Future Dataflow Bottlenecks Christopher O’Grady with A. Perazzo and M. Weaver Babar Dataflow Group.

Slides:



Advertisements
Similar presentations
IT253: Computer Organization
Advertisements

Dec/02/04 Su DongCaltech Trigger/DAQ/Online workshop1 Level 1 Trigger: Introduction L1 trigger objects and strategy Implementation features L1 composition.
Clara Gaspar on behalf of the LHCb Collaboration, “Physics at the LHC and Beyond”, Quy Nhon, Vietnam, August 2014 Challenges and lessons learnt LHCb Operations.
March 24-28, 2003Computing for High-Energy Physics Configuration Database for BaBar On-line Rainer Bartoldus, Gregory Dubois-Felsmann, Yury Kolomensky,
MICE Fiber Tracker Electronics AFEII for MICE (Front end readout board) Recall: AFEs mount on ether side of the VLPC cass, with fibers going to the VLPCs.
June 19, 2002 A Software Skeleton for the Full Front-End Crate Test at BNL Goal: to provide a working data acquisition (DAQ) system for the coming full.
LHCb Upgrade Overview ALICE, ATLAS, CMS & LHCb joint workshop on DAQ Château de Bossey 13 March 2013 Beat Jost / Cern.
20 Feb 2002Readout electronics1 Status of the readout design Paul Dauncey Imperial College Outline: Basic concept Features of proposal VFE interface issues.
CHEP04 - Interlaken - Sep. 27th - Oct. 1st 2004T. M. Steinbeck for the Alice Collaboration1/20 New Experiences with the ALICE High Level Trigger Data Transport.
1  2004 Morgan Kaufmann Publishers Chapter Six. 2  2004 Morgan Kaufmann Publishers Pipelining The laundry analogy.
6 June 2002UK/HCAL common issues1 Paul Dauncey Imperial College Outline: UK commitments Trigger issues DAQ issues Readout electronics issues Many more.
Target Monitoring and Control Current status DAQ card – NI 6254 Analog/Digital card Problems with Linux version drivers Currently reading up to 12 channels.
M. WeaverPEP-II MAC Review,15-17 Nov’07  Operational issues  radiation aborts  background monitoring  Background extrapolations  model comparisons.
Trigger-less and reconfigurable data acquisition system for J-PET
OEP infrastructure issues Gregory Dubois-Felsmann Trigger & Online Workshop Caltech 2 December 2004.
Trigger and online software Simon George & Reiner Hauser T/DAQ Phase 1 IDR.
Emlyn Corrin, DPNC, University of Geneva EUDAQ Status of the EUDET JRA1 DAQ software Emlyn Corrin, University of Geneva 1.
06/15/2009CALICE TB review RPC DHCAL 1m 3 test software: daq, event building, event display, analysis and simulation Lei Xia.
Jan 3, 2001Brian A Cole Page #1 EvB 2002 Major Categories of issues/work Performance (event rate) Hardware  Next generation of PCs  Network upgrade Control.
Hall A DAQ status and upgrade plans Alexandre Camsonne Hall A Jefferson Laboratory Hall A collaboration meeting June 10 th 2011.
Understanding and Building Basic Networks Chapter 6 Creating a Network.
The BaBar Event Building and Level-3 Trigger Farm Upgrade S.Luitz, R. Bartoldus, S. Dasu, G. Dubois-Felsmann, B. Franek, J. Hamilton, R. Jacobsen, D. Kotturi,
EGEE is a project funded by the European Union under contract IST HEP Use Cases for Grid Computing J. A. Templon Undecided (NIKHEF) Grid Tutorial,
25 April 2000 SEESCOASEESCOA STWW - Programma Evaluation of on-chip debugging techniques Deliverable D5.1 Michiel Ronsse.
FED RAL: Greg Iles5 March The 96 Channel FED Tester What needs to be tested ? Requirements for 96 channel tester ? Baseline design Functionality.
Ted Pedersen – CS 3011 – Chapter 10 1 A brief history of computer architectures CISC – complex instruction set computing –Intel x86, VAX –Evolved from.
LHCb DAQ system LHCb SFC review Nov. 26 th 2004 Niko Neufeld, CERN.
CSC321 Introduction to Neural Networks and Machine Learning Lecture 3: Learning in multi-layer networks Geoffrey Hinton.
