March 07, 2013
An unusual supercomputer had its official coming out party on Wednesday, March 6, at the MENA ICT Forum in Jordan. The public debut (and symbolic unveiling) put the spotlight on one of the country's proudest technological achievements: the IMAN1, Jordan's first supercomputer. Iman means "faith" in Arabic.
Zaid Abudayeh, an engineer at Jordanian computer consulting firm Al Oula, presented the machine as a great step forward for the country. Al Oula was involved in the computer's creation.
"This project embodies the Jordanian spirit of accomplishing great projects with limited resources and making the impossible possible," said Abudayeh at the presentation. "Our presence today reflects the true meaning of devotion and ambition and we are proud to be among the leaders in the ICT sector."
Certainly the accomplishment is all that and more. The computer was designed, developed and engineered in Jordan, partly in order to demonstrate the country's ingenuity and dedication to advanced technology. The goal of the IMAN1 project was to build a supercomputer with the most economical design possible.
The designers succeeded in that quest, and they did so with what might seem to be most unusual cores. IMAN1 was built from 2,260 Sony PlayStation3 devices. And why not? Several companies are working on HPC systems and datacenter servers based on ARM chips, which got their start in small devices, such as smart phones.
Al Oula was launched in 2004 as a "transmission and broadcasting technology solutions provider and subcontractor for radio, television and transmission maintenance and operations,” according to the company's website. The site does not say precisely what contribution the company made to the supercomputer's development, but does say it was involved with the project. The company also designs Android- and server-based software, assesses network security, works on the network infrastructure of Jordanian ISP IONET, does web development projects and conducts maintenance and upkeep of corporate network systems.
The Sony video game consoles sport some pretty decent technology. The PS3, first launched in 2005, uses a 3.2 GHz "Cell" microprocessor with a PowerPC RISC microprocessor at its core. The PowerPC chip family was considered to be possibly the fastest microprocessor in the world not too long ago. It was designed by IBM and first used in its RS/6000 computers, released in 1990. Apple, IBM and Motorola then teamed up a few years later to further the design in an attempt to break Intel's x86 hegemony. (The attempt didn't succeed.) For a while PowerPC chips were used in Apple's Power Mac computers. Apple switched to Intel chips with the introduction of the iMac in 2006.
The PS3 Cell processor peaks out at about 230 gigaflops. The PowerPC core, loaded with 512 kilobytes of L2 cache, is described as the Cell's "processing element," and it gets a lot of help. There are eight more processors on the Cell chip, known as Synergistic Processing Elements (SPE), Those chips are 128-bit SIMD vector processors with 256 kilobytes of SRAM each. The PowerPC delegates processing tasks to seven of the SPEs as they become available. The eighth is a backup in case of failure of any of the others.
The PS3 also sports 550 MHz NVIDIA G70 GPUs, co-designed with Sony. Also known as the "Reality Synthesizer," the G70 is a 550 MHz chip that packs in 300 million tranistors.
Based on all that horsepower, the IMAN1 claims 25 teraflops. That gives it about a third the processing power of the 500th most powerful computer in the world, according to the November 2012 TOP500 list – a Japanese computer that gets 76.4 teraflops Rmax. The designers also say it has one of the best price-performance ratios of any HPC system in the world, but doesn't reveal the numbers.
The project started in January 2010 and the IMAN1 was fired up in October 2011. It is now being used by Jordanian universities for science and engineering research.
In fact, this isn't the first time the PS3 has been used to build a supercomputer. There was a time when the PS3 was popular for labs building computer clusters. Perhaps the Jordanians got the idea from the US Air Force. In 2009 the Air Force Research Laboratory (AFRL) launched the Condor PS3 Cluster, which was built from 1,760 Sony PS3 processors and 168 general-purpose GPUs. It reached an estimated 500 teraflops, placing it among the top 50 of the world's fastest systems at the time. It cost AFRL $2 million to build, compared to about $20 million to $40 million using more conventional technology.
However, the Air force ended up regretting that decision. In March 2010, Sony removed a feature that allowed people to download other operating systems into the devices. ARFL – and some university labs – had used Linux in clusters made from PS3s. That made it nearly impossible to replace any of the devices when they failed. Even if they were sent back to Sony for refurbishing, they were returned with the gameOS firmware installed.
There's no word on what operating system the IMAN1 uses.
Related Articles:
Air Force's PS3 Condor Cluster Takes Flight
Air Force May Suffer Collateral Damage from PS3 Firmware Update
Jun 18, 2013 |
The world's largest supercomputers, like Tianhe-2, are great at traditional, compute-intensive HPC workloads, such as simulating atomic decay or modeling tornados. But data-intensive applications--such as mining big data sets for connections--is a different sort of workload, and runs best on a different sort of computer.
Read more...
Jun 18, 2013 |
Researchers are finding innovative uses for Gordon, the 285 teraflop supercomputer housed at the San Diego Supercomputer Center (SDSC) that has a unique Flash-based storage system. Since going online, researchers have put the incredibly fast I/O to use on a wide variety of workloads, ranging from chemistry to political science.
Read more...
Jun 17, 2013 |
The advent of low-power mobile processors and cloud delivery models is changing the economics of computing. But just as an economy car is good at different things than a full size truck, an HPC workload still has certain computing demands that neither the fastest smartphone nor the most elastic cloud cluster can fulfill.
Read more...
Jun 14, 2013 |
For all the progress we've made in IT over the last 50 years, there's one area of life that has steadfastly eluded the grasp of computers: understanding human language. Now, researchers at the Texas Advanced Computing Center (TACC) are utilizing a Hadoop cluster on its Longhorn supercomputer to move the state of the art of language processing a little bit further.
Read more...
Jun 13, 2013 |
Titan, the Cray XK7 at the Oak Ridge National Lab that debuted last fall as the fastest supercomputer in the world with 17.59 petaflops of sustained computing power, will rely on its previous LINPACK test for the upcoming edition of the Top 500 list.
Read more...
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.
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.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?
Join our webinar to learn how IT managers can migrate to a more resilient, flexible and scalable solution that grows with the data center. Mellanox VMS is future-proof, efficient and brings significant CAPEX and OPEX savings. The VMS is available today.