jianxind commented on pull request #7029:
URL: https://github.com/apache/arrow/pull/7029#issuecomment-619501029
> Just curious if you see and impact on parquet-arrow-reader-writer
benchmarks? That is the ultimate goal of the speedup.
No impact, I checked all items for parquet-arrow-reader-writer-benchmark...
Below is the perf top on the bench-marking of BM_ReadColumn<true,Int32Type>
and BM_WriteColumn<true,Int32Type>, seems these function is not on the path for
them.
BM_ReadColumn<true,Int32Type>:
31.60% libparquet.so.18.0.0 [.]
_ZN5arrow4util10RleDecoder22GetBatchWithDictSpacedIiEEiPKT_iPS3_iiPKhl
21.74% libparquet.so.18.0.0 [.]
_ZN7parquet8internalL24DefinitionLevelsToBitmapEPKslssPlS3_Phl
BM_WriteColumn<true,Int32Type>:
20.64% libparquet.so.18.0.0 [.]
_ZN5mpark6detail10visitation4base17make_fmatrix_implIONS1_7variant13value_visitorIRZN7parquet5arrow12_GLOBAL__N_19WritePathENS7_12Ele
16.19% libparquet.so.18.0.0 [.]
_ZN7parquet15DictEncoderImplINS_12PhysicalTypeILNS_4Type4typeE1EEEE3PutERKi.constprop.455
11.50% libparquet.so.18.0.0 [.]
_ZN7parquet12LevelEncoder6EncodeEiPKs
7.93% libparquet.so.18.0.0 [.]
_ZN5arrow4util10RleEncoder15FlushLiteralRunEb
----------------------------------------------------------------
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]
