Re: [PR] [GLUTEN-5569][VL] Hide child WriteFilesExec from VeloxColumnarWriteFilesExec on UI [incubator-gluten]

2024-05-31 Thread via GitHub
ulysses-you commented on PR #5698: URL: https://github.com/apache/incubator-gluten/pull/5698#issuecomment-2141318794 @FelixYBW yea, it has landed at [Spark 4.0.0](https://github.com/apache/spark/pull/46240), but it did not help the older Spark version we support.. -- This is an

Re: [I] Arrow CSV reader peak memory is very large [incubator-gluten]

2024-05-31 Thread via GitHub
FelixYBW commented on issue #5766: URL: https://github.com/apache/incubator-gluten/issues/5766#issuecomment-2141314435 > Arrow is easy to support file offset and length, we just need to use `RandomAccessFile` to generate `InputStream`. FileSource class constructor is > > ``` >

Re: [I] Arrow CSV reader peak memory is very large [incubator-gluten]

2024-05-31 Thread via GitHub
jinchengchenghh commented on issue #5766: URL: https://github.com/apache/incubator-gluten/issues/5766#issuecomment-2141312309 Arrow is easy to support file offset and length, we just need to use `RandomAccessFile` to generate `InputStream`. FileSource class constructor is ```

Re: [PR] [GLUTEN-5901][CH] Support CH backend parquet + delta [incubator-gluten]

2024-05-31 Thread via GitHub
github-actions[bot] commented on PR #5902: URL: https://github.com/apache/incubator-gluten/pull/5902#issuecomment-2141302865 Run Gluten Clickhouse CI -- 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

Re: [PR] [GLUTEN-5901][CH] Support CH backend parquet + delta [incubator-gluten]

2024-05-31 Thread via GitHub
github-actions[bot] commented on PR #5902: URL: https://github.com/apache/incubator-gluten/pull/5902#issuecomment-2141300232 Run Gluten Clickhouse CI -- 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

Re: [PR] [CORE] Use the smaller table to build hashmap in shuffled hash join [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5750: URL: https://github.com/apache/incubator-gluten/pull/5750#issuecomment-2141265623 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [I] [VL] Optimize sort based shuffle [incubator-gluten]

2024-05-30 Thread via GitHub
guhaiyan0221 commented on issue #5929: URL: https://github.com/apache/incubator-gluten/issues/5929#issuecomment-2141254938 > Thank you for reporting, @XinShuoWang . we noted the issue and trying to fix. We plan to rewrite the logic. any design doc? -- This is an automated message

Re: [PR] [VL] Upgrade simdjson to 3.9.3 in vcpkg build [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5938: URL: https://github.com/apache/incubator-gluten/pull/5938#issuecomment-2141237948 Thanks for opening a pull request! Could you open an issue for this pull request on Github Issues?

[PR] [VL] Upgrade simdjson to 3.9.3 in vcpkg build [incubator-gluten]

2024-05-30 Thread via GitHub
PHILO-HE opened a new pull request, #5938: URL: https://github.com/apache/incubator-gluten/pull/5938 ## What changes were proposed in this pull request? See velox commit: https://github.com/facebookincubator/velox/commit/f9ae45acbfe2ae742c46bcb39f77ef3824f95c84 ## How was

Re: [PR] [GLUTEN-5569][VL] Hide child WriteFilesExec from VeloxColumnarWriteFilesExec on UI [incubator-gluten]

2024-05-30 Thread via GitHub
FelixYBW commented on PR #5698: URL: https://github.com/apache/incubator-gluten/pull/5698#issuecomment-2141229854 > @zhztheplayer @ulysses-you Thank you very much for the optimization and suggestions. Indeed, extending a case class in Scala is not considered good practice. However,

Re: [PR] [VL] Gluten-it: Optimize Maven dependency list [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5925: URL: https://github.com/apache/incubator-gluten/pull/5925#issuecomment-2141215530 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [PR] [GLUTEN-4942][VL] Adding arrow port in VCPKG [incubator-gluten]

2024-05-30 Thread via GitHub
zhouyuan commented on PR #5926: URL: https://github.com/apache/incubator-gluten/pull/5926#issuecomment-2141215023 > thank you! > > > how far we can move to static build as default? > > static build by default is ok, but let's stay aligned on this matter: Gluten needs to

Re: [I] Result mismatch when data contains empty map [incubator-gluten]

