Related papers: NOM: Network-On-Memory for Inter-Bank Data Transfe…
Large language model (LLM) inference has been a prevalent demand in daily life and industries. The large tensor sizes and computing complexities in LLMs have brought challenges to memory, computing, and databus. This paper proposes a…
Running neural networks (NNs) on microcontroller units (MCUs) is becoming increasingly important, but is very difficult due to the tiny SRAM size of MCU. Prior work proposes many algorithm-level techniques to reduce NN memory footprints,…
Distributed antenna system (DAS) has been deployed for over a decade. DAS has advantages in capacity especially for the cell edge users, in both single-cell and multi-cell environments. In this paper, non-orthogonal multiple access (NOMA)…
Transformer-based models dominate modern AI workloads but exacerbate memory bottlenecks due to their quadratic attention complexity and ever-growing model sizes. Existing accelerators, such as Groq and Cerebras, mitigate off-chip traffic…
In this paper, a backscatter cooperation (BC) scheme is proposed for non-orthogonal multiple access (NOMA) downlink transmission. The key idea is to enable one user to split and then backscatter part of its received signals to improve the…
Conventional wisdom holds that an efficient interface between an OS running on a CPU and a high-bandwidth I/O device should use Direct Memory Access (DMA) to offload data transfer, descriptor rings for buffering and queuing, and interrupts…
Memory disaggregation has emerged as an alternative to traditional server architecture in data centers. This paper introduces DRackSim, a simulation infrastructure to model rack-scale hardware disaggregated memory. DRackSim models multiple…
Computing-in-memory (CIM) has attracted significant attentions in recent years due to its massive parallelism and low power consumption. However, current CIM designs suffer from large area overhead of small CIM macros and bad programmablity…
We consider uplink power control in wireless communication when a large number of users compete over the channel resources. The CDMA protocol, as a supporting technology of 3G networks accommodating signal from different sources over the…
The proliferation of connected vehicles along with the high demand for rich multimedia services constitute key challenges for the emerging 5G-enabled vehicular networks. These challenges include, but are not limited to, high spectral…
DRAM-based main memories have read operations that destroy the read data, and as a result, must buffer large amounts of data on each array access to keep chip costs low. Unfortunately, system-level trends such as increased memory contention…
In this study, we propose a novel three-user noise-domain non-orthogonal multiple access (ND-NOMA) scheme by introducing the correlation as a new dimension besides mean and variance quantities used in two-user ND-NOMA. The new three-user…
Non-orthogonal multiple access (NOMA) technique is important for achieving a high data rate in next-generation wireless communications. A key challenge to fully utilizing the effectiveness of the NOMA technique is the optimization of the…
Multiple-input multiple-output non-orthogonal multiple access (MIMO-NOMA) cellular network is promising for supporting massive connectivity. This paper exploits low-latency machine learning in the MIMO-NOMA uplink transmission environment,…
The computing wall and data movement challenges of deep neural networks (DNNs) have exposed the limitations of conventional CMOS-based DNN accelerators. Furthermore, the deep structure and large model size will make DNNs prohibitive to…
Compute-in-memory (CIM) techniques are widely employed in energy-efficient artificial intelligent (AI) processors. They alleviate power and latency bottlenecks caused by extensive data movements between compute and storage units. To extend…
Finding the best way to leverage non-volatile memory (NVM) on modern database systems is still an open problem. The answer is far from trivial since the clear boundary between memory and storage present in most systems seems to be…
Compute-In-Memory (CiM) is a promising solution to accelerate Deep Neural Networks (DNNs) as it can avoid energy-intensive DNN weight movement and use memory arrays to perform low-energy, high-density computations. These benefits have…
We propose a co-design approach for compute-in-memory inference for deep neural networks (DNN). We use multiplication-free function approximators based on ell_1 norm along with a co-adapted processing array and compute flow. Using the…
6G wireless networks will require the flexibility to accommodate an extremely diverse set of service types. This necessitates the use of mixed numerologies to accommodate different quality of service (QoS) requirements. Non-orthogonal…