Skip to content

Commit

Permalink
Auto-merge updates from auto-update branch
Browse files Browse the repository at this point in the history
  • Loading branch information
@mlcommons-bot
mlcommons-bot committed Dec 25, 2024
2 parents 33fad87 + 7b24f2b commit 1645b5c
Show file tree
Hide file tree
Showing 52 changed files with 4,022 additions and 4,024 deletions.
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 mlcommons@mlperf-automations --checkout=225220c7d9bb7e66e5b9a1e1ebfc3e0180fbd094
cm pull repo mlcommons@mlperf-automations --checkout=a90475d2de72bf0622cebe8d5ca8eb8c9d872fbd

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=242af263479b \
--env.CM_DOCKER_CONTAINER_ID=e8ed1d33e4c0 \
--env.CM_MLPERF_LOADGEN_COMPLIANCE_TEST=TEST04 \
--add_deps_recursive.compiler.tags=gcc \
--add_deps_recursive.coco2014-original.tags=_full \
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`: `502795.0`
`Samples per query`: `498904.0`
36 changes: 18 additions & 18 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 @@
[2024-12-23 00:11:50,691 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x2
[2024-12-23 00:11:50,868 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x2_TRT/resnet50/MultiStream
[2024-12-23 00:11:50,868 __init__.py:46 INFO] Running command: ./build/bin/harness_default --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x2-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/5860c00d55d14786/inference/mlperf.conf" --tensor_path="build/preprocessed_data/imagenet/ResNet50/int8_linear" --use_graphs=true --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/4e6a5741f75b4ffdb16375bfdfcf40d5.conf" --gpu_engines="./build/engines/RTX4090x2/resnet50/MultiStream/resnet50-MultiStream-gpu-b8-int8.lwis_k_99_MaxP.plan" --max_dlas=0 --scenario MultiStream --model resnet50
[2024-12-23 00:11:50,868 __init__.py:53 INFO] Overriding Environment
[2024-12-24 23:15:46,315 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x2
[2024-12-24 23:15:46,483 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x2_TRT/resnet50/MultiStream
[2024-12-24 23:15:46,484 __init__.py:46 INFO] Running command: ./build/bin/harness_default --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x2-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/5860c00d55d14786/inference/mlperf.conf" --tensor_path="build/preprocessed_data/imagenet/ResNet50/int8_linear" --use_graphs=true --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/ad206b0bdf344f129717e94ac08e54e5.conf" --gpu_engines="./build/engines/RTX4090x2/resnet50/MultiStream/resnet50-MultiStream-gpu-b8-int8.lwis_k_99_MaxP.plan" --max_dlas=0 --scenario MultiStream --model resnet50
[2024-12-24 23:15:46,484 __init__.py:53 INFO] Overriding Environment
benchmark : Benchmark.ResNet50
buffer_manager_thread_count : 0
data_dir : /home/cmuser/CM/repos/local/cache/4db00c74da1e44c8/data
Expand All @@ -11,7 +11,7 @@ gpu_copy_streams : 1
gpu_inference_streams : 1
input_dtype : int8
input_format : linear
log_dir : /home/cmuser/CM/repos/local/cache/94a57f78972843c6/repo/closed/NVIDIA/build/logs/2024.12.23-00.11.49
log_dir : /home/cmuser/CM/repos/local/cache/94a57f78972843c6/repo/closed/NVIDIA/build/logs/2024.12.24-23.15.45
map_path : data_maps/imagenet/val_map.txt
mlperf_conf_path : /home/cmuser/CM/repos/local/cache/5860c00d55d14786/inference/mlperf.conf
multi_stream_expected_latency_ns : 0
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/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/4e6a5741f75b4ffdb16375bfdfcf40d5.conf
user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/ad206b0bdf344f129717e94ac08e54e5.conf
system_id : RTX4090x2
config_name : RTX4090x2_resnet50_MultiStream
workload_setting : WorkloadSetting(HarnessType.LWIS, AccuracyTarget.k_99, PowerSetting.MaxP)
Expand All @@ -39,27 +39,27 @@ power_limit : None
cpu_freq : None
&&&& RUNNING Default_Harness # ./build/bin/harness_default
[I] mlperf.conf path: /home/cmuser/CM/repos/local/cache/5860c00d55d14786/inference/mlperf.conf
[I] user.conf path: /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/4e6a5741f75b4ffdb16375bfdfcf40d5.conf
[I] user.conf path: /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/ad206b0bdf344f129717e94ac08e54e5.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 78, GPU 837 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 79, GPU 847 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +6, GPU +10, now: CPU 77, GPU 837 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +2, GPU +10, now: CPU 79, 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/RTX4090x2/resnet50/MultiStream/resnet50-MultiStream-gpu-b8-int8.lwis_k_99_MaxP.plan has been successfully loaded.
[I] [TRT] Loaded engine size: 26 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 108, GPU 581 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +2, GPU +10, now: CPU 110, GPU 591 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +6, GPU +10, now: CPU 108, GPU 580 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 109, GPU 590 (MiB)
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +25, now: CPU 0, GPU 49 (MiB)
[I] Device:1.GPU: [0] ./build/engines/RTX4090x2/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 83, GPU 839 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 83, GPU 847 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +10, now: CPU 82, GPU 839 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 82, GPU 847 (MiB)
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +17, now: CPU 0, GPU 66 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +10, now: CPU 84, GPU 583 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 84, GPU 591 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +10, now: CPU 83, GPU 582 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +8, now: CPU 84, GPU 590 (MiB)
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +17, now: CPU 0, GPU 83 (MiB)
[I] Start creating CUDA graphs
[I] Capture 8 CUDA graphs
Expand All @@ -68,7 +68,7 @@ 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 5.02405s.
Finished warmup. Ran for 5.02417s.
Starting running actual test.

