLCommons/code/retinanet/README.md

@@ -0,0 +1 @@
+TBD

open/MLCommons/measurements/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/retinanet/multistream/README.md

@@ -0,0 +1,135 @@
+This experiment is generated using the [MLCommons Collective Mind automation framework (CM)](https://github.com/mlcommons/cm4mlops).
+
+*Check [CM MLPerf docs](https://docs.mlcommons.org/inference) for more details.*
+
+## Host platform
+
+* OS version: Linux-6.8.0-49-generic-x86_64-with-glibc2.29
+* CPU version: x86_64
+* Python version: 3.8.10 (default, Nov  7 2024, 13:10:47) 
+[GCC 9.4.0]
+* 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=225220c7d9bb7e66e5b9a1e1ebfc3e0180fbd094
+
+cm run script \
+	--tags=app,mlperf,inference,generic,_nvidia,_retinanet,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream \
+	--quiet=true \
+	--env.CM_QUIET=yes \
+	--env.CM_MLPERF_IMPLEMENTATION=nvidia \
+	--env.CM_MLPERF_MODEL=retinanet \
+	--env.CM_MLPERF_RUN_STYLE=valid \
+	--env.CM_MLPERF_SKIP_SUBMISSION_GENERATION=False \
+	--env.CM_DOCKER_PRIVILEGED_MODE=True \
+	--env.CM_MLPERF_BACKEND=tensorrt \
+	--env.CM_MLPERF_SUBMISSION_SYSTEM_TYPE=datacenter,edge \
+	--env.CM_MLPERF_CLEAN_ALL=True \
+	--env.CM_MLPERF_DEVICE=cuda \
+	--env.CM_MLPERF_SUBMISSION_DIVISION=closed \
+	--env.CM_MLPERF_USE_DOCKER=True \
+	--env.CM_NVIDIA_GPU_NAME=rtx_4090 \
+	--env.CM_HW_NAME=RTX4090x1 \
+	--env.CM_RUN_MLPERF_SUBMISSION_PREPROCESSOR=yes \
+	--env.CM_MLPERF_INFERENCE_PULL_CODE_CHANGES=yes \
+	--env.CM_MLPERF_INFERENCE_PULL_SRC_CHANGES=yes \
+	--env.OUTPUT_BASE_DIR=/home/arjun/gh_action_results \
+	--env.CM_MLPERF_INFERENCE_SUBMISSION_DIR=/home/arjun/gh_action_submissions \
+	--env.CM_MLPERF_SUBMITTER=MLCommons \
+	--env.CM_USE_DATASET_FROM_HOST=yes \
+	--env.CM_USE_MODEL_FROM_HOST=yes \
+	--env.CM_MLPERF_LOADGEN_ALL_SCENARIOS=yes \
+	--env.CM_MLPERF_LOADGEN_COMPLIANCE=yes \
+	--env.CM_MLPERF_SUBMISSION_RUN=yes \
+	--env.CM_RUN_MLPERF_ACCURACY=on \
+	--env.CM_RUN_SUBMISSION_CHECKER=yes \
+	--env.CM_TAR_SUBMISSION_DIR=yes \
+	--env.CM_MLPERF_SUBMISSION_GENERATION_STYLE=full \
+	--env.CM_MLPERF_INFERENCE_VERSION=4.1-dev \
+	--env.CM_RUN_MLPERF_INFERENCE_APP_DEFAULTS=r4.1-dev_default \
+	--env.CM_MLPERF_LOADGEN_ALL_MODES=yes \
+	--env.CM_MLPERF_INFERENCE_SOURCE_VERSION=4.1.23 \
+	--env.CM_MLPERF_LAST_RELEASE=v4.1 \
+	--env.CM_TMP_PIP_VERSION_STRING= \
+	--env.CM_MODEL=retinanet \
+	--env.CM_MLPERF_CLEAN_SUBMISSION_DIR=yes \
+	--env.CM_RERUN=yes \
+	--env.CM_MLPERF_LOADGEN_EXTRA_OPTIONS= \
+	--env.CM_MLPERF_LOADGEN_MODE=performance \
+	--env.CM_MLPERF_LOADGEN_SCENARIO=MultiStream \
+	--env.CM_MLPERF_LOADGEN_SCENARIOS,=SingleStream,Offline,MultiStream,Server \
+	--env.CM_MLPERF_LOADGEN_MODES,=performance,accuracy \
