taiyang-li commented on PR #8708:
URL: 
https://github.com/apache/incubator-gluten/pull/8708#issuecomment-2656198113

   ```
   ### sparkDivide:  当分母为常数时,加速比24x
   优化后
   ------------------------------------------------------------------------
   Benchmark                              Time             CPU   Iterations
   ------------------------------------------------------------------------
   BM_SparkDivide_VectorVector       127921 ns       127916 ns         5409
   BM_SparkDivide_VectorConstant       1428 ns         1428 ns       497549
   BM_SparkDivide_ConstantVector     109748 ns       109744 ns         6521
   
   优化前
   ------------------------------------------------------------------------
   Benchmark                              Time             CPU   Iterations
   ------------------------------------------------------------------------
   BM_SparkDivide_VectorVector       129609 ns       129605 ns         5408
   BM_SparkDivide_VectorConstant      33923 ns        33921 ns        20599
   BM_SparkDivide_ConstantVector     105231 ns       105228 ns         6682    
   
   
   ### sparkCastFloattoInt*: float转int32加速比1.67x
   优化后
   --------------------------------------------------------------------
   Benchmark                          Time             CPU   Iterations
   --------------------------------------------------------------------
   BM_OptSparkCastFloatToInt     112905 ns       112900 ns         6178
   
   优化前
   --------------------------------------------------------------------
   Benchmark                          Time             CPU   Iterations
   --------------------------------------------------------------------
   BM_OptSparkCastFloatToInt     188640 ns       188631 ns         3795 
   
   
   
   ### checkDecimalOverflowSparkOrNull:  decimal转decimal  1.2x
   优化后 
   
---------------------------------------------------------------------------------
   Benchmark                                       Time             CPU   
Iterations
   
---------------------------------------------------------------------------------
   BM_OptCheckDecimalOverflowSparkOrNull1     619780 ns       619460 ns         
1105
   BM_OptCheckDecimalOverflowSparkOrNull2     547584 ns       547237 ns         
1290
   
   优化前
   
---------------------------------------------------------------------------------
   Benchmark                                       Time             CPU   
Iterations
   
---------------------------------------------------------------------------------
   BM_OptCheckDecimalOverflowSparkOrNull1     749359 ns       749337 ns         
 956
   BM_OptCheckDecimalOverflowSparkOrNull2     669309 ns       669282 ns         
1075
   ```


-- 
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.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to