Analytics and Journals

Some good journals for reading on analytics-

1) JSS

http://www.jstatsoft.org/

present research that demonstrates the joint evolution of computational and statistical methods and techniques.  Implementations can use languages such as C, C++, S, Fortran, Java, PHP, Python and Ruby or environments such as Mathematica, MATLAB, R, S-PLUS, SAS, Stata, and XLISP-STAT.

There are currently 370 articles, 23 code snippets, 86 book reviews, 4 software reviews, and 7 special volumes in archives

2) R Journal

http://journal.r-project.org/

The  Journal

3) Pharma Programming

http://maney.co.uk/index.php/journals/pha/

Pharmaceutical Programming is the official journal of the Pharmaceutical Users Software Exchange (PhUSE), a non-profit membership society with the objective of educating programmers and their managers working in the pharmaceutical industry. Available both in print and online, Pharmaceutical Programming is an international journal with focus on programming in the regulated environment of the pharmaceutical and life sciences industry.

4) SAS Papers – User Groups

http://www.lexjansen.com/

4569 SAS papers presented
at SGF/SUGI 1996-2010.
1343 SAS papers presented
at PharmaSUG 2000-2010.
1810 SAS papers presented
at NESUG 1997-2009.
1191 SAS papers presented
at SESUG 1999-2009.
463 SAS papers presented
at PhUSE 2005-2009.
787 SAS papers presented
at WUSS 2003-2009.
337 SAS papers presented
at MWSUG 2001, 2004-2009.
188 SAS papers presented
at PNWSUG 2004-2009.
246 SAS papers presented
at SCSUG 2003-2007, 2009.
221 SAS papers related to CDISC.
Easy access to the CDISC Forum.

5) http://analyticsmagazine.com/

Magazine by http://www.informs.org/

6) Data Mining Journals

Academic Journals

Journals relevant to Data Mining

SAS/Blades/Servers/ GPU Benchmarks

Just checked out cool new series from NVidia servers.

Now though SAS Inc/ Jim Goodnight thinks HP Blade Servers are the cool thing- the GPU takes hardware high performance computing to another level. It would be interesting to see GPU based cloud computers as well – say for the on Demand SAS (free for academics and students) but which has had some complaints of being slow.

See this for SAS and Blade Servers-

http://www.sas.com/success/ncsu_analytics.html

To give users hands-on experience, the program is underpinned by a virtual computing lab (VCL), a remote access service that allows users to reserve a computer configured with a desired set of applications and operating system and then access that computer over the Internet. The lab is powered by an IBM BladeCenter infrastructure, which includes more than 500 blade servers, distributed between two locations. The assignment of the blade servers can be changed to meet shifts in the balance of demand among the various groups of users. Laura Ladrie, MSA Classroom Coordinator and Technical Support Specialist, says, “The virtual computing lab chose IBM hardware because of its quality, reliability and performance. IBM hardware is also energy efficient and lends itself well to high performance/low overhead computing.

Thats interesting since IBM now competes (as owner of SPSS) and also cooperates with SAS Institute

And

http://www.theaustralian.com.au/australian-it/the-world-according-to-jim-goodnight-blade-switch-slashes-job-times/story-e6frgakx-1225888236107

You’re effectively turbo-charging through deployment of many processors within the blade servers?

Yes. We’ve got machines with 192 blades on them. One of them has 202 or 203 blades. We’re using Hewlett-Packard blades with 12 CP cores on each, so it’s a total 2300 CPU cores doing the computation.

Our idea was to give every one of those cores a little piece of work to do, and we came up with a solution. It involved a very small change to the algorithm we were using, and it’s just incredible how fast we can do things now.

I don’t think of it as a grid, I think of it as essentially one computer. Most people will take a blade and make a grid out of it, where everything’s a separate computer running separate jobs.

We just look at it as one big machine that has memory and processors all over the place, so it’s a totally different concept.

GPU servers can be faster than CPU servers, though , Professor G.




