The microservice architecture has dramatically reduced user effort in adopting and
maintaining servers by providing a catalog of functions as services that can be used as …

To accelerate the training of Deep Learning (DL) models, clusters of machines equipped
with hardware accelerators such as GPUs are leveraged to reduce execution time. State-of …

Heterogeneous architectures consisting of general-purpose CPUs and throughput-
optimized GPUs are projected to be the dominant computing platforms for many classes of …

As GPUs make headway in the computing landscape spanning mobile platforms,
supercomputers, cloud and virtual desktop platforms, supporting concurrent execution of …

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 …

This paper introduces a new resource virtualization framework, Zorua, that decouples the
programmer-specified resource usage of a GPU application from the actual allocation in the …

Graphics Processing Units (GPUs) are increasingly widely used in the cloud to accelerate
compute-heavy tasks. However, GPU-compute applications stress the GPU architecture in …

To harness a heterogeneous memory hierarchy, it is advantageous to integrate application
knowledge in guiding frequent memory move, ie, replicating or migrating virtual memory …

Managing the thread-level parallelism (TLP) of GPGPU applications by limiting it to a certain
degree is known to be effective in improving the overall performance. However, we find that …