Skip to content

Commit

Permalink
Results from GH action on NVIDIA_RTX4090x1
Browse files Browse the repository at this point in the history
  • Loading branch information
@arjunsuresh
arjunsuresh committed Nov 25, 2024
1 parent 5c59872 commit 575e0d9
Show file tree
Hide file tree
Showing 47 changed files with 4,220 additions and 3,761 deletions.
14 changes: 7 additions & 7 deletions closed/MLCommons/systems/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config.json
View file
Original file line number Diff line number Diff line change
@@ -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": "",
Expand All @@ -16,13 +16,13 @@
"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",
Expand Down
6 changes: 3 additions & 3 deletions ...ia_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ pip install -U cmind

cm rm cache -f

cm pull repo gateoverflow@cm4mlops --checkout=4109129057f4953f1513f4dcac8c60ceef79b728
cm pull repo gateoverflow@cm4mlops --checkout=c10b61abeabfc24b30f56a70c735b93eac8681db

cm run script \
--tags=app,mlperf,inference,generic,_nvidia,_resnet50,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream \
Expand Down Expand Up @@ -71,7 +71,7 @@ cm run script \
--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=5237b98af46b \
--env.CM_DOCKER_CONTAINER_ID=74a1d855824d \
--env.CM_MLPERF_LOADGEN_COMPLIANCE_TEST=TEST04 \
--add_deps_recursive.submission-checker-src.tags=_branch.dev \
--add_deps_recursive.compiler.tags=gcc \
Expand Down Expand Up @@ -130,4 +130,4 @@ Model Precision: int8
`acc`: `76.064`, Required accuracy for closed division `>= 75.6954`

