CALL FOR PAPERS
Springer International Journal of Parallel Programming (IJPP)
Special Issue on Workload Optimized Systems
==============================
The slowdown in Moore's Law makes it increasingly important to optimize
systems around specific workloads. Such workload optimized systems have
hardware and/or software specifically designed to run well for a particular
workload or workload class. Such systems include, but are not limited to
traditional CPUs assisted with accelerators (ASICs, FPGAs, GPUs), memory
accelerators, I/O accelerators, hybrid systems, and IT appliances. This
workload optimized system approach contrasts to the broad general purpose
direction of computing over many decades. The workload optimized systems
approach is growing in importance, as we see in systems from cellphones to
tablets to routers to game machines to Top500 supercomputers, and IT
appliances such as IBM's DataPower and Netezza, and Oracle's Exadata. The
goal of this special issue is to foster awareness in industry and academic
community on workload optimized systems and to expose cross hw/sw stack
unique systems and software research challenges associated with such
systems. All submitted papers are subject to the same review process as those
papers accepted for publication in the regular issues. The special issue seeks
original papers on a range of topics related to workload optimized systems
including, but not limited to
GPUs, FPGAs, ASIC Accelerators
Memory and I/O accelerators
Network accelerators
Storage optimized systems
System level accelerators
IT Appliances
Systems in specific domains like analytics, cloud, cognitive, mobile etc.
Converged/Hybrid/Heterogeneous systems
Cross hardware/software stack design and optimization
Programming models for workload optimized systems
Measurements and Experimentation
Workload characterization and profiling
Performance modeling and optimization
Workload scheduling and orchestration
Runtime management systems
Industrial Experiences
===============
Important Dates
===============
Manuscript due: March 27, 2015
Initial Notice: June 5, 2015
Revisions Due: July 10, 2015
Final Notification: Aug 14, 2015
Final Versions Due: Sep 11, 2015
===========
Submissions
===========
Authors are encouraged to submit high-quality, original work that
has neither appeared in, nor is under consideration by, other
journals. All papers will be reviewed following standard reviewing
procedures for the Journal. Papers must be prepared in accordance
with the Journal guidelines: http://www.springer.com/10766.
Manuscripts must be submitted to: http://IJPP.edmgr.com.
Choose “S.I.: Workload Optimized Systems” as the article type.
=============
Guest editors
=============
Erik Altman, IBM Research, Yorktown Heights, NY. ealtman@us.ibm.com
Parijat Dube, IBM Research, Yorktown Heights, NY. pdube@us.ibm.com
Springer International Journal of Parallel Programming (IJPP)
Special Issue on Workload Optimized Systems
==============================
The slowdown in Moore's Law makes it increasingly important to optimize
systems around specific workloads. Such workload optimized systems have
hardware and/or software specifically designed to run well for a particular
workload or workload class. Such systems include, but are not limited to
traditional CPUs assisted with accelerators (ASICs, FPGAs, GPUs), memory
accelerators, I/O accelerators, hybrid systems, and IT appliances. This
workload optimized system approach contrasts to the broad general purpose
direction of computing over many decades. The workload optimized systems
approach is growing in importance, as we see in systems from cellphones to
tablets to routers to game machines to Top500 supercomputers, and IT
appliances such as IBM's DataPower and Netezza, and Oracle's Exadata. The
goal of this special issue is to foster awareness in industry and academic
community on workload optimized systems and to expose cross hw/sw stack
unique systems and software research challenges associated with such
systems. All submitted papers are subject to the same review process as those
papers accepted for publication in the regular issues. The special issue seeks
original papers on a range of topics related to workload optimized systems
including, but not limited to
GPUs, FPGAs, ASIC Accelerators
Memory and I/O accelerators
Network accelerators
Storage optimized systems
System level accelerators
IT Appliances
Systems in specific domains like analytics, cloud, cognitive, mobile etc.
Converged/Hybrid/Heterogeneous systems
Cross hardware/software stack design and optimization
Programming models for workload optimized systems
Measurements and Experimentation
Workload characterization and profiling
Performance modeling and optimization
Workload scheduling and orchestration
Runtime management systems
Industrial Experiences
===============
Important Dates
===============
Manuscript due: March 27, 2015
Initial Notice: June 5, 2015
Revisions Due: July 10, 2015
Final Notification: Aug 14, 2015
Final Versions Due: Sep 11, 2015
===========
Submissions
===========
Authors are encouraged to submit high-quality, original work that
has neither appeared in, nor is under consideration by, other
journals. All papers will be reviewed following standard reviewing
procedures for the Journal. Papers must be prepared in accordance
with the Journal guidelines: http://www.springer.com/10766.
Manuscripts must be submitted to: http://IJPP.edmgr.com.
Choose “S.I.: Workload Optimized Systems” as the article type.
=============
Guest editors
=============
Erik Altman, IBM Research, Yorktown Heights, NY. ealtman@us.ibm.com
Parijat Dube, IBM Research, Yorktown Heights, NY. pdube@us.ibm.com
No comments:
Post a Comment