Abstract. Synchronous Transfer Architecture (STA) is a coarse-grain reconfigurable hardware. It is modelled by using a common machine description that is suitable for both compiler and core generator. STA is a Very Long Instruction Word (VLIW) architecture and in addition it uses a non-orthogonal Instruction Set Architecture (ISA). Generating efficient code for such ISA needs highly optimizing techniques. This paper presents a basic data routing Integer Linear Programming (ILP) model for STA code generation. We will also show in this paper, the execution time of the assembly code can be dramatically reduced. The code generation can be accomplished in acceptable time and it can even be real time by reducing the degree of optimality.
he compiler tool Unison uses combinatorial optimisation to perform integrated register allocation an...
Given all its merits and potential, Reconfigurable Computing has attracted lots of research work. Re...
A common approach to enhance the performance of processors is to increase the number of function uni...
Static multi-issue machines, such as traditional Very Long Instructional Word (VLIW) architectures, ...
International audienceIn this paper, we present a constraint programming-based approach for optimiza...
The Synchronous Transfer Architecture is a low power architecture of VLIW processor, which enables t...
Widespread adoption of reconfigurable devices requires system level synthesis techniques to take an ...
As superscalar processors are becoming more and more complex due to dynamic scheduling of instructio...
This paper presents an adaptation of the list scheduling algorithm to generate code for processors o...
International audienceIn this paper, we introduce a constraint programming-based approach for optimi...
Abstract—We propose a new FPGA routing approach that, when combined with a low-cost architecture cha...
Abstract-The most creative step in synthesizing data paths executing software descriptions is the ha...
Data parallel programming provides a simple and powerful framework for designing parallel algorithms...
Silicon compilers are often used in conjunction with Field Programmable Gate Arrays (FPGAs) to deliv...
Abstract—As the logic capacity of field-programmable gate arrays (FPGAs) increases, they are increas...
he compiler tool Unison uses combinatorial optimisation to perform integrated register allocation an...
Given all its merits and potential, Reconfigurable Computing has attracted lots of research work. Re...
A common approach to enhance the performance of processors is to increase the number of function uni...
Static multi-issue machines, such as traditional Very Long Instructional Word (VLIW) architectures, ...
International audienceIn this paper, we present a constraint programming-based approach for optimiza...
The Synchronous Transfer Architecture is a low power architecture of VLIW processor, which enables t...
Widespread adoption of reconfigurable devices requires system level synthesis techniques to take an ...
As superscalar processors are becoming more and more complex due to dynamic scheduling of instructio...
This paper presents an adaptation of the list scheduling algorithm to generate code for processors o...
International audienceIn this paper, we introduce a constraint programming-based approach for optimi...
Abstract—We propose a new FPGA routing approach that, when combined with a low-cost architecture cha...
Abstract-The most creative step in synthesizing data paths executing software descriptions is the ha...
Data parallel programming provides a simple and powerful framework for designing parallel algorithms...
Silicon compilers are often used in conjunction with Field Programmable Gate Arrays (FPGAs) to deliv...
Abstract—As the logic capacity of field-programmable gate arrays (FPGAs) increases, they are increas...
he compiler tool Unison uses combinatorial optimisation to perform integrated register allocation an...
Given all its merits and potential, Reconfigurable Computing has attracted lots of research work. Re...
A common approach to enhance the performance of processors is to increase the number of function uni...