Acceleration of parallel-blocked QR decomposition of tall-and-skinny matrices on FPGAs

JMR Borbon, J Huang, BM Wong, W Najjar - ACM Transactions on …, 2021 - dl.acm.org
QR decomposition is one of the most useful factorization kernels in modern numerical linear
algebra algorithms. In particular, the decomposition of tall-and-skinny matrices (TSMs) has …

A 1.2 mm 416 mW 1.44 Mmat/s 6416 Matrix Preprocessing ASIC for Massive MIMO in 22FDX

D Nonaca, C Studer - arXiv preprint arXiv:2410.13838, 2024 - arxiv.org
Massive multiuser (MU) multiple-input multiple-output (MIMO) enables concurrent
transmission of multiple users to a multi-antenna basestation (BS). To detect the users' data …

A 1.2 mm² 416mW 1.44 Mmat/s 64x16 Matrix Preprocessing ASIC for Massive MIMO in 22FDX

D Nonaca, C Studer - European Solid-State Electronics …, 2024 - research-collection.ethz.ch
Massive multiuser (MU) multiple-input multipleoutput (MIMO) enables concurrent
transmission of multiple users to a multi-antenna basestation (BS). To detect the users' data …

[图书][B] Acceleration of Compute-Intensive Applications on Field Programmable Gate Arrays

JMR Borbón - 2020 - search.proquest.com
In recent years, the field of high-performance computing has been facing a new challenge:
achieving high throughput at the lowest energy cost. Recent interest in field-programmable …

A Matrix Inversion Method Based on LDLT Decomposition and its Application in STAP

W Li, Z Lei, G Wu, Z Huang - 2022 7th International Conference …, 2022 - ieeexplore.ieee.org
This paper presents matrix inversion algorithms based on LU decomposition and QR
decomposition and LDLT decomposition (ie improved Cholesky decomposition) and the …