Jiang SChen H.-WMING-SYAN CHEN2022-04-252022-04-252021https://www.scopus.com/inward/record.uri?eid=2-s2.0-85123184538&doi=10.1109%2fICFPT52863.2021.9609814&partnerID=40&md5=3a537bdc02a533c77f96fa9e9b59dab9https://scholars.lib.ntu.edu.tw/handle/123456789/607259Tall and skinny QR (TSQR) decomposition is an essential matrix operation with various applications in edge computing, including data compression, subspace projection, and dimension reduction. As a critical component in TSQR, Dual-Triangular QR (DTQR) decomposition is solved by the Normal QR method in most works without utilizing the dual-triangular structure. Therefore, we propose a novel DTQR accelerator by recursively exploring the DT structure and propose three acceleration strategies with the systolic array to achieve higher parallelism. Experimental results manifest that our algorithm achieves 21.55x on average speedup compared with the baselines. ? 2021 IEEE.Dual-triangular matrixHigh-Level SynthesisQR decompositionHigh level synthesisMatrix algebraDataflowEdge computingEssential matrixHigh-level synthesisMatrix operationsSubspace projectionTriangular matrixTriangular structuresSystolic arraysHigh level synthesis; Matrix algebra; Dataflow; Dual-triangular matrix; Edge computing; Essential matrix; High-level synthesis; Matrix operations; QR decomposition; Subspace projection; Triangular matrix; Triangular structures; Systolic arraysconference paper10.1109/ICFPT52863.2021.96098142-s2.0-85123184538