BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Talk by Microsoft Cancelled on Short Notice
DTSTART;VALUE=DATE-TIME:20201201T131500Z
DTEND;VALUE=DATE-TIME:20201201T134500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1385@events.chpc.ac.za
DESCRIPTION:https://events.chpc.ac.za/event/84/contributions/1385/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1385/
END:VEVENT
BEGIN:VEVENT
SUMMARY:The Role of Storage for efficient Machine Learning
DTSTART;VALUE=DATE-TIME:20201130T134500Z
DTEND;VALUE=DATE-TIME:20201130T141500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1382@events.chpc.ac.za
DESCRIPTION:Speakers: Sven Breuner (Excelero)\nNowadays\, many organizatio
 ns are trying to find ways to converge classic HPC and AI. There are gener
 ally good reasons to do this because of significant similarities between H
 PC and AI workloads and workload scaling. However\, for AI workloads to pe
 rform well on clusters\, it is also important to be aware of the differenc
 es for AI workloads (especially DeepLearning) compared to classic HPC work
 loads. One of the most important differences are the requirements for stor
 age systems for AI compared to classic HPC. This talk will provide an over
 view of the special storage system challenges that come with AI workloads\
 , how to characterize and simulate them and especially how to overcome the
 m to ensure that the GPUs can run efficiently instead of stalling on stora
 ge access.\n\nhttps://events.chpc.ac.za/event/84/contributions/1382/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1382/
END:VEVENT
BEGIN:VEVENT
SUMMARY:AMD’s Heterogeneous Path to Exascale
DTSTART;VALUE=DATE-TIME:20201201T134500Z
DTEND;VALUE=DATE-TIME:20201201T141500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1381@events.chpc.ac.za
DESCRIPTION:Speakers: Matt Foley (Advanced Micro Devices)\nTomorrow’s su
 percomputers will need to leverage the power of heterogeneous architecture
 s in more graceful ways than what can be done today. Doing so will improve
  the trajectory of future performance gains.\n\nhttps://events.chpc.ac.za/
 event/84/contributions/1381/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1381/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Diversified Computing Power for Pervasive Intelligence
DTSTART;VALUE=DATE-TIME:20201201T120000Z
DTEND;VALUE=DATE-TIME:20201201T123000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1380@events.chpc.ac.za
DESCRIPTION:Speakers: Bin Zhou ()\nWith the maturity of AI algorithms\, in
 creased computing power and explosive growth of data\, manual labor has be
 come a GPT technology that will Will Drive Social Development Profoundly. 
 AI will also serve as an important technology\, cooperating with HPC\, sho
 wing its prominence in scientific research in various fields.\n\nhttps://e
 vents.chpc.ac.za/event/84/contributions/1380/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1380/
END:VEVENT
BEGIN:VEVENT
SUMMARY:NVIDIA Mellanox InfiniBand In-Network Computing
DTSTART;VALUE=DATE-TIME:20201201T101500Z
DTEND;VALUE=DATE-TIME:20201201T104500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1364@events.chpc.ac.za
DESCRIPTION:Speakers: Gilad Shainer (Nvidia)\nAccelerating scientific Comp
 uting and deep learning applications with NVIDIA Mellanox In-Network Compu
 ting engines.\n\nhttps://events.chpc.ac.za/event/84/contributions/1364/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1364/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Accelerating HPC+AI science workflows using NVIDIA GPU
DTSTART;VALUE=DATE-TIME:20201130T131500Z
DTEND;VALUE=DATE-TIME:20201130T134500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1318@events.chpc.ac.za
DESCRIPTION:Speakers: Gunter  Röth (NVIDIA SA)\nNVIDIA has early identifi
 ed the promising HPC – AI convergence trend and has been working on enab
 ling it. The growing adoption of NVIDIA Ampere GPU by the Top 500 Supercom
 puters highlights the need of computing acceleration for this HPC & AI con
 vergence. Many projects today demonstrate the benefit of AI for HPC\, in t
 erms of accuracy and time to solution\, in many domains such as Computatio
 nal Mechanics (Computational Fluid Mechanics\, Solid Mechanics…)\, Earth
  Sciences (Climate\, Weather and Ocean Modelling)\, Life Sciences (Genomic
 s\, Proteomics…)\, Computational Chemistry (Quantum Chemistry\, Molecula
 r Dynamics…)\, Computational Physics. NVIDIA today for instance\, uses P