2024-05-30 Thread via GitHub
yma11 commented on issue #4587: URL: https://github.com/apache/incubator-gluten/issues/4587#issuecomment-2141204053 Thanks for ping. Let me have a check. -- 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

Re: [PR] [CORE] Do not skip updating children's metrics while visiting an operator with NoopMetricsUpdater [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5933: URL: https://github.com/apache/incubator-gluten/pull/5933#issuecomment-2141188735 Run Gluten Clickhouse CI -- 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

Re: [PR] [CORE] Offload TakeOrderedAndProjectExec at planning time rather than at runtime [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5927: URL: https://github.com/apache/incubator-gluten/pull/5927#issuecomment-2141188654 Run Gluten Clickhouse CI -- 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

Re: [PR] [CORE] Remove IteratorApi.genNativeFileScanRDD, both velox and clickhouse backend needn't it. [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5937: URL: https://github.com/apache/incubator-gluten/pull/5937#issuecomment-2141187474 Run Gluten Clickhouse CI -- 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

Re: [PR] [CORE] Remove IteratorApi.genNativeFileScanRDD, both velox and clickhouse backend needn't it. [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5937: URL: https://github.com/apache/incubator-gluten/pull/5937#issuecomment-2141187249 Thanks for opening a pull request! Could you open an issue for this pull request on Github Issues?

[PR] [CORE] Remove IteratorApi.genNativeFileScanRDD, both velox and clickhouse backend needn't it. [incubator-gluten]

2024-05-30 Thread via GitHub
baibaichen opened a new pull request, #5937: URL: https://github.com/apache/incubator-gluten/pull/5937 ## What changes were proposed in this pull request? Remove unnessary API `IteratorApi.genNativeFileScanRDD` ## How was this patch tested? Using existed UT. -- This

Re: [PR] [VL] Daily Update Velox Version (2024_05_31) [incubator-gluten]

2024-05-30 Thread via GitHub
PHILO-HE commented on PR #5931: URL: https://github.com/apache/incubator-gluten/pull/5931#issuecomment-2141174366 /Benchmark Velox TPCDS -- 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

Re: [PR] [CORE] Use the smaller table to build hashmap in shuffled hash join [incubator-gluten]

2024-05-30 Thread via GitHub
zml1206 commented on PR #5750: URL: https://github.com/apache/incubator-gluten/pull/5750#issuecomment-2141172967 Thanks all for review. -- 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

Re: [PR] [VL] Remove reselect build side in ShuffledHashJoinExecTransformer [incubator-gluten]

2024-05-30 Thread via GitHub
zml1206 commented on PR #5935: URL: https://github.com/apache/incubator-gluten/pull/5935#issuecomment-2141172079 /Benchmark Velox TPCDS -- 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

Re: [PR] [VL] Remove reselect build side in ShuffledHashJoinExecTransformer [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5935: URL: https://github.com/apache/incubator-gluten/pull/5935#issuecomment-2141170366 Thanks for opening a pull request! Could you open an issue for this pull request on Github Issues?

[PR] [VL] Remove reselect build side in ShuffledHashJoinExecTransformer [incubator-gluten]

2024-05-30 Thread via GitHub
zml1206 opened a new pull request, #5935: URL: https://github.com/apache/incubator-gluten/pull/5935 ## What changes were proposed in this pull request? After #5750 , velox backend supporttd use the smaller table to build hashmap in shuffled hash join ,`preferredBuildSide` in

Re: [PR] [CORE] Move driver/executor endpoint to CH backend [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5914: URL: https://github.com/apache/incubator-gluten/pull/5914#issuecomment-2141169617 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [PR] [VL] Fallback collect_set, min, max with array,map,struct type [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5934: URL: https://github.com/apache/incubator-gluten/pull/5934#issuecomment-2141164651 Thanks for opening a pull request! Could you open an issue for this pull request on Github Issues?

