You are viewing archived content (2011-2018). For current research, visit research.colfax-intl.com

Get Ready for Intel’s Knights Landing (KNL) – 3 papers

2nd generation Intel Xeon Phi processors code-named Knights Landing (KNL) are expected to provide up to 3X higher performance than the 1st generation. With on-board high-bandwidth memory and optional integrated high-speed fabric—plus the availability of socket form-factor — these powerful components will transform the fundamental building block of technical computing.

Download three essential publications on new features in Knights Landing Processors:

Automatic Vectorization with Intel AVX-512 Instructions in KNL

AVX512-platformsIn this document, we focus on the new vector instruction set introduced in Knights Landing processors, Intel® Advanced Vector Extensions 512 (Intel® AVX-512). The discussion includes:

  • Introduction to vector instructions in general,
  • The structure and specifics of AVX-512, and
  • Practical usage tips: checking if a processor has support for various features, compilation process and compiler arguments, pros and cons of explicit and automatic vectorization, using the Intel® C++ Compiler and the GNU Compiler Collection.

Clustering Modes in Knights Landing Processors

nested-omp-quadrantsWe start a discussion of what types of applications benefit from the clustering modes and why clustering modes help these applications. After that we cover the specifics of the available cluster modes: all-to-all, quadrant, hemisphere, SNC-4 and SNC-2. Finally, we discuss how to make the application NUMA-aware for use in SNC modes. In this context, we give recipes for nested OpenMP and hybrid MPI+OpenMP approaches combined with first-touch allocation policy, numactl tool and memkind library.

MCDRAM as High-Bandwidth Memory (HBM) in KNL Processors

knl-hybrid-mcdramIn this document we discuss the on-package high-bandwidth memory (HBM) based on the multi-channel dynamic random access memory (MCDRAM) technology:

  • Three configuration modes of HBM: Flat mode, Cache mode and Hybrid mode
  • Utilization of the HBM as addressable memory using two methods: by setting affinity policy with the numactl tool and through the usage of special allocators in the memkind library
  • Guidelines for determining the optimal usage model for applications running on bootable Knights Landing.

Webinar

Developer's Guide to Knights Landing - 2-Hour Webinar

If you are interested in the above publication, you may also find this useful. Register for one of the upcoming 2-hour introductory webinars or download slide deck (FREE).

Learn Even More

HOW Series - Code Modernization and Optimization Training with Remote Access

Want to know what it really takes to optimize your application for KNL? Register for a free 10-day HOW Series workshop. You will get remote access to a 1st generation Intel Xeon Phi coprocessor and all the exercises and support channels you need for world-class developer education.