2020
DOI: 10.1007/978-3-030-58144-2_17
|View full text |Cite
|
Sign up to set email alerts
|

OpenMP Device Offloading to FPGAs Using the Nymble Infrastructure

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(4 citation statements)
references
References 28 publications
0
4
0
Order By: Relevance
“…This typically leads to very high compile times and very low FPGA occupation and performance, since CPU-and GPU-optimized code is notably inefficient in the FPGA architectures. Further work by Knaust [13] and Huthmann [14] attack this problem in different ways. The first one opts to prototype the FPGA device with OpenCL and compiler-specific interfaces, requiring IR (Intermediate Representation) backporting to make use of the HLS system and OpenCL interfaces.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…This typically leads to very high compile times and very low FPGA occupation and performance, since CPU-and GPU-optimized code is notably inefficient in the FPGA architectures. Further work by Knaust [13] and Huthmann [14] attack this problem in different ways. The first one opts to prototype the FPGA device with OpenCL and compiler-specific interfaces, requiring IR (Intermediate Representation) backporting to make use of the HLS system and OpenCL interfaces.…”
Section: Related Workmentioning
confidence: 99%
“…More flexible than [13,14] is the aforementioned Yviquel et al [10] work. It does not generate target binary code but rather a Scala implementation (as a Java runtime binary) to be ran on any Apache Spark cluster.…”
Section: Related Workmentioning
confidence: 99%
“…The work by Huthmann et al in [62] presents an approach to OpenMP device offloading for FPGAs based on the LLVM compiler infrastructure and the Nymble HLS compiler. The automatic compilation flow uses LLVM IR for HLS-specific optimizations and transformation and for the interaction with the Nymble HLS compiler.…”
Section: Related Workmentioning
confidence: 99%
“…The authors in [62] argue that scaling OpenMP onto multiple FPGAs is an open question. They suggest that one could rely on OpenMP's accelerator directives, and treat each device as a discrete system with little to no access to other systems and create/include special hardware to (for example) support a shared-memory view across multiple FPGAs, or use tasks as containers that encapsulate produced/consumed data, that are exchanged among FPGAs.…”
Section: Chapter 6 Final Remarks and Conclusionmentioning
confidence: 99%