Hari Sivaraman

An Automation Framework for Benchmarking and Optimizing Performance of Remote Desktops in the Cloud

In the current trend of moving everything into the cloud, cloud-based remote desktops are not an exception. Benchmarking virtual remote desktops for performance optimization is an important task for the successful development and deployment planning of virtual desktop infrastructure (VDI) used to deliver remote desktops. This task is very challenging at cloud scale because of rapid evolution of VDI software architectures with a very large number of remote desktops to be managed. In this paper, we present a new framework for evaluating VDI performance that has the capabilities of simulating real world VDI workloads and measuring important performance metrics at scale. Its design aims to provide facilities to easily automate the performance benchmarking tasks and the flexibility of adapting to changes in VDI software architecture, which are two major limitations of the existing solution. For evaluation, we present performance results of this framework.

Machine Learning Using Virtualized GPUs in Cloud Environments

Using graphic processing units (GPU) to accelerate machine learning applications has become a focus of high performance computing (HPC) in recent years. In cloud environments, many different cloud-based GPU solutions have been introduced to seamlessly and securely use GPU resources without sacrificing their performance benefits. Among them are two main approaches: using direct pass-through technologies available on hypervisors and using virtual GPU technologies introduced by GPU vendors. In this paper, we present a performance study of these two GPU virtualization solutions for machine learning in the cloud. We evaluate the advantages and disadvantages of each solution and introduce new findings of their performance impact on machine learning applications in different real-world use-case scenarios. We also examine the benefits of virtual GPUs for machine learning alone and for machine learning applications running together with other GPU-based applications like 3D-graphics on the same server with multiple GPUs to better leverage computing resources. Based on our experimental results benchmarking machine learning applications developed with TensorFlow, we discuss the scaling from one to multiple GPUs and compare the performance between two virtual GPU solutions. Finally, we show that mixing machine learning and other GPU-based workloads can help to reduce combined execution time as compared to running these workloads sequentially.