Source-

http://www.nvidia.com/object/preconfigured_clusters.html

TESLA GPU COMPUTING SOLUTIONS FOR DATA CENTERS
Supercharge your cluster with the Tesla family of GPU computing solutions. Deploy 1U systems from NVIDIA or hybrid CPU-GPU servers from OEMs that integrate NVIDIA® Tesla™ GPU computing processors.

When compared to the latest quad-core CPU, Tesla 20-series GPU computing processors deliver equivalent performance at 1/20th the power consumption and 1/10th the cost. Each Tesla GPU features hundreds of parallel CUDA cores and is based on the revolutionary NVIDIA® CUDA™ parallel computing architecture with a rich set of developer tools (compilers, profilers, debuggers) for popular programming languages APIs like C, C++, Fortran, and driver APIs like OpenCL and DirectCompute.

NVIDIA’s partners provide turnkey easy-to-deploy Preconfigured Tesla GPU clusters that are customizable to your needs. For 3D cloud computing applications, our partners offer the Tesla RS clusters that are optimized for running RealityServer with iray.

Available Tesla Products for Data Centers:
– Tesla S2050
– Tesla M2050/M2070
– Tesla S1070
– Tesla M1060

Also I liked the hybrid GPU and CPU

And from a paper on comparing GPU and CPU using Benchmark tests on BLAS from a Debian- Dirk E’s excellent blog

http://dirk.eddelbuettel.com/blog/

Usage of accelerated BLAS libraries seems to shrouded in some mystery, judging from somewhat regularly recurring requests for help on lists such as r-sig-hpc(gmane version), the R list dedicated to High-Performance Computing. Yet it doesn’t have to be; installation can be really simple (on appropriate systems).

Another issue that I felt needed addressing was a comparison between the different alternatives available, quite possibly including GPU computing. So a few weeks ago I sat down and wrote a small package to run, collect, analyse and visualize some benchmarks. That package, called gcbd (more about the name below) is now onCRAN as of this morning. The package both facilitates the data collection for the paper it also contains (in the vignette form common among R packages) and provides code to analyse the data—which is also included as a SQLite database. All this is done in the Debian and Ubuntu context by transparently installing and removing suitable packages providing BLAS implementations: that we can fully automate data collection over several competing implementations via a single script (which is also included). Contributions of benchmark results is encouraged—that is the idea of the package.

And from his paper on the same-

Analysts are often eager to reap the maximum performance from their computing platforms.

A popular suggestion in recent years has been to consider optimised basic linear algebra subprograms (BLAS). Optimised BLAS libraries have been included with some (commercial) analysis platforms for a decade (Moler 2000), and have also been available for (at least some) Linux distributions for an equally long time (Maguire 1999). Setting BLAS up can be daunting: the R language and environment devotes a detailed discussion to the topic in its Installation and Administration manual (R Development Core Team 2010b, appendix A.3.1). Among the available BLAS implementations, several popular choices have emerged. Atlas (an acronym for Automatically Tuned Linear Algebra System) is popular as it has shown very good performance due to its automated and CPU-speci c tuning (Whaley and Dongarra 1999; Whaley and Petitet 2005). It is also licensed in such a way that it permits redistribution leading to fairly wide availability of Atlas.1 We deploy Atlas in both a single-threaded and a multi-threaded con guration. Another popular BLAS implementation is Goto BLAS which is named after its main developer, Kazushige Goto (Goto and Van De Geijn 2008). While `free to use’, its license does not permit redistribution putting the onus of con guration, compilation and installation on the end-user. Lastly, the Intel Math Kernel Library (MKL), a commercial product, also includes an optimised BLAS library. A recent addition to the tool chain of high-performance computing are graphical processing units (GPUs). Originally designed for optimised single-precision arithmetic to accelerate computing as performed by graphics cards, these devices are increasingly used in numerical analysis. Earlier criticism of insucient floating-point precision or severe performance penalties for double-precision calculation are being addressed by the newest models. Dependence on particular vendors remains a concern with NVidia’s CUDA toolkit (NVidia 2010) currently still the preferred development choice whereas the newer OpenCL standard (Khronos Group 2008) may become a more generic alternative that is independent of hardware vendors. Brodtkorb et al. (2010) provide an excellent recent survey. But what has been lacking is a comparison of the e ective performance of these alternatives. This paper works towards answering this question. By analysing performance across ve di erent BLAS implementations|as well as a GPU-based solution|we are able to provide a reasonably broad comparison.