 Basically, Architects design, build, and or supervise the construction of buildings.  The building that they build must be safe and follow all of the.
Why it might be interesting to look at ARM Ben Couturier, Vijay Kartik Niko Neufeld, PH-LBC SFT Technical Group Meeting 08/10/2012.
Sep. 17, 2002BESIII Review Meeting BESIII DAQ System BESIII Review Meeting IHEP · Beijing · China Sep , 2002.
Accessing PBeast and monitoring the L1 trigger Emily Thompson.
SCT Readiness for Heavy Ion Collisions Dave Robinson on behalf of SCT 15/9/101Dave Robinson Heavy Ion Review.
June 17th, 2002Gustaaf Brooijmans - All Experimenter's Meeting 1 DØ DAQ Status June 17th, 2002 S. Snyder (BNL), D. Chapin, M. Clements, D. Cutts, S. Mattingly.
28 June 2004ATLAS Pixel/SCT TIM FDR/PRR1 TIM tests with ROD Crate John Hill.
1 MICE Tracker Readout Update AFE IIt firmware development VLSB firmware development Hardware progress Summary Terry Hart, MICE Tracker Meeting, August.
SoLiD/PVDIS DAQ Alexandre Camsonne. DAQ limitations Electronics Data transfer.
Trigger and DAQ System Zhao Jing Wei Sept. 2002, BESIII review, Beijing Outline Trigger system Event rate estimation Principle of design Scheme Monte Carlo.
STAR J/  Trigger in dA Manuel Calderon for the Heavy-Flavor Group Trigger Workshop at BNL October 21, 2002.
1  1998 Morgan Kaufmann Publishers Chapter Six. 2  1998 Morgan Kaufmann Publishers Pipelining Improve perfomance by increasing instruction throughput.
Ted Liu, July 5,00, idea on Ztrigger L1 Trigger Strategy L1 Trigger Requirements and Trigger Lines L1 Trigger performance Background Study Improving Performance:
1 MICE Tracker Readout Update Introduction/Overview TriP-t hardware tests AFE IIt firmware development VLSB firmware development Hardware progress Summary.
October Test Beam DAQ. Framework sketch Only DAQs subprograms works during spills Each subprogram produces an output each spill Each dependant subprogram.
LKr readout and trigger R. Fantechi 3/2/2010. The CARE structure.
APEX DAQ rate capability April 19 th 2015 Alexandre Camsonne.
M. WeaverB-Factory Operations Review April 24, 2006 BaBar Backgrounds Matt Weaver B-Factory Operations Review April 24, 2006.
PHENIX DAQ RATES. RHIC Data Rates at Design Luminosity PHENIX Max = 25 kHz Every FEM must send in 40 us. Since we multiplex 2, that limit is 12 kHz and.
Markus Frank (CERN) & Albert Puig (UB).  An opportunity (Motivation)  Adopted approach  Implementation specifics  Status  Conclusions 2.
News and Related Issues Ted & Kirsten May 27, 2005 TDWG News since last meeting (April 29th) Organization Issues: how to improve communication Future Plans:
DAQ 1000 Tonko Ljubicic, Mike LeVine, Bob Scheetz, John Hammond, Danny Padrazo, Fred Bieser, Jeff Landgraf.
Overview B A B AR L1 DCT Upgrade FDR Masahiro Morii Harvard University Scope of the Project Current Status Schedule  Commissioning.
Some thoughs about trigger/DAQ … Dominique Breton (C.Beigbeder, G.Dubois-Felsmann, S.Luitz) SuperB meeting – La Biodola – June 2008.
MASS Java Documentation, Verification, and Testing
Modifications to the DRS4’s code
ETD summary D. Breton, S.Luitz, U.Marconi
Current Electricity.
Enrico Gamberini, Giovanna Lehmann Miotto, Roland Sipos
AFE II Status First board under test!!.
Trigger, DAQ, & Online: Perspectives on Electronics
DCH Electronics Upgrade: Overview and Status
Special edition: Farewell for Valerie Halyo
L1 Trigger Strategy Ted Liu, Lawrence Berkeley Lab
Dominique Breton, Jihane Maalmi
Special edition: Farewell for Stephen Bailey
Special edition: Farewell for Eunil Won
Trickle Background Investigation
Long term projections summary
How clearly does your work flow and tell a story?
ETD parallel session March 18th 2010
Perugia SuperB Workshop June 16-19, 2009
Presentation transcript:

