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 Dec 25, 2024
1 parent 1317bae commit 9bea238
Show file tree
Hide file tree
Showing 25 changed files with 890 additions and 890 deletions.
6 changes: 3 additions & 3 deletions ...-nvidia_original-gpu-tensorrt-vdefault-default_config/bert-99/offline/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,_bert-99,_tensorrt,_cuda,_valid,_r4.1-dev_default,_offline \
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=b8ce345e7cfa \
--env.CM_DOCKER_CONTAINER_ID=c66a229e22cf \
--env.CM_MLPERF_LOADGEN_COMPLIANCE_TEST=TEST01 \
--add_deps_recursive.compiler.tags=gcc \
--add_deps_recursive.coco2014-original.tags=_full \
Expand Down Expand Up @@ -129,4 +129,4 @@ Model Precision: int8
`F1`: `90.15674`, Required accuracy for closed division `>= 89.96526`

### Performance Results
`Samples per second`: `4119.08`
`Samples per second`: `4125.31`
62 changes: 31 additions & 31 deletions ...nvidia_original-gpu-tensorrt-vdefault-default_config/bert-99/offline/accuracy_console.out
View file
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
[2024-12-23 02:01:52,311 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x1
[2024-12-23 02:01:52,813 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x1_TRT/bert-99/Offline
[2024-12-23 02:01:52,813 __init__.py:46 INFO] Running command: ./build/bin/harness_bert --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/bert-99/offline/accuracy" --logfile_prefix="mlperf_log_" --performance_sample_count=10833 --test_mode="AccuracyOnly" --gpu_batch_size=256 --mlperf_conf_path="/home/cmuser/CM/repos/local/cache/adc9dc0382544ffd/inference/mlperf.conf" --tensor_path="build/preprocessed_data/squad_tokenized/input_ids.npy,build/preprocessed_data/squad_tokenized/segment_ids.npy,build/preprocessed_data/squad_tokenized/input_mask.npy" --use_graphs=false --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/eb9854064bde419c94548e4a59d8e6b4.conf" --gpu_inference_streams=2 --gpu_copy_streams=2 --gpu_engines="./build/engines/RTX4090x1/bert/Offline/bert-Offline-gpu-int8_S_384_B_256_P_2_vs.custom_k_99_MaxP.plan" --scenario Offline --model bert
[2024-12-23 02:01:52,813 __init__.py:53 INFO] Overriding Environment
[2024-12-24 23:00:52,890 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x1
[2024-12-24 23:00:53,380 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x1_TRT/bert-99/Offline
[2024-12-24 23:00:53,380 __init__.py:46 INFO] Running command: ./build/bin/harness_bert --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/bert-99/offline/accuracy" --logfile_prefix="mlperf_log_" --performance_sample_count=10833 --test_mode="AccuracyOnly" --gpu_batch_size=256 --mlperf_conf_path="/home/cmuser/CM/repos/local/cache/e824f0bb4919400f/inference/mlperf.conf" --tensor_path="build/preprocessed_data/squad_tokenized/input_ids.npy,build/preprocessed_data/squad_tokenized/segment_ids.npy,build/preprocessed_data/squad_tokenized/input_mask.npy" --use_graphs=false --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/aab71c24a07442c090544e000738c311.conf" --gpu_inference_streams=2 --gpu_copy_streams=2 --gpu_engines="./build/engines/RTX4090x1/bert/Offline/bert-Offline-gpu-int8_S_384_B_256_P_2_vs.custom_k_99_MaxP.plan" --scenario Offline --model bert
[2024-12-24 23:00:53,380 __init__.py:53 INFO] Overriding Environment
benchmark : Benchmark.BERT
buffer_manager_thread_count : 0
coalesced_tensor : True
Expand All @@ -11,8 +11,8 @@ gpu_copy_streams : 2
gpu_inference_streams : 2
input_dtype : int32
input_format : linear
log_dir : /home/cmuser/CM/repos/local/cache/ba8d5f2a6bc546f9/repo/closed/NVIDIA/build/logs/2024.12.23-02.01.51
mlperf_conf_path : /home/cmuser/CM/repos/local/cache/adc9dc0382544ffd/inference/mlperf.conf
log_dir : /home/cmuser/CM/repos/local/cache/ba8d5f2a6bc546f9/repo/closed/NVIDIA/build/logs/2024.12.24-23.00.51
mlperf_conf_path : /home/cmuser/CM/repos/local/cache/e824f0bb4919400f/inference/mlperf.conf
offline_expected_qps : 0.0
precision : int8
preprocessed_data_dir : /home/cmuser/CM/repos/local/cache/a8c152aef5494496/preprocessed_data
Expand All @@ -21,7 +21,7 @@ system : SystemConfiguration(host_cpu_conf=CPUConfiguration(layout={CPU(name='AM
tensor_path : build/preprocessed_data/squad_tokenized/input_ids.npy,build/preprocessed_data/squad_tokenized/segment_ids.npy,build/preprocessed_data/squad_tokenized/input_mask.npy
test_mode : AccuracyOnly
use_graphs : False
user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/eb9854064bde419c94548e4a59d8e6b4.conf
user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/aab71c24a07442c090544e000738c311.conf
