This session is a continuation of the Advanced Toolchain Usage series started at LCU14. These sessions will cover a variety of topics, such as: symbol-versioning how-to, what the compiler can’t know, search paths (LD_LIBRARY_PATH, RPATH, RUNPATH), versioning structures, ELF sections on ARM/Aarch64, addressing models and performance considerations (PIC, short branches, long branches, relative addressing, trampolines, relaxation, etc), data alignment performance considerations on ARM/Aarch64, Timers,Timestamps and the VDSO, branch prediction extensions vs hardware auto branch prediction. Out-of-order execution vs in-order execution performance considerations, and others.
Suresh’s bio: Dr. Suresh Gopalakrishnan is the corporate vice president and general manager of AMD’s server business. He is responsible for driving the end-to-end business execution of AMD server solutions worldwide. Under his leadership, AMD is pursuing a server strategy that leverages AMD’s broad IP portfolio to deliver disruptive products for the virtualized datacenter, software defined storage, high performance data analytics and IoT infrastructure. Prior to joining the company in June 2012, Dr. Gopalakrishnan served as vice president of engineering at Extreme Networks, a leader in high-performance Ethernet switching for cloud, data center, and mobile networks. During his tenure at Extreme Networks, Dr. Gopalakrishnan was also vice president of marketing and product management, as well as general manager of multiple business units. He has led large product teams that have defined and delivered Ethernet switching systems to enterprise, data center and carrier markets. He also has a strong semiconductor background in designing and leading teams that delivered CPUs, workstation chipsets, digital signal processors, and networking ASICs.
Prior to Extreme Networks, Dr. Gopalakrishnan held a variety of leadership positions at Riverstone Networks/Cabletron Systems, ZSP Corporation, Sun Microsystems and HP.
Dr. Gopalakrishnan holds a Ph.D. in Electrical Engineering from the University of Idaho and has completed the Advanced Executive Program at Northwestern University’s Kellogg School of Management. He is based in Sunnyvale, California.
This presentation will focus on beginner’s benchmarking best practices covering the three Rs: repeatability, reproducibility, and reporting. An experiment is repeatable if one team can repeatedly run the same experiment over short periods of time and get the same results. An experiment is reproducible if external teams can run the same experiment over large periods of time and get comparable results. Clear, concise reporting allows others to utilise benchmark results.
14:30 – CentOS: Taking the Excitement out of your Development Process
Speaker: Jim Perrin, CentOS Project Developer
Abstract: Developers and end users have enough to worry about without the operating system getting in the way. CentOS has a proven history for the x86/x86_64 platforms, and now we’re working to bring that same level of dedication to AArch64. We’ll demo installation, development tooling, containers, and discuss how everyone can be a part of the future improvements.
There has been recent work upstream to enable the LKP tests to build and execute on ARM platforms. The QA team has been involved with the integration of these tests into Linaroäó»s Automated Validation Architecture, and this presentation will provide a brief overview of the LKP results that have been obtained. It will also demonstrate useful way to compare the data.
11:15 – CERN: ARM64/AArch64 for Scientific Computing at the CERN CMS Particle Detector
Speaker: David Abdurachmanov Software Engineer/Consultant at CERN
Abstract: The purpose of this talk is to provide an overview of efforts at CERN (the European Laboratory for Particle Physics, in Geneva, Switzerland) to introduce ARMv8 64-bit (aka AArch64) for large scale scientific computing. The objective is to crunch data from the 14 000 ton CMS particle physics detector located 100 meters underground on a 27 kilometer long circular particle accelerator (the Large Hadron Collider, LHC) running under the Switzerland-France border. The CMS and ATLAS experiments at CERN announced the discovery of Higgs boson in 2012, leading to the awarding of the 2013 Nobel Prize in Physics.
The Kernel Consolidation 2.0 lead project aims to identify and work on reducing areas where vendors need to ship out of tree modifications and additions to kernel frameworks in order to deliver key functionality. In this session we will discuss how we are going to organize and coordinate this work in conjunction with other efforts in the community.