Related papers: Mapping Parallel Matrix Multiplication in GotoBLAS…

The high computational and memory demands of modern deep learning (DL) workloads have led to the development of specialized hardware devices from cloud to edge, such as AMD's Ryzen AI XDNA NPUs. Optimizing general matrix multiplication…

Scaling laws for Large Language Models (LLMs) establish that model quality improves with computational scale, yet edge deployment imposes strict constraints on compute, memory, and power. Since General Matrix Multiplication (GEMM) accounts…

The growing adoption of domain-specific architectures in edge computing platforms for deep learning has highlighted the efficiency of hardware accelerators. However, integrating custom accelerators into modern machine learning (ML)…

The alternating direction method of multipliers (ADMM) is a powerful operator splitting technique for solving structured convex optimization problems. Due to its relatively low per-iteration computational cost and ability to exploit…

Many scientific computing problems can be reduced to Matrix-Matrix Multiplications (MMM), making the General Matrix Multiply (GEMM) kernels in the Basic Linear Algebra Subroutine (BLAS) of interest to the high-performance computing…

We present the design and implementation details of a geometric multigrid method on adaptively refined meshes for massively parallel computations. The method uses local smoothing on the refined part of the mesh. Partitioning is achieved by…

High Bandwidth Memory with Processing-in-Memory (HBM-PIM) offers an opportunity to reduce data movement by executing computation directly inside memory, but current commercial platforms expose limited instruction sets and require…

Complex, high-throughput data acquisition and processing systems, such as those used in high-energy physics experiments, are increasingly moving sophisticated pattern recognition and data compression algorithms closer to the sensors…

General matrix multiplication (GEMM) operations are the fundamental building blocks of computational domains including artificial intelligence (AI). As GPU architectures evolve and high-performance AI becomes increasingly important,…

Computation-in-Memory (CiM) is attracting attention as a technology that can perform MAC calculations required for AI accelerators, at high speed with low power consumption. However, there is a problem regarding power consumption and…

Optical architectures have been emerging as an energy-efficient and high-throughput hardware platform to accelerate computationally intensive general matrix-matrix multiplications (GEMMs) in modern machine learning (ML) algorithms. However,…

Convolutional Neural Networks (CNNs) remain prevalent in computer vision applications, and FPGAs, known for their flexibility and energy efficiency, have become essential components in heterogeneous acceleration systems. However,…

Many of today's deep neural network accelerators, e.g., Google's TPU and NVIDIA's tensor core, are built around accelerating the general matrix multiplication (i.e., GEMM). However, supporting convolution on GEMM-based accelerators is not…

The growing demand for efficient, high-performance processing in machine learning (ML) and image processing has made hardware accelerators, such as GPUs and Data Streaming Accelerators (DSAs), increasingly essential. These accelerators…

Distributed computing has been widely applied in distributed edge networks for reducing the processing burden of high-dimensional data centralization, where a high-dimensional computational task is decomposed into multiple low-dimensional…

The increasing computational and memory requirements of Deep Learning (DL) workloads has led to outstanding innovations in hardware architectures. An archetype of such architectures is the novel Versal AI Engine (AIE) by AMD/Xilinx. The AIE…

Processing in memory (PIM) moves computation into memories with the goal of improving throughput and energy-efficiency compared to traditional von Neumann-based architectures. Most existing PIM architectures are either general-purpose but…

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…

General Matrix Multiplication (GEMM) is the cornerstone of HPC workloads and Deep Learning. State-of-the-art vendor libraries tune tensor layouts, parallelization schemes, and cache blocking to minimize data movement across the memory…

General matrix-matrix multiplications with double-precision real and complex entries (DGEMM and ZGEMM) in vendor-supplied BLAS libraries are best optimized for square matrices but often show bad performance for tall & skinny matrices, which…