Skip to content

Commit 8b6efc8

Browse files
mlcommons-botmlcommons-bot
committed
Auto-merge updates from auto-update branch
2 parents 53b5b20 + f7bf7d7 commit 8b6efc8

File tree

26 files changed

+2253
-2224
lines changed

26 files changed

+2253
-2224
lines changed

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

+8-8
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,9 @@
11
{
2-
"accelerator_frequency": "2520000 MHz",
2+
"accelerator_frequency": "2610000 MHz",
33
"accelerator_host_interconnect": "N/A",
44
"accelerator_interconnect": "N/A",
55
"accelerator_interconnect_topology": "",
6-
"accelerator_memory_capacity": "23.64971923828125 GB",
6+
"accelerator_memory_capacity": "23.54595947265625 GB",
77
"accelerator_memory_configuration": "N/A",
88
"accelerator_model_name": "NVIDIA GeForce RTX 4090",
99
"accelerator_on-chip_memories": "",
@@ -16,17 +16,17 @@
1616
"host_network_card_count": "1",
1717
"host_networking": "Gig Ethernet",
1818
"host_networking_topology": "N/A",
19-
"host_processor_caches": "L1d cache: 576 KiB, L1i cache: 384 KiB, L2 cache: 24 MiB, L3 cache: ",
20-
"host_processor_core_count": "24",
21-
"host_processor_frequency": "5800.0000",
19+
"host_processor_caches": "L1d cache: 512 KiB, L1i cache: 512 KiB, L2 cache: 16 MiB, L3 cache: 64 MiB",
20+
"host_processor_core_count": "16",
21+
"host_processor_frequency": "5881.0000",
2222
"host_processor_interconnect": "",
23-
"host_processor_model_name": "13th Gen Intel(R) Core(TM) i9-13900K",
23+
"host_processor_model_name": "AMD Ryzen 9 7950X 16-Core Processor",
2424
"host_processors_per_node": "1",
25-
"host_storage_capacity": "9.4T",
25+
"host_storage_capacity": "6.8T",
2626
"host_storage_type": "SSD",
2727
"hw_notes": "",
2828
"number_of_nodes": "1",
29-
"operating_system": "Ubuntu 20.04 (linux-6.8.0-49-generic-glibc2.31)",
29+
"operating_system": "Ubuntu 20.04 (linux-6.8.0-51-generic-glibc2.31)",
3030
"other_software_stack": "Python: 3.8.10, GCC-9.4.0, Using Docker , CUDA 12.2",
3131
"status": "available",
3232
"submitter": "MLCommons",

‎open/MLCommons/measurements/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/3d-unet-99.9/offline/README.md

+3-3
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ pip install -U cmind
1919

2020
cm rm cache -f
2121

22-
cm pull repo mlcommons@mlperf-automations --checkout=a90475d2de72bf0622cebe8d5ca8eb8c9d872fbd
22+
cm pull repo mlcommons@mlperf-automations --checkout=467517e4a572872046058e394a0d83512cfff38b
2323

2424
cm run script \
2525
--tags=app,mlperf,inference,generic,_nvidia,_3d-unet-99.9,_tensorrt,_cuda,_valid,_r4.1-dev_default,_offline \
@@ -71,7 +71,7 @@ cm run script \
7171
--env.CM_DOCKER_REUSE_EXISTING_CONTAINER=yes \
7272
--env.CM_DOCKER_DETACHED_MODE=yes \
7373
--env.CM_MLPERF_INFERENCE_RESULTS_DIR_=/home/arjun/gh_action_results/valid_results \
74-
--env.CM_DOCKER_CONTAINER_ID=a8263c5f491a \
74+
--env.CM_DOCKER_CONTAINER_ID=e0979bc4bb63 \
7575
--env.CM_MLPERF_LOADGEN_COMPLIANCE_TEST=TEST01 \
7676
--add_deps_recursive.compiler.tags=gcc \
7777
--add_deps_recursive.coco2014-original.tags=_full \
@@ -129,4 +129,4 @@ Model Precision: int8
129129
`DICE`: `0.86236`, Required accuracy for closed division `>= 0.86084`
130130

131131
### Performance Results
132-
`Samples per second`: `4.16751`
132+
`Samples per second`: `3.45061`

‎open/MLCommons/measurements/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/3d-unet-99.9/offline/accuracy_console.out

