paper-with-me

홈 › Papers

Autoencoder for Interconnect's Bandwidth Relaxation in Large Scale MIMO-OFDM Processing

2019-09-19

Deep learning is playing an instrumental role in the design of the next generation of communication systems. In this letter, we address the massive MIMO interconnect's bandwidth constraint relaxation using autoencoders. The autoencoder is trained to learn the received signal structure so that a low dimension latent variable is transferred as opposed to the original high dimension signal. For an efficient implementation, the approach suggests to separately deploy the autoencoder components, namely the encoder and the decoder, in massive MIMO radio head and central processing units respectively. The simulation results show that one can relax the interconnect's bandwidth by a factor of up to 16 with non-substantial performance degradation of the centralized and the decentralized processing. Fortunately, such a loss can be compensated by running few extra iterations in the detection process which renders the autoencoder-iterative detection an interconnect's bandwidth and computational complexity design trade-off.

📄 PDF Abstract BibTeX arXiv:1907.12613

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Similar Papers 제목 키워드 기반

UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods

2026-07-07 · Yipeng Liu, Chang Liu, Si Shen, Jiaqi Zheng 외 arxiv

The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA's NVL72/576 and Huawei's CloudMatrix384, introduces critical challenges beyond raw interconnect bandwidth. While th…

Accelerating Frontier MoE Training with 3D Integrated Optics

2025-09-09 · Mikhail Bernadskiy, Peter Carson, Thomas Graham, Taylor Groves 외 arxiv

The unabated growth in AI workload demands is driving the need for concerted advances in compute, memory, and interconnect performance. As traditional semiconductor scaling slows, high-speed interconnects have emerged as…

Challenges and Research Directions for Large Language Model Inference Hardware

2026-01-08 · Xiaoyu Ma, David Patterson arxiv

Large Language Model (LLM) inference is hard. The autoregressive Decode phase of the underlying Transformer model makes LLM inference fundamentally different from training. Exacerbated by recent AI trends, the primary ch…

FlexLink: Boosting your NVLink Bandwidth by 27% without accuracy concern

2025-08-30 · Ao Shen, Rui Zhang, Junping Zhao arxiv

As large language models (LLMs) continue to scale, multi-node deployment has become a necessity. Consequently, communication has become a critical performance bottleneck. Current intra-node communication libraries, like …

On the Impact of Partial Sums on Interconnect Bandwidth and Memory Accesses in a DNN Accelerator

2020-11-02 · Mahesh Chandra

Dedicated accelerators are being designed to address the huge resource requirement of the deep neural network (DNN) applications. The power, performance and area (PPA) constraints limit the number of MACs available in th…