Improving particle filter performance using SSE instructions

Robotics researchers are often faced with real-time constraints, and for that reason algorithmic and implementation-level optimization can dramatically increase the overall performance of a robot. In this paper we illustrate how a substantial run-time gain can be achieved by taking advantage of the extended instruction sets found in modern processors, in particular the SSE1 and SSE2 instruction sets. We present an SSE version of Monte Carlo Localization that results in an impressive 9x speedup over an optimized scalar implementation. In the process, we discuss SSE implementations of atan, atan2 and exp that achieve up to a 4x speedup in these mathematical operations alone.

Authors

• Peter Djeu
• Michael J. Quinlan
• Peter Stone 0001

Keywords

• Particle filters
• Intelligent robots
• Monte Carlo methods
• Robot sensing systems
• Runtime
• Instruction sets
• Computer aided instruction
• Concurrent computing
• Libraries
• USA Councils
• Particle Filter
• Educational Settings
• Mathematical Operations
• Robot Performance
• Parallelization
• Range Expansion
• Pose Estimation
• Arithmetic Operations
• Scale Experiments
• Ideal Setting
• Power Series
• Side Branches
• Return Value
• Open Reduction
• Optimal Code
• 32-bit Floating-point
• Runtime Performance
• Helper Function
• Scalar Particle
• Bitwise Operations
• Floating-point Values