Back to Table of contents

Primeur weekly 2011-11-14

Special

International data Grids to be highlighted by RENCI at SC11 ...

Japan's K Computer tops 10 Petaflop/s to stay atop TOP500 List ...

NASA and DOE's Lawrence Livermore National Laboratory confirm Obsidian's BGFC first order functionality ...

Adaptive Computing delivers intelligent Grid resource management to Gaea, NOAA's new climate modelling and research system ...

Exascale supercomputing

NCAR selects IBM for key components of new Supercomputing Center ...

The Cloud

Terascala announces enhanced version of proven storage management solution for fast data analysis in the Cloud and in shared resource environments ...

Terascala announces support for Lustre 2,1 ...

The Green Grid and Open Data Center Alliance form strategic collaboration to drive efficient Cloud resource standards ...

EuroFlash

Submissions for ISC research papers and tutorials now being accepted ...

Post Doc position available at INAF in Catania, Sicily ...

DataDirect Networks' groundbreaking Storage Fusion Architecture (SFA) System selected to power Europe's fastest supercomputer ...

European industry and research centres join forces to create a European Technology Platform for High Performance Computing ...

Russian Academy of Sciences expands GPU supercomputing infrastructure to accelerate scientific research ...

PRACE to issue project access 4th call for proposals for Tier-0 and Synchronized Call for Tier-1 ...

USFlash

Terascala announces membership in OpenSFS ...

Supercomputers accelerate development of advanced materials ...

Kraken set to deliver 2 billionth CPU hour, sustains 96 percent utilization ...

NEC developing next generation vector supercomputer - aiming for the world's leading energy-efficient supercomputer ...

Blacklight goes to work at the Pittsburgh Supercomputing Center ...

Fujitsu launches PRIMEHPC FX10 supercomputer ...

Platform Computing announces support for upcoming Intel Many Integrated Core architecture-based products ...

NASA selects next-generation SGI ICE HPC platform for technology upgrade ...

SDSC's Triton Resource helps develop new model for forecasting California solar power production ...

U.S. Department of Energy Laboratory selects DataDirect Networks' SFA12K Storage to enable clean energy technology insight and discovery ...

Rensselaer Polytechnic Institute researchers use supercomputer to study effects of stacking graphene nanoribbons ...

Appro has been selected for the second time to support the High Performance Computing Modernization Programme (HPCMP) to improve supercomputing capabilities ...

Chinese researchers tap GPU supercomputer for world's first simulation of complete H1N1 virus ...

For the first time, IBM brings mainframe and Windows together ...

AMD processors power leading research and academic supercomputers ...

Mali-T658 GPU extends graphics and GPU compute leadership for high performance devices ...

ORNL fundamental discovery casts enzymes in new light ...

Altera's Stratix IV FPGAs deliver unprecedented acceleration for world's most powerful reconfigurable supercomputer ...

Mali-T658 GPU extends graphics and GPU compute leadership for high performance devices

10 Nov 2011 Tokyo - ARM has launched the ARM Mali-T658 Graphics Processing Unit (GPU) - the latest member of the Midgard architecture-based GPU family targeting high performance devices, such as superphones, tablets and smart-TVs. The Mali-T658 GPU leverages the unique ARM system-level approach to multicore design that optimizes both performance and energy-efficiency. To address high-end consumer requirements, the Mali-T658 GPU delivers up to ten times the graphics performance of the Mali-400 MP GPU, found in a wide range of today’s mainstream consumer products. It also features four times the GPU Compute performance of the Mali-T604 GPU, enabling a raft of new use-cases outside of traditional graphics processing, including computational photography, image-processing and augmented reality.

"Following the recent introduction of big.LITTLE processing and the ARMv8 architecture, the launch of Mali-T658 is another example of how ARM is seeking to redefine heterogeneous computing for the embedded space", stated Jon Peddie, President of specialist graphics research consultancy, Jon Peddie Research. "This will provide high-performance graphics and compute systems for low-power applications."

Supported by lead ARM Partners, such as Fujitsu Semiconductor, LG Electronics, Nufront and Samsung, the Mali-T658 GPU enables an immersive visual computing experience on a range of 'always on, always connected' consumer devices. These include high-performance, energy-sensitive superphones, smartphones and tablets, as well as smart-TVs and automotive infotainment solutions. Building on the success of the Mali-T604 GPU, the Mali-T658 extends ARM performance leadership with scalability up to eight cores, and by doubling of the number of arithmetic pipelines within each of these cores. It is also compatible with the ARMv8 architecture.

"ARM is in a unique position to integrate CPU, GPU and interconnect technology into optimized, coherent systems, and by doing so improve performance and enable more efficient data sharing", stated Rock Yang, VP Marketing, Nufront. "This will allow partners, such as Beijing Nufront, to make the most of the leading capabilities of each system component and maximize throughput in ARM technology-based compute sub-systems."

