MCAPI abstraction on FPGA based SoC design

Abstract

FPGAs are traditionally designed with RTL-level IP-block descriptions. Many FPGA designs include several synthesizable processors and SW executables are mapped to them after a separate software development process. The tools help connecting physical blocks together and typically provide a board support package for SW development to access HW from the application code. The designer is still responsible of carefully planning how the applications on multiple cores communicate, which is getting the more difficult the more cores and other IP blocks are introduced. We apply Multicore Association Communications API (MCAPI) to implement hardware independent communication mechanism between the applications. The benefit is a unified programming API to different processor and operating system types, but also for hardware IP-blocks that the cores can access. We introduce MCAPI and show a case study of a simple video encoder with and without MCAPI abstraction. Porting an application function takes 3 hours with MCAPI and 5 without, i.e. 40 % reduction. However, the overhead from MCAPI is increase memory footprint by 25 KB and effect on the video encoder performance -22 % compared to non-MCAPI case.

Automatic Synthesis over Multiple APIs from Uml/Marte Models for Easy Platform Mapping and Reuse

“…In [22], MCAPI is deployed on Intel's Singlechip Cloud Computer (SCC), a 48-core concept vehicle for future many-core systems. In [21], its application to FPGAs aims for 40% performance improvement. In [29], its application to map components to DSPs is presented.…”

A Co-design Approach for Hardware Optimizations in Multicore Architectures Using MCAPI

“…However, implementing a standard software API for an existing architecture may compromise some performance figures. In [4], an implementation of the Multicore Communication API (MCAPI) is done in an FPGA platform with NiosII processors. Although the implementation was successfully validated, the measurements showed a decrease between 21% and 32% of fps (frames per second) for a simplified version of H.263 video encoder when compared to non-MCAPI implementation.…”