Mapping complex algorithm into FPGA with High Level Synthesis reconfigurable chips with High Level Synthesis compared with CPU, GPGPU

摘要

This presentation discusses on the comparison between "Reconfigurable Chip with High Level Synthesis" and "CPU, GPCPU with compiler such as CUDA" from the compiler perspective. Initially, we introduce several demands for acceleration with FPGA to achieve low latency calculation and control. As an application example, we show a High Frequency Trading. We accelerate it by FPGA NIC with C-based and SQL-based HLS, and show the necessity of high level language customizable reconfigurable chip. Then, we illustrate the difference of FPGA and processor (CPU, GPGPU) with the "FSM+Datapath" model and examine how the architecture difference affects delay and parallelism of operations. Next, we discuss parallelization of operations, threads with High Level Synthesis for FPGA and software compiler for processors. The main advantage of the former method is it is able to parallelize operations beyond control dependencies while the latter method has to obey control dependencies. Finally, some experimental results prove that "FPGA and HLS" generate better performance than a processor for control intensive algorithm.