Results from GH action on NVIDIA_RTX4090x2

closed/MLCommons/code/retinanet/README.md

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

closed/MLCommons/systems/RTX4090x2-nvidia-gpu-TensorRT-default_config.json

@@ -0,0 +1,37 @@
+{
+  "accelerator_frequency": "2520000 MHz",
+  "accelerator_host_interconnect": "N/A",
+  "accelerator_interconnect": "N/A",
+  "accelerator_interconnect_topology": "",
+  "accelerator_memory_capacity": "23.64019775390625 GB",
+  "accelerator_memory_configuration": "N/A",
+  "accelerator_model_name": "NVIDIA GeForce RTX 4090",
+  "accelerator_on-chip_memories": "",
+  "accelerators_per_node": 2,
+  "cooling": "air",
+  "division": "closed",
+  "framework": "TensorRT",
+  "host_memory_capacity": "192G",
+  "host_memory_configuration": "undefined",
+  "host_network_card_count": "1",
+  "host_networking": "Gig Ethernet",
+  "host_networking_topology": "N/A",
+  "host_processor_caches": "L1d cache: 1.1 MiB, L1i cache: 768 KiB, L2 cache: 48 MiB, L3 cache: 45 MiB",
+  "host_processor_core_count": "24",
+  "host_processor_frequency": "4800.0000",
+  "host_processor_interconnect": "",
+  "host_processor_model_name": "Intel(R) Xeon(R) w7-2495X",
+  "host_processors_per_node": "1",
+  "host_storage_capacity": "7.0T",
+  "host_storage_type": "SSD",
+  "hw_notes": "",
+  "number_of_nodes": "1",
+  "operating_system": "Ubuntu 20.04 (linux-6.8.0-51-generic-glibc2.31)",
+  "other_software_stack": "Python: 3.8.10, GCC-9.4.0, Using Docker  , CUDA 12.2",
+  "status": "available",
+  "submitter": "MLCommons",
+  "sw_notes": "",
+  "system_name": "RTX4090x2",
+  "system_type": "datacenter,edge",
+  "system_type_detail": "edge server"
+}

open/MLCommons/code/retinanet/README.md

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

open/MLCommons/measurements/RTX4090x2-nvidia-gpu-TensorRT-default_config/retinanet/multistream/README.md

@@ -0,0 +1,43 @@
+*Check [CM MLPerf docs](https://docs.mlcommons.org/inference) for more details.*
+
+## Host platform
+
+* OS version: Linux-6.8.0-51-generic-x86_64-with-glibc2.29
+* CPU version: x86_64
+* Python version: 3.8.10 (default, Jan 17 2025, 14:40:23) 
+[GCC 9.4.0]
+* MLC version: unknown
+
+## CM Run Command
+
+See [CM installation guide](https://docs.mlcommons.org/inference/install/).
+
+```bash
+pip install -U mlcflow
+
+mlc rm cache -f
+
+mlc pull repo mlcommons@mlperf-automations --checkout=7f1550ac1c2f254c951802093923a3c1423f7b86
+
+
+```
+*Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf,
+ you should simply reload mlcommons@mlperf-automations without checkout and clean MLC cache as follows:*
+
+```bash
+mlc rm repo mlcommons@mlperf-automations
+mlc pull repo mlcommons@mlperf-automations
+mlc rm cache -f
+
+```
+
+## Results
+
+Platform: RTX4090x2-nvidia-gpu-TensorRT-default_config
+
+Model Precision: int8
+
+### Accuracy Results 
+
+### Performance Results 
+`Samples per query`: `5656717.0`

open/MLCommons/measurements/RTX4090x2-nvidia-gpu-TensorRT-default_config/retinanet/multistream/RTX4090x2-nvidia-gpu-TensorRT-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/RTX4090x2-nvidia-gpu-TensorRT-default_config/retinanet/multistream/accuracy_console.out

