News Posts matching "Tesla"

Return to Keyword Browsing

NVIDIA Unveils World's Fastest, Most Efficient Accelerators

NVIDIA today unveiled the NVIDIA Tesla K20 family of GPU accelerators, the highest performance, most efficient accelerators ever built, and the technology powering Titan, the world's fastest supercomputer according to the TOP500 list released this morning at the SC12 supercomputing conference.

Armed with 18,688 NVIDIA Tesla K20X GPU accelerators, the Titan supercomputer at Oak Ridge National Laboratory in Oak Ridge, Tenn. seized the No. 1 supercomputer ranking in the world from Lawrence Livermore National Laboratory's Sequoia system with a performance record of 17.59 petaflops as measured by the LINPACK benchmark.

Asetek RackCDU Liquid Cools NVIDIA Tesla K20 GPU Accelerators

Asetek Inc., the world's leading supplier of liquid cooling solutions for computers, announced today that its hot water, direct-to-chip RackCDU liquid cooling systems will cool NVIDIA Tesla K20 GPU accelerators and that these cooling solutions will be on display at SC12.

Asetek direct-to-chip technology captures heat directly into liquid and removes it from the data center in an all liquid path. Asetek liquid is 4000 times more efficient as a coolant than air. With this efficiency, Asetek RackCDU makes deploying high density racks more practical at a data center scale while simultaneously reducing data center cooling energy consumption by over 50%. Density is particularly important in HPC/supercomputing applications where large numbers of servers work simultaneously on the same problem and maintaining short communication paths between servers is critical to the overall performance of the supercomputer.

NVIDIA Reports Financial Results for Third Quarter Fiscal Year 2013

NVIDIA (NASDAQ: NVDA) today reported record revenue of $1.20 billion for the third quarter of fiscal 2013 ended Oct. 28, 2012, up 15.3 percent from the previous quarter and up 12.9 percent from a year earlier.

The company also announced that it is initiating the payment of a quarterly cash dividend, and extending its existing $2.7 billion share-repurchase program, initiated in August 2004, through December 2014.

"Investments in our new growth strategies paid off this quarter in record revenues and margins," said Jen-Hsun Huang, president and chief executive officer of NVIDIA. "Kepler GPUs are winning across the special-purpose PC markets we serve, from gaming to design to supercomputing. And Tegra is powering some of the most innovative tablets, phones and cars in the market."

NVIDIA Tesla Could Integrate 64-bit ARM Cores

Following last week's announcement of the ARM Cortex-A50 series, SoC designers formed a bee-line to license the ARMv8 IP. Among them is NVIDIA, and not just for its Tegra line of high-performance mobile chips, but also for Tesla, its GPU compute accelerator line. In an interview with InfoWorld, NVIDIA CTO for Tesla, Steve Scott, was quoted saying, "Tegra is going to become GPU computing capable in the not-so-distant future. Sometime this decade we are also going to start bringing integrated CPUs and GPUs together in the Tesla line". NVIDIA perhaps is looking at building Tesla GPU compute servers with the x86 CPU completely replaced with efficient ARMv8 64-bit processors.

Source: Tom's Hardware

Tesla K20 GPU Compute Processor Specifications Released

Specifications of NVIDIA's Tesla K20 GPU compute processor, which was launched way back in May, are finally disclosed. We've known since then that the K20 is based on NVIDIA's large GK110 GPU, a chip never used to power a GeForce graphics card, yet. Apparently, NVIDIA is leaving some room on the silicon that allows it to harvest it better. According to a specifications sheet compiled by Heise.de, Tesla K20 will feature 13 SMX units, compared to the 15 available on the GK110 silicon.

With 13 streaming multiprocessor (SMX) units, the K20 will be configured with 2,496 CUDA cores (as opposed to 2,880 physically present on the chip). The core will be clocked at 705 MHz, yielding single-precision floating point performance of 3.52 TFLOP/s, and double-precision floating point performance of 1.17 TFLOP/s. The card packs 5 GB of GDDR5 memory, with memory bandwidth of 200 GB/s. Dynamic parallelism, Hyper-Q, GPUDirect with RDMA are part of the new feature-set. The TDP of the GPU is rated at 225W, and understandably, it uses a combination of 6-pin and 8-pin PCI-Express power connectors. Built in the 28 nm process, the GK110 packs a whopping 7.1 billion transistors.

