Stato progetto COSA 2016 http://www.cosa-project.it.

Slides:



Advertisements
Similar presentations
PCI Express® technology in 28-nm FPGAs
Advertisements

Performance Analysis of Virtualization for High Performance Computing A Practical Evaluation of Hypervisor Overheads Matthew Cawood University of Cape.
Seven Minute Madness: Special-Purpose Parallel Architectures Dr. Jason D. Bakos.
Some Thoughts on Technology and Strategies for Petaflops.
Computing on Low Power SoC Architecture
5 th LHCb Computing Workshop, May 19 th 2015 Niko Neufeld, CERN/PH-Department
RapidIO based Low Latency Heterogeneous Supercomputing Devashish Paul, Director Strategic Marketing, Systems Solutions
APE group Remote Direct Memory Access between NVIDIA GPUs with the APEnet 3D Torus Interconnect SC11 Seattle, Nov 14-17,
Networking Virtualization Using FPGAs Russell Tessier, Deepak Unnikrishnan, Dong Yin, and Lixin Gao Reconfigurable Computing Group Department of Electrical.
Motivation “Every three minutes a woman is diagnosed with Breast cancer” (American Cancer Society, “Detailed Guide: Breast Cancer,” 2006) Explore the use.
GPU Programming with CUDA – Accelerated Architectures Mike Griffiths
LARGE SCALE DEPLOYMENT OF DAP AND DTS Rob Kooper Jay Alemeda Volodymyr Kindratenko.
Niko Neufeld, CERN/PH-Department
Looking Ahead: A New PSU Research Cloud Architecture Chuck Gilbert - Systems Architect and Systems Team Lead Research CI Coordinating Committee Meeting.
Tracking with CACTuS on Jetson Running a Bayesian multi object tracker on a low power, embedded system School of Information Technology & Mathematical.
March 9, 2015 San Jose Compute Engineering Workshop.
Latest ideas in DAQ development for LHC B. Gorini - CERN 1.
Building an Exotic HPC Ecosystem at The University of Tulsa John Hale Peter Hawrylak Andrew Kongs Tandy School of Computer Science.
Why it might be interesting to look at ARM Ben Couturier, Vijay Kartik Niko Neufeld, PH-LBC SFT Technical Group Meeting 08/10/2012.
Revision - 01 Intel Confidential Page 1 Intel HPC Update Norfolk, VA April 2008.
© 2007 Altera Corporation FPGA Coprocessing in Multi-Core Architectures for DSP J Ryan Kenny Bryce Mackin Altera Corporation 101 Innovation Drive San Jose,
Understanding Parallel Computers Parallel Processing EE 613.
Cray XD1 Reconfigurable Computing for Application Acceleration.
HEPMARK2 Consiglio di Sezione 9 Luglio 2012 Michele Michelotto - Padova.
GFlow: Towards GPU-based High- Performance Table Matching in OpenFlow Switches Author : Kun Qiu, Zhe Chen, Yang Chen, Jin Zhao, Xin Wang Publisher : Information.
Parallel Computers Today Oak Ridge / Cray Jaguar > 1.75 PFLOPS Two Nvidia 8800 GPUs > 1 TFLOPS Intel 80- core chip > 1 TFLOPS  TFLOPS = floating.
ROM. ROM functionalities. ROM boards has to provide data format conversion. – Event fragments, from the FE electronics, enter the ROM as serial data stream;
Introducing the Raspberry Pi Nauru ICT Department April 2016.
+ The INFN COSA project Daniele Cesini – INFN-CNAF (On behalf of the COSA collaboration)
+ The INFN COSA project Tommaso Boccali (alcune slides riadattate da Daniele Cesini)
Daniele Cesini - INFN CNAF. INFN-CNAF 20 maggio 2014 CNAF 2 CNAF hosts the Italian Tier1 computing centre for the LHC experiments ATLAS, CMS, ALICE and.
IBM Power system – HPC solution
The Evolution of the Italian HPC Infrastructure Carlo Cavazzoni CINECA – Supercomputing Application & Innovation 31 Marzo 2015.
A Practical Evaluation of Hypervisor Overheads Matthew Cawood Supervised by: Dr. Simon Winberg University of Cape Town Performance Analysis of Virtualization.
Does HPC really fit GPUs ? Davide Rossetti INFN – Roma Napoli, January 2010 APE group January Incontro di.
APE group Many-core platforms and HEP experiments computing XVII SuperB Workshop and Kick-off Meeting Elba, May 29-June 1,
Parallel Computers Today LANL / IBM Roadrunner > 1 PFLOPS Two Nvidia 8800 GPUs > 1 TFLOPS Intel 80- core chip > 1 TFLOPS  TFLOPS = floating point.
High throughput computing collaboration (HTCC) Jon Machen, Network Software Specialist DCG IPAG, EU Exascale Labs INTEL Switzerland.
 A few notes on testing  Preliminary tests  Computed Tomography  Astrophysics  Molecular Dynamics  HS COSA f2f - 18/05/ Lucia Morganti – INFN-CNAF.
Accelerating particle identification for high-speed data-filtering using OpenCL on FPGAs and other architectures for FPL 2016 Srikanth Sridharan CERN 8/31/2016.
+ The INFN COSA project Michele Michelotto
Fast iteration and prototyping in high-performance computing medical applications: a case study with Mentor Vista 8th INFIERI WORKSHOP 10/21/2016.
Brief introduction about “Grid at LNS”
Bringing Hardware Acceleration closer to the programmer
COMETA Sara Pirrone INFN.
Evaluation of HEP worker nodes Michele Michelotto at pd.infn.it
M. Bellato INFN Padova and U. Marconi INFN Bologna
Intel Many Integrated Cores Architecture
NFV Compute Acceleration APIs and Evaluation
LHCb and InfiniBand on FPGA
NaNet Problem: lower communication latency and its fluctuations. How?
Community Grids Laboratory
FPGAs for next gen DAQ and Computing systems at CERN
Buying into “Summit” under the “Condo” model
Modern supercomputers, Georgian supercomputer project and usage areas
Alessandro Lonardo Referente Locale TT Sezione di Roma 1 Piero Vicini
Daniele Cesini – INFN-CNAF - 19/09/2017
GPU Computing Jan Just Keijser Nikhef Jamboree, Utrecht
Scientific requirements and dimensioning for the MICADO-SCAO RTC
Low Power processors in HEP
Infrastructure for testing accelerators and new
Low Latency Analytics HPC Clusters
Computer-Generated Force Acceleration using GPUs: Next Steps
Parallel Computers Today
Super Micro Technology Computing
IXPUG Abstract Submission Instructions
Footer.
IXPUG Asia Guangzhou, China
Luca dell’Agnello, Daniele Cesini – INFN-CNAF CCR - 23/05/2017
Jianting Zhang1,2 Simin You2, Le Gruenwald3
Presentation transcript:

