GPUs are a compelling solution for HPC, boasting impressive densities and exceptional performance per watt with GPU-accelerated supercomputers dominating the Green500 list. Thanks to major advances in GPU technology and the rise of OpenCL™, the open standard for parallel programming, more science and engineering firms are turning to GPU servers and clusters to crunch complex datasets.
Learn what Dr. David Rohr, designer of the L-CSC cluster, has to say about achieving 1st spot on the Green500 list.
Learn moreAMD Firepro™ S9170 GPU Speeds HPC Applications
Watch the video interview of Dr. David Rohr and Professor Lindenstruth talking about the L-CSC cluster, #1 ranked supercomputer on the Green500.
AMD FirePro™ S-Series Server GPUs for HPC
Equip your HPC solution with the same GPU accelerator used to power the world’s most energy efficient supercomputer – the AMD FirePro™ S9150! ¹
AMD offers a great solution designed with HPC professionals and workflows in mind. The AMD FirePro™ S9150 is based on AMD’s latest Graphics Core Next (GCN) GPU architecture. It is specifically designed to offer the best in both single and double-precision compute performance, with no other single-GPU card capable of matching its speed or power efficiency.¹ ²
AMD FirePro™ Server GPU Momentum
AMD FirePro S9150 is the first card to deliver two teraflops of sustained DGEMM double-precision compute performance², but the list of achievements doesn’t stop there. AMD has broken new ground in a number of areas, including:
- FIRST on the November 2014 Green500 List¹
- FIRST to break the 5 GFLOPS-per-watt barrier¹
- FIRST GPU server card to have full double-precision floating point performance²
- FIRST GPU server card to have 16GB GDDR5 memory, the largest for a single-chip server GPU4
- BEST performance per watt¹
- GREAT performance per dollar
- SUPPORT for OpenCL™ 2.0³
Maximum Performance, Maximum Efficiency
Whether you’re doing scientific computing, data analytics, or seismic processing, the AMD FirePro S9150 can help accelerate all of your demanding GPU compute needs. Accelerate past our competition, with over 50% more double-precision performance than the comparable Tesla K40. ²
Hardware configurations: K40 - The OS is SLED 11 SP3, with driver 340.65 and CUDA 6.5 SDK, S9150 - The OS is SLED 11 SP3, AMD 15.20 driver
DGEMM, or Double-precision General Matrix-Matrix multiplication, measures floating point execution rate for double precision, real matrix-matrix multiplication. There are many real-world applications that take advantage of double-precision matrix operations. These include computational fluid dynamics, finite element analysis and structural modelling, and molecular dynamics.
With our AMD OpenCL BLAS implementation, we are able to achieve 2 TFLOPS of sustained DGEMM performance with the S9150, while the Tesla K40 achieves 1.3 TFLOPS DGEMM.
Recently, PathScale collaborated with Cirrascale to conduct a test on the OpenACC SPEC-ACCEL benchmark using the AMD FirePro™ S9150. The PathScale ENZO compiler generating an AMD FirePro S9150 executable is now the fastest OpenACC solution as of March, 2015, according to PathScale.
SPECACCEL_ACC_PEAK
For more details, please check out this report.
Buy an AMD FirePro™ S9150, and Start Accelerating Your Applications Today
Purchase your AMD FirePro™ GPU equipped server from any of our following technology partners.
Resources
