AMD Stream Computing-Breaking the 1 TeraFLOP Barrier
[October 20, 2008, Taipei] -Sapphire Technology today announced next-generation AMD FireStream 9250 processor accelerates scientific and engineering calculations, efficiently delivering supercomputer performance at up to eight gigaflops-per-watt -
AMD's next-generation stream processor, the AMD FireStream 9250 is specifically designed to accelerate critical algorithms in high-performance computing (HPC), mainstream and consumer applications. Leveraging the GPU design expertise of AMD's Graphics Product Group, AMD FireStream 9250 occupies a single PCI-E 2.0 slot only, breaks the one teraflop barrier for single precision performance. AMD FireStream 9250 can deliver performance of up to eight GigaFLOPS per watt in single-precision, and more than 200 gigaflops raw double-precision performance.
The AMD FireStream 9250's compact size makes it ideal for small 1U servers as well as most desktop systems, workstations, and larger servers and it features 1GB of GDDR3 memory, enabling developers to handle large, complex problems. For example, developers are reporting up to a 55x performance increase on financial analysis codes as compared to processing on the CPU alone, which supports their efforts to make better and faster decisions.*
AMD Stream SDK leverage open source technology and software technology partners to provide a robust, open, multi-layer development environment on 32 and 64 bit Linux and Windows environments.
Developers can begin with Brook＋, the popular open-source C-level language and compiler. Math function can be implemented using a new release of AMD Core Math Library for the GPU (ACML-GPU). Tools like GPU Shader Analyzer and AMD Code Analyst help identify and correct performance issues.
AMD's Compute Abstraction Layer (CAL) provides low level access to the GPU for development and performance tuning. AMD's open systems approach allows developers access to all key API's and specification, enabling performance tuning at the lowest level and development of third party tools.
How AMD Stream Computing helps
AMD Stream Computing provides industry-leading performance to handle the hardest HPC Application.
1. Up to 8 GFLOPs per watt-One teraflop of raw performance at under 150 watts.
2. Commodity GPU technology-Affordable 1 TeraFLOP performance
3. Multiple software development paths from high level languages and libraries to low level inter-block communications.
4. Solution scalability through combinations of CPUs and GPUs to match specific problem needs.
5. Support from AMD engineers and partners throughout your development process.
Industries and Applications
Energy, Oil and Gas
Computer Aided Engineering (CFD, FEA, etc.)
The FireStream 9250 and the supporting SDK are available in beginning of November 2008.
AMD FireStream 9170, the industry's first double-precision floating point stream processor, is currently available for purchase
For more information about AMD FireStream 9250 or AMD FireStream 9170 or AMD's complete line of stream computing solutions, please visit http://www.amd.com/stream.
Latest News Posts
- Nintendo NX might use both cartridges and discs
- This emotional AMD commercial invites you to join the Radeon Rebellion
- Oculus walks back restrictive DRM, pledges to not use hardware checks
- No Man's Sky is 'even bigger than you can imagine,' says dev
- 80 games at E3 2016 were powered by Epic's Unreal Engine
- GA-Z77-UD5H and W10 Sata Port Recognition?
- re image
- Logitech G502 Proteus Spectrum RGB Tunable Gaming Mouse Review
- RAM Speed in H61 boards.
- Logitech G910 Orion Spark RGB Mechanical Gaming Keyboard Review
- ADATA launches the Premier SP550 M.2 2280 SATA 6Gb/s SSD
- Mangstor's NX-Series storage arrays accelerate HPC throughput with new burst buffer capabilities
- Swiftech unveils new Komodo Waterblocks for NVIDIA GeForce GTX1080 and GTX1070 flagship video cards
- ADATA releases the HD700 and HV620S external hard drives
- BIOSTAR teams up with Apacer and Thermaltake to showcase high-end gaming machines