[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2017-05-11 Thread HyukjinKwon
Github user HyukjinKwon commented on the issue: https://github.com/apache/spark/pull/13891 I will propose to close this assuming this is inactive. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2017-02-09 Thread HyukjinKwon
Github user HyukjinKwon commented on the issue: https://github.com/apache/spark/pull/13891 @hqzizania If you check the log, there are some guides for how to. Should we maybe rebase this and check the logs? --- If your project is set up for it, you can reply to this email and have

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-26 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 @srowen I am not familiar with MiMa really, so what should I do now? Or just go back to [the previous commit](a6b5a16cd78e4efe99fda40f92592c9712b04146), and create a JIRA for the issue? ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-26 Thread srowen
Github user srowen commented on the issue: https://github.com/apache/spark/pull/13891 @hqzizania OK thanks for checking that. That may be an issue for this change. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-25 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 @srowen It seems mima test still fails when putting the new Param at the end of train method. :( --- If your project is set up for it, you can reply to this email and have your reply appear on

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-25 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test FAILed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-25 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/67523/ Test FAILed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-25 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67523 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67523/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-25 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67523 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67523/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-24 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 @mengxr @srowen @yanboliang A threshold param is added for unit tests. Does it look okay now? --- If your project is set up for it, you can reply to this email and have your reply appear on

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-24 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/67435/ Test PASSed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-24 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test PASSed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-24 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67435 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67435/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67435 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67435/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test FAILed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67434 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67434/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/67434/ Test FAILed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Build finished. Test FAILed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67432 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67432/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/67432/ Test FAILed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67434 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67434/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67432 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67432/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67424 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67424/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test FAILed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/67424/ Test FAILed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67424 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67424/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test FAILed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67423 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67423/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/67423/ Test FAILed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67423 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67423/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/67422/ Test FAILed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67422 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67422/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test FAILed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-23 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67422 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67422/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-21 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test PASSed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-21 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/67323/ Test PASSed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-21 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 @mengxr I see. I will add a param for it. :) --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-21 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67323 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67323/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-21 Thread mengxr
Github user mengxr commented on the issue: https://github.com/apache/spark/pull/13891 @hqzizania Thanks for the performance tests! This matches my guess. I'm not sure how often people use a rank greater than 1000 or even 250. But I think it is good to use BLAS level-3 routines. We

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-20 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #67323 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/67323/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-10-20 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 @yanboliang So sorry for my late response. Some regression performance test results: Datasets: using

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-09-21 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 @yanboliang sorry, i'm on a business trip and will upload the test result ASAP. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well.

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-09-21 Thread yanboliang
Github user yanboliang commented on the issue: https://github.com/apache/spark/pull/13891 @hqzizania Could you share the regression performance test result? I have time to get this in if it's ready. --- If your project is set up for it, you can reply to this email and have your

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-08-10 Thread yanboliang
Github user yanboliang commented on the issue: https://github.com/apache/spark/pull/13891 I'm making a pass now. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-08-03 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 cc @mengxr @yanboliang Was this patch Okay? --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-29 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test PASSed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-29 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/61465/ Test PASSed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-29 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #61465 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/61465/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-29 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #61465 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/61465/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-28 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/61381/ Test PASSed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-28 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test PASSed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-28 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #61381 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/61381/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-28 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 I set the stack size as 128 according to some more tests results, where 128 maybe a conservative size. However, this change will bypassing existing unit tests, as `doStack` is always `false`.

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-28 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 @srowen Ops~ The `copytoTri()` is indeed a little different in the test code. I change it into: ``` private def copyToTri(): Unit = { var i = 0 var j = 0

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-28 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #61381 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/61381/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-28 Thread srowen
Github user srowen commented on the issue: https://github.com/apache/spark/pull/13891 It may not matter much but your test code is a little different than in the patch, like for copyToTri(). It's optional, but a few comments explaining what addStack does might help readers. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-27 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 @mengxr this is a simple imitation of the loop in `computeFactors[ID]()` ALS using. It runs on a bare-metal node with 4 cores. All tests use all cores by RDD multi-partitions. --- If your

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-27 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 code for testing ``` def run(rank: Int, a:Int) = { println(s"blas.getclass() = ${blas.getClass.toString} on process $rank") val m = 1 << a val n = 1 << a

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test PASSed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/61184/ Test PASSed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #61184 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/61184/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 @mengxr Do you mean only test `add()` and `addStack()` without ALS? --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #61184 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/61184/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread mengxr
Github user mengxr commented on the issue: https://github.com/apache/spark/pull/13891 @hqzizania This could be tested with benchmarks without ALS. I guess even with a correct implementation, we need a large rank to see improvement. --- If your project is set up for it, you can reply

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Merged build finished. Test FAILed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread AmplabJenkins
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/13891 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/61171/ Test FAILed. ---

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #61171 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/61171/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread hqzizania
Github user hqzizania commented on the issue: https://github.com/apache/spark/pull/13891 This is a prototype. Actually, it is critical if it will be faster = =! I have done a simple test, the effect is up to "number of user for each product". The "number of user for each product"

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread SparkQA
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/13891 **[Test build #61171 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/61171/consoleFull)** for PR 13891 at commit

[GitHub] spark issue #13891: [SPARK-6685][MLLIB]Use DSYRK to compute AtA in ALS

2016-06-24 Thread srowen
Github user srowen commented on the issue: https://github.com/apache/spark/pull/13891 Is this actually faster though? --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and