Abstract-FPGAs, (Field-Programmable Gate Arrays) are often used for embedded image processing applications. Parallelism, and in particular pipelining, is the most suitable architecture for supporting the required high throughput. Although pipelining is a well known technique for hardware design and is simple to describe, our experience has been that people have many problems implementing working pipelines, especially for multiphase designs. Existing hardware description languages force developers to design pipelines as a special case of parallel architecture, which makes it difficult to ensure that the pipeline has internally consistent timing. This is especially problematic in multiphase pipelines. This paper shows how many of these proble...
Accommodating the uncertain latency of load instructions is one of the most vexing problems in in-or...
Pipeline parallelism organizes a parallel program as a linear sequence of stages. Each stage process...
Many problems currently require more processor throughput than can be achieved with current single-p...
Reconfigurable systems, and in particular, FPGA-based custom computing machines, offer a unique oppo...
Pipeline parallelism organizes a parallel program as a linear se-quence of s stages. Each stage proc...
Abstract — Multiprocessors on a chip are the reality of these days. Semiconductor industry has recog...
In this paper, we present an automated flow for insertion of pipeline stages in FPGA-based streaming...
. Pipeline morphing is a simple but effective technique for reconfiguring pipelined FPGA designs at ...
In this work the pipeline theory applied to computing systems is reviewed. The effects of the stage ...
This paper introduces a new methodology for pipeline synthesis with applications to data flow high-l...
This paper presents a clocking pipeline technique referred to as a single-pulse pipeline (PP-Pipelin...
Sequences of data-dependent tasks, each one traversing large data sets, exist in many applications (...
This paper introduces a new methodology for pipeline synthesis with applications to data flow high-l...
Pipelining is a technique of decomposing a sequential process into sub-operations, with each sub pro...
Data-driven array architectures seem to be important alternatives for coarse-grained reconfigurable ...
Accommodating the uncertain latency of load instructions is one of the most vexing problems in in-or...
Pipeline parallelism organizes a parallel program as a linear sequence of stages. Each stage process...
Many problems currently require more processor throughput than can be achieved with current single-p...
Reconfigurable systems, and in particular, FPGA-based custom computing machines, offer a unique oppo...
Pipeline parallelism organizes a parallel program as a linear se-quence of s stages. Each stage proc...
Abstract — Multiprocessors on a chip are the reality of these days. Semiconductor industry has recog...
In this paper, we present an automated flow for insertion of pipeline stages in FPGA-based streaming...
. Pipeline morphing is a simple but effective technique for reconfiguring pipelined FPGA designs at ...
In this work the pipeline theory applied to computing systems is reviewed. The effects of the stage ...
This paper introduces a new methodology for pipeline synthesis with applications to data flow high-l...
This paper presents a clocking pipeline technique referred to as a single-pulse pipeline (PP-Pipelin...
Sequences of data-dependent tasks, each one traversing large data sets, exist in many applications (...
This paper introduces a new methodology for pipeline synthesis with applications to data flow high-l...
Pipelining is a technique of decomposing a sequential process into sub-operations, with each sub pro...
Data-driven array architectures seem to be important alternatives for coarse-grained reconfigurable ...
Accommodating the uncertain latency of load instructions is one of the most vexing problems in in-or...
Pipeline parallelism organizes a parallel program as a linear sequence of stages. Each stage process...
Many problems currently require more processor throughput than can be achieved with current single-p...