Re: [PR] [GLUTEN-5569][VL] Hide child WriteFilesExec from VeloxColumnarWriteFilesExec on UI [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you commented on PR #5698: URL: https://github.com/apache/incubator-gluten/pull/5698#issuecomment-2141165195 @zhztheplayer OK. I get your point and agree actually. But I think it still overkill for the `VeloxColumnarWriteFilesExec` case. I will send a discusstion mail to

Re: [PR] [CORE] Use the smaller table to build hashmap in shuffled hash join [incubator-gluten]

2024-05-30 Thread via GitHub
rui-mo merged PR #5750: URL: https://github.com/apache/incubator-gluten/pull/5750 -- 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:

Re: [PR] [CH] Add Compatibility test found by internal [incubator-gluten]

2024-05-30 Thread via GitHub
baibaichen commented on PR #5882: URL: https://github.com/apache/incubator-gluten/pull/5882#issuecomment-2141145108 Releated with https://github.com/ClickHouse/ClickHouse/pull/64614 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to

Re: [PR] [VL] Do not skip updating children's metrics while visiting an operator with NoopMetricsUpdater [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5933: URL: https://github.com/apache/incubator-gluten/pull/5933#issuecomment-2141139615 Thanks for opening a pull request! Could you open an issue for this pull request on Github Issues?

Re: [PR] [VL] Do not skip updating children's metrics while visiting an operator with NoopMetricsUpdater [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5933: URL: https://github.com/apache/incubator-gluten/pull/5933#issuecomment-2141139787 Run Gluten Clickhouse CI -- 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

[PR] [VL] Do not skip updating children's metrics while visiting an operator with NoopMetricsUpdater [incubator-gluten]

2024-05-30 Thread via GitHub
zhztheplayer opened a new pull request, #5933: URL: https://github.com/apache/incubator-gluten/pull/5933 Rely on https://github.com/apache/incubator-gluten/pull/5927 Before: TBD After: TBD -- This is an automated message from the Apache Git Service. To respond

Re: [I] [VL] Performance regression since 4.12 [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you closed issue #5548: [VL] Performance regression since 4.12 URL: https://github.com/apache/incubator-gluten/issues/5548 -- 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

Re: [I] [VL] Performance regression since 4.12 [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you commented on issue #5548: URL: https://github.com/apache/incubator-gluten/issues/5548#issuecomment-2141128819 thank you @zhli1142015 it seems the regression is almost gone . I close this issue. -- This is an automated message from the Apache Git Service. To respond to the

Re: [PR] [VL] Fix shuffle with round robin partitioning fail [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5928: URL: https://github.com/apache/incubator-gluten/pull/5928#issuecomment-2141126945 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [I] [VL] Performance regression since 4.12 [incubator-gluten]

2024-05-30 Thread via GitHub
zhli1142015 commented on issue #5548: URL: https://github.com/apache/incubator-gluten/issues/5548#issuecomment-2141122515 I submited a PR to make the number drop ~30s, please see https://github.com/facebookincubator/velox/issues/9732 . still looking more. Thanks. -- This is

Re: [PR] [GLUTEN-5901][CH] Support CH backend parquet + delta [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5902: URL: https://github.com/apache/incubator-gluten/pull/5902#issuecomment-2141119136 Run Gluten Clickhouse CI -- 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

Re: [PR] [GLUTEN-4942][VL] Adding arrow port in VCPKG [incubator-gluten]

2024-05-30 Thread via GitHub
Yohahaha commented on PR #5926: URL: https://github.com/apache/incubator-gluten/pull/5926#issuecomment-2141117217 thank you! > how far we can move to static build as default? static build by default is ok, but let's stay aligned on this matter: Gluten needs to support both

Re: [PR] [CORE] Offload TakeOrderedAndProjectExec at planning time rather than at runtime [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5927: URL: https://github.com/apache/incubator-gluten/pull/5927#issuecomment-2141103413 Run Gluten Clickhouse CI -- 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

Re: [I] [VL] Performance regression since 4.12 [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you commented on issue #5548: URL: https://github.com/apache/incubator-gluten/issues/5548#issuecomment-2141102933 @zhztheplayer @zhli1142015 Is any updating about this issue ? thank you -- This is an automated message from the Apache Git Service. To respond to the message,

Re: [PR] DNM: [VL] Debug hash-join regression [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5401: URL: https://github.com/apache/incubator-gluten/pull/5401#issuecomment-2141097330 This PR is stale because it has been open 45 days with no activity. Remove stale label or comment or this will be closed in 10 days. -- This is an automated

Re: [I] [CH] Function trim only support const string [incubator-gluten]

2024-05-30 Thread via GitHub
zzcclp closed issue #5921: [CH] Function trim only support const string URL: https://github.com/apache/incubator-gluten/issues/5921 -- 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