+	--env.CM_OUTPUT_FOLDER_NAME=valid_results \
+	--env.CM_DOCKER_REUSE_EXISTING_CONTAINER=yes \
+	--env.CM_DOCKER_DETACHED_MODE=yes \
+	--env.CM_MLPERF_INFERENCE_RESULTS_DIR_=/home/arjun/gh_action_results/valid_results \
+	--env.CM_DOCKER_CONTAINER_ID=363b93e2602b \
+	--env.CM_MLPERF_LOADGEN_COMPLIANCE_TEST=TEST01 \
+	--add_deps_recursive.compiler.tags=gcc \
+	--add_deps_recursive.coco2014-original.tags=_full \
+	--add_deps_recursive.coco2014-preprocessed.tags=_full \
+	--add_deps_recursive.imagenet-original.tags=_full \
+	--add_deps_recursive.imagenet-preprocessed.tags=_full \
+	--add_deps_recursive.openimages-original.tags=_full \
+	--add_deps_recursive.openimages-preprocessed.tags=_full \
+	--add_deps_recursive.openorca-original.tags=_full \
+	--add_deps_recursive.openorca-preprocessed.tags=_full \
+	--add_deps_recursive.coco2014-dataset.tags=_full \
+	--add_deps_recursive.igbh-dataset.tags=_full \
+	--add_deps_recursive.get-mlperf-inference-results-dir.tags=_version.r4_1-dev \
+	--add_deps_recursive.get-mlperf-inference-submission-dir.tags=_version.r4_1-dev \
+	--add_deps_recursive.mlperf-inference-nvidia-scratch-space.tags=_version.r4_1-dev \
+	--adr.compiler.tags=gcc \
+	--adr.coco2014-original.tags=_full \
+	--adr.coco2014-preprocessed.tags=_full \
+	--adr.imagenet-original.tags=_full \
+	--adr.imagenet-preprocessed.tags=_full \
+	--adr.openimages-original.tags=_full \
+	--adr.openimages-preprocessed.tags=_full \
+	--adr.openorca-original.tags=_full \
+	--adr.openorca-preprocessed.tags=_full \
+	--adr.coco2014-dataset.tags=_full \
+	--adr.igbh-dataset.tags=_full \
+	--adr.get-mlperf-inference-results-dir.tags=_version.r4_1-dev \
+	--adr.get-mlperf-inference-submission-dir.tags=_version.r4_1-dev \
+	--adr.mlperf-inference-nvidia-scratch-space.tags=_version.r4_1-dev \
+	--v=False \
+	--print_env=False \
+	--print_deps=False \
+	--dump_version_info=True \
+	--env.CM_DATASET_OPENIMAGES_PATH=/home/cmuser/CM/repos/local/cache/a0a0d3a06d08433f/install/validation/data \
+	--env.CM_OPENIMAGES_CALIBRATION_DATASET_PATH=/home/cmuser/CM/repos/local/cache/5fd3118f48654bf7/install/calibration/data \
+	--env.CM_DATASET_OPENIMAGES_ANNOTATIONS_DIR_PATH=/home/cmuser/CM/repos/local/cache/963b6d6671ce444c \
+	--env.OUTPUT_BASE_DIR=/cm-mount/home/arjun/gh_action_results \
+	--env.CM_MLPERF_INFERENCE_SUBMISSION_DIR=/cm-mount/home/arjun/gh_action_submissions \
+	--env.MLPERF_SCRATCH_PATH=/home/cmuser/CM/repos/local/cache/5b2b0cc913a4453a
+```
+*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: RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config
+
+Model Precision: int8
+
+### Accuracy Results 
+`mAP`: `37.301`, Required accuracy for closed division `>= 37.1745`
+
+### Performance Results 
+`Samples per query`: `10894225.0`

