Issues and approaches to coarse-grain reconfigurable architecture development

@article{Eguro2003IssuesAA,
  title={Issues and approaches to coarse-grain reconfigurable architecture development},
  author={Ken Eguro and Scott Hauck},
  journal={11th Annual IEEE Symposium on Field-Programmable Custom Computing Machines, 2003. FCCM 2003.},
  year={2003},
  pages={111-120}
}
  • Ken Eguro, S. Hauck
  • Published 9 April 2003
  • Computer Science
  • 11th Annual IEEE Symposium on Field-Programmable Custom Computing Machines, 2003. FCCM 2003.
Although domain-specialized FPGAs (field programmable gate arrays) can offer significant area, speed and power improvements over conventional reconfigurable devices, there are several unique and unexplored design problems that complicate their development. One source of these problems is that the designers often opt to replace more universal, fine-grain logic elements with a specialized set of coarse-grain functional units to improve computation speed and reduce routing complexity. One issue… 
Integrated Floorplanning, Module-Selection, and Architecture Generation for Reconfigurable Devices
TLDR
This paper investigates the appropriate mix and floorplan of heterogeneous elements: multipliers, RAMs, and lookup table (LUT)-based logic, in order to maximize the performance of a set of digital signal processing (DSP) benchmark applications, given a fixed silicon budget.
Totem : Domain-Specific Reconfigurable Logic
TLDR
The lessons learned from the Totem Project are presented, including how best to create domain-specific architectures, how to instantiate that logic into silicon, and how to create CAD tools to support these architectures.
Synthesis Techniques for Semi-Custom Dynamically Reconfigurable Superscalar Processors
TLDR
This dissertation evaluates the area requirements for reconfigurable processing, an important yet often disregarded assessment for partial reconfiguration, and shows that even though performance density decreases with processor complexity, the additional area still provides a positive contribution to the aggregate parallel processing performance.
A Novel Heuristic and Provable Bounds for Reconfigurable Architecture Design
TLDR
This paper provides quantifications of the optimal performance/area-enhancing capability of multipliers and RAM blocks within a system context, and indicates that only a minimal performance benefit can be achieved over Virtex II by re-organising the device floorplan, when using optimal technology mapping.
Generation and exploration of reconfigurable architectures using mathematical programming
TLDR
In this paper, the problem is cast as a formal optimisation, and may be solved using existing optimisation tools, and the approach is adapted into an heuristic for larger benchmark sets.
Reconfiguration Framework for Multi-kernel Embedded Applications
TLDR
This paper presents the policy, experiments, and performance results of customizing and reconfiguring actual hardware for embedded kernels implemented on Field-Programmable Gate Arrays (FPGAs), and shows substantial performance improvement compared to FIFO heuristics, without ignoring reconfiguration overheads.
Handling different computational granularity by a reconfigurable IC featuring embedded FPGAs and a network-on-chip
  • F. Lertora, M. Borgatti
  • Computer Science
    13th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM'05)
  • 2005
TLDR
A system-on-chip integrating a microprocessor, three embedded FPGA (eFPGA) and an eight port network- on-chip (NoC) is implemented in a 90nm CMOS technology to execute complex multimedia applications by the use of hardware accelerators mapped to a reconfigured platform based on a message-passing architecture.
Reconfigurable Systems for Cryptography and Multimedia Applications
TLDR
This chapter explores, evaluates, and analyze the performance of a reconfigurable hardware, namely MorphoSys, considering certain key applications targeted for such hardware (Hauck, 1998).
An efficient approach to hide the run-time reconfiguration from SW applications
TLDR
An efficient approach similar to the cache miss and the data replacement in modern computer system for the reconfiguration ofynamically reconfigurable logic can be correctly issued without extra instructions inserted either manually by SW application programmers or automatically by compilers.
...
...

References

SHOWING 1-10 OF 17 REFERENCES
Architecture design of reconfigurable pipelined datapaths
This paper examines reconfigurable pipelined datapaths (RaPiDs), a new architecture style for computation-intensive applications that bridges the cost/performance gap between general purpose and
RaPiD - Reconfigurable Pipelined Datapath
TLDR
RaPiD is presented, a new coarse-grained FPGA architecture that is optimized for highly repetitive, computation-intensive tasks that make much more efficient use of silicon than traditional FPGAs and also yield much higher performance for a wide range of applications.
The effect of LUT and cluster size on deep-submicron FPGA performance and density
TLDR
This paper revisits the field-programmable gate-array (FPGA) architectural issue of the effect of logic block functionality on FPGA performance and density, and experimentally determines the relationship between the number of inputs required for a cluster as a function of the LUT size and cluster size.
FPGA routing architecture: segmentation and buffering to optimize speed and density
TLDR
This work investigates the routing architecture of FPGAs by determining the best distribution of routing segment lengths and the best mix of pass transistor and tri-state buffer routing switches, and shows that it is best for FPGA routing segments to have lengths of 4 to 8 logic blocks.
VPR: A new packing, placement and routing tool for FPGA research
TLDR
In terms of minimizing routing area, VPR outperforms all published FPGA place and route tools to which the authors can compare and presents placement and routing results on a new set of circuits more typical of today's industrial designs.
MARS - a candidate cipher for AES
TLDR
MARS is designed to take advantage of the powerful operations supported in today’s computers, resulting in a much improved security/performance tradeoff over existing ciphers, and offers better security than triple DES while running significantly faster than single DES.
Twofish : A 128-bit block cipher
TLDR
The design of both the round function and the key schedule permits a wide variety of tradeoffs between speed, software size, key setup time, gate count, and memory.
Serpent: A Proposal for the Advanced Encryption Standard
TLDR
A new block cipher is proposed that uses S-boxes similar to those of DES in a new structure that simultaneously allows a more rapid avalanche, a more efficient bitslice implementation, and an easy analysis that enables it to be more secure than three-key triple-DES.
Status of the Advanced Encryption Standard (AES) Development Effort
TLDR
This paper presents some general topics that can be elaborated upon in greater detail at NISSC 1999, and discusses the selection of the AES candidate algorithm finalists.
AES Proposal : Rijndael
TLDR
The Inverse Cipher is implemented with an 8-bit and 32-bit processor, and the structure is derived from the Inverse of the Rijndael Cipher, which is based on the Tournaisian Cipher.
...
...