Re: [PR] [GLUTEN-5921][CH] Function trim of trim_character support value from column [incubator-gluten]

2024-05-30 Thread via GitHub
zzcclp merged PR #5922: URL: https://github.com/apache/incubator-gluten/pull/5922 -- 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:

Re: [PR] [CORE] Offload TakeOrderedAndProjectExec at planning time rather than at runtime [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5927: URL: https://github.com/apache/incubator-gluten/pull/5927#issuecomment-2141088210 Run Gluten Clickhouse CI -- 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

Re: [PR] [GLUTEN-5414] [VL] Support arrow csv option and schema [incubator-gluten]

2024-05-30 Thread via GitHub
jinchengchenghh commented on PR #5850: URL: https://github.com/apache/incubator-gluten/pull/5850#issuecomment-2141087187 Can you help merge this one? Thanks! -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL

Re: [I] [VL] Static build failed on ubuntu 22.04 [incubator-gluten]

2024-05-30 Thread via GitHub
marin-ma closed issue #5924: [VL] Static build failed on ubuntu 22.04 URL: https://github.com/apache/incubator-gluten/issues/5924 -- 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

Re: [I] [VL] Static build failed on ubuntu 22.04 [incubator-gluten]

2024-05-30 Thread via GitHub
marin-ma commented on issue #5924: URL: https://github.com/apache/incubator-gluten/issues/5924#issuecomment-2141086620 @FelixYBW Thank you Binwei. I was building directly under the host environment, not in a docker container, so the environment is not clean. I will switch to docker and

Re: [PR] [VL] Gluten-it: Optimize Maven dependency list [incubator-gluten]

2024-05-30 Thread via GitHub
zhztheplayer merged PR #5925: URL: https://github.com/apache/incubator-gluten/pull/5925 -- 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:

Re: [PR] [CORE] Move driver/executor endpoint to CH backend [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you merged PR #5914: URL: https://github.com/apache/incubator-gluten/pull/5914 -- 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:

Re: [PR] [VL] Fix shuffle with round robin partitioning fail [incubator-gluten]

2024-05-30 Thread via GitHub
marin-ma merged PR #5928: URL: https://github.com/apache/incubator-gluten/pull/5928 -- 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:

Re: [PR] [GLUTEN-4942][VL] Adding arrow port in VCPKG [incubator-gluten]

2024-05-30 Thread via GitHub
zhouyuan commented on PR #5926: URL: https://github.com/apache/incubator-gluten/pull/5926#issuecomment-2141040386 @FelixYBW Spark UT is working on static building now. https://github.com/apache/incubator-gluten/pull/5906 We may need extra 2-3 patches for 1) allow Velox to use

Re: [PR] [VL] Daily Update Velox Version (2024_05_31) [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5931: URL: https://github.com/apache/incubator-gluten/pull/5931#issuecomment-2141038783 Thanks for opening a pull request! Could you open an issue for this pull request on Github Issues?

[PR] [VL] Daily Update Velox Version (2024_05_31) [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot opened a new pull request, #5931: URL: https://github.com/apache/incubator-gluten/pull/5931 Upstream Velox's New Commits: ```txt f9ae45acb by Sergey Pershin, Advance version of simdjson to the latest. (9985) a3239ff74 by Ke, Add initial table writer fuzzer (9685)

Re: [PR] [CORE] Offload TakeOrderedAndProjectExec at planning time rather than at runtime [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5927: URL: https://github.com/apache/incubator-gluten/pull/5927#issuecomment-2141003562 Run Gluten Clickhouse CI -- 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

Re: [PR] [GLUTEN-1632][CH]Daily Update Clickhouse Version (20240531) [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5930: URL: https://github.com/apache/incubator-gluten/pull/5930#issuecomment-2140980827 Run Gluten Clickhouse CI -- 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

Re: [PR] [GLUTEN-1632][CH]Daily Update Clickhouse Version (20240531) [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5930: URL: https://github.com/apache/incubator-gluten/pull/5930#issuecomment-2140980645 https://github.com/apache/incubator-gluten/issues/1632 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to

[PR] [GLUTEN-1632][CH]Daily Update Clickhouse Version (20240531) [incubator-gluten]

2024-05-30 Thread via GitHub
kyligence-git opened a new pull request, #5930: URL: https://github.com/apache/incubator-gluten/pull/5930 Auto commit by gluten daily build, please check the build status and merge it if it's green. -- This is an automated message from the Apache Git Service. To respond to the message,

