[hpc-announce] JSSPP 2024 (deadline extended) - Job Scheduling Strategies for Parallel Processing (in conjunction with IEEE IPDPS)

[Dalibor Klusáček]

=============================================================================

  Call for Papers: *JSSPP 2024* (in conjunction with IEEE IPDPS, San 
Francisco)
*27th workshop on Job Scheduling Strategies for Parallel Processing*

=============================================================================
*
Extended Paper Submission Deadline: February 18th, 2024*

Author Notification: March 1st, 2024
Workshop date: May 31st, 2024
Webpage: https://jsspp.org
Submission page: https://easychair.org/conferences/?conf=jsspp2024
contact: jssppw at gmail.com

*------------
Description
------------*
The 2024 edition of Job Scheduling Strategies for Parallel Processing 
(JSSPP) will be the 27th installment of this long-running and 
established workshop that addresses all aspects of resource management 
and scheduling in parallel computing, including cloud, grid, HPC & HTC, 
as well as "mixed/hybrid" systems.
JSSPP balances practice and theory in its program and provides a rich 
environment for technical debate about scheduling approaches among 
academic researchers as well as participants from the industry.

JSSPP welcomes Regular Papers (RP) as well as descriptions of Open 
Scheduling Problems (OSP) and Workload Traces (WT) coming from 
interesting scheduling domains (see below). Our goal with the OSP papers 
is to build a bridge between the production and research worlds, 
enhancing mutual understanding and reproducibility to facilitate direct 
collaborations and impact. Our goal with the WT papers is to tackle the 
lack of real-world data that often hampers the ability of the research 
community to engage with scheduling problems in a way that has a 
real-world impact.

*----------------------------
Call for Regular Papers (RP)
----------------------------*
JSSPP solicits regular papers that focus on challenges in parallel 
scheduling, including but not limited to:
- Design of new scheduling approaches.
- Performance evaluation of scheduling approaches, including 
methodology, benchmarks, and metrics.
- Fulfilling additional constraints in scheduling systems, like job 
priorities, price, energy requirements (Green Computing), accounting, 
load estimation, and quality of service guarantees.
- Impact of scheduling strategies on system utilization, application 
performance, user-friendliness, cost efficiency, and energy efficiency.
- Scaling and architecture of very large scheduling systems.
- Operational challenges: Capacity planning, service level assurance, 
reliability.
- Interaction between schedulers on different levels (e.g., processor vs 
cluster) and tenancy domains (single and multi-tenant)
- Interaction between applications/workloads, e.g., efficient batch job 
and container/Pod/VM co-scheduling within a single system, etc.
- Experience reports from large-scale compute production systems.
- GPU/Accelerator (co)scheduling.
- AI/ML-inspired scheduling approaches.

*-----------------------------
Call for Workload Traces (WT)
-----------------------------*
JSSPP welcomes papers introducing workload traces from workloads of real 
systems that offer challenges in the context of this workshop.  These 
submissions should include:
- Anonymized (if needed) workload artifacts that describe a significant 
share of individual units of resource scheduling (jobs, pods, VMs, 
functions, etc.) during a period of life in a parallel computing system.
- A description of the parallel system running these workloads.
- An analysis of the traces, modeling key workload features and 
highlighting scheduling challenges in their hosting systems.
We ask submitters to employ known workload description languages (e.g., 
SWF) to represent their traces or to attach schemas that allow 
interpreting them. The submission of artifacts that model the workloads 
is also encouraged.

*---------------------------------------
Call for Open Scheduling Problems (OSP)
---------------------------------------*
JSSPP welcomes papers describing open problems in large-scale 
scheduling. We believe that clearly described real-world scheduling 
problems will help both the industry and the scientific communities to 
bridge the gap that often prevents the adoption of newly proposed 
scheduling techniques in practice.
Effective scheduling approaches are predicated on three things:
- A concise understanding of scheduling goals, and how they relate to 
one another.
- Details of the workload (job arrival times, sizes, shareability, 
deadlines, etc.)
- Details of the system being managed (size, break/fix lifecycle, 
allocation constraints)
Submissions must include a concise description of the key metrics of the 
system and how they are calculated, as well as anonymized data 
publication of the system workload and production schedule. Ideally, 
anonymized operational logs would also be published, though we 
understand this might be more difficult.
We envision that OSP papers will stimulate the development of new 
scheduling approaches, which can be robustly compared with the schedules 
used in production facilities, and other approaches to solve the same 
problems.

-----------------
Submission Format
-----------------
Paper formatting requirements are the same for Regular Papers, Workload 
Traces, and OSP-related submissions. Papers should be no longer than 20 
single-spaced pages, 10pt font, including figures and references. All 
submissions must follow the LNCS format. See the instructions at 
Springer's website: http://www.springer.com/lncs
All papers in scope will be reviewed by at least three members of the 
program committee.
Submissions are accepted by EasyChair submission page: 
https://easychair.org/conferences/?conf=jsspp2024

-----------------
Workshop Webpage
-----------------
Up-to-date information and further details are available at JSSPP 2024 
page: https://jsspp.org