Tartan: Microarchitecting a Robotic Processor

Mohammad Bakhshalipour, Phillip B. Gibbons

Abstract: This paper presents Tartan, a CPU architecture designed for a wide range of robotic applications. Tartan provides architectural support for common robotic kernels, ensuring its broad utility across different robotic tasks. The architecture effectively addresses both computational and memory bottlenecks, marking a significant advancement over previous works. Key features of Tartan include architectural support for oriented vectorization, approximate acceleration with accurate outcome, robot-semantic prefetching, and intra-application cache partitioning. On the six end-to-end robots in the RoWild Suite, Tartan boosts the performance of legacy robotic software by $1.2 \times$ (up to $1.4 \times$), non-approximable software optimized for Tartan by $1.61 \times$ (up to $3.54 \times$), and approximable software optimized for Tartan by $2.11 \times$ (up to $3.87 \times$).