+12-12
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,8 @@
1-
[2024-12-24 20:58:26,838 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x1
2-
[2024-12-24 20:58:27,177 harness.py:249 INFO] The harness will load 3 plugins: ['build/plugins/pixelShuffle3DPlugin/libpixelshuffle3dplugin.so', 'build/plugins/conv3D1X1X1K4Plugin/libconv3D1X1X1K4Plugin.so', 'build/plugins/conv3D3X3X3C1K32Plugin/libconv3D3X3X3C1K32Plugin.so']
3-
[2024-12-24 20:58:27,177 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x1_TRT/3d-unet-99.9/Offline
4-
[2024-12-24 20:58:27,177 __init__.py:46 INFO] Running command: ./build/bin/harness_3dunet --plugins="build/plugins/pixelShuffle3DPlugin/libpixelshuffle3dplugin.so,build/plugins/conv3D1X1X1K4Plugin/libconv3D1X1X1K4Plugin.so,build/plugins/conv3D3X3X3C1K32Plugin/libconv3D3X3X3C1K32Plugin.so" --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/3d-unet-99.9/offline/accuracy" --logfile_prefix="mlperf_log_" --performance_sample_count=43 --test_mode="AccuracyOnly" --gpu_copy_streams=1 --gpu_inference_streams=1 --use_deque_limit=true --gpu_batch_size=8 --map_path="data_maps/kits19/val_map.txt" --mlperf_conf_path="/home/cmuser/CM/repos/local/cache/90c7069b92e34687/inference/mlperf.conf" --tensor_path="build/preprocessed_data/KiTS19/inference/int8" --use_graphs=false --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/d45c91f344264e3aa96127ea0f4c45ed.conf" --unet3d_sw_gaussian_patch_path="/home/cmuser/CM/repos/local/cache/a8c152aef5494496/preprocessed_data/KiTS19/etc/gaussian_patches.npy" --gpu_engines="./build/engines/RTX4090x1/3d-unet/Offline/3d-unet-Offline-gpu-b8-int8.custom_k_99_9_MaxP.plan" --max_dlas=0 --slice_overlap_patch_kernel_cg_impl=false --scenario Offline --model 3d-unet
5-
[2024-12-24 20:58:27,177 __init__.py:53 INFO] Overriding Environment
1+
[2024-12-28 13:51:30,390 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x1
2+
[2024-12-28 13:51:30,759 harness.py:249 INFO] The harness will load 3 plugins: ['build/plugins/pixelShuffle3DPlugin/libpixelshuffle3dplugin.so', 'build/plugins/conv3D1X1X1K4Plugin/libconv3D1X1X1K4Plugin.so', 'build/plugins/conv3D3X3X3C1K32Plugin/libconv3D3X3X3C1K32Plugin.so']
3+
[2024-12-28 13:51:30,759 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x1_TRT/3d-unet-99.9/Offline
4+
[2024-12-28 13:51:30,759 __init__.py:46 INFO] Running command: ./build/bin/harness_3dunet --plugins="build/plugins/pixelShuffle3DPlugin/libpixelshuffle3dplugin.so,build/plugins/conv3D1X1X1K4Plugin/libconv3D1X1X1K4Plugin.so,build/plugins/conv3D3X3X3C1K32Plugin/libconv3D3X3X3C1K32Plugin.so" --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/3d-unet-99.9/offline/accuracy" --logfile_prefix="mlperf_log_" --performance_sample_count=43 --test_mode="AccuracyOnly" --gpu_copy_streams=1 --gpu_inference_streams=1 --use_deque_limit=true --gpu_batch_size=8 --map_path="data_maps/kits19/val_map.txt" --mlperf_conf_path="/home/cmuser/CM/repos/local/cache/90c7069b92e34687/inference/mlperf.conf" --tensor_path="build/preprocessed_data/KiTS19/inference/int8" --use_graphs=false --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/bf1ea864b7174d989fcad62caf788ae1.conf" --unet3d_sw_gaussian_patch_path="/home/cmuser/CM/repos/local/cache/a8c152aef5494496/preprocessed_data/KiTS19/etc/gaussian_patches.npy" --gpu_engines="./build/engines/RTX4090x1/3d-unet/Offline/3d-unet-Offline-gpu-b8-int8.custom_k_99_9_MaxP.plan" --max_dlas=0 --slice_overlap_patch_kernel_cg_impl=false --scenario Offline --model 3d-unet
5+
[2024-12-28 13:51:30,759 __init__.py:53 INFO] Overriding Environment
66
benchmark : Benchmark.UNET3D
77
buffer_manager_thread_count : 0
