Skip to content

Commit 726b152

Browse files
mlcommons-botmlcommons-bot
committed
Auto-merge updates from auto-update branch
2 parents c307246 + 5dc0163 commit 726b152

File tree

13 files changed

+411
-432
lines changed

13 files changed

+411
-432
lines changed

‎open/MLCommons/measurements/gh_ubuntu-latest-reference-cpu-tvm-onnx_v1.19.2-default_config/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
| Model | Scenario | Accuracy | Throughput | Latency (in ms) |
22
|----------|------------|------------|--------------|-------------------|
3-
| resnet50 | offline | 80 | 1.712 | - |
3+
| resnet50 | offline | 80 | 1.718 | - |

‎open/MLCommons/measurements/gh_ubuntu-latest-reference-cpu-tvm-onnx_v1.19.2-default_config/resnet50/offline/README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ pip install -U mlcflow
1717

1818
mlc rm cache -f
1919

20-
mlc pull repo anandhu-eng@mlperf-automations --checkout=cb411cf5aaa32ba8642bd1c0838ddab2b30b74dc
20+
mlc pull repo anandhu-eng@mlperf-automations --checkout=2d10b02bf8b09bc258d666cb21ce73bc9bc9d4ab
2121

2222

2323
```
@@ -41,4 +41,4 @@ Model Precision: fp32
4141
`acc`: `80.0`, Required accuracy for closed division `>= 75.6954`
4242

4343
### Performance Results
44-
`Samples per second`: `1.712`
44+
`Samples per second`: `1.71803`

‎open/MLCommons/measurements/gh_ubuntu-latest-reference-cpu-tvm-onnx_v1.19.2-default_config/resnet50/offline/accuracy_console.out

Lines changed: 6 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,9 @@
1-
python3 python/main.py --profile resnet50-onnxruntime --model "/home/runner/MLC/repos/local/cache/get-tvm-model_95cd4a00/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_6fcea732 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_5e279bb6/test_results/gh_ubuntu-latest-reference-cpu-tvm-onnx-v1.19.2-default_config/resnet50/offline/accuracy" --backend tvm --scenario Offline --max-batchsize 1 --count 5 --threads 4 --user_conf /home/runner/MLC/repos/anandhu-eng@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/4416abd2d998404c87818d2c250c3eb9.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_6fcea732 --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_33d19d43/val.txt
2-
INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_6fcea732', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_33d19d43/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_95cd4a00/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_5e279bb6/test_results/gh_ubuntu-latest-reference-cpu-tvm-onnx-v1.19.2-default_config/resnet50/offline/accuracy', inputs=None, outputs=['ArgMax:0'], backend='tvm', device=None, model_name='resnet50', threads=4, qps=None, cache=0, cache_dir='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_6fcea732', preprocessed_dir=None, use_preprocessed_dataset=True, accuracy=True, find_peak_performance=False, debug=False, user_conf='/home/runner/MLC/repos/anandhu-eng@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/4416abd2d998404c87818d2c250c3eb9.conf', audit_conf='audit.config', time=None, count=5, performance_sample_count=None, max_latency=None, samples_per_query=8)
1+
python3 python/main.py --profile resnet50-onnxruntime --model "/home/runner/MLC/repos/local/cache/get-tvm-model_668441ad/resnet50_v1.onnx" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_12d64445 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_c5a1d2f8/test_results/gh_ubuntu-latest-reference-cpu-tvm-onnx-v1.19.2-default_config/resnet50/offline/accuracy" --backend tvm --scenario Offline --max-batchsize 1 --count 5 --threads 4 --user_conf /home/runner/MLC/repos/anandhu-eng@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/41f5d675935e4456b56b9a9c99b099fc.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_12d64445 --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_20708dfb/val.txt
2+
INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_12d64445', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_20708dfb/val.txt', data_format=None, profile='resnet50-onnxruntime', scenario='Offline', max_batchsize=1, model='/home/runner/MLC/repos/local/cache/get-tvm-model_668441ad/resnet50_v1.onnx', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_c5a1d2f8/test_results/gh_ubuntu-latest-reference-cpu-tvm-onnx-v1.19.2-default_config/resnet50/offline/accuracy', inputs=None, outputs=['ArgMax:0'], backend='tvm', device=None, model_name='resnet50', threads=4, qps=None, cache=0, cache_dir='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_12d64445', preprocessed_dir=None, use_preprocessed_dataset=True, accuracy=True, find_peak_performance=False, debug=False, user_conf='/home/runner/MLC/repos/anandhu-eng@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/41f5d675935e4456b56b9a9c99b099fc.conf', audit_conf='audit.config', time=None, count=5, performance_sample_count=None, max_latency=None, samples_per_query=8)
33
INFO:imagenet:Loading 5 preprocessed images using 4 threads
44
INFO:imagenet:loaded 5 images, cache=0, already_preprocessed=True, took=0.0sec
5-
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_95cd4a00/model-tvm.so
5+
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_668441ad/model-tvm.so
66
INFO:main:starting TestScenario.Offline
7-
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_95cd4a00/model-tvm.so
8-
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_95cd4a00/model-tvm.so
9-
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_95cd4a00/model-tvm.so
10-
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_95cd4a00/model-tvm.so
11-
TestScenario.Offline qps=1.72, mean=1.7643, time=2.911, acc=80.000%, queries=5, tiles=50.0:1.4814,80.0:1.7778,90.0:2.3313,95.0:2.6080,99.0:2.8294,99.9:2.8793
7+
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_668441ad/model-tvm.so
8+
TVM: loading model /home/runner/MLC/repos/local/cache/get-tvm-model_668441ad/model-tvm.so
9+
TestScenario.Offline qps=1.65, mean=1.8861, time=3.022, acc=80.000%, queries=5, tiles=50.0:1.6168,80.0:1.9065,90.0:2.4481,95.0:2.7189,99.0:2.9356,99.9:2.9843

‎open/MLCommons/measurements/gh_ubuntu-latest-reference-cpu-tvm-onnx_v1.19.2-default_config/resnet50/offline/cpu_info.json

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -20,6 +20,7 @@
2020
"MLC_HOST_CPU_L2_CACHE_SIZE": "1 MiB (2 instances)",
2121
"MLC_HOST_CPU_L3_CACHE_SIZE": "32 MiB (1 instance)",
2222
"MLC_HOST_CPU_NUMA_NODES": "1",
23+
"MLC_HOST_CPU_START_CORES": "0",
2324
"MLC_HOST_CPU_TOTAL_LOGICAL_CORES": "4",
2425
"MLC_HOST_CPU_TOTAL_PHYSICAL_CORES": "2",
2526
"MLC_HOST_CPU_PHYSICAL_CORES_LIST": "0-1",

0 commit comments

Comments
 (0)