Deep learning systems have been successfully applied to Euclidean data such as images,
video, and audio. In many applications, however, information and their relationships are …

Recent trends in deep learning (DL) imposed hardware accelerators as the most viable
solution for several classes of high-performance computing (HPC) applications such as …

Sparse linear algebra includes the fundamental and important operations in various large-
scale scientific computing and real-world applications. There exists performance bottleneck …

Since its discovery, surface-enhanced Raman spectroscopy (SERS) has shown outstanding
promise of identifying trace amounts of unknown molecules in rapid, portable formats …

A bstract We propose a new technique to incorporate multiple fermion flavors in the tensor
renormalization group method for lattice gauge theories, where fermions are treated by the …

The parallel simulation of Spiking Neural P systems is mainly based on a matrix
representation, where the graph inherent to the neural model is encoded in an adjacency …

The ever-increasing size of modern deep neural network (DNN) architectures has put
increasing strain on the hardware needed to implement them. Sparsified DNNs can greatly …

Sparse general matrix-matrix multiplication (SpGEMM) is an important kernel in
computational science and engineering, and has been widely studied on homogeneous …

Performance in scientific and engineering applications such as computational physics,
algebraic graph problems or Convolutional Neural Networks (CNN), is dominated by the …

This paper proposes the Tensor Marshaling Unit (TMU), a near-core programmable dataflow
engine for multicore architectures that accelerates tensor traversals and merging, the most …