FPGA based on-chip memory for data dependent applications

Deepa, P.; Vasanthanayaki, C.

doi:10.1109/iciev.2012.6317461

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2015

2020

Publication Types

Select...

Other2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data dependent applications such as video compression algorithms, on the contrary, may not be able to benefit from static scratchpad memory management as the memory access pattern depends on the input data [4]. Dynamic memory replacement methods, although can adapt to different memory access patterns, they cannot guarantee 100% hit rate on the other hand.…”

Section: Introductionmentioning

confidence: 99%

OpenCL computing on FPGA using multiported

Mutlugun

Wang

2015

2015 25th International Conference on Field Programmable Logic and Applications (FPL)

View full text Add to dashboard Cite

This paper focuses on memory access improvements for the OpenCL architecture for FPGAs with the goal of achieving trade-off between performance and required resources. In OpenCL compute units, there is usually a linear relation between computation time and local memory access latency. This latency is normally hidden by increasing the parallel workload. However, with such an approach, the target FPGA device could easily run out of resources. In this work, conflict-free multiported memories are used to minimize local memory access latency. Experiments show that multiported memories can successfully increase computation speed and reduce the required parallel workload for maximum throughput to practical amounts.

show abstract

Section: Introductionmentioning

confidence: 99%