### Performance Results
`Samples per query`: `465830.0`
`Samples per query`: `467260.0`
30 changes: 15 additions & 15 deletions ...a_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/accuracy_console.out
View file
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
[2024-11-22 19:51:19,068 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x1
[2024-11-22 19:51:19,200 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x1_TRT/resnet50/MultiStream
[2024-11-22 19:51:19,200 __init__.py:46 INFO] Running command: ./build/bin/harness_default --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/accuracy" --logfile_prefix="mlperf_log_" --performance_sample_count=2048 --test_mode="AccuracyOnly" --gpu_copy_streams=1 --gpu_inference_streams=1 --use_deque_limit=true --gpu_batch_size=8 --map_path="data_maps/imagenet/val_map.txt" --mlperf_conf_path="/home/cmuser/CM/repos/local/cache/977d4292c8bb4b81/inference/mlperf.conf" --tensor_path="build/preprocessed_data/imagenet/ResNet50/int8_linear" --use_graphs=true --user_conf_path="/home/cmuser/CM/repos/gateoverflow@cm4mlops/script/generate-mlperf-inference-user-conf/tmp/f3820e52bb0e4d878f1d8383b185c447.conf" --gpu_engines="./build/engines/RTX4090x1/resnet50/MultiStream/resnet50-MultiStream-gpu-b8-int8.lwis_k_99_MaxP.plan" --max_dlas=0 --scenario MultiStream --model resnet50
[2024-11-22 19:51:19,200 __init__.py:53 INFO] Overriding Environment
[2024-11-25 00:58:55,607 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x1
[2024-11-25 00:58:55,739 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x1_TRT/resnet50/MultiStream
[2024-11-25 00:58:55,739 __init__.py:46 INFO] Running command: ./build/bin/harness_default --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/accuracy" --logfile_prefix="mlperf_log_" --performance_sample_count=2048 --test_mode="AccuracyOnly" --gpu_copy_streams=1 --gpu_inference_streams=1 --use_deque_limit=true --gpu_batch_size=8 --map_path="data_maps/imagenet/val_map.txt" --mlperf_conf_path="/home/cmuser/CM/repos/local/cache/5622a5b65e1043fd/inference/mlperf.conf" --tensor_path="build/preprocessed_data/imagenet/ResNet50/int8_linear" --use_graphs=true --user_conf_path="/home/cmuser/CM/repos/gateoverflow@cm4mlops/script/generate-mlperf-inference-user-conf/tmp/7e3934f91ddc417f920f6965cafd7087.conf" --gpu_engines="./build/engines/RTX4090x1/resnet50/MultiStream/resnet50-MultiStream-gpu-b8-int8.lwis_k_99_MaxP.plan" --max_dlas=0 --scenario MultiStream --model resnet50
[2024-11-25 00:58:55,739 __init__.py:53 INFO] Overriding Environment
benchmark : Benchmark.ResNet50
buffer_manager_thread_count : 0
data_dir : /home/cmuser/CM/repos/local/cache/5b2b0cc913a4453a/data
Expand All @@ -11,9 +11,9 @@ gpu_copy_streams : 1
gpu_inference_streams : 1
input_dtype : int8
input_format : linear
log_dir : /home/cmuser/CM/repos/local/cache/6bf76155ad874a21/repo/closed/NVIDIA/build/logs/2024.11.22-19.51.18
log_dir : /home/cmuser/CM/repos/local/cache/6bf76155ad874a21/repo/closed/NVIDIA/build/logs/2024.11.25-00.58.54
map_path : data_maps/imagenet/val_map.txt
mlperf_conf_path : /home/cmuser/CM/repos/local/cache/977d4292c8bb4b81/inference/mlperf.conf
mlperf_conf_path : /home/cmuser/CM/repos/local/cache/5622a5b65e1043fd/inference/mlperf.conf
multi_stream_expected_latency_ns : 0
multi_stream_samples_per_query : 8
multi_stream_target_latency_percentile : 99
Expand All @@ -25,7 +25,7 @@ tensor_path : build/preprocessed_data/imagenet/ResNet50/int8_linear
test_mode : AccuracyOnly
use_deque_limit : True
use_graphs : True
user_conf_path : /home/cmuser/CM/repos/gateoverflow@cm4mlops/script/generate-mlperf-inference-user-conf/tmp/f3820e52bb0e4d878f1d8383b185c447.conf
user_conf_path : /home/cmuser/CM/repos/gateoverflow@cm4mlops/script/generate-mlperf-inference-user-conf/tmp/7e3934f91ddc417f920f6965cafd7087.conf
system_id : RTX4090x1
config_name : RTX4090x1_resnet50_MultiStream
workload_setting : WorkloadSetting(HarnessType.LWIS, AccuracyTarget.k_99, PowerSetting.MaxP)
Expand All @@ -38,18 +38,18 @@ 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/977d4292c8bb4b81/inference/mlperf.conf
[I] user.conf path: /home/cmuser/CM/repos/gateoverflow@cm4mlops/script/generate-mlperf-inference-user-conf/tmp/f3820e52bb0e4d878f1d8383b185c447.conf
[I] mlperf.conf path: /home/cmuser/CM/repos/local/cache/5622a5b65e1043fd/inference/mlperf.conf
[I] user.conf path: /home/cmuser/CM/repos/gateoverflow@cm4mlops/script/generate-mlperf-inference-user-conf/tmp/7e3934f91ddc417f920f6965cafd7087.conf
Creating QSL.
Finished Creating QSL.
Setting up SUT.
[I] [TRT] Loaded engine size: 26 MiB
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +6, GPU +10, now: CPU 72, GPU 837 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +2, GPU +10, now: CPU 74, GPU 847 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +7, GPU +10, now: CPU 72, GPU 837 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 73, GPU 847 (MiB)
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +24, now: CPU 0, GPU 24 (MiB)
[I] Device:0.GPU: [0] ./build/engines/RTX4090x1/resnet50/MultiStream/resnet50-MultiStream-gpu-b8-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 +10, now: CPU 47, GPU 839 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +1, GPU +10, now: CPU 47, GPU 839 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 47, GPU 847 (MiB)
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +17, now: CPU 0, GPU 41 (MiB)
[I] Start creating CUDA graphs
Expand All @@ -58,7 +58,7 @@ Setting up SUT.
[I] Creating batcher thread: 0 EnableBatcherThreadPerDevice: false
Finished setting up SUT.
Starting warmup. Running for a minimum of 5 seconds.
Finished warmup. Ran for 5.02604s.
Finished warmup. Ran for 5.02586s.
Starting running actual test.

No warnings encountered during test.
Expand All @@ -71,8 +71,8 @@ Device Device:0.GPU processed:
PerSampleCudaMemcpy Calls: 0
BatchedCudaMemcpy Calls: 6250
&&&& PASSED Default_Harness # ./build/bin/harness_default
[2024-11-22 19:51:32,001 run_harness.py:166 INFO] Result: Accuracy run detected.
[2024-11-22 19:51:32,001 __init__.py:46 INFO] Running command: python3 /home/cmuser/CM/repos/local/cache/6bf76155ad874a21/repo/closed/NVIDIA/build/inference/vision/classification_and_detection/tools/accuracy-imagenet.py --mlperf-accuracy-file /cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/accuracy/mlperf_log_accuracy.json --imagenet-val-file data_maps/imagenet/val_map.txt --dtype int32
[2024-11-25 00:59:08,548 run_harness.py:166 INFO] Result: Accuracy run detected.
[2024-11-25 00:59:08,548 __init__.py:46 INFO] Running command: python3 /home/cmuser/CM/repos/local/cache/6bf76155ad874a21/repo/closed/NVIDIA/build/inference/vision/classification_and_detection/tools/accuracy-imagenet.py --mlperf-accuracy-file /cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/accuracy/mlperf_log_accuracy.json --imagenet-val-file data_maps/imagenet/val_map.txt --dtype int32
accuracy=76.064%, good=38032, total=50000