No warnings encountered during test.
Expand All @@ -86,8 +86,8 @@ Device Device:1.GPU processed:
PerSampleCudaMemcpy Calls: 0
BatchedCudaMemcpy Calls: 3125
&&&& PASSED Default_Harness # ./build/bin/harness_default
[2024-12-23 00:12:06,094 run_harness.py:166 INFO] Result: Accuracy run detected.
[2024-12-23 00:12:06,094 __init__.py:46 INFO] Running command: python3 /home/cmuser/CM/repos/local/cache/94a57f78972843c6/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/RTX4090x2-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
[2024-12-24 23:16:01,951 run_harness.py:166 INFO] Result: Accuracy run detected.
[2024-12-24 23:16:01,951 __init__.py:46 INFO] Running command: python3 /home/cmuser/CM/repos/local/cache/94a57f78972843c6/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/RTX4090x2-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
2 changes: 1 addition & 1 deletion ...x2-nvidia_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/os_info.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -26,5 +26,5 @@
],
"CM_HOST_PLATFORM_FLAVOR": "x86_64",
"CM_HOST_PYTHON_BITS": "64",
"CM_HOST_SYSTEM_NAME": "242af263479b"
"CM_HOST_SYSTEM_NAME": "e8ed1d33e4c0"
}
68 changes: 34 additions & 34 deletions ...riginal-gpu-tensorrt-vdefault-default_config/resnet50/multistream/performance_console.out
View file
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
[2024-12-23 00:01:23,139 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x2
[2024-12-23 00:01:23,305 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x2_TRT/resnet50/MultiStream
[2024-12-23 00:01:23,306 __init__.py:46 INFO] Running command: ./build/bin/harness_default --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x2-nvidia_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/performance/run_1" --logfile_prefix="mlperf_log_" --performance_sample_count=2048 --test_mode="PerformanceOnly" --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/5860c00d55d14786/inference/mlperf.conf" --tensor_path="build/preprocessed_data/imagenet/ResNet50/int8_linear" --use_graphs=true --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/0d6dab1298e34a73990864b7d89f11a0.conf" --gpu_engines="./build/engines/RTX4090x2/resnet50/MultiStream/resnet50-MultiStream-gpu-b8-int8.lwis_k_99_MaxP.plan" --max_dlas=0 --scenario MultiStream --model resnet50
[2024-12-23 00:01:23,306 __init__.py:53 INFO] Overriding Environment
[2024-12-24 23:05:18,829 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x2
[2024-12-24 23:05:18,999 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x2_TRT/resnet50/MultiStream
[2024-12-24 23:05:19,000 __init__.py:46 INFO] Running command: ./build/bin/harness_default --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x2-nvidia_original-gpu-tensorrt-vdefault-default_config/resnet50/multistream/performance/run_1" --logfile_prefix="mlperf_log_" --performance_sample_count=2048 --test_mode="PerformanceOnly" --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/5860c00d55d14786/inference/mlperf.conf" --tensor_path="build/preprocessed_data/imagenet/ResNet50/int8_linear" --use_graphs=true --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/4f537047cf444b288f6102750b4ade03.conf" --gpu_engines="./build/engines/RTX4090x2/resnet50/MultiStream/resnet50-MultiStream-gpu-b8-int8.lwis_k_99_MaxP.plan" --max_dlas=0 --scenario MultiStream --model resnet50
[2024-12-24 23:05:19,000 __init__.py:53 INFO] Overriding Environment
benchmark : Benchmark.ResNet50
buffer_manager_thread_count : 0
data_dir : /home/cmuser/CM/repos/local/cache/4db00c74da1e44c8/data
Expand All @@ -11,7 +11,7 @@ gpu_copy_streams : 1
gpu_inference_streams : 1
input_dtype : int8
input_format : linear
log_dir : /home/cmuser/CM/repos/local/cache/94a57f78972843c6/repo/closed/NVIDIA/build/logs/2024.12.23-00.01.21
log_dir : /home/cmuser/CM/repos/local/cache/94a57f78972843c6/repo/closed/NVIDIA/build/logs/2024.12.24-23.05.17
map_path : data_maps/imagenet/val_map.txt
mlperf_conf_path : /home/cmuser/CM/repos/local/cache/5860c00d55d14786/inference/mlperf.conf
multi_stream_expected_latency_ns : 0
Expand All @@ -25,7 +25,7 @@ tensor_path : build/preprocessed_data/imagenet/ResNet50/int8_linear
test_mode : PerformanceOnly
use_deque_limit : True
use_graphs : True
user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/0d6dab1298e34a73990864b7d89f11a0.conf
user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/4f537047cf444b288f6102750b4ade03.conf
system_id : RTX4090x2
config_name : RTX4090x2_resnet50_MultiStream
workload_setting : WorkloadSetting(HarnessType.LWIS, AccuracyTarget.k_99, PowerSetting.MaxP)
Expand All @@ -39,27 +39,27 @@ power_limit : None
cpu_freq : None
&&&& RUNNING Default_Harness # ./build/bin/harness_default
[I] mlperf.conf path: /home/cmuser/CM/repos/local/cache/5860c00d55d14786/inference/mlperf.conf
[I] user.conf path: /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/0d6dab1298e34a73990864b7d89f11a0.conf
[I] user.conf path: /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/4f537047cf444b288f6102750b4ade03.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 78, GPU 837 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 79, GPU 847 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +6, GPU +10, now: CPU 77, GPU 837 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +2, GPU +10, now: CPU 79, 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/RTX4090x2/resnet50/MultiStream/resnet50-MultiStream-gpu-b8-int8.lwis_k_99_MaxP.plan has been successfully loaded.
[I] [TRT] Loaded engine size: 26 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 108, GPU 580 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +2, GPU +10, now: CPU 110, GPU 590 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +6, GPU +10, now: CPU 108, GPU 581 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 109, GPU 591 (MiB)
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +25, now: CPU 0, GPU 49 (MiB)
[I] Device:1.GPU: [0] ./build/engines/RTX4090x2/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 83, GPU 839 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 83, GPU 847 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +10, now: CPU 82, GPU 839 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 82, GPU 847 (MiB)
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +17, now: CPU 0, GPU 66 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +10, now: CPU 84, GPU 582 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 84, GPU 590 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +10, now: CPU 83, GPU 583 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +8, now: CPU 84, GPU 591 (MiB)
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +17, now: CPU 0, GPU 83 (MiB)
[I] Start creating CUDA graphs
[I] Capture 8 CUDA graphs
Expand All @@ -68,37 +68,37 @@ 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 5.02414s.
Finished warmup. Ran for 5.02411s.
Starting running actual test.
================================================
MLPerf Results Summary
================================================
SUT name : LWIS_Server
Scenario : MultiStream
Mode : PerformanceOnly
99th percentile latency (ns) : 502574
99th percentile latency (ns) : 498723
Result is : VALID
Min duration satisfied : Yes
Min queries satisfied : Yes
Early stopping satisfied: Yes
Early Stopping Result:
* Processed at least 662 queries (1237051).
* Would discard 12112 highest latency queries.
* Early stopping 99th percentile estimate: 502795
* Processed at least 662 queries (1240784).
* Would discard 12149 highest latency queries.
* Early stopping 99th percentile estimate: 498904