Source: Heise.de

NVIDIA to Take on Xeon and Opteron with a "Boulder"

The enterprise CPU market is about to flare up soon, with the introduction of a third player in high-performance chips, next to Intel Xeon and AMD Opteron. X-bit Labs unearthed plans by NVIDIA to build on its Tegra success by designing high-performance server processors based on the ARM machine-architecture. The server market is far more varied in terms of machine-architectures, than PC, and the addition of an ARM-based high-performance chip is unlikely to fail. NVIDIA reportedly codenamed its development "Project Boulder."

Due in 2014, the CPU built under Project Boulder will be designed to, at least initially, replace traditional x86 Xeon/Opteron CPUs in Tesla Compute Accelerators, machines loaded with Tesla GPUs to process complex computational problems. The Boulder chip will be designed to handle serial processing loads, leaving parallel loads to the GPUs. A lot could ride on Boulder's success, as it could motivate NVIDIA to address other computing segments.

Source: X-bit Labs

NVIDIA Responds to Questions About Consistency of Features Across Platforms

NVIDIA posted a statement following last week's interactive session lead by Linus Torvalds, at a Finnish University, which didn't end too well for NVIDIA. The audience complained to Torvalds about lack of consistency between features available to Windows and Linux, and NVIDIA's stubbornness to help the community come up with alternative solutions to get the advertised features (such as Optimus) to work. NVIDIA's statement focuses on exactly that, consistency of features across platforms, and states that it is one of NVIDIA's priorities.

The statement by NVIDIA doesn't refute any of what a member of the audience complained about. There is still no proper Optimus feature made available by NVIDIA to Linux users, but a reminder that NVIDIA recently made changes to its drivers that makes interface with an alternative system software made by various open-source communities, the Bumblebee Project, easier. Said the statement "While we understand that some people would prefer us to provide detailed documentation on all of our GPU internals, or be more active in Linux kernel community development discussions, we have made a decision to support Linux on our GPUs by leveraging NVIDIA common code, rather than the Linux common infrastructure. While this may not please everyone, it does allow us to provide the most consistent GPU experience to our customers, regardless of platform or operating system."

The statement follows:

German Scientists Tap NVIDIA GPUs To Unlock Secrets Of The Brain

NVIDIA today announced that its GPUs will be used by scientists at Germany's Forschungszentrum Jülich, which hosts the Jülich Supercomputing Centre, one of Europe's largest and most powerful supercomputing resources, to accelerate advanced neurological research targeted at unlocking secrets of the human brain.

NVIDIA also announced a new, multiyear collaboration with the center to drive the next generation of GPU-accelerated scientific research in neuroscience and a range of other fields, including astronomy, astrophysics, material science, particle physics, and protein folding. Together the two organizations are launching the "NVIDIA Application Lab," a jointly run and staffed resource for the European scientific community located at the center's facilities in Jülich.

India Bolsters National Space Program Using NVIDIA GPU-Accelerated Supercomputer

NVIDIA today announced that the SAGA system, India's most powerful supercomputer and the holder of the 85 position on the Top500 list released yesterday, is leveraging NVIDIA GPUs to dramatically improve the design and analysis of the delivery vehicles critical to the nation's space program.

Developed by the Indian Space Research Organization (ISRO), one of the six largest space research agencies in the world, the SAGA supercomputer is used to tackle complex aeronautical problems. Harnessing the power of 640 NVIDIA Tesla GPUs and providing up to 394 teraflops of peak performance, SAGA enables ISRO to accelerate and improve the design and analysis of new and existing satellite launch vehicles by enabling more complex and accurate design simulations.