 hysics Informed Neural Networks for the heat sink design in our DGX system
 .\n\nhttps://events.chpc.ac.za/event/84/contributions/1318/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1318/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Artificial Techniques in Pharmaceuticals and Drug Discovery
DTSTART;VALUE=DATE-TIME:20201201T123000Z
DTEND;VALUE=DATE-TIME:20201201T130000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1362@events.chpc.ac.za
DESCRIPTION:Speakers: Adnan Khaleel (Dell)\nIn spite of all the recent adv
 ances in biochemistry and several associated areas\, pharmaceutical drug d
 iscovery is still notoriously difficult to do\, with lives literally at st
 ake. A typical drug interacts with 300 other enzymes and processes within 
 the human body\, and a drug has to pass with minimal disruptions to all of
  these processes in order to deemed safe. Nearly 90% of all targeted drugs
  fail in Phase 1 of the clinical trials\, but today\, with AI\, we’re fi
 nding ways to improve our chances of success. In some cases\, AI can creat
 e designer molecules that are already screened for previous toxicity and h
 old the promise to drastically reduce the time to creation of new drugs. I
 n this talk\, I’ll be giving a very brief overview of the various AI tec
 hniques that are currently being used today.\n\nhttps://events.chpc.ac.za/
 event/84/contributions/1362/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1362/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Budgets and Allocation in HPC
DTSTART;VALUE=DATE-TIME:20201201T104500Z
DTEND;VALUE=DATE-TIME:20201201T111500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1359@events.chpc.ac.za
DESCRIPTION:Speakers: Ian Littlewood (Altair Engineering Ltd)\nBudgets and
  management of allocations in an HPC are valuable tools that manage user b
 ehavior and the real costs associated with running an HPC either on premis
 e or in the cloud.  This talk will explain how Altair PBS Professional 202
 0.1 deliver these tools and will briefly demonstrate how simple and robust
  they are in use.\n\nhttps://events.chpc.ac.za/event/84/contributions/1359
 /
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1359/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Stories from the Front Lines: The Good\, Bad\, and Ugly of Buildin
 g an Opensource Distributed Platform for Scientific Compute: Software\, Ha
 rdware\, and Community
DTSTART;VALUE=DATE-TIME:20201130T123000Z
DTEND;VALUE=DATE-TIME:20201130T130000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1331@events.chpc.ac.za
DESCRIPTION:Speakers: Rudolph Pienaar (Boston Children's Hospital)\nIn thi
 s talk I'll provide some stories from leading the ChRIS computing\neffort 
 (https://chrisproject.org) over several years as it grew from\nsimple scri
 pts that ran neuro-MRI analysis programs in a small lab to a\ndistributed 
 container based platform that is both cloud and HPC ready\nand currently a
 ctively supported by Red Hat\, Inc\, and their OpenShift\nplatform for clo
 ud computing.\n\nWhile providing conceptual overviews of the system archit
 ecture\, I will\nfocus specifically on how choices in programming language
 \, frameworks\,\narchitecture\, documentation\, github and more all played
  out -- the\ngood\, the bad\, and the ugly.\n\nI'll touch on how these cho
 ices impact portability across computing\narchitectures -- including Power
 PC and of course upcoming ARM\narchitectures in Apple consumer products.\n
 \nFinally\, I'll talk about the complexity in fostering community about\ng
 rowing open source scientific projects with some insights into some of\nth
 e pitfalls and highlights.\n\nhttps://events.chpc.ac.za/event/84/contribut
 ions/1331/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1331/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Configuring the Kaldi ASR toolkit for the Lengau Cluster
DTSTART;VALUE=DATE-TIME:20201130T120000Z
DTEND;VALUE=DATE-TIME:20201130T123000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1217@events.chpc.ac.za
DESCRIPTION:Speakers: Ewald Van der Westhuizen (Stellenbosch University)\n
 Kaldi] is an open source software project that was initiated by the Center
  for Language and Speech Processing\,Johns Hopkins University.  It is one 
 of the leading toolkits used for research in automatic speech recognition 
 (ASR).The toolkit employs current machine learning techniques such  a  dee
 p  neural  networks  and  is  capable  of  state-of-the-art  performance. 
