Associative processing (AP) is a promising PIM paradigm that overcomes the von Neumann
bottleneck (memory wall) by virtue of a radically different execution model. By decomposing …

GPUs are prevalent in modern computing systems at all scales. They consume a significant
fraction of the energy in these systems. However, vendors do not publish the actual cost of …

In this paper, we present PPT-GPU, a scalable performance prediction toolkit for GPUs. PPT-
GPU achieves scalability through a hybrid high-level modeling approach where some …

Graphics processing units (GPUs) are continually evolving to cater to the computational
demands of contemporary general-purpose workloads, particularly those driven by artificial …

Graphics Processing Units (GPUs) are now considered the leading hardware to accelerate
general-purpose workloads such as AI, data analytics, and HPC. Over the last decade …

Modern GPU applications, such as machine learning (ML), can only partially utilize GPUs,
leading to GPU underutilization in cloud environments. Sharing GPUs across multiple …

In this paper, we introduce an accurate and scalable memory modeling framework for
General Purpose Graphics Processor units (GPGPUs), PPT-GPU-Mem. That is Performance …

With the growing number of data-intensive workloads, GPU, which is the state-of-the-art
single-instruction-multiple-thread (SIMT) processor, is hindered by the memory bandwidth …

Mobile GPUs are extremely under-utilized for DNN computations across different mobile
deep learning frameworks and multiple DNNs with various complexities. We explore the …

Modern GPU applications, such as machine learning (ML) frameworks, can only partially
utilize beefy GPUs, leading to GPU underutilization in cloud environments. Sharing GPUs …