NVIDIA Tesla K10 GPU Hits New Performance Milestones For Scientific Simulation

ISC'12 - NVIDIA Tesla K10 GPUs offer performance breakthroughs on popular high performance computing (HPC) applications -- ranging from seismic processing to life sciences to video processing -- according to new benchmarks NVIDIA released today.

Based on the new NVIDIA Kepler computing architecture, the Tesla K10 GPU delivers the industry's highest single precision performance (4.58 teraflops) and highest memory bandwidth (320 GB/sec) in a single accelerator. This is 12 times higher single precision flops and 6.4 times higher memory bandwidth than the latest-generation Intel Sandy Bridge CPUs.

Fujitsu Brings NVIDIA GPU-Accelerated Supercomputing to the Masses

NVIDIA today announced that NVIDIA Tesla GPUs are now available in Fujitsu's PRIMERGY CX400 S1 servers, offering high-performance GPU-accelerated computing to Fujitsu's large installed base of customers in Japan and Europe.

Fujitsu designed the PRIMERGY CX400 S1 server for high performance in a compact form factor by using half-wide, two-socket server nodes -- doubling the number of cores per unit height. The system houses either four 1U hot-plug PRIMERGY CX250 S1 server nodes with two CPUs per node, or two 2U hot-plug CX270 S1 server nodes with two CPUs and one NVIDIA Tesla GPU per node.

Dell Introduces the First Multi-User 2U Rack Workstation for Virtualized 3D Workloads

Dell announced today it is expanding its client virtualization solutions with the introduction of the first virtualized 2U rack workstation enabling up to four concurrent professional graphics users to work from a single workstation from virtually anywhere. The Dell Precision R5500 rack workstation is the first four-GPU (graphics processing unit) configuration to be certified by Citrix with GPU pass-through on Citrix XenServer 6 using Citrix XenDesktop HDX 3D Pro, and brings additional security, IT resource optimization and end user flexibility to high performance workloads. This new usage model is designed for customers running 3D workloads in the engineering, medical, media and entertainment, scientific, software development and economic and finance market segments looking to support additional users on a single workstation.

SGI Expands Rackable Server Line to Support New NVIDIA Tesla K10 GPUs

SGI, the trusted leader in technical computing, today announced the availability of a complete, managed GPU solution of its SGI Rackable servers with the new high-performance NVIDIA Tesla K10 GPU Computing Accelerator. Coupled with SGI Management and Performance Suite software, the solution is built, completely integrated, and tested in SGI's manufacturing facility so that it can be installed at the customer site and begin running application codes in less than a day.

The next-generation NVIDIA Tesla K10 GPU Accelerator is designed for throughput and performance per watt. It features two ultra-efficient GK104 GPUs that provide up to 2X performance per watt for single precision applications than its predecessor, the M2090. The NVIDIA Tesla K10 features two GK104 GPUs with 1536 CUDA cores each and 4 GB of memory operating at 160 GB/second per GPU. These GPUs are shown to be particularly well suited to single high precision workloads, including seismic processing, signal, image and video analysis, and radio astronomy.

NVIDIA Pioneers New Standard for HPC With Tesla GPUs Built on Kepler Architecture

NVIDIA today unveiled a new family of Tesla GPUs based on the revolutionary NVIDIA Kepler GPU computing architecture, which makes GPU-accelerated computing easier and more accessible for a broader range of high performance computing (HPC) scientific and technical applications.

The new NVIDIA Tesla K10 and K20 GPUs are computing accelerators built to handle the most complex HPC problems in the world. Designed with an intense focus on high performance and extreme power efficiency, Kepler is three times as efficient as its predecessor, the NVIDIA Fermi architecture, which itself established a new standard for parallel computing when introduced two years ago.

NVIDIA GPUs Accelerate DNA Sequencing at BGI

NVIDIA today announced that BGI, the world's largest genomics institute, is launching a service that will enable researchers worldwide to perform affordable next-generation sequencing (NGS) bioinformatics analysis in the cloud.

The new "EasyGenomics" service from Shenzhen, China-based BGI combines an intuitive user interface with BGI's automated pipeline analysis, software and tools. These are integrated with the industry's largest sequencing platform to provide everything biologists, bioinformaticists and, ultimately, physicians need to submit and receive an automated analysis of DNA sequencing data.