   Kaldi  can  be  configured  for  a  single personal computer or a high p
 erformance computing (HPC) cluster using the Sun Grid Engine.  Although co
 nfiguring Kaldi for parallelisation on a cluster is well documented\, it i
 s assumed that the user has complete control.  A researcher may have the o
 ption to set up an in-house cluster with the advantage of complete control
 \, but maintaining the cluster can become a task that distracts from  the 
  research  work.   The  size  of  an  in-house  cluster is also limited by
  the resources and funds available to the researcher.  When the disadvanta
 ges outweigh the advantages\, migrating to a larger\, community-based clus
 ter with on-site support becomes attractive.  Because such clusters host u
 sers from various institutions and disciplines\, usage policies and restri
 ctions apply which were not applicable to the in-house cluster. These rest
 rictions affect how Kaldi can be used.\n\n[Full abstract added as a PDF at
 tachment.]\n\nhttps://events.chpc.ac.za/event/84/contributions/1217/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1217/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Two decades of African research on academia-industry high performa
 nce computing access and utilization – A systematic literature review
DTSTART;VALUE=DATE-TIME:20201201T093000Z
DTEND;VALUE=DATE-TIME:20201201T100000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1317@events.chpc.ac.za
DESCRIPTION:Speakers: Liezel Cilliers (University of Fort Hare)\nThere are
  arguments amongst academics and practitioners alike for the importance of
  countries on the African to plug into the information society. On the gro
 und\, this has resulted in an emphasis on the importance of partnerships n
 ot just within institutions of higher learning but also amongst those in i
 ndustry. Internationally\, we note the growth in interest of research arou
 nd such partnerships and a documented trail of evidence within the academi
 c and practitioner press. The focal point of such research appears to be c
 entered on documented evidence-based interactions of such partnerships. Su
 ch international research is lauded in aiding our understanding and proffe
 ring best practices around human and computer system interaction issues. D
 espite this progress\, we note with concern scant focus on African case ex
 amples around academia-industry collaborations and issues related to high 
 performance computing access and utilization. In this study\, through a sy
 stematic literature review\, we attempt to present the state of being arou
 nd such research on the African continent using published peer-reviewed st
 udies published between 2000 and 2020. The research findings are grouped a
 round: a) the research methods utilized\; b) underpinning theories and c) 
 key factors employed to study academia-industry information collaboration\
 , utilization\, and access issues related to high-performance computing sy
 stems. Based on the review\, we then suggest future research directions in
 cluding themes that may enhance academia-industry partnerships around issu
 es related to high-performance computing systems access and utilization on
  the African continent. This research provides useful insights to academic
 s and practitioners on the African continent against the presented ideals.
 \n\nhttps://events.chpc.ac.za/event/84/contributions/1317/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1317/
END:VEVENT
BEGIN:VEVENT
SUMMARY:From touching the code to online coding clubs
DTSTART;VALUE=DATE-TIME:20201201T090000Z
DTEND;VALUE=DATE-TIME:20201201T093000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1207@events.chpc.ac.za
DESCRIPTION:Speakers: Jean Greyling (Nelson Mandela University)\nThe TANGI
 BL coding project hosted at Nelson Mandela University Computing Sciences\,
  aims at introducing learners to coding concepts without the use of comput
 ers. It uses mobile apps\, customized tokens and image recognition to give
  learners the experience of actual code executing. Since 2017\, over 20000
  learners across the country have been reached through interactive worksho
 ps. With the COVID-19 lockdown regulations these workshops became impossib
 le. Consequently the team introduced the concept of virtual tournaments wh
 ere learners could play from home. More than 1000 learners participated in
  3 very successful tournaments\, making a wide ranging impact.\n\nhttps://
 events.chpc.ac.za/event/84/contributions/1207/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1207/
END:VEVENT
BEGIN:VEVENT
SUMMARY:LANL HPC Storage Thrusts
