Related papers: Performance Modeling of Streaming Kernels and Spar…

The matrices used in many computational settings are naturally sparse, holding a small percentage of nonzero elements. Storing such matrices in specialized sparse formats enables algorithms that avoid wasting computation on zeros,…

Coordinating the design of sampling and sparse-dense matrix multiplication (SpMM) is crucial for accelerating graph neural networks (GNNs). However, due to irrational sampling strategies, existing methods face a trade-off between accuracy…

Recently, graphics processors (GPUs) have been increasingly leveraged in a variety of scientific computing applications. However, architectural differences between CPUs and GPUs necessitate the development of algorithms that take advantage…

The recent research advances in deep learning have led to the development of small and powerful Convolutional Neural Network (CNN) architectures. Meanwhile Field Programmable Gate Arrays (FPGAs) has become a popular hardware target choice…

The Emu Chick prototype implements migratory memory-side processing in a novel hardware system. Rather than transferring large amounts of data across the system interconnect, the Emu Chick moves lightweight thread contexts to near-memory…

Modern GPGPUs provide massive arithmetic throughput, yet many scientific kernels remain limited by memory bandwidth. In particular, repeatedly loading precomputed auxiliary data wastes abundant compute resources while stressing the memory…

Scaling up the sparse matrix-vector multiplication kernel on modern Graphics Processing Units (GPU) has been at the heart of numerous studies in both academia and industry. In this article we present a novel non-parametric, self-tunable,…

Sparse deep learning has reduced computation significantly, but its irregular non-zero data distribution complicates the data flow and hinders data reuse, increasing on-chip SRAM access and thus power consumption of the chip. This paper…

Deep convolutional neural networks (CNN) are widely used in modern artificial intelligence (AI) and smart vision systems but also limited by computation latency, throughput, and energy efficiency on a resource-limited scenario, such as…

This review examines the rapidly evolving landscape of ultra-low-power edge processors, covering heterogeneous Systems-on-Chips (SoCs), neural accelerators, near-sensor and in-sensor architectures, and emerging dataflow and memory-centric…

The kernel embedding algorithm is an important component for adapting kernel methods to large datasets. Since the algorithm consumes a major computation cost in the testing phase, we propose a novel teacher-learner framework of learning…

Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution…

While Compute Express Link (CXL) enables support for cache-coherent shared memory among multiple nodes, it also introduces new types of failures--processes can fail before data does, or data might fail before a process does. The lack of a…

In this paper we explore the performance of Intel Xeon MAX CPU Series, representing the most significant new variation upon the classical CPU architecture since the Intel Xeon Phi Processor. Given the availability of a large on-package…

This Article presents two optimized multi-GPU algorithms for Fock matrix construction, building on the work of Ufimtsev et al. and Barca et al. The novel algorithms, opt-UM and opt-Brc, introduce significant enhancements, including improved…

This paper is focused on improving multi-GPU performance of a research CFD code on structured grids. MPI and OpenACC directives are used to scale the code up to 16 GPUs. This paper shows that using 16 P100 GPUs and 16 V100 GPUs can be…

FPGAs are increasingly utilized in data centers due to their capacity to exploit data parallelism in computationally intensive workloads. Furthermore, the processing of modern data center workloads requires moving vast amounts of data,…

Matrix computations are a fundamental building-block of edge computing systems, with a major recent uptick in demand due to their use in AI/ML training and inference procedures. Existing approaches for distributing matrix computations…

Large-scale AI training and inference require hundreds of gigabytes to terabytes of DRAM with high peak to average utilization ratios, resulting in overprovisioning. In cloud computing, DRAM constitutes a significant share of the cost. Yet,…

Sparse matrix-vector multiplication (SpMV) is a fundamental operation with a wide range of applications in scientific computing and artificial intelligence. However, the large scale and sparsity of sparse matrix often make it a performance…