Performance is measured as an end-user would experience it: we record computing times from launching commands in the interactive R environment (R Development Core Team 2010a) to their completion.

And

Basic Linear Algebra Subprograms (BLAS) provide an Application Programming Interface
(API) for linear algebra. For a given task such as, say, a multiplication of two conformant
matrices, an interface is described via a function declaration, in this case sgemm for single
precision and dgemm for double precision. The actual implementation becomes interchangeable
thanks to the API de nition and can be supplied by di erent approaches or algorithms. This
is one of the fundamental code design features we are using here to benchmark the di erence
in performance from di erent implementations.
A second key aspect is the di erence between static and shared linking. In static linking,
object code is taken from the underlying library and copied into the resulting executable.
This has several key implications. First, the executable becomes larger due to the copy of
the binary code. Second, it makes it marginally faster as the library code is present and
no additional look-up and subsequent redirection has to be performed. The actual amount
of this performance penalty is the subject of near-endless debate. We should also note that
this usually amounts to only a small load-time penalty combined with a function pointer
redirection|the actual computation e ort is unchanged as the actual object code is identi-
cal. Third, it makes the program more robust as fewer external dependencies are required.
However, this last point also has a downside: no changes in the underlying library will be
reected in the binary unless a new build is executed. Shared library builds, on the other
hand, result in smaller binaries that may run marginally slower|but which can make use of
di erent libraries without a rebuild.

Basic Linear Algebra Subprograms (BLAS) provide an Application Programming Interface(API) for linear algebra. For a given task such as, say, a multiplication of two conformantmatrices, an interface is described via a function declaration, in this case sgemm for singleprecision and dgemm for double precision. The actual implementation becomes interchangeablethanks to the API de nition and can be supplied by di erent approaches or algorithms. Thisis one of the fundamental code design features we are using here to benchmark the di erencein performance from di erent implementations.A second key aspect is the di erence between static and shared linking. In static linking,object code is taken from the underlying library and copied into the resulting executable.This has several key implications. First, the executable becomes larger due to the copy ofthe binary code. Second, it makes it marginally faster as the library code is present andno additional look-up and subsequent redirection has to be performed. The actual amountof this performance penalty is the subject of near-endless debate. We should also note thatthis usually amounts to only a small load-time penalty combined with a function pointerredirection|the actual computation e ort is unchanged as the actual object code is identi-cal. Third, it makes the program more robust as fewer external dependencies are required.However, this last point also has a downside: no changes in the underlying library will bereected in the binary unless a new build is executed. Shared library builds, on the otherhand, result in smaller binaries that may run marginally slower|but which can make use ofdi erent libraries without a rebuild.

And summing up,

reference BLAS to be dominated in all cases. Single-threaded Atlas BLAS improves on the reference BLAS but loses to multi-threaded BLAS. For multi-threaded BLAS we nd the Goto BLAS dominate the Intel MKL, with a single exception of the QR decomposition on the xeon-based system which may reveal an error. The development version of Atlas, when compiled in multi-threaded mode is competitive with both Goto BLAS and the MKL. GPU computing is found to be compelling only for very large matrix sizes. Our benchmarking framework in the gcbd package can be employed by others through the R packaging system which could lead to a wider set of benchmark results. These results could be helpful for next-generation systems which may need to make heuristic choices about when to compute on the CPU and when to compute on the GPU.

Source – DirkE’paper and blog http://dirk.eddelbuettel.com/papers/gcbd.pdf

Quite appropriately-,

Hardware solutions or atleast need to be a part of Revolution Analytic’s thinking as well. SPSS does not have any choice anymore though 😉

It would be interesting to see how the new SAS Cloud Computing/ Server Farm/ Time Sharing facility is benchmarking CPU and GPU for SAS analytics performance – if being done already it would be nice to see a SUGI paper on the same at http://sascommunity.org.

