How can the CS education community shift to teach more parallel and distributedcomputing (PDC) soon enough to prepare its graduates for their careers? The CSin parallel project implements strategies that would accomp...
详细信息
ISBN:
(纸本)9781467309745
How can the CS education community shift to teach more parallel and distributedcomputing (PDC) soon enough to prepare its graduates for their careers? The CSin parallel project implements strategies that would accomplish such a shift. An Early Adopter project to correlate CSin parallel materials and NSF/TCPP Curricular Recommendations is described. Citing research on scalability of innovations, such synergistic collaborations offer hope for scalably and rapidly adding PDC to undergraduate CS education.
Nowadays more and more users have mobile devices with high computing power. This fact allows taking advantage of that processing power to design applications that allow users to interact remotely with the system simpl...
详细信息
Routine operations of emergency first responders are usually well managed. The situation is different for mass casualty emergencies where more people and properties are threatened. In such situations there are no pred...
详细信息
Today, telcos and Internet players are obliged to define new business models sustainable. In the telcos, Service Deliver Platform (SDP) is a key logical entity to deliver services and is the point where mix Internet a...
详细信息
Today, telcos and Internet players are obliged to define new business models sustainable. In the telcos, Service Deliver Platform (SDP) is a key logical entity to deliver services and is the point where mix Internet and telco assets. In parallel, Cloud computing has become a major issue to offer services on demand. In our approach, we tackle a step forward to build up a SDP in the cloud, which can be offered to those operators with lacks in the SDP infrastructure needed to deliver new services to the clients.
Overlapping computations and communication is a key to accelerating stencil applications on parallel computers, especially for GPU clusters. However, such programming is a time-consuming part of the stencil applicatio...
详细信息
Overlapping computations and communication is a key to accelerating stencil applications on parallel computers, especially for GPU clusters. However, such programming is a time-consuming part of the stencil application development. To address this problem, we developed an automatic code generation tool to produce a parallel stencil application with latency hiding automatically from its dataflow model. With this tool, users visually construct the workflows of stencil applications in a dataflow programming model. Our dataflow compiler determines a data decomposition policy for each application, and generates source code that overlaps the stencil computations and communication (MPI and PCIe). We demonstrate two types of overlapping models, a CPU-GPU hybrid execution model and a GPU-only model. We use a CFD benchmark computing 19-point 3D stencils to evaluate our scheduling performance, which results in 1.45 TFLOPS in single precision on a cluster with 64 Tesla C1060 GPUs.
Cloud computing has changed considerably the architecture of modern IT systems introducing new design principles based on the notion of the service as main building unit. Decoupling the service offering from the under...
详细信息
Cloud computing has changed considerably the architecture of modern IT systems introducing new design principles based on the notion of the service as main building unit. Decoupling the service offering from the underlying infrastructure, cloud computing allows for more efficient management of the required resources which in business level is translated into higher flexibility and increased profit. To this end, Clouds are not only an innovative technological environment but also a beneficial market for all the involved stakeholders. This market expands continuously and new service aggregations, customizations and business models are offered in order to cover the needs of all end-users. However, even in this new business ecosystem, the question still remains: “Which offering should I buy”? In this paper we present an approach for incorporating business intelligence in cloud marketplaces through a mechanism for answering this question based on the individual requirements and use profile of each particular cloud customer.
The past decade has witnessed a major paradigm shift in high performance computing with the introduction of accelerators as general purpose processors. These computing devices make available very high parallel computi...
详细信息
ISBN:
(纸本)9781467309752
The past decade has witnessed a major paradigm shift in high performance computing with the introduction of accelerators as general purpose processors. These computing devices make available very high parallelcomputing power at low cost and power consumption, transforming current high performance platforms into heterogeneous CPU-GPU equipped systems. Although the theoretical performance achieved by these hybrid systems is impressive, taking practical advantage of this computing power remains a very challenging problem. Most applications are still deployed to either GPU or CPU, leaving the other resource under- or un-utilized. In this paper, we propose, implement, and evaluate a performance aware scheduling technique along with optimizations to make efficient collaborative use of CPUs and GPUs on a parallel system. In the context of feature computations in large scale image analysis applications, our evaluations show that intelligently co-scheduling CPUs and GPUs can significantly improve performance over GPU-only or multi-core CPU-only approaches.
暂无评论