Entries filed under “Enterprise HPC”

This week NCSA announced that it has won an NSF grant to understand the gaps between the needs of industry today and the capabilities of simulation-based engineering and science

The National Science Foundation has awarded $200,000 to the National Center for Supercomputing Applications (NCSA) to investigate the use of simulation-based engineering and science in industry and to report on areas where scientific advances are required to achieve gains in simulation capability. This Early-Concept Grants for Exploratory Research (EAGER) project will be carried out over the next 15 months by NCSA’s Private Sector Program staff.

NCSA will host a series of meetings and surveys to capture the perspectives of current industry users about the challenges they face in using simulation more extensively in their businesses

“Private sector engagement at NCSA has revealed significant opportunities for bringing science and industry together more completely,” said Merle Giles, leader of NCSA’s Private Sector Program. “It is our intention to document the industrial challenges sufficiently so as to bring scientists from both the public and private sectors together to pursue breakthroughs that are likely to lead to economic development.”

NCSA will focus on large original equipment manufacturers (companies that manufacture products or components that are then sold and retailed under the purchasers brand name). The Ohio Supercomputer Center and the Information Sciences Institute at the University of Southern California have received related grants from NSF’s EAGER program and will focus on small and medium enterprises.

I was unaware of the EAGER program, and I think its a good thing if it actually pushes a boundary. We already know, having asked dozens of times over the past decade and gotten the same answer every time, that skills, software, and cost of entry are the major challenges that industrial users identify when discussing obstacles to adoption of modeling and simulation. What we need is information that is specific enough to form a nucleation site for ideas that address the challenges to start to crystallize and fall out of solution.

I thought this might be of interest to at least some of you — Pervasive Software announced last week that their flagship DataRush product posted a rate of 2 TB/hr on MalStone B (a stylized benchmark for data intensive computing, Robert Grossman describes it here) using a 32-core Intel Xeon 7550 server. MalStone B10 has 10 billion records, which equates to just under 1 Terabyte of data (100 byte, fixed record size).

“These results provide powerful validation of the ability of Pervasive DataRush to scale massively and consume all available cores as commercially available core counts increase,” said Ray Newmark, vice president of sales and marketing for Pervasive DataRush. “This kind of performance is a beacon for organizations struggling with complex or large data who want to harness the power of multicore. We enable users to process large amounts of data to obtain actionable information faster and more cost-effectively than other technologies.”

Pervasive DataRush ran the 10-billion-row benchmark on an Intel server with a 64-bit JVM 6 installed on 64-bit Windows 2008. The Pervasive DataRush runtime of 31.5 minutes was 26 times faster than the same test in a published benchmark using Hadoop on a 20-node cluster. Not only did Pervasive DataRush achieve superior performance, the application showed excellent scalability from two to thirty-two cores. This level of performance and scalability allows organizations to leverage the most appropriate hardware for the performance desired.

We’ve written about Pervasive before; you can find an in-depth piece here.

I didn’t really have a point of reference for the significance of this result, so I got in touch with the company. Here’s what they had to say

The run-time we are publishing (31.5 minutes) is faster than many of the other published runtimes (maybe faster than all, we’d need to double check on the latest published). One of the main precepts of DataRush is our ability to process large amounts of data, hence our focus on the throughput rate, not just the wall clock time.

The 2 Terabyte/hour rate is excellent for this benchmark. This is especially so given that we are comparing ourselves against other runs that were made using clusters. This shows that a single machine can handle jobs that once were only considered feasible on cluster configurations. Again, one of our focuses with DataRush is to run on commodity hardware. We configured the system using the RAID card that came with the box using terabyte drives we bought at a local electronics store. We used a RAID-0 configuration.

Yesterday Platform Computing announced the launch of the Platform ISF Starter Pack, “an out-of-the-box, end-to-end software product and services offering for companies to quickly set up a private cloud.”

Platform ISF was introduced in 2009; the Starter Pack is aimed at letting small groups get their feet wet without investing in a substantial deployment.

For only US$4,995, the Platform ISF Starter Pack includes a one-year Platform ISF license for 10 sockets, consulting, training and support.

…“Organizations have plenty of toolkits to choose from as they evaluate private cloud, but they require multiple tools that users must string together themselves,” said James Pang, Vice President Product Management, Platform Computing. “What’s more, these toolkits can cost $50,000 or more, and require 30-plus days of onsite consulting to build and customize an evaluation environment. We wanted to provide a cheap and easy way for users to get up and running quickly with a single product. The Platform ISF Starter Pack is an ideal entry into private cloud computing for organizations that want to first demonstrate the value of private cloud to their organizations without making a large upfront time or resource investment.”

The Starter Pack also includes training and consultation to get you going.

Unrelated: I really like Platform’s spiffy logo.