Delivery of a common set of compatible drivers for all Midgard architecture-based Mali GPUs enables faster time-to-market and minimizes software upgrade costs for future implementations. The ARM Mali-T658 GPU supports a wide range of graphics and compute APIs, including Microsoft DirectX 11, Khronos OpenGL ES, OpenVG, Khronos OpenCL, Google Renderscript and Microsoft DirectCompute.

The Mali-T658 has been designed to work seamlessly with the ARM Cortex-A15 and Cortex-A7 processors either in standalone modes or in big.LITTLE processing mode. The autonomous nature of the Mali Job Manager, and its ability to carry on graphics processing with a reduced load on the CPU, means it is very well suited to work alongside a big.LITTLE CPU system. By using the right processor for the right task the Mali-T658 is able to handle GPU compute tasks in parallel with the CPU handling the always-on always-connected tasks. The ability of the Mali-T658 GPU to scale up to eight cores provides unprecedented energy-efficiency, flexibility and scalability to match the CPU and GPU performance points through one coherent interface.

"Next generation consumer devices based on the Mali-T658 GPU will address the growing user expectation for slick user interfaces and desktop-class graphics", stated Pete Hutton, general manager, Media Processing Division, ARM. "Intuitive user interfaces will mean that consumers can access the full functionality of their connected devices, for richer user experiences. This includes HD gaming and new compute-intensive applications, such as augmented reality."

Cache coherency is essential in multicore computing devices to maintain the consistency of data stored in local caches of a shared resource. This ensures optimum performance and energy-efficiency of complex heterogeneous SoC designs, and is designed to address next generation, high-performance computing devices. ARM system IP, such as CoreLink, enables system level cache coherency across clusters of multicore processors, including the Cortex-A15 MPCore processors and Mali-T658 graphics processors.
Source: ARM

Back to Table of contents

Primeur weekly 2011-11-14

Special

International data Grids to be highlighted by RENCI at SC11 ...

Japan's K Computer tops 10 Petaflop/s to stay atop TOP500 List ...

NASA and DOE's Lawrence Livermore National Laboratory confirm Obsidian's BGFC first order functionality ...

Adaptive Computing delivers intelligent Grid resource management to Gaea, NOAA's new climate modelling and research system ...

Exascale supercomputing

NCAR selects IBM for key components of new Supercomputing Center ...

The Cloud

Terascala announces enhanced version of proven storage management solution for fast data analysis in the Cloud and in shared resource environments ...

Terascala announces support for Lustre 2,1 ...

The Green Grid and Open Data Center Alliance form strategic collaboration to drive efficient Cloud resource standards ...

EuroFlash

Submissions for ISC research papers and tutorials now being accepted ...

Post Doc position available at INAF in Catania, Sicily ...

DataDirect Networks' groundbreaking Storage Fusion Architecture (SFA) System selected to power Europe's fastest supercomputer ...

European industry and research centres join forces to create a European Technology Platform for High Performance Computing ...

Russian Academy of Sciences expands GPU supercomputing infrastructure to accelerate scientific research ...

PRACE to issue project access 4th call for proposals for Tier-0 and Synchronized Call for Tier-1 ...

USFlash

Terascala announces membership in OpenSFS ...

Supercomputers accelerate development of advanced materials ...

Kraken set to deliver 2 billionth CPU hour, sustains 96 percent utilization ...

NEC developing next generation vector supercomputer - aiming for the world's leading energy-efficient supercomputer ...

Blacklight goes to work at the Pittsburgh Supercomputing Center ...

Fujitsu launches PRIMEHPC FX10 supercomputer ...

Platform Computing announces support for upcoming Intel Many Integrated Core architecture-based products ...

NASA selects next-generation SGI ICE HPC platform for technology upgrade ...

SDSC's Triton Resource helps develop new model for forecasting California solar power production ...

U.S. Department of Energy Laboratory selects DataDirect Networks' SFA12K Storage to enable clean energy technology insight and discovery ...

Rensselaer Polytechnic Institute researchers use supercomputer to study effects of stacking graphene nanoribbons ...

Appro has been selected for the second time to support the High Performance Computing Modernization Programme (HPCMP) to improve supercomputing capabilities ...

Chinese researchers tap GPU supercomputer for world's first simulation of complete H1N1 virus ...

For the first time, IBM brings mainframe and Windows together ...

AMD processors power leading research and academic supercomputers ...

Mali-T658 GPU extends graphics and GPU compute leadership for high performance devices ...

ORNL fundamental discovery casts enzymes in new light ...

Altera's Stratix IV FPGAs deliver unprecedented acceleration for world's most powerful reconfigurable supercomputer ...