In recent years, there has been tremendous advances in hardware acceleration of deep
neural networks. However, most of the research has focused on optimizing accelerator …

Contemporary GPUs are widely used for throughput-oriented data-parallel workloads and
increasingly are being considered for latency-sensitive applications in datacenters …

With the continuous improvement of on-chip integrated voltage regulators (IVRs) and fast,
adaptive frequency control, dynamic voltage-frequency scaling (DVFS) transition times have …

The performance of graphics processing units (GPU) workloads can be sensitive to the
various clock domains which are dynamically tunable in modern GPUs. In this work, we …

On FPGAs, customizing data parallelism can significantly improve performances of
applications. However, a large number of applications, such as sparse matrix multiplication …

Graphic Processing Units (GPUs) are known for the large computing capabilities they offer
users compared to traditional CPUs. However, the issue of resource under-utilization is …

With the advent of GPU computing, profiling tools are now widely used to assist developers
in identifying and solving performance bottlenecks. Those tools are commonly relying on …

Abstract General Purpose Graphics Processing Units (GPGPUs) have become the prevalent
processor for AI/ML and other large computational problems because parallel processing …

Training a modern deep learning model is extremely time-consuming. The
software/hardware deployments that machine learning (ML) programmers use in practice …

This is the second in a sequence of three Hardware Evaluation milestones that provide
insight into the following questions: What are the sources of excess data movement across …