2023
DOI: 10.1007/s11227-022-05040-y
|View full text |Cite
|
Sign up to set email alerts
|

EPSILOD: efficient parallel skeleton for generic iterative stencil computations in distributed GPUs

Abstract: Iterative stencil computations are widely used in numerical simulations. They present a high degree of parallelism, high locality and mostly-coalesced memory access patterns. Therefore, GPUs are good candidates to speed up their computation. However, the development of stencil programs that can work with huge grids in distributed systems with multiple GPUs is not straightforward, since it requires solving problems related to the partition of the grid across nodes and devices, and the synchronization and data m… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 40 publications
(48 reference statements)
0
1
0
Order By: Relevance
“…Unfortunately, the experiment section does not discuss the use of multiple GPUs [14]. EPSILOD tests prototypes for stencil operations but misses a generic stencil implementation [15]. ExaStencil provides a domain-specific language for stencil operations, therefore it misses the option to parallelize pre-and post-processing steps [16].…”
Section: Related Workmentioning
confidence: 99%
“…Unfortunately, the experiment section does not discuss the use of multiple GPUs [14]. EPSILOD tests prototypes for stencil operations but misses a generic stencil implementation [15]. ExaStencil provides a domain-specific language for stencil operations, therefore it misses the option to parallelize pre-and post-processing steps [16].…”
Section: Related Workmentioning
confidence: 99%