[
https://issues.apache.org/jira/browse/SYSTEMML-918?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15495062#comment-15495062
]
Imran Younus commented on SYSTEMML-918:
---------------------------------------
After latest changes (maybe these
https://github.com/apache/incubator-systemml/commit/085009a367519d437558b2004ac93d8b6ea60195),
this problem is fixed. Now the data loading takes almost 30sec.
> Severe performance drop when using csv matrix -> spark df -> systemml binary
> block
> ----------------------------------------------------------------------------------
>
> Key: SYSTEMML-918
> URL: https://issues.apache.org/jira/browse/SYSTEMML-918
> Project: SystemML
> Issue Type: Improvement
> Components: Runtime
> Reporter: Nakul Jindal
> Attachments: stages.jpg
>
>
> Imran is trying to read in a csv file which encodes a matrix.
> The dimensions of the matrix are 10000 x 784
> Here is what the metadata looks like:
> {
> "data_type": "matrix",
> "value_type": "double",
> "rows": 10000,
> "cols": 784,
> "format": "csv",
> "header": false,
> "sep": ",",
> "description": { "author": "SystemML" }
> }
> There are two ways I read this matrix into the
> [tSNE|https://github.com/iyounus/incubator-systemml/blob/SYSTEMML-831_Implement_tSNE/scripts/staging/tSNE.dml#L25]
> algorithm as variable X.
> 1. The csv file is read into a dataframe and then the MLContext api is used
> to convert it to the binary block format. Here is the code used to create the
> dataframe:
> {code}
> val X0 = {sqlContext.read
> .format("com.databricks.spark.csv")
> .option("header", "false") // Use first line of all files as header
> .option("inferSchema", "true") // Automatically infer data types
> .load("hdfs://rr-dense1/user/iyounus/data/mnist_test.csv")
> }
> // code for tsne ..........
> val X = X0.drop(X0.col("C784")) // Drop last column
> val tsneScript = dml(tsne).in("X", X).out("Y", "C")
> println(Calendar.getInstance().get(Calendar.MINUTE))
> val res = ml.execute(tsneScript)
> {code}
> 2. A DML read statement reads the csv file directly.
> Option 2 happens almost instantaneously. Option 1 takes about 8 minutes on a
> beefy machine with 40g allocated to the driver and 60g allocated to the
> executors on a 7 node cluster.
> Looking at the spark web UI and following the code path, it leads us to this
> function:
> https://github.com/apache/incubator-systemml/blob/master/src/main/java/org/apache/sysml/runtime/instructions/spark/utils/RDDConverterUtilsExt.java#L874-L879
> This needs some investigation.
> [~iyounus], [~fschueler]
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