Re: [PR] [GLUTEN-5904][CH] Convert `nan` to `null` which comes from `stddev` [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5913: URL: https://github.com/apache/incubator-gluten/pull/5913#issuecomment-2140732909 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [PR] [GLUTEN-5904][CH] Convert `nan` to `null` which comes from `stddev` [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5913: URL: https://github.com/apache/incubator-gluten/pull/5913#issuecomment-2140567463 = Performance report for TPCDS SF2000 with Velox backend, for reference only query

Re: [PR] [GLUTEN-4942][VL] Adding arrow port in VCPKG [incubator-gluten]

2024-05-30 Thread via GitHub
FelixYBW commented on PR #5926: URL: https://github.com/apache/incubator-gluten/pull/5926#issuecomment-2140556250 @zhouyuan how far we can move to static build as default? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

Re: [I] [VL] Optimize sort based shuffle [incubator-gluten]

2024-05-30 Thread via GitHub
FelixYBW commented on issue #5929: URL: https://github.com/apache/incubator-gluten/issues/5929#issuecomment-2140514389 Thank you for reporting, @XinShuoWang . we noted the issue and trying to fix. We plan to rewrite the logic. -- This is an automated message from the Apache Git Service.

Re: [I] [VL] Static build failed on ubuntu 22.04 [incubator-gluten]

2024-05-30 Thread via GitHub
FelixYBW commented on issue #5924: URL: https://github.com/apache/incubator-gluten/issues/5924#issuecomment-2140506886 @marin-ma It's because the jemalloc conflict. You need to uninstall jemalloc from system. It's marked here:

Re: [PR] [GLUTEN-5701][VL] Add overflow test case for from_unixtime function [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5894: URL: https://github.com/apache/incubator-gluten/pull/5894#issuecomment-2139990116 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [I] [CH] Mismatched results from `stddev` [incubator-gluten]

2024-05-30 Thread via GitHub
zzcclp closed issue #5904: [CH] Mismatched results from `stddev` URL: https://github.com/apache/incubator-gluten/issues/5904 -- 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

Re: [PR] [GLUTEN-5904][CH] Convert `nan` to `null` which comes from `stddev` [incubator-gluten]

2024-05-30 Thread via GitHub
zzcclp merged PR #5913: URL: https://github.com/apache/incubator-gluten/pull/5913 -- 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:

Re: [PR] [GLUTEN-5701][VL] Add overflow test case for from_unixtime function [incubator-gluten]

2024-05-30 Thread via GitHub
PHILO-HE merged PR #5894: URL: https://github.com/apache/incubator-gluten/pull/5894 -- 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:

Re: [I] [VL] Results are mismatch with vanilla Spark when uses from_unixtime with overflowed parameter and query config setted time zone [incubator-gluten]

2024-05-30 Thread via GitHub
PHILO-HE closed issue #5701: [VL] Results are mismatch with vanilla Spark when uses from_unixtime with overflowed parameter and query config setted time zone URL: https://github.com/apache/incubator-gluten/issues/5701 -- This is an automated message from the Apache Git Service. To respond to

Re: [PR] [VL] Daily Update Velox Version (2024_05_30) [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5919: URL: https://github.com/apache/incubator-gluten/pull/5919#issuecomment-2139678729 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [PR] [VL] Daily Update Velox Version (2024_05_30) [incubator-gluten]

2024-05-30 Thread via GitHub
PHILO-HE merged PR #5919: URL: https://github.com/apache/incubator-gluten/pull/5919 -- 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:

Re: [PR] [GLUTEN-5625][VL] Support window range frame [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5626: URL: https://github.com/apache/incubator-gluten/pull/5626#issuecomment-2139529557 Run Gluten Clickhouse CI -- 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

Re: [PR] [GLUTEN-5625][VL] Support window range frame [incubator-gluten]

2024-05-30 Thread via GitHub
WangGuangxin commented on code in PR #5626: URL: https://github.com/apache/incubator-gluten/pull/5626#discussion_r1620692238 ## gluten-core/src/main/java/org/apache/gluten/substrait/expression/WindowFunctionNode.java: ## @@ -80,20 +92,53 @@ private