open/MLCommons/measurements/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/retinanet/multistream/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config.json

@@ -0,0 +1,7 @@
+{
+  "starting_weights_filename": "https://zenodo.org/record/6617981/files/resnext50_32x4d_fpn.pth",
+  "retraining": "no",
+  "input_data_types": "int8",
+  "weight_data_types": "int8",
+  "weight_transformations": "quantization, affine fusion"
+}

open/MLCommons/measurements/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/retinanet/multistream/accuracy_console.out

@@ -0,0 +1,105 @@
+[2024-12-23 01:45:31,593 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x1
+[2024-12-23 01:45:31,659 harness.py:249 INFO] The harness will load 2 plugins: ['build/plugins/NMSOptPlugin/libnmsoptplugin.so', 'build/plugins/retinanetConcatPlugin/libretinanetconcatplugin.so']
+[2024-12-23 01:45:31,659 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x1_TRT/retinanet/MultiStream
+[2024-12-23 01:45:31,659 __init__.py:46 INFO] Running command: ./build/bin/harness_default --plugins="build/plugins/NMSOptPlugin/libnmsoptplugin.so,build/plugins/retinanetConcatPlugin/libretinanetconcatplugin.so" --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/retinanet/multistream/accuracy" --logfile_prefix="mlperf_log_" --performance_sample_count=64 --test_mode="AccuracyOnly" --gpu_copy_streams=1 --gpu_inference_streams=1 --use_deque_limit=true --gpu_batch_size=2 --map_path="data_maps/open-images-v6-mlperf/val_map.txt" --mlperf_conf_path="/home/cmuser/CM/repos/local/cache/c1d8c371d52d46a3/inference/mlperf.conf" --tensor_path="build/preprocessed_data/open-images-v6-mlperf/validation/Retinanet/int8_linear" --use_graphs=true --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/e1ace0f9265f4e04aa8e64bd67cded3a.conf" --gpu_engines="./build/engines/RTX4090x1/retinanet/MultiStream/retinanet-MultiStream-gpu-b2-int8.lwis_k_99_MaxP.plan" --max_dlas=0 --scenario MultiStream --model retinanet --response_postprocess openimageeffnms
+[2024-12-23 01:45:31,659 __init__.py:53 INFO] Overriding Environment
+benchmark : Benchmark.Retinanet
+buffer_manager_thread_count : 0
+data_dir : /home/cmuser/CM/repos/local/cache/5b2b0cc913a4453a/data
+disable_beta1_smallk : True
+gpu_batch_size : 2
+gpu_copy_streams : 1
+gpu_inference_streams : 1
+input_dtype : int8
+input_format : linear
+log_dir : /home/cmuser/CM/repos/local/cache/dfbf240f980947f5/repo/closed/NVIDIA/build/logs/2024.12.23-01.45.30
+map_path : data_maps/open-images-v6-mlperf/val_map.txt
+mlperf_conf_path : /home/cmuser/CM/repos/local/cache/c1d8c371d52d46a3/inference/mlperf.conf
+multi_stream_expected_latency_ns : 0
+multi_stream_samples_per_query : 8
+multi_stream_target_latency_percentile : 99
+precision : int8
+preprocessed_data_dir : /home/cmuser/CM/repos/local/cache/5b2b0cc913a4453a/preprocessed_data
+scenario : Scenario.MultiStream
+system : SystemConfiguration(host_cpu_conf=CPUConfiguration(layout={CPU(name='13th Gen Intel(R) Core(TM) i9-13900K', architecture=<CPUArchitecture.x86_64: AliasedName(name='x86_64', aliases=(), patterns=())>, core_count=24, threads_per_core=1): 1}), host_mem_conf=MemoryConfiguration(host_memory_capacity=Memory(quantity=131.634476, byte_suffix=<ByteSuffix.GB: (1000, 3)>, _num_bytes=131634476000), comparison_tolerance=0.05), accelerator_conf=AcceleratorConfiguration(layout=defaultdict(<class 'int'>, {GPU(name='NVIDIA GeForce RTX 4090', accelerator_type=<AcceleratorType.Discrete: AliasedName(name='Discrete', aliases=(), patterns=())>, vram=Memory(quantity=23.98828125, byte_suffix=<ByteSuffix.GiB: (1024, 3)>, _num_bytes=25757220864), max_power_limit=450.0, pci_id='0x268410DE', compute_sm=89): 1})), numa_conf=None, system_id='RTX4090x1')
+tensor_path : build/preprocessed_data/open-images-v6-mlperf/validation/Retinanet/int8_linear
+test_mode : AccuracyOnly
+use_deque_limit : True
+use_graphs : True
+user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/e1ace0f9265f4e04aa8e64bd67cded3a.conf
