Skip to content

[SYSTEMDS-3929] Speed up Parquet frame reader/writer #2528

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Jakob-al28 wants to merge 5 commits into
base: main
Choose a base branch
from
Open

[SYSTEMDS-3929] Speed up Parquet frame reader/writer #2528

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
20e3c66
[SYSTEMDS-3929] Speed up Parquet frame reader/writer
Jul 1, 2026
e0916e1
Generate parquet test files with Spark
Jul 2, 2026
462335e
Merge branch 'main' into SYSTEMDS-3929-parquet
Jakob-al28 Jul 4, 2026
5d59591
Merge remote-tracking branch 'upstream/main' into SYSTEMDS-3929-parquet
Jakob-al28 Jul 12, 2026
257cfa8
[SYSTEMDS-3929] Improve array-direct parquet frame reader
Jakob-al28 Jul 14, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions src/main/java/org/apache/sysds/parser/DMLTranslator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1058,6 +1058,7 @@ public void constructHops(StatementBlock sb) {
case LIBSVM:
case HDF5:
case DELTA:
case PARQUET:
// columnar/text formats: no block layout (blocksize -1)
ae.setOutputParams(ae.getDim1(), ae.getDim2(), ae.getNnz(), ae.getUpdateType(), -1);
break;
Expand Down
2 changes: 2 additions & 0 deletions src/main/java/org/apache/sysds/runtime/io/FrameReaderFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,8 @@ public static FrameReader createFrameReader(FileFormat fmt, FileFormatProperties
case PROTO:
// TODO performance improvement: add parallel reader
return new FrameReaderProto();
case PARQUET:
return binaryParallel ? new FrameReaderParquetParallel() : new FrameReaderParquet();
case DELTA:
return textParallel ? new FrameReaderDeltaParallel() : new FrameReaderDelta();
default:
Expand Down
Loading