Related papers: ReFloat: Low-Cost Floating-Point Processing in ReR…
Neural networks are an increasingly attractive algorithm for natural language processing and pattern recognition. Deep networks with >50M parameters are made possible by modern GPU clusters operating at <50 pJ per op and more recently,…
Processing-in-memory (PIM) architectures have demonstrated great potential in accelerating numerous deep learning tasks. Particularly, resistive random-access memory (RRAM) devices provide a promising hardware substrate to build PIM…
In this paper, we propose a mixed-precision convolution unit architecture which supports different integer and floating point (FP) precisions. The proposed architecture is based on low-bit inner product units and realizes higher precision…
Matrix-vector multiplication forms the basis of many iterative solution algorithms and as such is an important algorithm also for hierarchical matrices which are used to represent dense data in an optimized form by applying low-rank…
Artificial neural networks have become ubiquitous in modern life, which has triggered the emergence of a new class of application specific integrated circuits for their acceleration. ReRAM-based accelerators have gained significant traction…
Transformers have significantly advanced AI and machine learning through their powerful attention mechanism. However, computing attention on long sequences can become a computational bottleneck. FlashAttention mitigates this by fusing the…
The second-order training methods can converge much faster than first-order optimizers in DNN training. This is because the second-order training utilizes the inversion of the second-order information (SOI) matrix to find a more accurate…
Recommendation system has gained a large popularity for a variety of personalized suggestion tasks, but the ever-increasing number of user data makes real-time processing of recommendation systems difficult. NAND flash memory-based…
The widespread adoption of machine learning algorithms necessitates hardware acceleration to ensure efficient performance. This acceleration relies on custom matrix engines that operate on full or reduced-precision floating-point…
Small animal PET scanners require high spatial resolution and good sensitivity. To reconstruct high-resolution images in 3D-PET, iterative methods, such as OSEM, are superior to analytical reconstruction algorithms, although their high…
Resistive random-access memory (RRAM) provides an excellent platform for analog matrix computing (AMC), enabling both matrix-vector multiplication (MVM) and the solution of matrix equations through open-loop and closed-loop circuit…
Transformers are central to advances in artificial intelligence (AI), excelling in fields ranging from computer vision to natural language processing. Despite their success, their large parameter count and computational demands challenge…
To support emerging applications ranging from holographic communications to extended reality, next-generation mobile wireless communication systems require ultra-fast and energy-efficient (UFEE) baseband processors. Traditional…
The numerical flow iteration method has recently been proposed as a memory-slim solution method for the Vlasov--Poisson system. It stores the temporal evolution of the electric field and reconstructs the solution in each time step by…
Low precision data representation is important to reduce storage size and memory access for convolutional neural networks (CNNs). Yet, existing methods have two major limitations: (1) requiring re-training to maintain accuracy for deep…
The acceleration of deep-learning kernels in hardware relies on matrix multiplications that are executed efficiently on Systolic Arrays (SA). To effectively trade off deep-learning training/inference quality with hardware cost, SA…
The increasing computational and memory demands of large language models (LLMs) necessitate innovative approaches to optimize resource usage without compromising performance. This paper leverages microscaling floating-point formats, a novel…
Graph accelerators have emerged as a promising solution for processing large-scale sparse graphs, leveraging the in-situ compu-tation of ReRAM-based crossbars to maximize computational efficiency. However, existing designs suffer from…
Iterative solvers are frequently used in scientific applications and engineering computations. However, the memory-bound Sparse Matrix-Vector (SpMV) kernel computation hinders the efficiency of iterative algorithms. As modern hardware…
As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck stems from two hardware limitations: (1) limited data…