Performance (single precision, per GPU-proc.) As The K10 is a dual-GPU, the table is per GPU. Let’s put into perspective why this is, by comparing the TESLA K10 against the FirePro S9000. Performance comparisonĪt IBC’12 I was at the AMD booth and looked at the impressive performance of OpenCL-enabled software by AMD-partners when using the latest GPUs in the 9000-series. Therefore I put a lot of weight on memory and cache available per GPU and core. Compute-problems are most times memory-bound and that is an important factor that GPUs outperform CPUs, as they have a very high memory bandwidth. As the communication goes via the PCI-bus still, the compute-capabilities between two GPU cards and a multi-GPU card is not that different. Edit: About the multi-GPU configurationĪ multi-GPU card has various advantages as it uses less power and space, but does not compare to a single GPU. It also outperforms the unreleased Intel Xeon Phi in single precision and is close in double precision. At StreamHPC we are happy with that, as AMD is a strong OpenCL-supporter and FirePro GPUs give much more performance than TESLAs. What does this mean? We finally get a very good alternative to TESLA: servers with probably 2 (1U) or 4+ (3U) FirePro GPUs giving 6.46 to up to 12.92 TFLOPS or more theoretical extra performance on top of the available CPU. SuperMicro, Dell and HP will probably be one of the first. AMD partners for servers will have products ready Q1 2013 or even before. They use passive cooling, as server-racks are actively cooled already. Recently AMD announced their new FirePro GPUs to be used in servers: the S9000 (shown at the right) and the S7000. How can I get through the recruitment process?.What does it mean to work at Stream HPC?.Other Mobile & Embedded – Various new languages have emerged.Low Power – Apps, embedded and portable solutions.Low Latency – Small data-sizes, low response times.Intel – XeonPhi Accelerators, Xeon CPUs.HPC – High Level Programming – Directives and C++.AMD – HIPified CUDA for HSA-enabled GPUs.HPC – Explicit Programming – Accelerated applications and simulations.You can click on the logos of the Programming APIs and Hardware Brands. The below technologies we have experience with and can use them to program CPUs, GPUs, FPGAs and DSPs.
0 kommentar(er)