DTSTART;VALUE=DATE-TIME:20201202T131500Z
DTEND;VALUE=DATE-TIME:20201202T134500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1208@events.chpc.ac.za
DESCRIPTION:Speakers: Gary Grider (Los Alamos National Laboratory)\nThis t
 alk will cover current LANL HPC storage environments and methods\,  new di
 rections  and technologies  being explored\, and how HPC\, AI\, and Analyt
 ics storage workloads might  be serviced  by a  single  flexible storage s
 ystem a few years  from now.  Additionally information on  a few of the ma
 ny  HPC storage  related R&D projects LANL and its  partners is working on
 .  Also\, information on partnering with LANL  to  solve important  HPC te
 chnology related problems in storage and other  areas will be presented.\n
 \nhttps://events.chpc.ac.za/event/84/contributions/1208/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1208/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Managing Bufferbloat in Storage Systems
DTSTART;VALUE=DATE-TIME:20201202T134500Z
DTEND;VALUE=DATE-TIME:20201202T141500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1311@events.chpc.ac.za
DESCRIPTION:Speakers: Carlos Maltzahn (University of California\, Santa Cr
 uz)\nScalable storage servers consist of multiple parts that communicate a
 synchronously via queues. There is usually a frontend that queues access r
 equests from storage clients and uses one or more threads to forward queue
 d requests to a backend. The backend queues these forwarded requests and b
 atches them to efficiently use storage devices it manages. Storage servers
  can have multiple kinds of backends with different design assumptions abo
 ut their underlying storage device technologies. Requests are scheduled in
  the frontend to ensure different levels of service for different classes 
 of requests. For example\, requests that are generated by data scrubbers w
 orking in the background generally have a lower priority than requests fro
 m an application. A common solution to the above problem is to move reques
 t scheduling from the frontend to the backend. For various reasons that is
  not always practical. The scope of the proposed project is to have the sc
 heduler reside in the frontend and to explore designs for backends to dyna
 mically control the admission of requests depending on continually changin
 g workloads and storage device technologies. \n\nScheduling in the fronten
 d and batching in the backend work best if there are enough requests in th
 eir respective queues. This raises the question: what is enough for the fr
 ontend and for the backend? If there are too few requests in the frontend 
 but more than enough requests in the backend\, the system might work well 
 in terms of overall throughput but might poorly enforce scheduling objecti
 ves. If there are too few requests in the backend\, then overall throughpu
 t and latency suffer no matter the scheduling objectives. If\, however\, t
 he backend has the ability to admit just enough requests from the frontend
  but not more\, throughput and latency of the backend is likely satisfacto
 ry. If there is enough work overall\, the frontend has enough requests to 
 meet scheduling objectives. How many requests are just enough for the back
 end?\n\nIn this talk I will give an overview of an ongoing research projec
 t at the UC Santa Cruz Center for Research in Open Source Software (cross.
 ucsc.edu) to reframe this question as a bufferbloat mitigation problem usi
 ng algorithms similar to the ones used for bufferbloat in networking.\n\nh
 ttps://events.chpc.ac.za/event/84/contributions/1311/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1311/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Stitch-IO for Additive Manufacturing Simulation
DTSTART;VALUE=DATE-TIME:20201202T123000Z
DTEND;VALUE=DATE-TIME:20201202T130000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1312@events.chpc.ac.za
DESCRIPTION:Speakers: Jay Lofstead (Sandia National Laboratories)\nSimulat
 ing Additive Manufacturing (AM) has been difficult because simulation doma
 ins can be extremely large and the computational load is minimal. With the
  way that AM works\, only a small part of the simulation domain is require
 d at any time. Stitch-IO offers a way to decompose AM simulations into a s
 eries of short runs over short time and space scales and then enables stit
 ching together the output into a lossless\, coherent form. The data storag
 e requirement drops dramatically while requiring as little as a laptop and
  runs the whole simulation in the same wall clock time as if it were on a 
