[GitHub] [arrow] jhorstmann commented on pull request #8929: ARROW-10914: [Rust] Refactor simd arithmetic kernels to use chunked iteration

[GitBox <gi...@apache.org>]

jhorstmann commented on pull request #8929:
URL: https://github.com/apache/arrow/pull/8929#issuecomment-746051869


   I'm seeing bigger variations on the benchmark numbers between runs, the results below between current master and this pr are from one of the faster runs:
   
   ```
   ~/arrow/rust/arrow$ cargo +nightly-2020-11-24 bench --features simd --bench arithmetic_kernels
      Compiling arrow v3.0.0-SNAPSHOT (/home/ubuntu/arrow/rust/arrow)
       Finished bench [optimized] target(s) in 1m 39s
        Running /home/ubuntu/arrow/rust/target/release/deps/arithmetic_kernels-4b00176b1c415f0c
   Gnuplot not found, using plotters backend
   add 512                 time:   [319.21 ns 319.38 ns 319.52 ns]                    
                           change: [-24.243% -24.193% -24.140%] (p = 0.00 < 0.05)
                           Performance has improved.
   Found 10 outliers among 100 measurements (10.00%)
     2 (2.00%) low severe
     5 (5.00%) low mild
     2 (2.00%) high mild
     1 (1.00%) high severe
   
   subtract 512            time:   [387.54 ns 387.86 ns 388.40 ns]                         
                           change: [-19.909% -19.766% -19.578%] (p = 0.00 < 0.05)
                           Performance has improved.
   Found 6 outliers among 100 measurements (6.00%)
     1 (1.00%) low mild
     3 (3.00%) high mild
     2 (2.00%) high severe
   
   multiply 512            time:   [515.01 ns 517.68 ns 522.09 ns]                          
                           change: [-9.9324% -9.6166% -9.1766%] (p = 0.00 < 0.05)
                           Performance has improved.
   Found 4 outliers among 100 measurements (4.00%)
     1 (1.00%) high mild
     3 (3.00%) high severe
   
   divide 512              time:   [430.74 ns 430.80 ns 430.86 ns]                       
                           change: [-41.347% -41.234% -41.143%] (p = 0.00 < 0.05)
                           Performance has improved.
   Found 10 outliers among 100 measurements (10.00%)
     1 (1.00%) low mild
     6 (6.00%) high mild
     3 (3.00%) high severe
   
   limit 512, 512          time:   [107.84 ns 107.94 ns 108.12 ns]                           
                           change: [+0.6778% +0.9025% +1.2602%] (p = 0.00 < 0.05)
                           Change within noise threshold.
   Found 7 outliers among 100 measurements (7.00%)
     1 (1.00%) low mild
     4 (4.00%) high mild
     2 (2.00%) high severe
   
   add_nulls_512           time:   [383.53 ns 383.61 ns 383.69 ns]                          
                           change: [-20.450% -20.350% -20.270%] (p = 0.00 < 0.05)
                           Performance has improved.
   Found 10 outliers among 100 measurements (10.00%)
     1 (1.00%) low severe
     1 (1.00%) low mild
     3 (3.00%) high mild
     5 (5.00%) high severe
   
   divide_nulls_512        time:   [543.48 ns 543.96 ns 544.84 ns]                              
                           change: [-23.819% -23.700% -23.587%] (p = 0.00 < 0.05)
                           Performance has improved.
   Found 10 outliers among 100 measurements (10.00%)
     3 (3.00%) low severe
     1 (1.00%) low mild
     1 (1.00%) high mild
     5 (5.00%) high severe
   ```


----------------------------------------------------------------
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:
users@infra.apache.org