@@ -0,0 +1,120 @@
+[2025-01-29 23:50:31,220 main.py:229 INFO] Detected system ID: KnownSystem.e7bff0656085
+[2025-01-29 23:50:31,303 harness.py:249 INFO] The harness will load 2 plugins: ['build/plugins/NMSOptPlugin/libnmsoptplugin.so', 'build/plugins/retinanetConcatPlugin/libretinanetconcatplugin.so']
+[2025-01-29 23:50:31,304 generate_conf_files.py:107 INFO] Generated measurements/ entries for e7bff0656085_TRT/retinanet/MultiStream
+[2025-01-29 23:50:31,304 __init__.py:46 INFO] Running command: ./build/bin/harness_default --plugins="build/plugins/NMSOptPlugin/libnmsoptplugin.so,build/plugins/retinanetConcatPlugin/libretinanetconcatplugin.so" --logfile_outdir="/mlc-mount/home/arjun/gh_action_results/valid_results/RTX4090x2-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/mlcuser/MLC/repos/local/cache/get-git-repo_4cd85a18/inference/mlperf.conf" --tensor_path="build/preprocessed_data/open-images-v6-mlperf/validation/Retinanet/int8_linear" --use_graphs=true --user_conf_path="/home/mlcuser/MLC/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/22a091d0057b427a93d508033599dd79.conf" --gpu_engines="./build/engines/e7bff0656085/retinanet/MultiStream/retinanet-MultiStream-gpu-b2-int8.lwis_k_99_MaxP.plan" --max_dlas=0 --scenario MultiStream --model retinanet --response_postprocess openimageeffnms
+[2025-01-29 23:50:31,304 __init__.py:53 INFO] Overriding Environment
+benchmark : Benchmark.Retinanet
+buffer_manager_thread_count : 0
+data_dir : /home/mlcuser/MLC/repos/local/cache/get-mlperf-inference-nvidia-scratch-space_5aab030f/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/mlcuser/MLC/repos/local/cache/get-git-repo_8953de2a/repo/closed/NVIDIA/build/logs/2025.01.29-23.50.29
+map_path : data_maps/open-images-v6-mlperf/val_map.txt
+mlperf_conf_path : /home/mlcuser/MLC/repos/local/cache/get-git-repo_4cd85a18/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/mlcuser/MLC/repos/local/cache/get-mlperf-inference-nvidia-scratch-space_5aab030f/preprocessed_data
+scenario : Scenario.MultiStream
+system : SystemConfiguration(host_cpu_conf=CPUConfiguration(layout={CPU(name='Intel(R) Xeon(R) w7-2495X', architecture=<CPUArchitecture.x86_64: AliasedName(name='x86_64', aliases=(), patterns=())>, core_count=24, threads_per_core=2): 1}), host_mem_conf=MemoryConfiguration(host_memory_capacity=Memory(quantity=197.33452799999998, byte_suffix=<ByteSuffix.GB: (1000, 3)>, _num_bytes=197334528000), 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, 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=500.0, pci_id='0x268410DE', compute_sm=89): 1})), numa_conf=NUMAConfiguration(numa_nodes={}, num_numa_nodes=1), system_id='e7bff0656085')
+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/mlcuser/MLC/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/22a091d0057b427a93d508033599dd79.conf
+system_id : e7bff0656085
+config_name : e7bff0656085_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/mlcuser/MLC/repos/local/cache/get-git-repo_4cd85a18/inference/mlperf.conf
+[I] user.conf path: /home/mlcuser/MLC/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/22a091d0057b427a93d508033599dd79.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 126, GPU 881 (MiB)
+[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 127, 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/e7bff0656085/retinanet/MultiStream/retinanet-MultiStream-gpu-b2-int8.lwis_k_99_MaxP.plan has been successfully loaded.
+[I] [TRT] Loaded engine size: 73 MiB
+[W] [TRT] Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
+[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +6, GPU +10, now: CPU 160, GPU 625 (MiB)
+[I] [TRT] [MemUsageChange] Init cuDNN: CPU +2, GPU +10, now: CPU 162, GPU 635 (MiB)
+[I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +69, now: CPU 0, GPU 137 (MiB)
+[I] Device:1.GPU: [0] ./build/engines/e7bff0656085/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 89, GPU 893 (MiB)
+[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 89, GPU 901 (MiB)
+[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +1, GPU +1528, now: CPU 1, GPU 1665 (MiB)
+[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 90, GPU 637 (MiB)
+[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 90, GPU 645 (MiB)
+[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +1528, now: CPU 1, GPU 3193 (MiB)
+[I] Start creating CUDA graphs
+[I] Capture 2 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 5.14365s.
+Starting running actual test.
+
+No warnings encountered during test.
+
+No errors encountered during test.
+Finished running actual test.
+Device Device:0.GPU processed:
+  6196 batches of size 2
+  Memcpy Calls: 0
+  PerSampleCudaMemcpy Calls: 0
+  BatchedCudaMemcpy Calls: 6196
+Device Device:1.GPU processed:
+  6196 batches of size 2
+  Memcpy Calls: 0
+  PerSampleCudaMemcpy Calls: 0
+  BatchedCudaMemcpy Calls: 6196
+&&&& PASSED Default_Harness # ./build/bin/harness_default
+[2025-01-29 23:51:08,313 run_harness.py:166 INFO] Result: Accuracy run detected.
+[2025-01-29 23:51:08,313 __init__.py:46 INFO] Running command: python3 /home/mlcuser/MLC/repos/local/cache/get-git-repo_8953de2a/repo/closed/NVIDIA/build/inference/vision/classification_and_detection/tools/accuracy-openimages.py --mlperf-accuracy-file /mlc-mount/home/arjun/gh_action_results/valid_results/RTX4090x2-nvidia_original-gpu-tensorrt-vdefault-default_config/retinanet/multistream/accuracy/mlperf_log_accuracy.json --openimages-dir /home/mlcuser/MLC/repos/local/cache/get-mlperf-inference-nvidia-scratch-space_5aab030f/preprocessed_data/open-images-v6-mlperf --output-file build/retinanet-results.json
+loading annotations into memory...
+Done (t=0.50s)
+creating index...
+index created!
+Loading and preparing results...
+DONE (t=17.48s)
+creating index...
+index created!
+Running per image evaluation...
+Evaluate annotation type *bbox*
+DONE (t=132.60s).
+Accumulating evaluation results...
+DONE (t=32.29s).
+ 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 ] = 0.413
+ 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 ] = 0.628
+ 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=37.340%
+
+======================== Result summaries: ========================
+

