Related papers: Balancing FP8 Computation Accuracy and Efficiency …
While embedded FPGAs are attractive platforms for DNN acceleration on edge-devices due to their low latency and high energy efficiency, the scarcity of resources of edge-scale FPGA devices also makes it challenging for DNN deployment. In…
Accurate brain tumor segmentation is significant for clinical diagnosis and treatment but remains challenging due to tumor heterogeneity. Mamba-based State Space Models have demonstrated promising performance. However, despite their…
Diffusion Transformers (DiTs) have recently gained substantial attention in both industrial and academic fields for their superior visual generation capabilities, outperforming traditional diffusion models that use U-Net. However,the…
Adopting FPGA as an accelerator in datacenters is becoming mainstream for customized computing, but the fact that FPGAs are hard to program creates a steep learning curve for software programmers. Even with the help of high-level synthesis…
The current state of the art of Simultaneous Localisation and Mapping, or SLAM, on low power embedded systems is about sparse localisation and mapping with low resolution results in the name of efficiency. Meanwhile, research in this field…
Bit-serial Processing-In-Memory (PIM) is an attractive paradigm for accelerator architectures, for parallel workloads such as Deep Learning (DL), because of its capability to achieve massive data parallelism at a low area overhead and…
This paper presents a programmable in-memory-computing processor, demonstrated in a 65nm CMOS technology. For data-centric workloads, such as deep neural networks, data movement often dominates when implemented with today's computing…
Recent advances in deep learning methods such as LLMs and Diffusion models have created a need for improved quantization methods that can meet the computational demands of these modern architectures while maintaining accuracy. Towards this…
Compute-in-memory (CIM) accelerators using non-volatile memory (NVM) devices offer promising solutions for energy-efficient and low-latency Deep Neural Network (DNN) inference execution. However, practical deployment is often hindered by…
Recent work has explored reduced numerical precision for parameters, activations, and gradients during neural network training as a way to reduce the computational cost of training (Na & Mukhopadhyay, 2016) (Courbariaux et al., 2014). We…
Leveraging the high density and energy efficiency of Compute-In-Memory (CIM) crossbar-based Deep Neural Network (DNN) accelerators requires optimal Design Space Exploration (DSE), which becomes increasingly challenging as complex models for…
Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition. TSC tasks require models to effectively capture discriminative information for…
Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets. However, existing mixed-precision methods typically suffer from one of two limitations: they either rely on expensive…
Compute-in-Read-Only-Memory (CiROM) accelerators offer outstanding energy efficiency for CNNs by eliminating runtime weight updates. However, their scalability to Large Language Models (LLMs) is fundamentally constrained by their vast…
With today's increasing demand for digital devices in Substation Automation Systems (SAS) based on the IEC61850 standard, the measured data error due to the synchronization problem should be considered as a significant problem in…
The growing demand for edge-AI systems requires arithmetic units that balance numerical precision, energy efficiency, and compact hardware while supporting diverse formats. Posit arithmetic offers advantages over floating- and fixed-point…
With the rapid advancements in coherent Passive Optical Network (PON) technologies featuring 100G and higher data rates, this paper addresses the urgent requirement for sophisticated simulation and MAC layer development within the domain of…
This paper introduces the first implementation of digital Tsetlin Machines (TMs) on flexible integrated circuit (FlexIC) using Pragmatic's 600nm IGZO-based FlexIC technology. TMs, known for their energy efficiency, interpretability, and…
Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…
We propose a hardware-efficient RBD accelerator based on FPGA, introducing three key innovations. First, we propose a precision-aware quantization framework that reduces DSP demand while preserving motion accuracy. This is also the first…