Многопроцессорные вычислители

High Perfomance Computing

Xilinx 7-Series FPGAs and All Programmable SoCs deliver power efficient, high-performance processing solutions for aerospace and defense, medical, scientific, oil and gas, financial, communications and life science applications. The parallelism and customizable architecture inherent in the FPGA architecture is ideal for high-throughput processing and software acceleration. These devices are built on a 28nm silicon process that introduces HKMG technology to maximize usable system performance through lower power. All Xilinx devices support long product lifecycles that mitigate obsolescence risk. These factors combine to allow HPC platforms based on Xilinx devices to deliver massive processing performance up to 2 TFLOPS, in a single chip, at a fraction of the power of GPUs and multi-core DSPs.

Single Precision Floating-Point Performance/Watt


Rapid Prototyping in C/C++ using Vivado HLS

Rapid prototyping with Xilinx delivers uncompromised reliability, Xilinx is known for, with the most raw compute power at the lowest power.  Confidently go from concept to market with Xilinx compute acceleration solutions.  Vivado HLS provides rapid prototyping design flow software applications developed in single or double precision C/C++.  These applications can be compiled to efficient hardware implementations that can be programmed into Xilinx 28nm devices.  Vivado HLS is includes as part of Vivado Design Suite: System Edition.

Software Based System Realization with C/C++ and OpenCL

Xilinx is currently working with early customers on a new system level, heterogeneous parallel programming environment that leverage abstractions such as C/C++ and Open Computing Language (OpenCL®), in a comprehensive Eclipse-based development environment.

This environment provides market-specific libraries to significantly improve productivity of verified heterogeneous systems with Xilinx All Programmable devices and is architected to empower system architects, SW application developers, and embedded designers who require a parallel architecture, to increase system performance, BOM cost reductions and total power reduction with development time in line with ASSP, DSPs, and GPUs. For more information about Xilinx software-based system realization, please contact your local sales team.