1

EIC Computing Meeting

Oct. 18 2021

D. Lawrence

Computing Plan Status

Data Storage and Compute

2

ECCE Bi-Weekly meeting - Computing Team Report - Sep. 27, 2021

Experimental Hall and Counting House (Project Funds)

Data Center(s): SDCC [,JLab, …]

(Operations Funds)

HTC Compute Facilities

SDCC ,JLab, …

(Operations)

O(100Tbps)

O(10Tbps)

O(0.1Tbps)

O(0.1Tbps)

O(10GB/s)

O(1GB/s)

O(0.1Tbps)

O(0.01Tbps)

reduce ~x2

mitigate risk of network failure

Data Storage and Compute

3

ECCE Bi-Weekly meeting - Computing Team Report - Sep. 27, 2021

Experimental Hall and Counting House (Project Funds)

Data Center(s): SDCC [,JLab, …]

(Operations Funds)

HTC Compute Facilities

SDCC ,JLab, …

(Operations)

O(100Tbps)

O(10Tbps)

O(1Tbps)

O(0.1Tbps)

O(10GB/s)

O(1GB/s)

O(0.1Tbps)

O(0.01Tbps)

O(1Tbps)

reduce ~x2

mitigate risk of network failure

EIC Streaming Readout (From Fernando Barbosa’s talk at AI4EIC Sep. 9, 2021)

factor of 100 in data reduction

from EIC Yellow Report

From YR 2.10

​

“Most of the key physics topics discussed in the EIC White Paper [2] are

achievable with an integrated luminosity of 10 fb⁻¹ corresponding to 30 weeks of

operations.”

10x10³³ cm^-2s^-1 x 30 weeks

=

18.1 fb^-1

(assumes 100% beam up time. YR also says 60% operational efficiency which would bring this to 10.3 fb^-1)

​

bottom line: 10fb^-1 represents roughly first year of running with about half of that for ep scattering

For ep scattering representing half of a 30 week year of running we expect:

​

50μb x 5fb^-1 = 250B collisions

​

Inclusive ep scattering MC DST: ~600MB/2k events = 300kB/event

​

250B/(15weeks*7days/wk*24hr/d*3600s/hr)/(60% accel. efficiency) =46kHz

​

46kHz * 300kB = 14GB/s (140Gbps)

from EIC Yellow Report

close to Jin’s simulation calculation of O(100Gbps)

Multiple levels of event filter

Federated Computing Model

Detector

FEB (digitization)

O(100Tbps)

O(10Tbps)

O(1Tbps)

FELIX-like

FEP (initial filter)

Online Event Filter

CPU, FPGA, GPU

Online Buffer

EBDC (few days)

Offline Event Filter

O(0.1Tbps)

reduce ~x2

mitigate risk of network failure

Federated Computing Model

Benefits of using a federated model in the near-time pipeline�

• Each site only needs to handle a fraction of data�
• EIC computing becomes a smaller fraction of each compute farm�
• One site having diminished capacity temporarily can easily be absorbed by others without reconfiguration

Worldwide LHC Computing Grid (WLCG)

• Tier 0 - LHC
• Store all raw data
• 20% of LHC computing
• Initial reconstruction
• Distribute raw data and initial recon to all Tier 1 sites
• Tier 1 - multiple sites(13)
• Combined capacity to store all data from Tier 0
• Compute for large scale reprocessing
• Distribute data to Tier 2 sites
• Store simulated data from Tier 2 sites
• Tier 2 - Universities and Scientific sites (155)
• Compute for specific analysis tasks
• Some reconstruction
• Simulation
• Tier 3 - End users
• small clusters or personal computers

​

https://home.cern/science/computing/grid-system-tiers

An EIC Butterfly Model

EIC

BATES

NERSC

OSG

University

University

University

University

University

University

University

University

Tier 0

Tier 1

Tier 2

Tier 3

Tier 3

Nearly all storage (raw data, reconstructed data, simulated data) is stored across Tier 1 sites

ECCE Computing Plan

12

ECCE Bi-Weekly meeting - Computing Team Report - Sep. 13, 2021

• Internal deadline of Oct. 23
• rough draft, all sections�
• Internal review Oct. 24-30�
• Designated Reader review Nov. 1-15�
• Final draft Nov. 30

Key features:

• Streaming Readout
• Reconstruction in near-real time (~2weeks)
• Federated Computing

Open Questions

• Computing/Storage�
• What are DOE rules, where are they written, can they be updated?�
• LHC-style pyramid model vs. butterfly model?�
• Common system for all EIC experiments?�
• Data Processing/Software�
• Limitations on calibration latency? (e.g. detector design)�
• Nature and number of filters. Types of technology that can be used (e.g. FPGA, GPU, …)

Backups