jonatan1626 edited a comment on issue #17159: Performance regression from 1.4.1 
to 1.5.1
URL: 
https://github.com/apache/incubator-mxnet/issues/17159#issuecomment-568782727
 
 
   @apeforest so I think it's using Apache MXNet already? When running the 
script this is printed:
   ```
   EIA context not available, trying GPU...
   GPU not available, trying CPU...
   @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
   starting test for Model: resnext-50 as float32 with batch size 1
   ```
   
   I reran the benchmark with the above script on c5.18xlarge:
   
   ```
   export OMP_NUM_THREADS=28
   export KMP_AFFINITY=granularity=fine,noduplicates,compact,1,0
   numactl --physcpubind=0-27 --membind=0 python gluon_resnext50.py --iteration 
100000
   ```
   
   **1.4.1**
   Install: `pip install mxnet-mkl==1.4.1`
   Output:
   ```
   Model: resnext-50
        ----Latency----
        Model Partition Time: 0
        Model Load Time: 91.20917320251465
        First Inference: 116.30487442016602
        p99: 16.54815673828125
        p90: 16.46280288696289
        p50: 16.413450241088867
        Avg: 16.413932993352866
        StdDev: 0.09641098586944327
   ```
   
   **1.5**
   Install: `pip install mxnet-mkl==1.5.1`
   Output:
   ```
   Model: resnext-50
        ----Latency----
        Model Partition Time: 0
        Model Load Time: 96.67277336120605
        First Inference: 135.10727882385254
        p99: 32.649993896484375
        p90: 31.419754028320312
        p50: 29.414892196655273
        Avg: 29.275005764308506
        StdDev: 1.75405292166976
   ```
   
   **1.6**
   Install: `pip install mxnet-mkl==1.6.0b20191025`
   Output:
   ```
   Model: resnext-50
        ----Latency----
        Model Partition Time: 0
        Model Load Time: 87.45336532592773
        First Inference: 116.45269393920898
        p99: 18.494844436645508
        p90: 18.326282501220703
        p50: 18.211841583251953
        Avg: 18.22383847160674
        StdDev: 0.09122314713059498
   ```

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to