88
data_dir : /home/cmuser/CM/repos/local/cache/a8c152aef5494496/data
@@ -11,7 +11,7 @@ gpu_copy_streams : 1
1111
gpu_inference_streams : 1
1212
input_dtype : int8
1313
input_format : linear
14-
log_dir : /home/cmuser/CM/repos/local/cache/ba8d5f2a6bc546f9/repo/closed/NVIDIA/build/logs/2024.12.24-20.58.25
14+
log_dir : /home/cmuser/CM/repos/local/cache/ba8d5f2a6bc546f9/repo/closed/NVIDIA/build/logs/2024.12.28-13.51.27
1515
map_path : data_maps/kits19/val_map.txt
1616
mlperf_conf_path : /home/cmuser/CM/repos/local/cache/90c7069b92e34687/inference/mlperf.conf
1717
offline_expected_qps : 0.0
@@ -25,7 +25,7 @@ test_mode : AccuracyOnly
2525
unet3d_sw_gaussian_patch_path : /home/cmuser/CM/repos/local/cache/a8c152aef5494496/preprocessed_data/KiTS19/etc/gaussian_patches.npy
2626
use_deque_limit : True
2727
use_graphs : False
28-
user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/d45c91f344264e3aa96127ea0f4c45ed.conf
28+
user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/bf1ea864b7174d989fcad62caf788ae1.conf
2929
system_id : RTX4090x1
3030
config_name : RTX4090x1_3d-unet_Offline
3131
workload_setting : WorkloadSetting(HarnessType.Custom, AccuracyTarget.k_99_9, PowerSetting.MaxP)
@@ -39,7 +39,7 @@ power_limit : None
3939
cpu_freq : None
4040
&&&& RUNNING MLPerf_Inference_3DUNet_Harness # ./build/bin/harness_3dunet
4141
[I] mlperf.conf path: /home/cmuser/CM/repos/local/cache/90c7069b92e34687/inference/mlperf.conf
42-
[I] user.conf path: /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/d45c91f344264e3aa96127ea0f4c45ed.conf
42+
[I] user.conf path: /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/bf1ea864b7174d989fcad62caf788ae1.conf
4343
Creating QSL.
4444
Finished Creating QSL.
4545
Setting up SUT.
@@ -50,12 +50,12 @@ Setting up SUT.
5050
[I] Device:0: ./build/engines/RTX4090x1/3d-unet/Offline/3d-unet-Offline-gpu-b8-int8.custom_k_99_9_MaxP.plan has been successfully loaded.
5151
[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.)
5252
[I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 52, GPU 1820 (MiB)
53-
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 52, GPU 1828 (MiB)
53+
[I] [TRT] [MemUsageChange] Init cuDNN: CPU +1, GPU +8, now: CPU 53, GPU 1828 (MiB)
5454
[I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +2218, now: CPU 0, GPU 2247 (MiB)
5555
[I] Creating batcher thread: 0 EnableBatcherThreadPerDevice: true
5656
Finished setting up SUT.
5757
Starting warmup. Running for a minimum of 5 seconds.
58-
Finished warmup. Ran for 5.43752s.
58+
Finished warmup. Ran for 5.44189s.
5959
Starting running actual test.
6060

6161
No warnings encountered during test.
@@ -72,8 +72,8 @@ Device Device:0 processed:
7272
PerSampleCudaMemcpy Calls: 43
7373
BatchedCudaMemcpy Calls: 0
7474
&&&& PASSED MLPerf_Inference_3DUNet_Harness # ./build/bin/harness_3dunet
75-
[2024-12-24 20:58:45,473 run_harness.py:166 INFO] Result: Accuracy run detected.
76-
[2024-12-24 20:58:45,473 __init__.py:46 INFO] Running command: python3 code/3d-unet/tensorrt/accuracy_kits.py --log_file /cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/3d-unet-99.9/offline/accuracy/mlperf_log_accuracy.json
75+
[2024-12-28 13:51:55,689 run_harness.py:166 INFO] Result: Accuracy run detected.
76+
[2024-12-28 13:51:55,690 __init__.py:46 INFO] Running command: python3 code/3d-unet/tensorrt/accuracy_kits.py --log_file /cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/3d-unet-99.9/offline/accuracy/mlperf_log_accuracy.json
7777
Loading necessary metadata...
7878
Loading loadgen accuracy log...
7979
Running postprocessing...

0 commit comments

Comments
 (0)