Intel HPC Speakerships 2020: Online June 22-24, 2020 |
Conference website | https://www.intel.com |
Submission link | https://easychair.org/conferences/?conf=intelspeakershipsati |
Abstract registration deadline | May 15, 2020 |
Submission deadline | May 15, 2020 |
Update May 15, 2020: Abstract submissions are now closed. Thank you.
On April 8, 2020 the in person ISC 2020 event in Frankfurt, Germany was cancelled given the current global health situation. The ISC organizers plan to offer a leaner, digital version of the conference with details forthcoming. Intel will now present technical content via webinars, podcasts, or other virtual means in the late June timeframe.
Welcome to the Intel® HPC Speakerships 2020 abstract submissions site. By invitation from the Intel Planning Committee, please use this form to submit your abstract for upcoming online speakership opportunities by May 15, 2020 or sooner. Update May 15, 2020: Abstract submissions are now closed. We are looking for abstracts for Technical Talks (15 minutes) and Fireside Chats (20 minutes) to take place online. We invite you to share your research and breakthrough results, connecting with experts in the HPC and AI community interested in advancements made possible with the Intel portfolio of architecture and tools. Preference will be given to proposals of the highest technical merit and that lend themselves best to compelling, engaging, and interactive experiences for online attendees. Formats:
- Technical Talk: 15 minutes, 15 slides maximum, typically 1 speaker.
- Fireside Chat: 20 minutes, title slide only, an informal conversation between 1 moderator and up to 2 guests on a focus theme.
List of Topics
- Artificial Intelligence/High Performance Data Analytics: Data is the new gold of computing driving AI, driving business growth and innovation. The choices made for HPC infrastructure should cater to HPC, AI, and Data Analytics workloads all using a unified hardware-software infrastructure. The journey starts with examples and hands-on experiences in machine learning, deep learning and high performance data analytics. We welcome sessions ranging from beginner, intermediate, and advanced levels on application development, scaling techniques in HPC environments, and research to help start the AI and high performance data analytics journey. Content that addresses: Machine Learning, Deep Learning, AI Frameworks, Optimization or Results on Intel Platforms, Big Data, High Performance Data Analytics, etc.
- HPC in the Cloud: High Performance Computing in the cloud continues to mature, and with much research and deployment to support expanding from on-premise compute resources, exciting use models are emerging to satisfy compute needs. We welcome technical sessions that show technical solutions, effective use, deployment and results from using HPC in the cloud resources. Content that addresses: Job management, deployment, optimizations, containers, distributed/MPI applications
- Parallel Programming (High Performance Computing): Parallelism is critical to achieving performance at all levels of the computing landscape, from small edge devices to the largest supercomputers. Taking advantage of parallelism requires the right programming tools, techniques, and knowledge. We welcome experiences in all aspects of code modernization from vectorization to threading to message passing on a variety of parallel computing platforms. Content that addresses: oneAPI and Data Parallel C++ (DPC++), Parallel Algorithms, Parallel Programming Tools or Libraries, Parallel Programming Debugging, Parallel Programming Optimization Techniques, Programming Heterogeneous Compute Resources
- High Productivity Languages: “Good, Cheap, and Fast… Pick Two” is the adage that is often used to highlight technology trade-offs. In programming, scripting languages typically can be described as “faster to learn, easy to write but not performant”, but you would really like all three! This technical track will focus on how high productivity languages such as Python, R, and Julia are delivering new levels of capability for HPC deployments – helping drive not only emerging research but also being deployed at scale in Big Data/Machine Learning HPC environments. Content that addresses: Python, R, MATLAB, Julia
- Storage: HPC has always been the domain of HUGE compute capacity in flops but to feed the computational monster HUGE amounts of data are required. HPC, Big Data, and AI are all data intensive in the ways of volume, velocity, and variety, and thus storage of this data and the ability to deliver it as needed is a never ending challenge. For the areas of storage we look for technical sessions that focus on meeting these challenges at the application, system, and I/O level. Content that addresses: Lustre, DAOS, SSD/Persistent Memory Storage, Parallel File Systems
- Systems: Configuration, Management & Cloud – Standing up HPC systems, keeping them healthy and running optimally is challenging at any scale. Additionally, the availability of cloud based HPC resources and containerization has fostered new usage models. This area’s focus will be on the deployment and management of HPC resources along with their complex software ecosystems. Content that addresses: OpenHPC, System Configuration and Management, Interconnects/Fabric, Containers, Cloud (setup or usage), and Portability
- Visualization Development: Visualizations serve a crucial role of making complex data intelligible and usable for scientific research, entertainment, and engineering. The highly flexible processing capability and directly accessible memory of Intel® parallel processors provide an excellent platform for high, interactive performance for both raster-based (OpenGL*) and ray-tracing based visualizations. We welcome case studies, implementations, and research involving Intel® architecture, visualization applications, and infrastructure. Content that addresses: Intel® oneAPI Rendering Toolkit, OpenSWR, OSPRay, Embree, ParaView, VTK, VTK-m, VisIt, VMD, EnSight, Mesa, In-Situ Visualization, and High Fidelity Interactive Rendering
Submission Guidelines
Submit your abstract by May 15, 2020 or sooner. Update May 15, 2020: Abstract submissions are now closed. If you do not already have an EasyChair account, create one and then follow the submission form link. Please provide the following key information via the submission form:
- Title (15 words maximum).
- Keywords (3 minimum).
- Format (select one).
- Technical Talk: 15 minutes, 15 slides maximum, typically 1 speaker.
- Fireside Chat: 20 minutes, title slide only, an informal conversation between 1 moderator and up to 2 guests on a focus theme.
- Topic (select all that apply). See detailed descriptions provided in the List of Topics above.
- Abstract description (250 words maximum). Please ensure that your abstract addresses: Why will this talk be impactful and interesting to the HPC community? For example, novel results, time to solution, power saving, etc. What will attendees learn from your presentation? How was Intel technology used in this work?
- Indicate the audience skill level your presentation is aimed for (select one).
- Specify the Intel architecture that will be referenced in your presentation (select all that apply).
- Is this a new solution/system? If not, when and where was it first shown?
- Do you have any schedule constraints we should be aware of?
- Speaker name
- Speaker job title
- Speaker short bio (may include social media links)
- Speaker headshot
Contact
All questions should be emailed to speaker manager Shari Lawrence sharix.lawrence@intel.com.