[
https://issues.apache.org/jira/browse/PARQUET-2190?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17696658#comment-17696658
]
ASF GitHub Bot commented on PARQUET-2190:
-----------------------------------------
jiangjiguang closed pull request #1006: PARQUET-2190 byte array has better
performance than ByteBuffer
URL: https://github.com/apache/parquet-mr/pull/1006
> byte array has better performance than ByteBuffer
> --------------------------------------------------
>
> Key: PARQUET-2190
> URL: https://issues.apache.org/jira/browse/PARQUET-2190
> Project: Parquet
> Issue Type: Improvement
> Reporter: jiangjiguang0719
> Priority: Major
>
> The BytePacker should add the following method
> public abstract void unpack8Values(final byte[] input, final int inPos, final
> int[] output, final int outPos);
> to replace method
> @Deprecated
> public void unpack8Values(final byte[] input, final int inPos, final int[]
> output, final int outPos) {
> unpack8Values(ByteBuffer.wrap(input), inPos, output, outPos);
> }
>
> Tested by me byte array has better performance than ByteBuffer,
> The test result is:
> [Unpack8ValuesByteArray spent time] 80 ms
> [Unpack8ValuesByteBuffer spent time] 133 ms
>
> The test code is:
> package org.apache.parquet.column.values.bitpacking;
> import java.nio.ByteBuffer;
> public class ByteBufferTest {
> private static final BytePacker bytePacker =
> Packer.LITTLE_ENDIAN.newBytePacker(7);
> private static final int COUNT = 100000;
> public static void main(String[] args) {
> byte [] in = new byte[1008];
> int [] out = new int[1152];
> int [] out1 = new int[1152];
> int [] out2 = new int[1152];
> int res = 0;
> for(int i = 0; i < in.length; i++) {
> in[i] = (byte) i;
> }
> for(int i = 0; i < COUNT; i++) {
> res += unpack8ValuesBytes(in, out, i % out.length);
> }
> res = 0;
> long t1 = System.currentTimeMillis();
> for(int i = 0; i < COUNT; i++) {
> res += unpack8ValuesBytes(in, out1, i % out.length);
> }
> long t2 = System.currentTimeMillis();
> System.out.println("[Unpack8ValuesByteArray spent time] " + (t2-t1) + "
> ms");
> ByteBuffer byteBuffer = ByteBuffer.wrap(in);
> for(int i = 0; i < COUNT; i++) {
> res += unpack8ValuesByteBuffer(byteBuffer, out, i % out.length);
> }
> res = 0;
> long t3 = System.currentTimeMillis();
> for(int i = 0; i < COUNT; i++) {
> res += unpack8ValuesByteBuffer(byteBuffer, out2, i % out.length);
> }
> long t4 = System.currentTimeMillis();
> System.out.println("[Unpack8ValuesByteBuffer spent time] " + (t4-t3) + "
> ms");
> for (int i=0; i<out1.length; i++) {
> if(out1[i] != out2[i]) {
> System.out.println("diff: " + out1[i] + " " + out2[i]);
> }
> }
> }
> private static int unpack8ValuesBytes(byte [] in, int [] out, int ctr) {
> for(int i = 0, j = 0; i < in.length; i+=7, j+=8) {
> bytePacker.unpack8Values(in, i, out, j);
> }
> return out[ctr];
> }
> private static int unpack8ValuesByteBuffer(ByteBuffer in, int [] out, int
> ctr) {
> for(int i = 0, j = 0; i < in.capacity(); i+=7, j+=8) {
> bytePacker.unpack8Values(in, i, out, j);
> }
> return out[ctr];
> }
> }
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
