“We present a state-of-the-art image recognition system, Deep Image, developed using end-to-end deep learning. The key components are a custom-built supercomputer dedicated to deep learning, a highly optimized parallel algorithm using new strategies for data partitioning and communication, larger deep neural network models, novel data augmentation approaches, and usage of multi-scale high-resolution images.”
In this video from WestGrid in Canada, Dr. Yussanne Ma from the Michael Smith Genome Sciences Centre describes how high performance computing supports her research group’s work, highlighting a recent project where a bioinformatics pipeline was built for the personalized onco-genomics project (POG) at the BC Cancer Agency.
“Our computing systems continue to evolve, providing significant challenges to the programming teams managing large, long-lived projects. Issues include rapidly increasing on-node parallelism, varying forms of heterogeneity, deepening memory hierarchies, growing concerns around resiliency and silent data corruption, and worsening storage bottlenecks.”
“We present results for a platform consisting of an NVM Express SSD, a CAPI accelerator card and a software stack running on a Power8 system. We show how the threading of the Power8 CPU can be used to move data from the SSD to the CAPI card at very high speeds and implement accelerator functions inside the CAPI card that can process the data at these speeds.”
Learn how OpenACC runtimes also exposes performance-related information revealing where your OpenACC applications are wasting clock cycles. The talk will show that profilers can connect with OpenACC applications to record how much time is spent in OpenACC regions and what device activity it turns into.
The 2nd Workshop on Accelerator Programming using Directives has issued its Call for Papers. The WACCPD Workshop takes place Nov. 16 in Austin in conjunction with SC15.
“Rapid growth in the use cases and demands for extreme computing and huge data processing is leading to convergence of the two infrastructures. The trend towards convergence is not only strategic however but rather inevitable as the Moore’s law ends such that sustained growth in data capabilities, not compute, will advance the capacity and thus the overall capacities towards accelerating research and ultimately the industry.”
“In this session we describe how GPUs can be used within virtual environments with near-native performance. We begin by showing GPU performance across four hypervisors: VMWare ESXi, KVM, Xen, and LXC. After showing that performance characteristics of each platform, we extend the results to the multi-node case with nodes interconnected by QDR InfiniBand. We demonstrate multi-node GPU performance using GPUDirect-enabled MPI, achieving efficiencies of 97-99% of a non-virtualized system.”