Multi threading needs to be taken care automatically by statistical software to optimize current local computing (including for New R)

Acceptable benchmarks for testing hardware as well as software need to be reinforced and published across vendors, academics  and companies.

What do you think?


Dryad- Microsoft's answer to MR

While reading across the internet I came across Microsoft’s version to MapReduce called Dryad- which has been around for some time, but has not generated quite the buzz that Hadoop or MapReduce are doing.

http://research.microsoft.com/en-us/projects/dryadlinq/

DryadLINQ

DryadLINQ is a simple, powerful, and elegant programming environment for writing large-scale data parallel applications running on large PC clusters.

Overview

New! An academic release of Dryad/DryadLINQ is now available for public download.

The goal of DryadLINQ is to make distributed computing on large compute cluster simple enough for every programmers. DryadLINQ combines two important pieces of Microsoft technology: the Dryad distributed execution engine and the .NET Language Integrated Query (LINQ).

Dryad provides reliable, distributed computing on thousands of servers for large-scale data parallel applications. LINQ enables developers to write and debug their applications in a SQL-like query language, relying on the entire .NET library and using Visual Studio.

DryadLINQ translates LINQ programs into distributed Dryad computations:

  • C# and LINQ data objects become distributed partitioned files.
  • LINQ queries become distributed Dryad jobs.
  • C# methods become code running on the vertices of a Dryad job.

DryadLINQ has the following features:

  • Declarative programming: computations are expressed in a high-level language similar to SQL
  • Automatic parallelization: from sequential declarative code the DryadLINQ compiler generates highly parallel query plans spanning large computer clusters. For exploiting multi-core parallelism on each machine DryadLINQ relies on the PLINQ parallelization framework.
  • Integration with Visual Studio: programmers in DryadLINQ take advantage of the comprehensive VS set of tools: Intellisense, code refactoring, integrated debugging, build, source code management.
  • Integration with .Net: all .Net libraries, including Visual Basic, and dynamic languages are available.
  • and
  • Conciseness: the following line of code is a complete implementation of the Map-Reduce computation framework in DryadLINQ:
    • public static IQueryable<R>
      MapReduce<S,M,K,R>(this IQueryable<S> source,
      Expression<Func<S,IEnumerable<M>>> mapper,
      Expression<Func<M,K>> keySelector,
      Expression<Func<K,IEnumerable<M>,R>> reducer)
      {
      return source.SelectMany(mapper).GroupBy(keySelector, reducer);
      }

    and http://research.microsoft.com/en-us/projects/dryad/

    Dryad

    The Dryad Project is investigating programming models for writing parallel and distributed programs to scale from a small cluster to a large data-center.

    Overview

    New! An academic release of DryadLINQ is now available for public download.

    Dryad is an infrastructure which allows a programmer to use the resources of a computer cluster or a data center for running data-parallel programs. A Dryad programmer can use thousands of machines, each of them with multiple processors or cores, without knowing anything about concurrent programming.

    The Structure of Dryad Jobs

    A Dryad programmer writes several sequential programs and connects them using one-way channels. The computation is structured as a directed graph: programs are graph vertices, while the channels are graph edges. A Dryad job is a graph generator which can synthesize any directed acyclic graph. These graphs can even change during execution, in response to important events in the computation.

    Dryad is quite expressive. It completely subsumes other computation frameworks, such as Google’s map-reduce, or the relational algebra. Moreover, Dryad handles job creation and management, resource management, job monitoring and visualization, fault tolerance, re-execution, scheduling, and accounting.

    The Dryad Software Stack

    As a proof of Dryad’s versatility, a rich software ecosystem has been built on top Dryad:

    • SSIS on Dryad executes many instances of SQL server, each in a separate Dryad vertex, taking advantage of Dryad’s fault tolerance and scheduling. This system is currently deployed in a live production system as part of one of Microsoft’s AdCenter log processing pipelines.
    • DryadLINQ generates Dryad computations from the LINQ Language-Integrated Query extensions to C#.
    • The distributed shell is a generalization of the pipe concept from the Unix shell in three ways. If Unix pipes allow the construction of one-dimensional (1-D) process structures, the distributed shell allows the programmer to build 2-D structures in a scripting language. The distributed shell generalizes Unix pipes in three ways:
      1. It allows processes to easily connect multiple file descriptors of each process — hence the 2-D aspect.
      2. It allows the construction of pipes spanning multiple machines, across a cluster.
      3. It virtualizes the pipelines, allowing the execution of pipelines with many more processes than available machines, by time-multiplexing processors and buffering results.
    • Several languages are compiled to distributed shell processes. PSQL is an early version, recently replaced with Scope.