NVIDIA Helps Power Bid for 2015 Moon Mission -- and $30 Million in Prizes

NVIDIA today announced that NVIDIA Tesla GPUs are being used by a team of German scientists participating in a global competition to land a robotic rover on the moon by 2015.

Developed to foster a new era of lunar exploration, the Google Lunar X PRIZE offers the largest international incentive prize in history. A total of $30 million will be awarded to the first privately funded teams that safely land a rover on the surface of the moon, drive the rover 500 meters over the lunar surface, and transmit detailed video, images and data back to Earth for further study.

NVIDIA GPUs Power Top Two Russian Supercomputers

NVIDIA today announced that the two most powerful supercomputers in Russia will use NVIDIA GPUs to address some of the world's most challenging scientific problems across a broad range of fields.

Underscoring the dramatic growth in the adoption of GPU computing across world scientific communities, the new Russia Top 50 supercomputer list released today reveals that the top two systems are accelerated by NVIDIA Tesla GPUs. These two supercomputers are housed at Lomonosov Moscow State University, which was recently named a CUDA Center of Excellence, and the Joint Supercomputer Center of the Russian Academy of Sciences (JSCC RAS). Moreover, GPUs are accelerating 12 of the country's top 50 systems -- up from seven just six months ago.

HPC Advisory Council to Create NVIDIA GPU Development Center

The HPC Advisory Council, a leading organization for high-performance computing (HPC) research, outreach and education, today announced a new NVIDIA GPU-based HPC development center. The new center is part of the HPC Advisory Council's High Performance Center, and will provide remote access to the HPC community free of charge for developing, testing and benchmarking the next generation of HPC applications.

The Center will provide developers with the ability to test their HPC applications on NVIDIA Tesla M2090 GPUs, the world's most powerful parallel processors. Designed from the ground up for HPC, computational science and supercomputing, NVIDIA's Tesla M2090 GPUs provide 512 CUDA cores with 665 gigaflops of peak performance to accelerate even the most demanding computationally intensive workloads.

NVIDIA Tesla GPUs Accelerate Science on HP ProLiant Generation 8 Servers

NVIDIA today announced that its NVIDIA Tesla GPUs will be included in HP ProLiant Generation 8 (Gen8) servers, delivering new levels of computational performance for scientific applications at world-class power efficiency.

HP ProLiant SL250 Gen8 CPU-GPU hybrid servers combine the world's most powerful parallel processors, NVIDIA Tesla M2090 GPUs, with new Intel Xeon E5-2600 series CPUs based on the Sandy Bridge microarchitecture.

NVIDIA GPUs Bring High Performance GPU Computing To New Dell PowerEdge Servers

NVIDIA today announced that its NVIDIA Tesla GPUs will be featured, for the first time, on two Dell PowerEdge 12th generation rack and tower servers.

Dell designed the new GPU-enabled PowerEdge R720 and PowerEdge T620 servers to accelerate a wide range of computationally intensive, industry standard applications, including Mathworks MATLAB (for computational research) and SIMULIA Abaqus (for computer-aided engineering). In addition, the new servers combine the 512-core NVIDIA Tesla M2090 GPUs with the latest Intel Xeon E5/R CPUs based on the Sandy Bridge microarchitecture to accelerate a range of scientific applications in fields such as life sciences, engineering, weather and climate, and others.

NVIDIA Tesla GPUs Again Power World's Greenest Petaflop Supercomputer

NVIDIA today announced that, for the second year in a row, the world's most energy efficient petaflop-class supercomputer is powered by NVIDIA Tesla GPUs.

The Tsubame 2.0 system at the Tokyo Institute of Technology's Global Scientific Information Center (GSIC) ranks as the greenest petaflop-class supercomputer on the recently released Green500 list. Published twice annually, the Green500 list, rates the 500 most energy efficient supercomputers based on performance achieved relative to power consumed.

