ABSTRACT
While FPGAs have been investigated for accelerating computing workloads in academia for many decades, industry started adopting FPGAs as an accelerator only in the last decade, but even those deployments have been fairly limited. This talk describes my journey over 15 years of building and deploying FPGA accelerated solutions. In my career, I have led the integration of FPGAs with CPUs in a variety of ways, each seeking the right mix of efficiency, capability, and cost. The first phase of the journey begins at Intel in 2008 in building the first solutions with socketed FPGAs attached to Xeon CPUs using FSB and QPI coherent buses. These coherently attached FPGAs enabled various new use cases beyond the PCIe attached FPGA accelerators leading to projections of wide scale deployment of FPGAs in the data center. Intel's acquisition of Altera in 2015 kicked off the second phase where we integrated a FPGA die with a Xeon die to produce a multi-chip package that dropped into a Xeon socket. This was introduced in the market targeting communication workloads. We formed Megh Computing in 2017 to enable a FPGA accelerated edge platform for analytics workloads in the enterprise which resulted in solutions for video surveillance. The talk will discuss the various challenges and breakthroughs in deploying FPGA accelerators from the edge to the datacenter, where I see the market headed in the near future and identify promising directions and tough problems the FPGA research community need to tackle to realize the potential of reconfigurable computing.
Index Terms
- My Fifteen Year Journey of Deploying FPGA Accelerated Solutions
Recommendations
Performance and toolchain of a combined GPU/FPGA desktop (abstract only)
FPGA '13: Proceedings of the ACM/SIGDA international symposium on Field programmable gate arraysLow-power, high-performance computing nowadays relies on accelerator cards to speed up the calculations. Combining the power of GPUs with the flexibility of FPGAs enlarges the scope of problems that can be accelerated [2, 3]. We describe the performance ...
Nuclear Reactor Simulations on OpenCL FPGA Platform
FPGA '19: Proceedings of the 2019 ACM/SIGDA International Symposium on Field-Programmable Gate ArraysField-programmable gate arrays (FPGAs) are becoming a promising choice as a heterogeneous computing component for scientific computing when floating-point optimized architectures are added to the current FPGAs. The maturing high-level synthesis (HLS) ...
Modeling and predicting performance of high performance computing applications on hardware accelerators
Hybrid-core systems speedup applications by offloading certain compute operations that can run faster on hardware accelerators. However, such systems require significant programming and porting effort to gain a performance benefit from the accelerators. ...
Comments