dongjoon-hyun commented on code in PR #52600:
URL: https://github.com/apache/spark/pull/52600#discussion_r2427777987
##########
core/benchmarks/ZStandardBenchmark-results.txt:
##########
@@ -3,80 +3,80 @@ Benchmark ZStandardCompressionCodec
================================================================================================
OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
-AMD EPYC 7763 64-Core Processor
+AMD EPYC 9V74 80-Core Processor
Benchmark ZStandardCompressionCodec: Best Time(ms) Avg
Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
--------------------------------------------------------------------------------------------------------------------------------------
-Compression 10000 times at level 1 without buffer pool 265
267 1 0.0 26513.9 1.0X
-Compression 10000 times at level 2 without buffer pool 298
300 1 0.0 29837.5 0.9X
-Compression 10000 times at level 3 without buffer pool 809
809 0 0.0 80903.8 0.3X
-Compression 10000 times at level 1 with buffer pool 578
579 0 0.0 57809.5 0.5X
-Compression 10000 times at level 2 with buffer pool 609
609 1 0.0 60892.6 0.4X
-Compression 10000 times at level 3 with buffer pool 717
728 9 0.0 71748.2 0.4X
+Compression 10000 times at level 1 without buffer pool 190
191 0 0.1 18996.4 1.0X
+Compression 10000 times at level 2 without buffer pool 214
215 0 0.0 21407.3 0.9X
+Compression 10000 times at level 3 without buffer pool 811
812 1 0.0 81094.7 0.2X
+Compression 10000 times at level 1 with buffer pool 640
640 0 0.0 63962.8 0.3X
+Compression 10000 times at level 2 with buffer pool 661
663 1 0.0 66123.6 0.3X
+Compression 10000 times at level 3 with buffer pool 758
758 0 0.0 75773.8 0.3X
OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
-AMD EPYC 7763 64-Core Processor
+AMD EPYC 9V74 80-Core Processor
Benchmark ZStandardCompressionCodec: Best Time(ms)
Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------------------------
-Decompression 10000 times from level 1 without buffer pool 592
595 4 0.0 59245.4 1.0X
-Decompression 10000 times from level 2 without buffer pool 592
594 1 0.0 59209.6 1.0X
-Decompression 10000 times from level 3 without buffer pool 593
593 0 0.0 59309.5 1.0X
-Decompression 10000 times from level 1 with buffer pool 540
541 0 0.0 54039.4 1.1X
-Decompression 10000 times from level 2 with buffer pool 541
541 0 0.0 54058.9 1.1X
-Decompression 10000 times from level 3 with buffer pool 540
541 0 0.0 54016.9 1.1X
+Decompression 10000 times from level 1 without buffer pool 166
167 0 0.1 16645.6 1.0X
+Decompression 10000 times from level 2 without buffer pool 166
166 0 0.1 16558.6 1.0X
+Decompression 10000 times from level 3 without buffer pool 166
167 0 0.1 16629.4 1.0X
Review Comment:
The ZSTD decompression speed is improved in Java 17 benchmark. Since Java 21
doesn't show any change, it could be some transient result.
--
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]
