Re: [PR] GroupVarInt Encoding Implementation for HNSW Graphs [lucene]

aylonsk commented on PR #14932: URL: https://github.com/apache/lucene/pull/14932#issuecomment-3156552514 Thank you for your suggestions @kaivalnp, I have pushed these changes to the PR. @jpountz I ran the knnPerfTest on the baseline VarInt vs candidate GroupVarInt implementations. T

Re: [PR] Removing unused parameter [lucene]

github-actions[bot] commented on PR #15033: URL: https://github.com/apache/lucene/pull/15033#issuecomment-3156519267 This PR does not have an entry in lucene/CHANGES.txt. Consider adding one. If the PR doesn't need a changelog entry, then add the skip-changelog label to it and you will stop

[PR] Removing unused parameter [lucene]

jainankitk opened a new pull request, #15033: URL: https://github.com/apache/lucene/pull/15033 ### Description Cleans up unused parameter in `MemorySegmentIndexInput` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub

Re: [PR] Adding profiling support for concurrent segment search [lucene]

jainankitk commented on PR #14413: URL: https://github.com/apache/lucene/pull/14413#issuecomment-3156324306 @jpountz - I have addressed all the comments from earlier review. Are you able to take another look, to help close this out? -- This is an automated message from the Apache Git Serv

Re: [PR] Move finishMerge to a finally block so it always runs [lucene]

dweiss commented on code in PR #14977: URL: https://github.com/apache/lucene/pull/14977#discussion_r2255099334 ## lucene/test-framework/src/java/org/apache/lucene/tests/codecs/asserting/AssertingKnnVectorsFormat.java: ## @@ -230,8 +230,7 @@ public Map getOffHeapByteSize(FieldInf

Re: [PR] GroupVarInt Encoding Implementation for HNSW Graphs [lucene]

kaivalnp commented on code in PR #14932: URL: https://github.com/apache/lucene/pull/14932#discussion_r2255078770 ## lucene/core/src/java/org/apache/lucene/codecs/lucene99/Lucene99HnswVectorsWriter.java: ## @@ -88,11 +90,24 @@ public Lucene99HnswVectorsWriter( int numMerge

Re: [PR] Implement off-heap quantized scoring [lucene]

kaivalnp commented on PR #14863: URL: https://github.com/apache/lucene/pull/14863#issuecomment-3155945254 Thanks for the review @thecoop! I've tried to address your comments above, do let me know if you have more feedback.. -- This is an automated message from the Apache Git Service. To r

Re: [PR] Add bulk off-heap scoring for float32 vectors [lucene]

mccullocht commented on PR #14980: URL: https://github.com/apache/lucene/pull/14980#issuecomment-3155740647 Hey Chris, I think when I tried my hand at a similar approach with panama I ran into similar (neutral) results on graviton2 and really the only thing that helped there was

Re: [PR] Implement off-heap quantized scoring [lucene]

kaivalnp commented on code in PR #14863: URL: https://github.com/apache/lucene/pull/14863#discussion_r2254730354 ## lucene/core/src/java24/org/apache/lucene/internal/vectorization/PanamaVectorUtilSupport.java: ## @@ -530,7 +566,41 @@ private int dotProductBody512Int4Packed(byte[

Re: [PR] Add bulk off-heap scoring for float32 vectors [lucene]

ChrisHegarty commented on PR #14980: URL: https://github.com/apache/lucene/pull/14980#issuecomment-3155502316 Thanks @mccullocht - not sure why you're not seeing improvement on Graviton2, but I'll post some more results that I see when testing across different platforms. Search laten

Re: [PR] Avoid reconstructing HNSW graph during singleton merges [lucene]

Pulkitg64 commented on code in PR #15003: URL: https://github.com/apache/lucene/pull/15003#discussion_r2254248192 ## lucene/core/src/java/org/apache/lucene/codecs/lucene99/Lucene99HnswVectorsWriter.java: ## @@ -347,12 +350,195 @@ private void reconstructAndWriteNeighbours(

Re: [PR] Avoid reconstructing HNSW graph during singleton merges [lucene]

Pulkitg64 commented on code in PR #15003: URL: https://github.com/apache/lucene/pull/15003#discussion_r2254248192 ## lucene/core/src/java/org/apache/lucene/codecs/lucene99/Lucene99HnswVectorsWriter.java: ## @@ -347,12 +350,195 @@ private void reconstructAndWriteNeighbours(

Re: [PR] Avoid reconstructing HNSW graph during singleton merges [lucene]

Pulkitg64 commented on code in PR #15003: URL: https://github.com/apache/lucene/pull/15003#discussion_r2254249820 ## lucene/core/src/java/org/apache/lucene/codecs/lucene99/Lucene99HnswVectorsWriter.java: ## @@ -347,12 +350,195 @@ private void reconstructAndWriteNeighbours(

Re: [PR] Implement off-heap quantized scoring [lucene]

thecoop commented on code in PR #14863: URL: https://github.com/apache/lucene/pull/14863#discussion_r2254223052 ## lucene/core/src/java24/org/apache/lucene/internal/vectorization/PanamaVectorUtilSupport.java: ## @@ -530,7 +566,41 @@ private int dotProductBody512Int4Packed(byte[]

Re: [PR] Implement off-heap quantized scoring [lucene]

thecoop commented on code in PR #14863: URL: https://github.com/apache/lucene/pull/14863#discussion_r2254223052 ## lucene/core/src/java24/org/apache/lucene/internal/vectorization/PanamaVectorUtilSupport.java: ## @@ -530,7 +566,41 @@ private int dotProductBody512Int4Packed(byte[]

Re: [PR] Implement off-heap quantized scoring [lucene]

thecoop commented on code in PR #14863: URL: https://github.com/apache/lucene/pull/14863#discussion_r2254153413 ## lucene/core/src/java24/org/apache/lucene/internal/vectorization/PanamaVectorUtilSupport.java: ## @@ -455,49 +455,85 @@ private static int dotProductBody128(ByteVect