Nvidia
NetApp
HPCwire

Since 1986 - Covering the Fastest Computers
in the World and the People Who Run Them

Language Flags

Visit additional Tabor Communication Publications

Datanami
Digital Manufacturing Report
HPC in the Cloud
Green Computing Report

Tabor Communications
Corporate Video

Scaled out Music, Scaled down Infrastructure


Sponsored Content by Fusion-io

If you’re one of the 175 million Pandora users, then you have surely experienced the excitement of having the Internet's most popular radio station introduce you to a brand-new artist or song. While it may seem like magic, there is a perfectly logical explanation behind Pandora’s ability to seemingly read your mind and know your taste in music. The true magic behind Pandora lies hidden in the numbers and data collected from music analysis, personalization, and the music delivery methods it uses.

The Music Genome Project – A Mind Reader for Music

Starting with the analysis of the raw data, musicologists undergo a lengthy process analyzing the distinct characteristics of each piece of music. Pandora's Music Genome Project looks at more than 450 attributes in order to create a musicological "DNA” for each track, including melody, harmony, instrumentation, rhythm, vocals and lyrics, to name a few. 

It states on Pandora’s website, “the Music Genome Project's database is built using a methodology that includes the use of precisely defined terminology, a consistent frame of reference, redundant analysis, and ongoing quality control to ensure that data integrity remains reliably high. Pandora does not use machine-listening or other forms of automated data extraction.” In 2012, Pandora’s library had over one million tracks by more than 100,000 artists. When you consider that this categorization is done manually, the scale of the project becomes almost overwhelming.   

Personalizing Power

The Music Genome Project is the largest musical categorization process of its kind. However, what makes Pandora unique and popular is the ability to personalize its music delivery. A user creates a station from a “seed” such as an artist, track, or genre. The Music Genome process then begins finding new songs of the same “DNA” and further personalizes itself as a user starts giving music a “thumbs up” or “thumb down.”

In 2012, users created over 1.6 billion unique stations, each personalized by one of the 175 million registered members. The “thumbs ups” and “thumbs down” feedback is invaluable. Beyond the benefit of personalized stations, Pandora is able to take that feedback and use it to enrich the Music Genome Project, allowing Pandora to curate better stations based on its listeners.

Delivering Music Everywhere You Go

Pandora is the largest Internet based radio station, capturing more than a 70 percent market share in Internet radio listening. In January 2013, Pandora owned an eight percent share of the total U.S. radio market, delivering 1.39 billion hours of music. In 2012, Pandora users listened to 13 billion hours of music. That’s the equivalent of 1.5 million years of straight music listening. 


Of the staggering 13 billion listening hours, 75 percent of the music delivered by Pandora was through mobile and other connected devices. Pandora just recently announced that it has over 1,000 partner integrations – 760 of them being consumer electronic devices such as phones, TVs, Blu-ray players, etc. Pandora is also available in 85 new car models and 175 different aftermarket car radio devices. 

The Technology

In order to maintain the high performance in delivery for each user, Pandora relies heavily on a caching system to help deliver its most popular tracks. Aaron Porter, Pandora’s Director of System Administration, explained that the growing popularity of Pandora presented challenges of scalability and reliability with this caching tier.

At first, Pandora loaded its servers with RAM to ensure a quick and quality experience for the end user. Scalability, however, became extremely difficult with this approach. Pandora turned to Fusion-io and its ioDrive platform, allowing it to use flash memory as a caching tier.

“The ioDrives perform as well as our RAM caches, but offer 10 times the capacity per server,” said Aaron. “Our total frequently-accessed music cache now holds 10 times the songs it used to, which both enhances existing user experience and gives us plenty of headroom for future growth.”

With the increase in capacity and performance delivered by the flash-based servers, Pandora was able to decrease its overall server footprint by 40 percent, allowing it to slow down its scale-out plans, and receive an almost instant ROI from the flash. You can learn more about Pandora’s experience with flash memory in this case study by Fusion-io.

