Initially introduced as special-purpose accelerators for graphics applications, graphics
processing units (GPUs) have now emerged as general purpose computing platforms for a …

Memory controllers in modern GPUs aggressively reorder requests for high bandwidth
usage, often interleaving requests from different warps. This leads to high variance in the …

Recent studies on commercial hardware demonstrated that irregular GPU applications can
bottleneck on virtual-to-physical address translations. In this work, we explore ways to …

Since the introduction of fully programmable vertex shader hardware, GPU computing has
made tremendous advances. Exception support and speculative execution are the next …

GPUs are increasingly being used to accelerate general-purpose applications, including
applications with data-dependent, irregular memory access patterns and control flow …

The rise of data-intensive algorithms, such as Machine Learning ones, has meant a strong
diversification of Graphics Processing Units (GPU) in fields with intensive Data-Level …

Future GPUs should have larger L2 caches based on the current trends in VLSI technology
and GPU architectures toward increase of processing core count. Larger L2 caches …

GPUs have become increasingly popular in recent years, in large part due to their potential
to offer a large amount of computational power at low prices. They offer massive potential …

GPUs are much more power-efficient devices compared to CPUs, but due to several
performance bottlenecks, the performance per watt of GPUs is often much lower than what …

With the rapid development of e-commerce and the adoption of dual channels, free riding
becomes more prevalent than ever before and often results in channel conflict. In this paper …