======================== Result summaries: ========================
Expand Down
73 changes: 73 additions & 0 deletions ...0x1-nvidia_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/cm-deps.mmd
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,73 @@
graph TD
app-mlperf-inference,d775cac873ee4231_(_nvidia,_resnet50,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream_) --> detect,os
app-mlperf-inference,d775cac873ee4231_(_nvidia,_resnet50,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream_) --> get,sys-utils-cm
app-mlperf-inference,d775cac873ee4231_(_nvidia,_resnet50,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream_) --> get,python
get-mlperf-inference-src,4b57186581024797 --> detect,os
get-mlperf-inference-src,4b57186581024797 --> get,python3
get-git-repo,ed603e7292974f10_(_branch.master,_repo.https://github.com/mlcommons/inference_) --> detect,os
get-mlperf-inference-src,4b57186581024797 --> get,git,repo,_branch.master,_repo.https://github.com/mlcommons/inference
app-mlperf-inference,d775cac873ee4231_(_nvidia,_resnet50,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream_) --> get,mlcommons,inference,src
pull-git-repo,c23132ed65c4421d --> detect,os
app-mlperf-inference,d775cac873ee4231_(_nvidia,_resnet50,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream_) --> pull,git,repo
get-mlperf-inference-utils,e341e5f86d8342e5 --> get,mlperf,inference,src
app-mlperf-inference,d775cac873ee4231_(_nvidia,_resnet50,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream_) --> get,mlperf,inference,utils
app-mlperf-inference,d775cac873ee4231_(_nvidia,_resnet50,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream_) --> get,dataset-aux,imagenet-aux
get-cuda-devices,7a3ede4d3558427a_(_with-pycuda_) --> get,cuda,_toolkit
get-cuda-devices,7a3ede4d3558427a_(_with-pycuda_) --> get,python3
get-cuda-devices,7a3ede4d3558427a_(_with-pycuda_) --> get,generic-python-lib,_package.pycuda
get-cuda-devices,7a3ede4d3558427a_(_with-pycuda_) --> get,generic-python-lib,_package.numpy
app-mlperf-inference,d775cac873ee4231_(_nvidia,_resnet50,_tensorrt,_cuda,_valid,_r4.1-dev_default,_multistream_) --> get,cuda-devices,_with-pycuda
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> detect,os
detect-cpu,586c8a43320142f7 --> detect,os
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> detect,cpu
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,sys-utils-cm
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,mlperf,inference,nvidia,scratch,space
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,generic-python-lib,_mlperf_logging
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,dataset,original,imagenet,_full
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,ml-model,resnet50,_fp32,_onnx,_opset-8
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,mlcommons,inference,src
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,nvidia,mlperf,inference,common-code,_mlcommons
pull-git-repo,c23132ed65c4421d --> detect,os
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> pull,git,repo
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
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-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> generate,user-conf,mlperf,inference
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,generic-python-lib,_package.pycuda
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,nvidia,mitten
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,cuda,_cudnn
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,tensorrt
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> build,nvidia,inference,server,_mlcommons
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> detect,os
detect-cpu,586c8a43320142f7 --> detect,os
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> detect,cpu
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,sys-utils-cm
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,mlperf,inference,nvidia,scratch,space,_version.4_0
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,generic-python-lib,_mlperf_logging
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,dataset,original,imagenet,_full
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,ml-model,resnet50,_fp32,_onnx,_opset-8
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,mlcommons,inference,src
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,nvidia,mlperf,inference,common-code,_mlcommons
pull-git-repo,c23132ed65c4421d --> detect,os
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> pull,git,repo
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,generic-python-lib,_package.pycuda
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,nvidia,mitten
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,cuda,_cudnn
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,tensorrt
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> build,nvidia,inference,server,_mlcommons
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> reproduce,mlperf,inference,nvidia,harness,_preprocess_data,_tensorrt,_cuda,_resnet50,_v4.1-dev
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,generic-python-lib,_onnx-graphsurgeon
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> get,generic-python-lib,_package.onnx
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8_) --> save,mlperf,inference,state
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> reproduce,mlperf,inference,nvidia,harness,_build_engine,_multistream,_tensorrt,_cuda,_resnet50,_v4.1-dev,_batch_size.8
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> reproduce,mlperf,inference,nvidia,harness,_preprocess_data,_tensorrt,_cuda,_resnet50,_v4.1-dev
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,generic-python-lib,_onnx-graphsurgeon
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> get,generic-python-lib,_package.onnx
detect-cpu,586c8a43320142f7 --> detect,os
benchmark-program,19f369ef47084895 --> detect,cpu
benchmark-program-mlperf,cfff0132a8aa4018 --> benchmark-program,program
app-mlperf-inference-nvidia,bc3b17fb430f4732_(_run_harness,_multistream,_tensorrt,_cuda,_resnet50,_rtx_4090_) --> benchmark-mlperf
Binary file modified ..._original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/cm-deps.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading

0 comments on commit 575e0d9

Please sign in to comment.