RSQP: Problem-specific Architectural Customization for Accelerated Convex Quadratic Optimization
Open Access
- 17 June 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Abstract
Convex optimization is at the heart of many performance-critical applications across a wide range of domains. Although many high-performance hardware accelerators have been developed for specific optimization problems in the past, designing such accelerator is a challenging task and the resulting computing architecture is often so specific to the targeted application that they can hardly be reused even in a related application within the same domain. To accelerate general-purpose optimization solvers that must operate on diverse user input during run time, an ideal hardware solver should be able to adapt to the provided optimization problem dynamically while achieving high performance and power-efficiency. In this work, a hardware-accelerated general-purpose quadratic program solver, called RSQP, with reconfigurable functional units and data path that facilitate problem-specific customization is presented. RSQP uses a string-based encoding to describe the problem structure with fine granularity. Based on this encoding, functional units and datapath customized to the sparsity pattern of the problem are created by solving a dictionary-based lossless string compression problem and a mixed integer linear program respectively. RSQP has been integrated to accelerate the general-purpose quadratic programming solver OSQP and has been tested using an extensive benchmark with 120 optimization problems from 6 application domains. Through architectural customization, RSQP achieves up to 7× performance improvement over its baseline generic design. Furthermore, when compared with a CPU and a GPU-accelerated implementation, RSQP achieves up to 31.2× and 6.9× end-to-end speedup on these benchmark programs, respectively. Finally, the FPGA accelerator operates at up to 6.6× lower dynamic power consumption and up to 22.7× higher power efficiency over the GPU implementation, making it an attractive solution for power-conscious datacenter applications.Keywords
This publication has 25 references indexed in Scilit:
- Optimising Sparse Matrix Vector multiplication for large scale FEM problems on FPGA2016
- Embedded Online Optimization for Model Predictive Control at Megahertz RatesIEEE Transactions on Automatic Control, 2014
- Performance Bounds and Suboptimal Policies for Multi-Period InvestmentFoundations and Trends® in Optimization, 2014
- An architecture for solving quadratic programs with the fast gradient method on a Field Programmable Gate Array2013
- Model predictive control for deeply pipelined field-programmable gate array implementation: algorithms and circuitryIET Control Theory & Applications, 2012
- Towards a Universal FPGA Matrix-Vector Multiplication Architecture2012
- Optimising Memory Bandwidth Use for Matrix-Vector Multiplication in Iterative Methods2010
- FPGA architecture and implementation of sparse matrix–vector multiplication for the finite element methodComputer Physics Communications, 2008
- SNOPT: An SQP Algorithm for Large-Scale Constrained OptimizationSIAM Review, 2005
- Compression of individual sequences via variable-rate codingIEEE Transactions on Information Theory, 1978