Re: [PR] [GLUTEN-5691][CH] Enable merge on local disk first after insert into mergetree [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5692: URL: https://github.com/apache/incubator-gluten/pull/5692#issuecomment-2139487389 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [I] [VL] Unsupported spark function list [please leave a comment if you plan to pick some] [incubator-gluten]

2024-05-30 Thread via GitHub
PHILO-HE commented on issue #4039: URL: https://github.com/apache/incubator-gluten/issues/4039#issuecomment-2139430047 > And there is a test for `collect_set` which used array_sort > >

Re: [PR] [VL] Fix shuffle with round robin partitioning fail [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you commented on PR #5928: URL: https://github.com/apache/incubator-gluten/pull/5928#issuecomment-2139419757 @marin-ma never mind.. I will drop null type column in this pr -- This is an automated message from the Apache Git Service. To respond to the message, please log on to

Re: [PR] [VL] Fix shuffle with round robin partitioning fail [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you commented on PR #5928: URL: https://github.com/apache/incubator-gluten/pull/5928#issuecomment-2139413259 @marin-ma Is null type the only unsupported data type for hash expression ? If so, I can drop null column before going to hash expression. -- This is an automated

Re: [PR] [VL] Fix shuffle with round robin partitioning fail [incubator-gluten]

2024-05-30 Thread via GitHub
marin-ma commented on PR #5928: URL: https://github.com/apache/incubator-gluten/pull/5928#issuecomment-2139406256 Thanks. Seems like this failure is because we creates a hash computation for all input columns. If there are any NullType in the input, those column types will be converted to

Re: [PR] [VL] Fix shuffle with round robin partitioning fail [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you commented on PR #5928: URL: https://github.com/apache/incubator-gluten/pull/5928#issuecomment-2139385648 cc @zhztheplayer @marin-ma thank you -- 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

Re: [PR] [VL] Fix shuffle with round robin partitioning fail [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5928: URL: https://github.com/apache/incubator-gluten/pull/5928#issuecomment-2139383237 Thanks for opening a pull request! Could you open an issue for this pull request on Github Issues?

[PR] [VL] Fix shuffle with round robin partitioning fail [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you opened a new pull request, #5928: URL: https://github.com/apache/incubator-gluten/pull/5928 ## What changes were proposed in this pull request? We should validate the project before sort rather than using ProjectExecTransformer directly. The hash expression may not

Re: [PR] [VL] Daily Update Velox Version (2024_05_30) [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5919: URL: https://github.com/apache/incubator-gluten/pull/5919#issuecomment-2139377368 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [PR] [GLUTEN-5701][VL] Add overflow test case for from_unixtime function [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5894: URL: https://github.com/apache/incubator-gluten/pull/5894#issuecomment-2139354772 Run Gluten Clickhouse CI -- 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

Re: [PR] [GLUTEN-5901][CH] Support CH backend parquet + delta [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5902: URL: https://github.com/apache/incubator-gluten/pull/5902#issuecomment-2139277084 Run Gluten Clickhouse CI -- 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

Re: [PR] [VL] Daily Update Velox Version (2024_05_30) [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5919: URL: https://github.com/apache/incubator-gluten/pull/5919#issuecomment-2139264073 = Performance report for TPCDS SF2000 with Velox backend, for reference only query

Re: [PR] [CORE] Use the smaller table to build hashmap in shuffled hash join [incubator-gluten]

2024-05-30 Thread via GitHub
zml1206 commented on code in PR #5750: URL: https://github.com/apache/incubator-gluten/pull/5750#discussion_r1620377219 ## backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxBackend.scala: ## @@ -376,13 +376,8 @@ object VeloxBackendSettings extends

Re: [PR] [GLUTEN-5691][CH] Enable merge on local disk first after insert into mergetree [incubator-gluten]

2024-05-30 Thread via GitHub
zzcclp merged PR #5692: URL: https://github.com/apache/incubator-gluten/pull/5692 -- 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:

Re: [I] [CH] Enable merge on local disk first after insert into mergetree [incubator-gluten]

2024-05-30 Thread via GitHub
zzcclp closed issue #5691: [CH] Enable merge on local disk first after insert into mergetree URL: https://github.com/apache/incubator-gluten/issues/5691 -- 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

Re: [PR] [CORE] Offload TakeOrderedAndProjectExec at planning time rather than at runtime [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5927: URL: https://github.com/apache/incubator-gluten/pull/5927#issuecomment-2139139030 Run Gluten Clickhouse CI -- 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