 large supercomputer with the whole simulation domain in RAM. With native P
 ython and C APIs\, Stitch-IO offers flexible analysis interfaces as well.\
 n\nhttps://events.chpc.ac.za/event/84/contributions/1312/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1312/
END:VEVENT
BEGIN:VEVENT
SUMMARY:A Workflow for Identifying Jobs with Similar I/O Behavior Utilizin
 g Time Series Analysis
DTSTART;VALUE=DATE-TIME:20201202T120000Z
DTEND;VALUE=DATE-TIME:20201202T123000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1314@events.chpc.ac.za
DESCRIPTION:Speakers: Julian Kunkel (University of Reading)\nOne goal of s
 upport staff at a data center is to identify inefficient jobs and to impro
 ve their efficiency.\nTherefore\, a data center deploys monitoring systems
  that capture the behavior of the executed jobs.\nWhile it is easy to util
 ize statistics to rank jobs based on the utilization of computing\, storag
 e\, and network\, it is tricky to find patterns in 100.000 jobs\, i.e.\, i
 s there a class of jobs that aren't performing well.\n\nIn this talk\, a m
 ethodology to rank the similarity of all jobs to a reference job based on 
 their temporal IO behavior is described.\nA study is conducted to explore 
 the effectivity of the approach which starts from three reference jobs and
  investigates related jobs.\nThe data stems from DKRZ's supercomputer Mist
 ral and includes more than 500.000 jobs that have been executed for more t
 han 6 months of operation.\n\nhttps://events.chpc.ac.za/event/84/contribut
 ions/1314/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1314/
END:VEVENT
BEGIN:VEVENT
SUMMARY:The GekkoFS Burst Buffer File System
DTSTART;VALUE=DATE-TIME:20201202T104500Z
DTEND;VALUE=DATE-TIME:20201202T111500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1310@events.chpc.ac.za
DESCRIPTION:Speakers: André Brinkmann (Johannes Gutenberg University Main
 z)\nMany scientific fields increasingly use high-performance computing (HP
 C) to process and analyze massive amounts of experimental data while stora
 ge systems in today’s HPC environments have to cope with new access patt
 erns. These patterns include many metadata operations\, small I/O requests
 \, or randomized file I/O\, while general-purpose parallel file systems ha
 ve been optimized for sequential shared access to large files. Burst buffe
 r file systems create a separate file system that applications can use to 
 store temporary data. They aggregate node-local storage available within t
 he compute nodes or use dedicated SSD clusters and offer a peak bandwidth 
 higher than that of the backend parallel file system without interfering w
 ith it. We present GekkoFS\, a temporary\, highly-scalable file system whi
 ch has been specifically optimized for the aforementioned use cases. Gekko
 FS provides relaxed POSIX semantics which only offers features which are a
 ctually required by most (not all) applications. GekkoFS is\, therefore\, 
 able to provide scalable I/O performance and reaches millions of metadata 
 operations already for a small number of nodes\, significantly outperformi
 ng the capabilities of common parallel file systems.\n\nhttps://events.chp
 c.ac.za/event/84/contributions/1310/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1310/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Converging Storage Technologies Using a Flexible HPC Storage Frame
 work
DTSTART;VALUE=DATE-TIME:20201202T101500Z
DTEND;VALUE=DATE-TIME:20201202T104500Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1315@events.chpc.ac.za
DESCRIPTION:Speakers: Michael Kuhn (Otto von Guericke University Magdeburg
 )\nTraditionally\, file systems are mostly monolithic\, making it hard to 
 experiment with new approaches and technologies. Exchanging core functiona
 lity within a file system is a burdensome task\, leading to a lack of inno
 vation in this area. However\, data volumes are growing rapidly because th
 e ability to capture and produce data is increasing at an exponential rate
 . Rising core counts and data volumes present challenges for contemporary 
 storage systems\, especially regarding metadata performance and data manag
 ement. This makes it even more important to investigate new ways of storin
 g and managing data efficiently.\n\nHPC storage systems are typically desi
 gned around POSIX-compliant parallel distributed file systems that are acc
 essed using sophisticated I/O libraries. The file system and library layer
 s are strictly separated for portability reasons. While this allows exchan
 ging individual layers\, their complexities pose a high barrier of entry. 
