Exploring Online Synthesis for CGRAs with Specialized Operator Sets
The design of energy-efficient systems has become a major challenge for engineers over the last decade. One way to save energy is to spread out computations in space rather than in time (as traditional processors do). Unfortunately, this requires to design specialized hardware for each application....
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2011-01-01
|
| Series: | International Journal of Reconfigurable Computing |
| Online Access: | http://dx.doi.org/10.1155/2011/601986 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832558113679474688 |
|---|---|
| author | Stefan Döbrich Christian Hochberger |
| author_facet | Stefan Döbrich Christian Hochberger |
| author_sort | Stefan Döbrich |
| collection | DOAJ |
| description | The design of energy-efficient systems has become
a major challenge for engineers over the last decade. One way
to save energy is to spread out computations in space rather
than in time (as traditional processors do). Unfortunately, this
requires to design specialized hardware for each application.
Also, the nonrecurring expenses for the manufacturing of
chips continuously grow. Implementing the computations on
FPGAs and CGRAs solves this dilemma, as the non recurring
expenses are shared between many different applications. We
believe that online synthesis that takes place during the execution
of an application is one way to broaden the applicability of
reconfigurable architectures as no expert knowledge of synthesis
and technologies is required. In this paper, we give a detailed
analysis of the amount and specialization of resources in a CGRA
that are required to grant a significant speedup of Java bytecode.
In fact, we show that even a relatively small number of specialized
reconfigurable resources is sufficient to speed up applications
considerably. Particularly, we look at the number of dedicated
multipliers and dividers. Also, we discuss the required number of
concurrent memory access operations inside the CGRA. Again,
it shows that two concurrent memory access operations are
sufficient for almost all applications. |
| format | Article |
| id | doaj-art-88e672fd6585406a9eea85075536d768 |
| institution | Kabale University |
| issn | 1687-7195 1687-7209 |
| language | English |
| publishDate | 2011-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Reconfigurable Computing |
| spelling | doaj-art-88e672fd6585406a9eea85075536d7682025-02-03T01:33:12ZengWileyInternational Journal of Reconfigurable Computing1687-71951687-72092011-01-01201110.1155/2011/601986601986Exploring Online Synthesis for CGRAs with Specialized Operator SetsStefan Döbrich0Christian Hochberger1Chair for Embedded Systems, Dresden University of Technology, Nöthnitzer Straße 46, 01187 Dresden, GermanyChair for Embedded Systems, Dresden University of Technology, Nöthnitzer Straße 46, 01187 Dresden, GermanyThe design of energy-efficient systems has become a major challenge for engineers over the last decade. One way to save energy is to spread out computations in space rather than in time (as traditional processors do). Unfortunately, this requires to design specialized hardware for each application. Also, the nonrecurring expenses for the manufacturing of chips continuously grow. Implementing the computations on FPGAs and CGRAs solves this dilemma, as the non recurring expenses are shared between many different applications. We believe that online synthesis that takes place during the execution of an application is one way to broaden the applicability of reconfigurable architectures as no expert knowledge of synthesis and technologies is required. In this paper, we give a detailed analysis of the amount and specialization of resources in a CGRA that are required to grant a significant speedup of Java bytecode. In fact, we show that even a relatively small number of specialized reconfigurable resources is sufficient to speed up applications considerably. Particularly, we look at the number of dedicated multipliers and dividers. Also, we discuss the required number of concurrent memory access operations inside the CGRA. Again, it shows that two concurrent memory access operations are sufficient for almost all applications.http://dx.doi.org/10.1155/2011/601986 |
| spellingShingle | Stefan Döbrich Christian Hochberger Exploring Online Synthesis for CGRAs with Specialized Operator Sets International Journal of Reconfigurable Computing |
| title | Exploring Online Synthesis for CGRAs with Specialized Operator Sets |
| title_full | Exploring Online Synthesis for CGRAs with Specialized Operator Sets |
| title_fullStr | Exploring Online Synthesis for CGRAs with Specialized Operator Sets |
| title_full_unstemmed | Exploring Online Synthesis for CGRAs with Specialized Operator Sets |
| title_short | Exploring Online Synthesis for CGRAs with Specialized Operator Sets |
| title_sort | exploring online synthesis for cgras with specialized operator sets |
| url | http://dx.doi.org/10.1155/2011/601986 |
| work_keys_str_mv | AT stefandobrich exploringonlinesynthesisforcgraswithspecializedoperatorsets AT christianhochberger exploringonlinesynthesisforcgraswithspecializedoperatorsets |