open/MLCommons/measurements/RTX4090x2-nvidia-gpu-TensorRT-default_config/retinanet/multistream/cpu_info.json

@@ -0,0 +1,27 @@
+{
+  "MLC_HOST_CPU_WRITE_PROTECT_SUPPORT": "yes",
+  "MLC_HOST_CPU_MICROCODE": "0x2b000603",
+  "MLC_HOST_CPU_FPU_SUPPORT": "yes",
+  "MLC_HOST_CPU_FPU_EXCEPTION_SUPPORT": "yes",
+  "MLC_HOST_CPU_BUGS": "spectre_v1 spectre_v2 spec_store_bypass swapgs eibrs_pbrsb bhi",
+  "MLC_HOST_CPU_TLB_SIZE": "Not Found",
+  "MLC_HOST_CPU_CFLUSH_SIZE": "64",
+  "MLC_HOST_CPU_ARCHITECTURE": "x86_64",
+  "MLC_HOST_CPU_TOTAL_CORES": "48",
+  "MLC_HOST_CPU_ON_LINE_CPUS_LIST": "0-47",
+  "MLC_HOST_CPU_THREADS_PER_CORE": "2",
+  "MLC_HOST_CPU_PHYSICAL_CORES_PER_SOCKET": "24",
+  "MLC_HOST_CPU_SOCKETS": "1",
+  "MLC_HOST_CPU_NUMA_NODES": "1",
+  "MLC_HOST_CPU_VENDOR_ID": "GenuineIntel",
+  "MLC_HOST_CPU_FAMILY": "6",
+  "MLC_HOST_CPU_MODEL_NAME": "Intel(R) Xeon(R) w7-2495X",
+  "MLC_HOST_CPU_MAX_MHZ": "4800.0000",
+  "MLC_HOST_CPU_L1D_CACHE_SIZE": "1.1 MiB",
+  "MLC_HOST_CPU_L1I_CACHE_SIZE": "768 KiB",
+  "MLC_HOST_CPU_L2_CACHE_SIZE": "48 MiB",
+  "MLC_HOST_CPU_L3_CACHE_SIZE": "45 MiB",
+  "MLC_HOST_CPU_TOTAL_LOGICAL_CORES": "48",
+  "MLC_HOST_MEMORY_CAPACITY": "192G",
+  "MLC_HOST_DISK_CAPACITY": "7.0T"
+}