    Publications

    Dryad: Distributed Data-Parallel Programs from Sequential Building Blocks
    Michael Isard, Mihai Budiu, Yuan Yu, Andrew Birrell, and Dennis Fetterly
    European Conference on Computer Systems (EuroSys), Lisbon, Portugal, March 21-23, 2007

    Video of a presentation on Dryad at the Google Campus, given by Michael Isard, Nov 1, 2007.

    Also interesting to read-

    Why does Dryad use a DAG?

    he basic computational model we decided to adopt for Dryad is the directed-acyclic graph (DAG). Each node in the graph is a computation, and each edge in the graph is a stream of data traveling in the direction of the edge. The amount of data on any given edge is assumed to be finite, the computations are assumed to be deterministic, and the inputs are assumed to be immutable. This isn’t by any means a new way of structuring a distributed computation (for example Condor had DAGMan long before Dryad came along), but it seemed like a sweet spot in the design space given our other constraints.

    So, why is this a sweet spot? A DAG is very convenient because it induces an ordering on the nodes in the graph. That makes it easy to design scheduling policies, since you can define a node to be ready when its inputs are available, and at any time you can choose to schedule as many ready nodes as you like in whatever order you like, and as long as you always have at least one scheduled you will continue to make progress and never deadlock. It also makes fault-tolerance easy, since given our determinism and immutability assumptions you can backtrack as far as you want in the DAG and re-execute as many nodes as you like to regenerate intermediate data that has been lost or is unavailable due to cluster failures.

    from

    http://blogs.msdn.com/b/dryad/archive/2010/07/23/why-does-dryad-use-a-dag.aspx

      Mapreduce Book

      Here is a new book on learning MapReduce and it has a free downloadable version as well.

      Data-Intensive Text Processing with MapReduce

      Jimmy Lin and Chris Dyer

      ABSTRACT

      Our world is being revolutionized by data-driven methods: access to large amounts of data has generated new insights and opened exciting new opportunities in commerce, science, and computing applications. Processing the enormous quantities of data necessary for these advances requires large clusters, making distributed computing paradigms more crucial than ever. MapReduce is a programming model for expressing distributed computations on massive datasets and an execution framework for large-scale data processing on clusters of commodity servers. The programming model provides an easy-to-understand abstraction for designing scalable algorithms, while the execution framework transparently handles many system-level details, ranging from scheduling to synchronization to fault tolerance. This book focuses on MapReduce algorithm design, with an emphasis on text processing algorithms common in natural language processing, information retrieval, and machine learning. We introduce the notion of MapReduce design patterns, which represent general reusable solutions to commonly occurring problems across a variety of problem domains. This book not only intends to help the reader “think in MapReduce”, but also discusses limitations of the programming model as well.

      You can download the book here

      This book is part of the Morgan & Claypool Synthesis Lectures on Human Language Technologies. If you’re at a university, your institution may already subscribe to the series, in which case you can access the electronic version directly without cost (see this page for a list of institutional subscribers). Otherwise, to purchase:

      Quite explicitly, this book focuses on MapReduce algorithm design, not Hadoop programming. Tom White’s Hadoop: The Definitive Guide is a great resource for learning Hadoop.

      Want to be notified of updates? Interested in MapReduce algorithm design? Follow @lintool on Twitter here!

      Using VM Player and Chromium OS on a PC

      Here is a short presentation tutorial including screenshots I made of using VM Player and playing with Chromium OS. Note- Its like a Machine (light weight linux) with a Chrome Browser. The real computing is when you use Chrome Extensions and/if you have a underpowered legacy PC.

      or you can see the file here if the above does not work 15 Clicks to a Cloud OS