Abstract:-In this paper an overview of the EU-FP6 "Smart Chips for Smart Surroundings" (4S) [7] project is given. The overall mission of the 4S project is to define and develop efficient (ultra low-power), flexible, reconfigurable core building blocks, including the supporting tools, for future ambient systems. Dynamic reconfiguration offers the flexibility and adaptability needed for future ambient devices, it provides the efficiency needed for these systems, it enables systems that can adapt to rapidly changing envi… Show more
“…10 Model of our multi-core reconfigurable processor [1] In this sub-section, we provide a brief overview of our multi-core reconfigurable processor 5 to the level of detail that is necessary to understand the experimental results. Our results (in comparison with Morpheus [14] and 4S [13]) show that our scheme is generic and is applicable to different kinds of multi-core reconfigurable processors. Fig.…”
Section: Experimental Results and Evaluationmentioning
confidence: 81%
“…However, state-of-the-art multi-core reconfigurable processors [1,13,14] do not exploit simultaneous multi-tasking (with both task-and instruction-level parallelism) at their full throttle, when considering the heterogeneous nature of fine-and coarse-grained reconfigurable fabrics and the scenarios of run-time varying task mapping, workload conditions, etc. Moreover, these processors lack efficient fabric allocation schemes that operate with consideration of simultaneous multi-tasking.…”
Section: Fig 1 Composition Of Applications and Accelerationmentioning
confidence: 99%
“…We implemented our scheme for KAHRIMSA [1] and compared the results with state-of-the-art multi-core reconfigurable processors (like 4S [13] and Morpheus [14]) and different task and functional block level fabric allocation policies. For a fair comparison, we have provided the same set of hardware accelerators and ISEs as well as the same amount of memory bandwidth and same input data for each comparison.…”
Section: Comparison To State-of-the-artmentioning
confidence: 99%
“…Fig. 12 shows the comparison to multi-core reconfigurable architectures like Morpheus [14] and 4S [13]. These architectures have already proposed solutions for mixed-grained fabric allocation to achieve adaptivity at the task level.…”
Section: Comparison To State-of-the-artmentioning
confidence: 99%
“…motion estimation or the actual encoding in case of a video encoder). Typically, reconfigurable architectures use Instruction Set Extensions (ISEs) to accelerate the kernels [1,13,14,22]. These ISEs consist of data-paths that may be reconfigured on parts of a fine-grained (FG) or a coarse-grained (CG) reconfigurable fabric [1,18].…”
We propose a novel scheme for run-time management of mixedgrained reconfigurable fabric for the purpose of simultaneous multi-tasking in multi-core reconfigurable processors. Traditionally, reconfigurable fabrics are allocated to distinct tasks in order to improve the overall performance without considering quality of service of the entire application (e.g. 30 fps in video conferencing application). We employ a new concept of task criticality that is based on performance constraints of each task at functional block level. Our scheme significantly reduces the number of deadline misses by dynamically evaluating the criticality of each task and performing an efficient load balancing of a mixed-grained reconfigurable fabric at run-time. We use a comprehensive video conferencing application as a benchmark to evaluate our scheme. Compared to the state-of-the-art our scheme reduces the number of deadline misses by 6x (on average) and improves the performance by 1.3x (on average).
“…10 Model of our multi-core reconfigurable processor [1] In this sub-section, we provide a brief overview of our multi-core reconfigurable processor 5 to the level of detail that is necessary to understand the experimental results. Our results (in comparison with Morpheus [14] and 4S [13]) show that our scheme is generic and is applicable to different kinds of multi-core reconfigurable processors. Fig.…”
Section: Experimental Results and Evaluationmentioning
confidence: 81%
“…However, state-of-the-art multi-core reconfigurable processors [1,13,14] do not exploit simultaneous multi-tasking (with both task-and instruction-level parallelism) at their full throttle, when considering the heterogeneous nature of fine-and coarse-grained reconfigurable fabrics and the scenarios of run-time varying task mapping, workload conditions, etc. Moreover, these processors lack efficient fabric allocation schemes that operate with consideration of simultaneous multi-tasking.…”
Section: Fig 1 Composition Of Applications and Accelerationmentioning
confidence: 99%
“…We implemented our scheme for KAHRIMSA [1] and compared the results with state-of-the-art multi-core reconfigurable processors (like 4S [13] and Morpheus [14]) and different task and functional block level fabric allocation policies. For a fair comparison, we have provided the same set of hardware accelerators and ISEs as well as the same amount of memory bandwidth and same input data for each comparison.…”
Section: Comparison To State-of-the-artmentioning
confidence: 99%
“…Fig. 12 shows the comparison to multi-core reconfigurable architectures like Morpheus [14] and 4S [13]. These architectures have already proposed solutions for mixed-grained fabric allocation to achieve adaptivity at the task level.…”
Section: Comparison To State-of-the-artmentioning
confidence: 99%
“…motion estimation or the actual encoding in case of a video encoder). Typically, reconfigurable architectures use Instruction Set Extensions (ISEs) to accelerate the kernels [1,13,14,22]. These ISEs consist of data-paths that may be reconfigured on parts of a fine-grained (FG) or a coarse-grained (CG) reconfigurable fabric [1,18].…”
We propose a novel scheme for run-time management of mixedgrained reconfigurable fabric for the purpose of simultaneous multi-tasking in multi-core reconfigurable processors. Traditionally, reconfigurable fabrics are allocated to distinct tasks in order to improve the overall performance without considering quality of service of the entire application (e.g. 30 fps in video conferencing application). We employ a new concept of task criticality that is based on performance constraints of each task at functional block level. Our scheme significantly reduces the number of deadline misses by dynamically evaluating the criticality of each task and performing an efficient load balancing of a mixed-grained reconfigurable fabric at run-time. We use a comprehensive video conferencing application as a benchmark to evaluate our scheme. Compared to the state-of-the-art our scheme reduces the number of deadline misses by 6x (on average) and improves the performance by 1.3x (on average).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.