system_id : RTX4090x1
config_name : RTX4090x1_bert_Offline
workload_setting : WorkloadSetting(HarnessType.Custom, AccuracyTarget.k_99, PowerSetting.MaxP)
Expand All @@ -34,40 +34,40 @@ skip_file_checks : True
power_limit : None
cpu_freq : None
&&&& RUNNING BERT_HARNESS # ./build/bin/harness_bert
I1223 02:01:52.866398 19723 main_bert.cc:163] Found 1 GPUs
I1223 02:01:53.259613 19723 bert_server.cc:147] Engine Path: ./build/engines/RTX4090x1/bert/Offline/bert-Offline-gpu-int8_S_384_B_256_P_2_vs.custom_k_99_MaxP.plan
I1224 23:00:53.437846 19726 main_bert.cc:163] Found 1 GPUs
I1224 23:00:53.830546 19726 bert_server.cc:147] Engine Path: ./build/engines/RTX4090x1/bert/Offline/bert-Offline-gpu-int8_S_384_B_256_P_2_vs.custom_k_99_MaxP.plan
[I] [TRT] Loaded engine size: 414 MiB
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +7, GPU +8, now: CPU 582, GPU 1232 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 583, GPU 1242 (MiB)
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +6, GPU +8, now: CPU 582, GPU 1232 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +2, GPU +10, now: CPU 584, GPU 1242 (MiB)
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +290, now: CPU 0, GPU 290 (MiB)
I1223 02:01:53.596822 19723 bert_server.cc:208] Engines Creation Completed
I1223 02:01:53.616966 19723 bert_core_vs.cc:385] Engine - Device Memory requirements: 704644608
I1223 02:01:53.616971 19723 bert_core_vs.cc:393] Engine - Number of Optimization Profiles: 2
I1223 02:01:53.616976 19723 bert_core_vs.cc:415] Engine - Profile 0 maxDims 98304 Bmax=256 Smax=384
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +1, GPU +8, now: CPU 170, GPU 1908 (MiB)
I1224 23:00:54.158447 19726 bert_server.cc:208] Engines Creation Completed
I1224 23:00:54.175813 19726 bert_core_vs.cc:385] Engine - Device Memory requirements: 704644608
I1224 23:00:54.175822 19726 bert_core_vs.cc:393] Engine - Number of Optimization Profiles: 2
I1224 23:00:54.175827 19726 bert_core_vs.cc:415] Engine - Profile 0 maxDims 98304 Bmax=256 Smax=384
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 170, GPU 1908 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 170, GPU 1916 (MiB)
I1223 02:01:53.672140 19723 bert_core_vs.cc:426] Setting Opt.Prof. to 0
I1223 02:01:53.672174 19723 bert_core_vs.cc:444] Context creation complete. Max supported batchSize: 256
I1224 23:00:54.230412 19726 bert_core_vs.cc:426] Setting Opt.Prof. to 0
I1224 23:00:54.230443 19726 bert_core_vs.cc:444] Context creation complete. Max supported batchSize: 256
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +0, now: CPU 0, GPU 290 (MiB)
I1223 02:01:53.673125 19723 bert_core_vs.cc:476] Setup complete
I1223 02:01:53.673296 19723 bert_core_vs.cc:385] Engine - Device Memory requirements: 704644608
I1223 02:01:53.673300 19723 bert_core_vs.cc:393] Engine - Number of Optimization Profiles: 2
I1223 02:01:53.673302 19723 bert_core_vs.cc:415] Engine - Profile 1 maxDims 98304 Bmax=256 Smax=384
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 292, GPU 2722 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +10, now: CPU 293, GPU 2732 (MiB)
I1223 02:01:53.727489 19723 bert_core_vs.cc:426] Setting Opt.Prof. to 1
I1224 23:00:54.231410 19726 bert_core_vs.cc:476] Setup complete
I1224 23:00:54.231583 19726 bert_core_vs.cc:385] Engine - Device Memory requirements: 704644608
I1224 23:00:54.231587 19726 bert_core_vs.cc:393] Engine - Number of Optimization Profiles: 2
I1224 23:00:54.231590 19726 bert_core_vs.cc:415] Engine - Profile 1 maxDims 98304 Bmax=256 Smax=384
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 293, GPU 2722 (MiB)
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +10, now: CPU 293, GPU 2732 (MiB)
I1224 23:00:54.285146 19726 bert_core_vs.cc:426] Setting Opt.Prof. to 1
[I] [TRT] Could not set default profile 0 for execution context. Profile index must be set explicitly.
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +1, GPU +0, now: CPU 1, GPU 290 (MiB)
I1223 02:01:53.727843 19723 bert_core_vs.cc:444] Context creation complete. Max supported batchSize: 256
I1223 02:01:53.728783 19723 bert_core_vs.cc:476] Setup complete
I1223 02:01:53.957628 19723 main_bert.cc:184] Starting running actual test.
I1223 02:01:56.618793 19723 main_bert.cc:190] Finished running actual test.
I1224 23:00:54.285508 19726 bert_core_vs.cc:444] Context creation complete. Max supported batchSize: 256
I1224 23:00:54.286469 19726 bert_core_vs.cc:476] Setup complete
I1224 23:00:54.514549 19726 main_bert.cc:184] Starting running actual test.
I1224 23:00:57.166287 19726 main_bert.cc:190] Finished running actual test.

