A highly parallel (more than a thousand) datapoW machine EM-4 is now under development. The EM-4 &sign principle is to construct a high performance computer using a compact architecture by overcoming several defects of dataflow machines. Constructing the EM-4, it is essential to fabricate a processing element (PE) on a sin-gle chip for reducing operation speed, system size, design complexhy and cost. In the EM-4. the PE. called EMC-R, has been specially designed using a 50,OOOgate gate array chip. This paper focuses on an architecture of the EMC-R. The distinctive features of it are: a strongly connected arc datafiow model; a direct matching scheme; a RISC-based design; a deadlock-free on-chip packet switch; and an integration of a pack...
International audienceEmbedded manycore architectures offer energy-efficient super-computing capabil...
International audienceThis paper presents an implementation of dataflow programs specified in RVC-CA...
This paper describes the evolution of dataflow computers from the first static design to the newest ...
EMC-Y is a new processing element for highly parallel computers designed to achieve high performance...
The architectural design and VLSi implementation of a highly reconfigurable dataflow RISC processing...
The primary objective of the proposed research is to define and evaluate an architecture for a compu...
We have implemented seven data-parallel primitives on the hybrid dataflow/von Neumann parallel compu...
In the last 15 years we have seen, as a response to power and thermal limits for current chip techno...
Abstract—System-on-the-chip can be defined as the integrated circuit (chip) which integrates all nec...
The objective of this work is to design a high performance dynamic dataflow processor for multiproce...
In the last 15 years we have seen, as a response to power and thermal limits for current chip techno...
Abstract—The path towards future high performance comput-ers requires architectures able to efficien...
International audienceEmbedded manycore architectures offer energy-efficient super-computing capabil...
International audienceEmbedded manycore architectures offer energy-efficient super-computing capabil...
International audienceThis paper presents an implementation of dataflow programs specified in RVC-CA...
This paper describes the evolution of dataflow computers from the first static design to the newest ...
EMC-Y is a new processing element for highly parallel computers designed to achieve high performance...
The architectural design and VLSi implementation of a highly reconfigurable dataflow RISC processing...
The primary objective of the proposed research is to define and evaluate an architecture for a compu...
We have implemented seven data-parallel primitives on the hybrid dataflow/von Neumann parallel compu...
In the last 15 years we have seen, as a response to power and thermal limits for current chip techno...
Abstract—System-on-the-chip can be defined as the integrated circuit (chip) which integrates all nec...
The objective of this work is to design a high performance dynamic dataflow processor for multiproce...
In the last 15 years we have seen, as a response to power and thermal limits for current chip techno...
Abstract—The path towards future high performance comput-ers requires architectures able to efficien...
International audienceEmbedded manycore architectures offer energy-efficient super-computing capabil...
International audienceEmbedded manycore architectures offer energy-efficient super-computing capabil...
International audienceThis paper presents an implementation of dataflow programs specified in RVC-CA...
This paper describes the evolution of dataflow computers from the first static design to the newest ...