 This is especially problematic for shorter research projects and presents 
 a significant hurdle for young researchers and students.\n\nWithin the JUL
 EA and CoSEMoS projects\, we are aiming to change this. JULEA is a flexibl
 e storage framework that can be used to prototype new ideas related to sto
 rage and file systems. It allows offering arbitrary I/O interfaces to appl
 ications and includes interfaces for object\, key-value and database stora
 ge. The framework has been designed to be easy to set up and run without a
 dministrative privileges\, so it can be used on a wide range of software a
 nd hardware environments. It also serves as the foundation of the CoSEMoS 
 project\, which explores the benefits of a coupled storage system for self
 -describing data formats\, such as HDF5 and ADIOS2. This allows the storag
 e system to manage file metadata found within these data formats and makes
  it possible to use structural information for selecting appropriate stora
 ge technologies. For instance\, metadata can be stored in database systems
  that can be queried efficiently. Moreover\, making use of established dat
 a formats allows running existing applications without modifications\, whi
 ch helps preserve past investments in software development.\n\nCoSEMoS ena
 bles novel data management approaches via a data analysis interface that g
 ives applications direct access to JULEA's backends\, eliminating the need
  to sift through large volumes of data to find relevant data points. Break
 ing up the strict separation has additional long-term benefits\, such as b
 eing able to take data migration decisions based on structural information
  found within the file formats.\n\nThis talk will briefly introduce the JU
 LEA and CoSEMoS projects\, and show the opportunities enabled by their nov
 el storage system design.\n\nhttps://events.chpc.ac.za/event/84/contributi
 ons/1315/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1315/
END:VEVENT
BEGIN:VEVENT
SUMMARY:SANReN Data Transfer Pilot Service and Performance Enhancement Res
 ponse Team update
DTSTART;VALUE=DATE-TIME:20201202T093000Z
DTEND;VALUE=DATE-TIME:20201202T100000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1316@events.chpc.ac.za
DESCRIPTION:Speakers: Kasandra Pillay (SANReN)\nMoving masses of data is a
  challenge. In most cases networks optimized for business\noperations are 
 neither designed for nor capable of supporting the data movement requireme
 nts of data intensive research. When scientists attempt to run data intens
 ive applications over these so called “general purpose”/enterprise net
 works\, the result is often poor performance – in many cases poor enough
  that the science mission is significantly impacted. At its worst this mea
 ns either not getting the data\, getting it too late or resorting to “de
 sperate” measures such as shipping disks around. The South African Natio
 nal Research Network (SANReN) has been piloting a data transfer service wi
 th the goal of changing this for our researchers/scientists and optimising
  the transfer of datasets across the network. The service makes use of dat
 a transfer nodes configured in a science DMZ architecture using specially 
 designed data transfer tools to assist to efficiently and securely move da
 ta between local institutions\, to and from the CHPC and internationally.\
 nThis presentation will present an overview of the SANReN Performance Enha
 ncement Response Team’s goals\, specifically with regards to the SANReN 
 Data Transfer Pilot service. This includes the science DMZ\, data transfer
  nodes\, tools and services implemented. An update will be given on this s
 ervice on planned way forward and results achieved so far.\nKeywords: Perf
 ormance Enhancement Response Team\, Science DMZ\, data transfer nodes\, op
 timising data transfer\n\nhttps://events.chpc.ac.za/event/84/contributions
 /1316/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1316/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Calabash - why store your data in a cloud when you can use a gourd
  ?
DTSTART;VALUE=DATE-TIME:20201202T090000Z
DTEND;VALUE=DATE-TIME:20201202T093000Z
DTSTAMP;VALUE=DATE-TIME:20260721T125134Z
UID:indico-contribution-453-1313@events.chpc.ac.za
DESCRIPTION:Speakers: Simon Ratcliffe (SARAO)\nTsolo Storage Systems is a 
 leading provider of petascale Ceph storage solutions. Through our partners
 hip with the South African Radio Astronomy Observatory\, we have delivered
  some of the largest storage installations in the country.\n\nOur next gen
 eration product seeks to democratise the power and cost-benefit of Ceph as
  an open-source storage solution in order to drastically simplify your sto
 rage needs.\n\nBuilding on top of a custom hardware platform we are able t
 o offer fully managed\, user provisioned\, S3 storage at a fraction of the
  price of the incumbent providers.\n\nThis talk will highlight the homegro
 wn innovation and technical solutions to local storage problems\, as well 
 as the successful public-private partnership with SARAO.\n\nhttps://events
 .chpc.ac.za/event/84/contributions/1313/
LOCATION:
URL:https://events.chpc.ac.za/event/84/contributions/1313/
END:VEVENT
END:VCALENDAR