No warnings encountered during test.

No errors encountered during test.
[2024-12-23 02:01:56,881 run_harness.py:166 INFO] Result: Accuracy run detected.
[2024-12-23 02:01:56,881 __init__.py:46 INFO] Running command: PYTHONPATH=code/bert/tensorrt/helpers python3 /home/cmuser/CM/repos/local/cache/ba8d5f2a6bc546f9/repo/closed/NVIDIA/build/inference/language/bert/accuracy-squad.py --log_file /cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/bert-99/offline/accuracy/mlperf_log_accuracy.json --vocab_file build/models/bert/vocab.txt --val_data /home/cmuser/CM/repos/local/cache/a8c152aef5494496/data/squad/dev-v1.1.json --out_file /cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/bert-99/offline/accuracy/predictions.json --output_dtype float16
[2024-12-24 23:00:57,429 run_harness.py:166 INFO] Result: Accuracy run detected.
[2024-12-24 23:00:57,429 __init__.py:46 INFO] Running command: PYTHONPATH=code/bert/tensorrt/helpers python3 /home/cmuser/CM/repos/local/cache/ba8d5f2a6bc546f9/repo/closed/NVIDIA/build/inference/language/bert/accuracy-squad.py --log_file /cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/bert-99/offline/accuracy/mlperf_log_accuracy.json --vocab_file build/models/bert/vocab.txt --val_data /home/cmuser/CM/repos/local/cache/a8c152aef5494496/data/squad/dev-v1.1.json --out_file /cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/bert-99/offline/accuracy/predictions.json --output_dtype float16
{"exact_match": 82.81929990539263, "f1": 90.15673510616978}
Reading examples...
Loading cached features from 'eval_features.pickle'...
Expand Down
Loading

0 comments on commit 9bea238

Please sign in to comment.