Future Dataflow Bottlenecks Christopher O’Grady with A. Perazzo and M. Weaver Babar Dataflow Group

View of the DAQ System A series of parallel assembly lines System runs as fast as the slowest worker on the assembly line Trigger rate projections tell us how fast workers should work, event size projections tell us how fast they actually take. Use software written by Amedeo Perazzo and James Swain to record system performance info We use this information to project into the future. All the following plots are made by Matt Weaver.

Projections On June 25, 2001 I predicted the DCH readout would be a bottleneck in Also, when we saw unexplained deadtime from GLT, the projection system “told” us that there was 90us delay shipping data (which we then saw on the scope). This projection system works well.

Projection Improvements Matt has split all occupancy projections into HER/LER/LUM components (previously, only for DCH). Using Jan 2004 background runs. Looks at all ROMs individually. Previously just the worst. Projecting through (3*10**34)

General Observations HER worse than 2002 LER better than 2002 Now see a luminosity term in sizes Event size is 75kb in 2007 (3*10**34)

Trigger Rate Projections From the Trigger Group: Need <140us!

Fiber Transfer Bottlenecks DCH/SVT the largest. GLT also important. 140us

Behaviour of Fiber Deadtime Worse than other deadtime, since “earliest” buffering in the system.

Plan of Attack for Fiber DCH: in progress GLT/DCT: sudong in progress, should be straightforward SVT: 1.try running system at 60MHz, or 2.reduce occupancy (and efficiency) with thresholds EMT: straightforward

Feature Extraction Bottleneck DCH/DRC/EMC/EMT/SVT ideally need work 140us

Plan of Attack for FEX DCH FEX taken care of with electronics upgrade. DRC and SVT FEX relatively easy (don’t “do” anything). EMT FEX requires data format change (some work but doable, in principle). Amedeo already did one pass. EMC FEX hard! Already a lot of work on that by Matt.

EMC FEX Need new idea (like Walt had) or new CPUs. new CPUs won't necessarily work easily: mechanical, electrical, software issues. significant work and money. Maybe 20% gain from nbr bits, but hardware untested and corners may not see gain.

VME Bottleneck Currently overestimated. EMC/DRC/SVT 140us

Plan of Attack for VME Many bottlenecks, but maybe not a problem. Could imagine going to all-network event build. For this would likely need ~150 Gbit network cards ($45K) + fibers + network switch ($60K?). Maybe more L3 nodes.

Summary Up until now have been able to reduce big bottlenecks: EMT FEX, EMC FEX, network stack, DCH data transfer(in progress), GLT/DCT data transfer (sudong, in progress). With the above work we should be able to sustain 5kHz in Not good enough for predicted 7kHz L1. EMC FEX and SVT fiber transfer hardest. Bottlenecks getting varied and difficult: ~$100K + significant code mods to eliminate VME. ~$500K for new CPUs, and new CPUs may be tough. There are deadtime periods we don’t quantitatively understand.

My Intuition It’s going to be a little rough by Continue improving the system piece by piece with manpower and money we have, BUT Tightening the trigger in 2007 will likely be necessary.