[
https://issues.apache.org/jira/browse/SPARK-39480?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Max Gekk updated SPARK-39480:
-----------------------------
Fix Version/s: (was: 3.3.0)
> Parquet bit-packing de/encode optimization
> ------------------------------------------
>
> Key: SPARK-39480
> URL: https://issues.apache.org/jira/browse/SPARK-39480
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 3.3.0
> Reporter: Fang-Xie
> Priority: Major
> Attachments: image-2022-06-15-22-50-12-759.png,
> image-2022-06-15-22-52-56-792.png, image-2022-06-15-22-53-35-937.png,
> image-2022-06-15-22-54-07-288.png
>
>
> Current Spark use Parquet-mr as parquet reader/writer library, but the
> built-in bit-packing en/decode is not efficient enough.
> Our optimization for Parquet bit-packing en/decode with jdk.incubator.vector
> in Open JDK18 brings prominent performance improvement.
> Due to Vector API is added to OpenJDK since 16, So this optimization request
> JDK16 or higher.
> *Below are our test results*
> Functional test is based on open-source parquet-mr Bit-pack decoding
> function: *_public final void unpack8Values(final byte[] in, final int inPos,
> final int[] out, final int outPos)_* __
> compared with our implementation with vector API *_public final void
> unpack8Values_vec(final byte[] in, final int inPos, final int[] out, final
> int outPos)_*
> We tested 10 pairs (open source parquet bit unpacking vs ours optimized
> vectorized SIMD implementation) decode function with bit
> width=\{1,2,3,4,5,6,7,8,9,10}, below are test results:
> !image-2022-06-15-22-50-12-759.png|width=513,height=259!
>
> We integrated our bit-packing decode implementation into parquet-mr, tested
> the parquet batch reader ability from Spark VectorizedParquetRecordReader
> which get parquet column data by the batch way. We construct parquet file
> with different row count and column count, the column data type is Int32, the
> maximum int value is 127 which satisfies bit pack encode with bit width=7,
> the count of the row is from 10k to 100 million and the count of the column
> is from 1 to 4.
> !image-2022-06-15-22-52-56-792.png|width=328,height=167!
> !image-2022-06-15-22-53-35-937.png|width=354,height=175!
> !image-2022-06-15-22-54-07-288.png|width=352,height=173!
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