Tsubame 2.0 is a heterogeneous supercomputer (combining both CPUs and GPUs) used to accelerate a range of scientific and industrial research in Japan. With sustained performance of 1.19 petaflops per second while consuming 1.2 megawatts, Tsubame 2.0 delivers 958 megaflops of processing power per watt of energy. It is 3.4-times more energy efficient than the next-closest x86 CPU-only petaflop system, the Cielo Cray supercomputer at Los Alamos National Laboratory, which delivers 278 megaflops per watt.

NVIDIA Reports Financial Results for Third Quarter Fiscal Year 2012

NVIDIA (NASDAQ: NVDA) reported revenue of $1.07 billion for the third quarter of fiscal 2012 ended Oct. 30, 2011, up 4.9 percent from the prior quarter, and up 26.3 percent from $843.9 million in the same period a year earlier.

On a GAAP basis, the company recorded net income of $178.3 million, or $0.29 per diluted share, for the third quarter of fiscal 2012. That compares with net income of $151.6 million, or $0.25 per diluted share, in the prior quarter and $84.9 million, or $0.15 per diluted share, in the same period a year earlier.

On a non-GAAP basis -- which excludes stock-based compensation, amortization of acquisition-related intangible assets, other acquisition related costs, and the tax impact associated with these items -- net income was $217.0 million, or $0.35 per diluted share. That compares with net income of $193.5 million, or $0.32 per diluted share, in the prior quarter, and net income of $117.4 million, $0.20 per share, in the same period a year earlier.

NVIDIA Reports Financial Results for Second Quarter Fiscal Year 2012

NVIDIA (NASDAQ: NVDA) today reported revenue of $1.02 billion for the second quarter of fiscal 2012 ended July 31, 2011, up 5.7 percent from the prior quarter, and up 25.3 percent from $811.2 million in the same period a year earlier. On a GAAP basis, the company recorded net income of $151.6 million, or $0.25 per diluted share, for the second quarter of fiscal 2012. This includes a two-cent dilutive impact from the Icera acquisition. It compares with net income of $135.2 million, or $0.22 per diluted share, in the prior quarter. In the same period a year earlier, the company had a net loss of $141.0 million, or $0.25 per diluted share.

On a non-GAAP basis -- which excludes stock-based compensation, amortization of acquisition-related intangible assets, other acquisition related costs, and the tax impact associated with these items -- net income was $193.5 million, or $0.32 per diluted share. That compares with net income of $165.7 million, or $0.27 per diluted share, in the prior quarter, and net income of $47.6 million, $0.08 per share, in the same period a year earlier.

TYAN to Showcase High-Density Cloud Computing Solutions

TYAN, an industry-leading server platform provider, and a subsidiary of MiTAC International Corp. will display a full line-up of cloud computing solutions that meet the increasing demand for higher density and lower power consumption at Computex 2011. TYAN will also provide a live demonstration of the FT77-B7015, a GPU Computing platform that features up to eight NVIDIA Tesla M2050 GPU computing processors in a 4U enclosure, at the TYAN booth (#407).

“Cloud Computing has changed the enterprise server landscape,” said Albert Mu, Vice President and General Manager of TYAN Business Unit at Mitac International Corp. “TYAN is now positioned to lead the industry with high-density server solutions that meet the demand for more computing power and lower power consumption – at higher densities.”

New NVIDIA Tesla GPU Smashes World Record in Scientific Computation

NVIDIA today unveiled the Tesla M2090 GPU, the world's fastest parallel processor for high performance computing. In addition, the Tesla M2090 GPU achieved the fastest-ever performance in a key measure of scientific computation. Equipped with 512 CUDA parallel processing cores, the Tesla M2090 GPU delivers 665 gigaflops of peak double-precision performance, enabling application acceleration by up to 10x compared to using a CPU alone.

In the latest version of AMBER 11, one of the most widely used applications for simulating behaviors of biomolecules, four Tesla M2090 GPUs coupled with four CPUs delivered record performance of 69 nanoseconds of simulation per day. The fastest AMBER performance recorded on a CPU-only supercomputer is 46 ns/day.
Return to Keyword Browsing