- Log In
Resources
We have collected presentations from IXPUG workshops, annual meetings, and BOF sessions, and made them accessible here to view or download. You may search by event, keyword, science domain or author’s name. The database will be updated as new talks are made available.
- CategoriesClear All
-
-
Search ResultShowing 1 - 10 of 270 Results
The Intel Xeon Phi Users Group Intro
Keyword(s): ixpug
Author : IXPUG User Group Read more | |DOE and NIH Partners Cancer and Brain
Keyword(s): ixpug
Author : Argonne, Rick Stevens Read more | |Many-core architectures such as Intel Knights Landing (KNL) are seeing widespread adoption in current and next-generation supercomputing systems due to their power/performance ratio. However, this increased density of the compute nodes and the performance characteristics of the new architecture bring in a new set of challenges that must be tackled to extract the best performance. In this work, we present some of the advanced designs to tackle such challenges in the MVAPICH2 MPI library on the KNL architecture. In particular, we focus on the following aspects --- a) how MVAPICH2 achieves fast and scalable startup on the KNL+Omni-Path architecture, b) contention-aware, kernel-assisted designs for large-message intra-node collectives, and c) designs for scalable reduction operations on different message sizes. We also compare the proposed designs against other state-of-the-art MPI libraries such as Intel MPI and OpenMPI. Experimental evaluations show that the proposed designs offer significant improvements in terms of time to launch large-scale jobs, performance of intra-node and inter-node collectives, and performance of applications.
Keyword(s): ixpug
Author : Pavan Balaji, Argonne National Laboratory Read more | |Tiger teams intro
Keyword(s): ixpug user
Author : Ixpug User Read more | |Annual Meeting of the Intel Xeon Phi Users Group
Keyword(s): ixpug user
Author : IXPUG User Group Read more | |MVAPICH2 and MVAPICH2-MIC: Latest Status
Keyword(s): ixpug
Author : Dhabaleswar (DK) Panda, Khaled Hamidouche Read more | |Libsim runs on Stampede 2
Keyword(s): ixpug user
Author : Intelligent Light, Applied Research Group Read more | |"Weather Research and Forecasting Model (WRF) is one of the most used models in Earth Sciences related fields. WRF code consumes significant core-hours on our Shaheen II XC40 supercomputer. The purpose of this study is to evaluate its performance on Intel Xeon Phi Knights Landing processor (KNL). Our test platform is a workstation equipped with an Intel KNL 7210, with 64 cores at 1.3Ghz, obtained through Intel’s developer access program. We compare WRF code performance on this workstation to one node of Shaheen II XC40 supercomputer, a dual socket Haswell with 16 cores per socket at 2.3Ghz. As a test case, we use the well-known domain Conus 12km on the latest WRF v3.8.1 and we try to investigate most of the approaches that we can use to identify the best execution of WRF on Intel KNL. We test and evaluate the performance of the code while using all the clustering modes with various combinations of MCDRAM usage. Moreover, we investigate the threads placement on the KNL through environment variables, the various affinity modes provided by Intel environment and we take advantage of the numtiles settings that WRF provide to achieve better performance. According to our experiments, the best performance achieved on the Intel KNL exhibits up to 20% performance improvement in comparison to a Shaheen II XC40 node, excluding I/O time."
Keyword(s): ixpug user
Author : George S. Markomanolis, Saber Feki Read more | |Profiling Tools for KNL
Keyword(s): ixpug user
Author : Carols Rosales Read more | |Moderniasation of the AVBP code for KNL. Performance and Optimisation tips using Intel Vector advisor
Keyword(s): ixpug user
Author : Zakhar Matveev, Georg Zitzlsberger, G Staffelbach, J Legaux, K. D. Oertel, L Duhem Read more | |