================================================
Additional Stats
================================================
Per-query latency:
Min latency (ns) : 442690
Max latency (ns) : 1509293
Mean latency (ns) : 474019
50.00 percentile latency (ns) : 472645
90.00 percentile latency (ns) : 484741
95.00 percentile latency (ns) : 490338
97.00 percentile latency (ns) : 494072
99.00 percentile latency (ns) : 502574
99.90 percentile latency (ns) : 648822
Min latency (ns) : 439652
Max latency (ns) : 899917
Mean latency (ns) : 472372
50.00 percentile latency (ns) : 471384
90.00 percentile latency (ns) : 482670
95.00 percentile latency (ns) : 487276
97.00 percentile latency (ns) : 491079
99.00 percentile latency (ns) : 498723
99.90 percentile latency (ns) : 647573

================================================
Test Parameters Used
Expand Down Expand Up @@ -128,17 +128,17 @@ No warnings encountered during test.
No errors encountered during test.
Finished running actual test.
Device Device:0.GPU processed:
618526 batches of size 8
620392 batches of size 8
Memcpy Calls: 0
PerSampleCudaMemcpy Calls: 0
BatchedCudaMemcpy Calls: 618526
BatchedCudaMemcpy Calls: 620392
Device Device:1.GPU processed:
618525 batches of size 8
620392 batches of size 8
Memcpy Calls: 0
PerSampleCudaMemcpy Calls: 0
BatchedCudaMemcpy Calls: 618525
BatchedCudaMemcpy Calls: 620392
&&&& PASSED Default_Harness # ./build/bin/harness_default
[2024-12-23 00:11:32,450 run_harness.py:166 INFO] Result: result_99.00_percentile_per_query_latency_ns: 502574, Result is VALID
[2024-12-24 23:15:28,338 run_harness.py:166 INFO] Result: result_99.00_percentile_per_query_latency_ns: 498723, Result is VALID

======================== Result summaries: ========================

Loading

0 comments on commit 1645b5c

Please sign in to comment.