Stato progetto COSA 2016 http://www.cosa-project.it

Daniele Cesini – INFN-CNAF 03/11/2016

INFN COSA project COSA: Computing On SOC Architecture Duration: 3 years from January 2015 Departments: 7 INFN CNAF, PI, PD, ROMA1, FE, PR, LNL BUDGET :53 kEu Year1, 53kEu Year2, 46 kEu Year3 Funded by INFN CSN5 Daniele Cesini – INFN-CNAF 03/11/2016

Objectives Acquire know-how Unification of INFN HW testing activities Porting and benchmarking of low power/low cost System on Chip Operations of Linux system on SoCs Benchmarking hybrid architectures Unification of INFN HW testing activities Continuation of the COKA project Computing on Knights Architecture Porting on traditional accelerator (GPU/MIC) Continuation of the HEPMARK projects X86 benchmarking Study of custom low latency interconnection built with ARM+FPGA devices Prepare H2020 proposals on LowPower computing calls Daniele Cesini – INFN-CNAF 03/11/2016

Assegnazioni Assegnazioni 2017: FE INV: sistema PASCAL (10 keu) CNAF INV: switch omnipath, schede omnipath pci, 3k schede SoC low power, picoitx (17keu) CNAF SW: rinnovo compilatore intel (6keu) Daniele Cesini – INFN-CNAF 03/11/2016

Inventariabile 2015/2016 2015 RM1 – 13k Switch di rete per cluster APEnet e acquisizione PCIe Fabric switch di AVAGO CNAF – 14k nodi cluster + 2 switch 1gb + 1 switch 10gb + schede 10gb + HDs vari + RAM varie + alimentatore FE – 7k co-finanziamento con UNIFE di un cluster di   32+5 schede NVIDIA-K80, ovvero 64+10 GPU PD - intel Xeon D 1540 8core con HT, AMD A1100 che e' un ARM A57 8core, 16GB di RAM 2016 CNAF: 4x jetson TX1 (fondi cnaf), 1.6 keu da spendere (consumo) RM1: FPGA Altera (Arria10 /Sratix10) ? + jetson x1 ? inv cnaf? FE: xeon PHI KNL? (preventivi disponibili) PD: arm64? Daniele Cesini – INFN-CNAF 03/11/2016

Milestones 2015 Daniele Cesini – INFN-CNAF 03/11/2016

Milestones 2016/2017 +2017: valutazione interconnessioni Omnipath Daniele Cesini – INFN-CNAF 03/11/2016

Afferenze Daniele Cesini – INFN-CNAF 03/11/2016

Pubblicazioni 2015 RM1 2015 FE 2015 CNAF 2016 X-Ray Computed Tomography Applied to Objects of Cultural Heritage: Porting and Testing the Filtered Back-Projection Reconstruction Algorithm on Low Power Systems-on-Chip - PDP 2016, 369-372, 2016 ​ Evaluating Systems on Chip through HPC Bioinformatics and Astrophysics Applications – PDP 2016, 541-544, 2016 Manzali/falabella/Giacomini LHCb Event Building on cosa cluster 2 pubblicazioni Daniele Cesini – INFN-CNAF 03/11/2016

Conferenze 2015: 2016: Presentazioni COLA WS ALTRO?? X-Ray Computed Tomography Applied to Objects of Cultural Heritage: Porting and Testing the Filtered Back-Projection Reconstruction Algorithm on Low Power Systems-on-Chip - PDP 2016 ​ Evaluating Systems on Chip through HPC Bioinformatics and Astrophysics Applications – PDP 2016 LHCb Event Building on low power systems @ SIF Genova ALTRO?? Daniele Cesini – INFN-CNAF 03/11/2016

Collaborazioni 2015/2016 Altro ?? progetto Hercules http://hipert.unimore.it/hercules/ CIRI-ICT UNIBO MICREL LAB Altro ?? Daniele Cesini – INFN-CNAF 03/11/2016