Scaling Users and Scaling Performance

It’s easy to see how impressive Pandora’s technology is when it comes to serving up its music library. But even more astounding is seeing how the company is capable of handling database demands as they continue to add music to their library, refine their personalization algorithms, and grow their user-base. Despite these increasing demands, Fusion-io's flash-based memory tier has helped slow Pandora’s hardware scale out. It will be interesting to see how Pandora’s continued innovations inside the datacenter, delivering higher performance and reduced energy consumption, will allow the company to enhance it’s magical customer experience.   

Sponsored Links

High-Performance Computing in Action
Businesses that want to be on the cutting edge of their industries are increasingly turning to high-performance computing (HPC) solutions to handle complex compute processes and speed up their rate of innovation. Download this Executive Brief to see how businesses in energy, life sciences and entertainment put HPC solutions to work in their operations.

Webinar: Programming Heterogeneous X64+GPU Systems Using OpenACC
Join Michael Wolfe as he compares the advantages and costs of using both low-level models and the directive-based OpenACC model for programming accelerated heterogeneous systems. Registration is free.

Accelerate your science with Seneca
One of the first HPC providers installing a 4X NVIDIA Kepler K-20 cluster. Invites you to a free evaluation on Seneca’s NVIDIA K20 Kepler cluster, pre-loaded with AMBER, NAMD, LAMMPS

May 21, 2013

May 20, 2013

May 17, 2013

May 16, 2013

May 15, 2013

May 14, 2013

May 13, 2013

May 10, 2013

May 09, 2013

May 08, 2013


Most Read Features

Most Read Around the Web

Most Read This Just In


Feature Articles

CERN, Google Drive Future of Global Science Initiatives

Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Read more...

Saddling Phi for TACC’s Stampede

The Xeon Phi coprocessor might be the new kid on the high performance block, but out of all first-rate kickers of the Intel tires, the Texas Advanced Computing Center (TACC) got the first real jab with its new top ten Stampede system.We talk with the center's Karl Schultz about the challenges of programming for Phi--but more specifically, the optimization...
Read more...

"No Exascale for You!" An Interview with Berkeley Lab's Horst Simon

Although Horst Simon was named Deputy Director of Lawrence Berkeley National Laboratory, he maintains his strong ties to the scientific computing community as an editor of the TOP500 list and as an invited speaker at conferences.
Read more...

Short Takes

Running Computational Fluid Dynamics in the Cloud

May 16, 2013 | When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
Read more...

Computing the Physics of Bubbles

May 15, 2013 | Supercomputers at the Department of Energy’s National Energy Research Scientific Computing Center (NERSC) have worked on important computational problems such as collapse of the atomic state, the optimization of chemical catalysts, and now modeling popping bubbles.
Read more...

Internet2 Awards Program Seeks Innovative Applications

May 10, 2013 | Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
Read more...

Floating Funding to Exascale Island

May 09, 2013 | The Japanese government has revealed its plans to best its previous K Computer efforts with what they hope will be the first exascale system...
Read more...

HPC and the True Cost of Cloud

May 08, 2013 | For engineers looking to leverage high-performance computing, the accessibility of a cloud-based approach is a powerful draw, but there are costs that may not be readily apparent.
Read more...

Sponsored Whitepapers

Best Practices in Big Data Storage

05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.

Progress in Parallel: the Bull Parallel Programming Center

04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.

Sponsored Multimedia

SGI DMF ZeroWatt Disk Solution

In this demonstration of SGI DMF ZeroWatt disk solution, Dr. Eng Lim Goh, SGI CTO, discusses a function of SGI DMF software to reduce costs and power consumption in an exascale (Big Data) storage datacenter.

Cray CS300-AC Cluster Supercomputer Air Cooling Technology Video

The Cray CS300-AC cluster supercomputer offers energy efficient, air-cooled design based on modular, industry-standard platforms featuring the latest processor and network technologies and a wide range of datacenter cooling requirements.

SC12 Editorial Feature HPCwire Soundbite sponsored by ISC

HPC Job Bank


Featured Events


  • June 16, 2013 - June 20, 2013
    ISC'13
    Leipzig,
    Germany

  • June 17, 2013 - June 18, 2013
    Forecast 2013
    San Francisco, CA
    United States





HPCwire Events