In this video from the Intel HPC Developer Conference in Denver, Michael Strickland describes how Intel FPGAs are powering new levels of performance and datacenter efficiency with FPGAs.
“Altera and Intel offers a broad range of FPGA devices – from the high performaning Stratix series to the flexible MAX 10 – so you can find a device that best meets your business needs.”
While FPGAs used to be very difficult to program, today multiple design entry methods are available to enable developers to harness the power of FPGAs to accelerate data-intensive applications like machine learning. High-level design takes algorithm experts directly from OpenCL programs, Simulink models, or signal-processing flow charts to an FPGA design.
The Intel FPGA SDK for Open Computing Language (OpenCL) allows a user to abstract away the traditional hardware FPGA development flow for a much faster and higher level software development flow:
- Emulate your OpenCL C accelerator code on an x86-based host in seconds, get a detailed optimization report with specific algorithm pipeline dependency information, pushing the longer compile time to the end when you are pleased with your kernel code results.
- Leverage prewritten optimized OpenCL or register transfer level (RTL) functions, calling them from the host or directly from within your OpenCL kernels.