Recently major cloud and HPC providers like aws, Alibaba, Huawei and Nimbix have started deploying FPGAs in their data centers. However, currently the development tools and frameworks offered by FPGA vendors and cloud providers do not allow the utilization of FPGA clusters from multiple applications. For example, if one application wants to distribute the workload into several FPGAs in a...
Suitable applications for FPGAs have traditionally been those whose architecture permit significant reuse of the on-chip memory to circumnavigate the relatively limited external memory bandwidth when compared with other acceleration technologies. Although this approach has been successful for applications such as deep learning, there are still many problems that would benefit from extra memory...
Natural language processing (NLP) is often used to perform tasks like sentiment analysis, relationship extraction and word sense disambiguation. Most traditional NLP algorithms operate over strings of words and are limited since they analyse meanings of the component words in a corpus without information about grammatical rules of the language. Consequently, the qualities of results of these...
Research in quantum computing is very important to develop applications for medicine, business, trade, environmental and national security purposes. Today's physical quantum computers suffers from noise and the difficulty of correcting the quantum errors.
The complexity of implementing Quantum bits is reduced by decoupling each Q bit and map it either in time or Space. Classical...
Major efforts to build an exascale class computer are under way in four regions of the world. This time, the game changer compared with the previous decade—sustained PF—is the impressive growth of Deep Learning/Ai/Data analytics in all industry segments. This sustained growth and inflexion towards data-centric workflows is having a significant impact on the architectural features, from HW and...
In the post-Moore’s law era, accelerators and special-purpose hardware may offer the best node-level performance for different algorithms and methods given constraints on energy and device design. How will a general purpose HPC center, like NERSC, adapt and serve the needs of a diverse scientific community? In this talk I will review NERSC’s experience with heterogenous systems and how we...
