The chapter discuss characterization and optimization methodology applied to a 3D finite differences (3DFD) algorithm used to solve constant or variable density isotropic acoustic wave equation (Iso3DFD). From an unoptimized version to the most optimized, the authors achieved a six-fold performance improvement on Intel Xeon E5-2697v2 processors and a nearly thirty-fold … [Read more...]
Portable Performance with OpenCL On Intel Xeon Phi
This High Performance Parallelism Pearl show the potential for using the OpenCL™ standard parallel programming language to deliver portable performance on Intel Xeon Phi coprocessors, Xeon processors, and many-core devices such as GPUs from multiple vendors. This portable performance can be delivered from a single program without needing multiple versions of the code, an … [Read more...]
High Performance Ray Tracing With Embree On Intel Xeon Phi
Ray tracing is a technique for generating images of synthetic scenes. Because ray tracing simulates the physics of light transport in the real world, it can be used to achieve high quality and even photorealistic results. The chapter authors in High Performance Parallelism Pearls describe how the Intel Embree ray tracing kernel library can be used to achieve high performance … [Read more...]
Data Transfer Using The Intel COI Library
This short chapter gives an introduction to the Intel COI library and discusses the pros and cons of different data buffers as well as provides benchmarks on transfer latency and bandwidth between the host and the coprocessor. For any non-trivial applications, there is likely going to be a need to share data between the host and the coprocessor. These valuable information are … [Read more...]
Register For Lustre’s Brent Gorda Parallel Storage and Big Data HP-Cast
Register here to join Brent Gorda, GM of Intel Corporations High Performance Data division as he presents on the topic of how the Intel® Enterprise Edition for Lustre* software makes parallel storage simpler to manage and more productive for data intensive applications. Big Data has been synonymous with high performance computing for decades, and has become the primary driver … [Read more...]
Performance Optimization Of Black-Scholes Pricing On Intel Xeon Phi
Who would have thought that a mere two hundred lines of code provide so many capabilities! The chapter authors (Iosif Meyerov, Alexander Sysoyev, Nikita Astafiev, and Ilya Burylov) apply their optimization expertise for Intel Xeon and Intel Xeon Phi to calculate the fair prices of a set of European options. They chose this the Black-Scholes calculation for the following … [Read more...]
Efficient Nested Parallelism On Large Scale Systems
Choosing right threading library is critical for application performance, as different threading libraries provide significantly different performance behavior, especially when dealing with the complex computer systems as Intel Xeon Phi coprocessor and NUMA Intel Xeon processor machines. Unfortunately, choosing the right threading library is not enough, addition application … [Read more...]
Nov. 10 Live and Webcast Hands-On Intel Xeon Phi Training
On Monday, November 10, 2014 from 9 AM to 4:30 PM EST Xsede and TACC will present a live AND webcast training event regarding using the Intel Xeon Phis on both the Beacon machine at NICS and the Stampede machine at TACC. There is no charge for registration, but there are only 16 seats for the live training and 25 75 participants allowed into the zoom webcast. The training will … [Read more...]
NWChem Quantum Chemistry Simulations at Scale
This chapter describes the performance of NWChem's CCSD(T) method running on a large-scale hybrid cluster of 460 dual-socket Xeon E5-2600 series nodes each of which is equipped with two Intel Xeon Phi 5110P coprocessor cards (a total of 62.5k hybrid cores). The chapter authors describe how, without any low-level programming, offload transfers and compute kernels have been … [Read more...]
Author Call for Volume 2 Of High Performance Parallelism Pearls
James Reinders and Jim Jeffers have opened up proposal submissions for another Intel Xeon and Intel Xeon Phi Pearls book tentatively titled, High Performance Parallelism Pearls – Multicore and Many-core Programming Approaches! It is expected that the submission deadline will be March 7, 2015. Proposal submission can be made here. Don't miss this opportunity to contribute … [Read more...]