Hi Evan,
Thank you for suggestion! BIDMat seems to have terrific speed. Do you know what
makes them faster than netlib-java?
The same group has BIDMach library that implements machine learning. For some
examples they use Caffe convolutional neural network library owned by another
group in
I'd be surprised of BIDMat+OpenBLAS was significantly faster than
netlib-java+OpenBLAS, but if it is much faster it's probably due to data
layout and fewer levels of indirection - it's definitely a worthwhile
experiment to run. The main speedups I've seen from using it come from
highly optimized
Y’all may already know this, but I haven’t seen it mentioned anywhere in
our docs on here and it’s a pretty easy win.
Maven supports parallel builds
https://cwiki.apache.org/confluence/display/MAVEN/Parallel+builds+in+Maven+3
with the -T command line option.
For example:
./build/mvn -T 1C
I've done this in the past, but back when I wasn't using Zinc it
didn't make a big difference. It's worth doing this in our jenkins
environment though.
- Patrick
On Thu, Feb 5, 2015 at 4:52 PM, Dirceu Semighini Filho
dirceu.semigh...@gmail.com wrote:
Thanks Nicholas, I didn't knew this.
here's the hash of the breaking commit:
Started on Feb 5, 2015 12:01:01 PM
Using strategy: Default
[poll] Last Built Revision: Revision
de112a2096a2b84ce2cac112f12b50b5068d6c35
(refs/remotes/origin/branch-1.3)
git ls-remote -h https://github.com/apache/spark.git branch-1.3 # timeout=10
[poll]
Thanks Nicholas, I didn't knew this.
2015-02-05 22:16 GMT-02:00 Nicholas Chammas nicholas.cham...@gmail.com:
Y’all may already know this, but I haven’t seen it mentioned anywhere in
our docs on here and it’s a pretty easy win.
Maven supports parallel builds
Thank you for explanation! I’ve watched the BIDMach presentation by John Canny
and I am really inspired by his talk and comparisons with Spark MLlib.
I am very interested to find out what will be better within Spark: BIDMat or
netlib-java with CPU or GPU natives. Could you suggest a fair way to
https://amplab.cs.berkeley.edu/jenkins/job/Spark-1.3-SBT/
we're seeing java OOMs and heap space errors:
https://amplab.cs.berkeley.edu/jenkins/job/Spark-1.3-SBT/AMPLAB_JENKINS_BUILD_PROFILE=hadoop1.0,label=centos/19/console
Hi Alexander,
Using GPUs with Spark would be very exciting. Small comment: Concerning
your question earlier about keeping data stored on the GPU rather than
having to move it between main memory and GPU memory on each iteration, I
would guess this would be critical to getting good performance.
Hi, Tathagata
Thanks for the information, I'm trying to build 1.3 snapshot and make
another try.
There are 2 reasons for why we use Kafka SimpleConsumer API
1. Previously, in our company, all of the real time processing system
were build on Apache Storm. So, the kafka environment
I'd expect that we can make GPU-accelerated BLAS faster than CPU blas in
many cases.
You might consider taking a look at the codepaths that BIDMat (
https://github.com/BIDData/BIDMat) takes and comparing them to
netlib-java/breeze. John Canny et. al. have done a bunch of work optimizing
to make
Dear Spark developers,
I am exploring how to make linear algebra operations faster within Spark. One
way of doing this is to use Scala Breeze library that is bundled with Spark.
For matrix operations, it employs Netlib-java that has a Java wrapper for BLAS
(basic linear algebra subprograms)
Hi Akhil
Those instructions you provided are showing how to manually build an sbt
project that may include adding spark dependencies. Whereas my OP was
about how to open the existing spark sbt project . These two are not
similar tasks.
2015-02-04 21:46 GMT-08:00 Akhil Das
I follow these ones to import sbt projects.
1. Install sbt plugins: Goto File - Settings - Plugins - Install
IntelliJ Plugins - Search for sbt and install it
2. File -Import-browse the root of spark source code
I hope this helps
On Fri, Feb 6, 2015 at 1:41 AM, Stephen Boesch
14 matches
Mail list logo