+system_id : RTX4090x1
+config_name : RTX4090x1_retinanet_MultiStream
+workload_setting : WorkloadSetting(HarnessType.LWIS, AccuracyTarget.k_99, PowerSetting.MaxP)
+optimization_level : plugin-enabled
+num_profiles : 1
+config_ver : lwis_k_99_MaxP
+accuracy_level : 99%
+inference_server : lwis
+skip_file_checks : False
+power_limit : None
+cpu_freq : None
+&&&& RUNNING Default_Harness # ./build/bin/harness_default
+[I] mlperf.conf path: /home/cmuser/CM/repos/local/cache/c1d8c371d52d46a3/inference/mlperf.conf
+[I] user.conf path: /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/e1ace0f9265f4e04aa8e64bd67cded3a.conf
+Creating QSL.
+Finished Creating QSL.
+Setting up SUT.
+[I] [TRT] Loaded engine size: 73 MiB
+[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +7, GPU +10, now: CPU 121, GPU 881 (MiB)
+[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 122, GPU 891 (MiB)
+[I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +68, now: CPU 0, GPU 68 (MiB)
+[I] Device:0.GPU: [0] ./build/engines/RTX4090x1/retinanet/MultiStream/retinanet-MultiStream-gpu-b2-int8.lwis_k_99_MaxP.plan has been successfully loaded.
+[E] [TRT] 3: [runtime.cpp::~Runtime::401] Error Code 3: API Usage Error (Parameter check failed at: runtime/rt/runtime.cpp::~Runtime::401, condition: mEngineCounter.use_count() == 1 Destroying a runtime before destroying deserialized engines created by the runtime leads to undefined behavior.)
+[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 49, GPU 893 (MiB)
+[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 49, GPU 901 (MiB)
+[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +1528, now: CPU 0, GPU 1596 (MiB)
+[I] Start creating CUDA graphs
+[I] Capture 2 CUDA graphs
+[I] Finish creating CUDA graphs
+[I] Creating batcher thread: 0 EnableBatcherThreadPerDevice: false
+Finished setting up SUT.
+Starting warmup. Running for a minimum of 5 seconds.
+Finished warmup. Ran for 5.14663s.
+Starting running actual test.
+
+No warnings encountered during test.
+
+No errors encountered during test.
+Finished running actual test.
+Device Device:0.GPU processed:
+  12392 batches of size 2
+  Memcpy Calls: 0
+  PerSampleCudaMemcpy Calls: 0
+  BatchedCudaMemcpy Calls: 12392
+&&&& PASSED Default_Harness # ./build/bin/harness_default
+[2024-12-23 01:46:24,174 run_harness.py:166 INFO] Result: Accuracy run detected.
+[2024-12-23 01:46:24,175 __init__.py:46 INFO] Running command: python3 /home/cmuser/CM/repos/local/cache/dfbf240f980947f5/repo/closed/NVIDIA/build/inference/vision/classification_and_detection/tools/accuracy-openimages.py --mlperf-accuracy-file /cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/retinanet/multistream/accuracy/mlperf_log_accuracy.json --openimages-dir /home/cmuser/CM/repos/local/cache/5b2b0cc913a4453a/preprocessed_data/open-images-v6-mlperf --output-file build/retinanet-results.json
+loading annotations into memory...
+Done (t=0.34s)
+creating index...
+index created!
+Loading and preparing results...
+DONE (t=11.52s)
+creating index...
+index created!
+Running per image evaluation...
+Evaluate annotation type *bbox*
+DONE (t=102.60s).
+Accumulating evaluation results...
+DONE (t=22.98s).
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.373
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.522
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.404
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.023
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.125
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.412
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.419
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.598
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.627
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.082
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.343
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.677
+mAP=37.301%
+
+======================== Result summaries: ========================
+