Re: [I] Result mismatch when data contains empty map [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you commented on issue #4587: URL: https://github.com/apache/incubator-gluten/issues/4587#issuecomment-2139134174 @yma11 @zhouyuan does this issue still exist ? it seems has been fixed by https://github.com/facebookincubator/velox/pull/9187 -- This is an automated message from

Re: [PR] [GLUTEN-5921][CH] Function trim of trim_character support value from column [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5922: URL: https://github.com/apache/incubator-gluten/pull/5922#issuecomment-2139125130 Run Gluten Clickhouse CI -- 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

Re: [PR] [GLUTEN-5656][CORE][FOLLOWUP] Support GetStructField with NullLiteralNode as subqueries not executing during validation [incubator-gluten]

2024-05-30 Thread via GitHub
GlutenPerfBot commented on PR #5923: URL: https://github.com/apache/incubator-gluten/pull/5923#issuecomment-2139117782 = Performance report for TPCH SF2000 with Velox backend, for reference only query

Re: [PR] [CORE] Move driver/executor endpoint to CH backend [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5914: URL: https://github.com/apache/incubator-gluten/pull/5914#issuecomment-2139107237 Run Gluten Clickhouse CI -- 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

Re: [PR] [GLUTEN-5898][CH] Fix regexp_extract function use bracket has diff behaver with spark [incubator-gluten]

2024-05-30 Thread via GitHub
zzcclp merged PR #5908: URL: https://github.com/apache/incubator-gluten/pull/5908 -- 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:

Re: [I] [CH] Unexpected csv result when use use_excel_serialization=true [incubator-gluten]

2024-05-30 Thread via GitHub
zzcclp closed issue #5898: [CH] Unexpected csv result when use use_excel_serialization=true URL: https://github.com/apache/incubator-gluten/issues/5898 -- 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

Re: [PR] [CORE] Move driver/executor endpoint to CH backend [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5914: URL: https://github.com/apache/incubator-gluten/pull/5914#issuecomment-2139087029 Run Gluten Clickhouse CI -- 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

Re: [PR] [CORE] Move driver/executor endpoint to CH backend [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you commented on code in PR #5914: URL: https://github.com/apache/incubator-gluten/pull/5914#discussion_r1620283224 ## gluten-core/src/main/scala/org/apache/gluten/backendsapi/ListenerApi.scala: ## @@ -16,11 +16,11 @@ */ package org.apache.gluten.backendsapi

Re: [PR] [CORE] Move driver/executor endpoint to CH backend [incubator-gluten]

2024-05-30 Thread via GitHub
ulysses-you commented on code in PR #5914: URL: https://github.com/apache/incubator-gluten/pull/5914#discussion_r1620281220 ## gluten-core/src/main/scala/org/apache/gluten/backendsapi/TransformerApi.scala: ## @@ -70,4 +70,6 @@ trait TransformerApi { def

Re: [PR] [CORE] Move driver/executor endpoint to CH backend [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5914: URL: https://github.com/apache/incubator-gluten/pull/5914#issuecomment-2139070735 Run Gluten Clickhouse CI -- 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

Re: [PR] [VL] Daily Update Velox Version (2024_05_30) [incubator-gluten]

2024-05-30 Thread via GitHub
zhouyuan commented on PR #5919: URL: https://github.com/apache/incubator-gluten/pull/5919#issuecomment-2139069444 /Benchmark Velox TPCDS -- 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

Re: [PR] [CORE] Offload TakeOrderedAndProjectExec at planning time rather than at runtime [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5927: URL: https://github.com/apache/incubator-gluten/pull/5927#issuecomment-2139068211 Run Gluten Clickhouse CI -- 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

Re: [PR] [CORE] Offload TakeOrderedAndProjectExec at planning time rather than at runtime [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5927: URL: https://github.com/apache/incubator-gluten/pull/5927#issuecomment-2139066716 Run Gluten Clickhouse CI -- 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

Re: [PR] [VL] Offload TakeOrderedAndProjectExec at planning time rather than at runtime [incubator-gluten]

2024-05-30 Thread via GitHub
github-actions[bot] commented on PR #5927: URL: https://github.com/apache/incubator-gluten/pull/5927#issuecomment-2139050164 Run Gluten Clickhouse CI -- 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

<    1   2   3   4   5   6   7   8   9   10   >