21 April 2020 in IEEE Transactions on Parallel and Distributed Systems
Coarse-Grained Reconfigurable Architectures (CGRA) is a promising solution for accelerating computation intensive tasks due to its good trade-off in energy efficiency and flexibility. One of the challenging research topic is how to effectively deploy loops onto CGRAs within acceptable compilation time. Modulo scheduling (MS) has shown to be efficient on deploying loops onto CGRAs. Existing CGRA MS algorithms still suffer from mapping loop with higher performance under acceptable compilation time, especially mapping large and irregular loops onto CGRAs with limited computational and routing resources. This is mainly due to the under utilization of the available buffer resources on CGRA, unawareness of critical mapping constraints and time consuming method of solving temporal and spatial mapping. This paper focus on improving the performance and compilation robustness of the modulo scheduling mapping algorithm for CGRAs. We decomposes the CGRA MS problem into the temporal and spatial mapping problem and reorganize the processes inside these two problems. For the temporal mapping problem, we provide a comprehensive and systematic mapping flow that includes a powerful buffer allocation algorithm, and efficient interconnection & computational constraints solving algorithms. For the spatial mapping problem, we develop a fast and stable spatial mapping algorithm with backtracking and reordering mechanism. Our MS mapping algorithm is able to map loops onto CGRA with higher performance and faster compilation time. Experiment results show that given the same compilation time budget, our mapping algorithm generates higher compilation success rate. Among the successfully compiled loops, our approach can improve 5.4% to 14.2% performance and takes x24 to x1099 less compilation time in average comparing with state-of-the-art CGRA mapping algorithms.
23 March 2020 in IEEE Transactions on Circuits and Systems I: Regular Papers
Carbon nanotube field effect transistor (CN-MOSFET) is attractive for the realization of future monolithic three-dimensional (M3D) memory circuits with ultra-high integration density, capacity, efficiency, and speed. However, the yield of each vertically-stacked active layer can be significantly degraded by the presence of metallic carbon nanotubes (m-CNs) caused by process imperfections. The potential integration density benefits of M3D circuits also may not be fully realized by the large area skews between different layers within standard cells. In this paper, ultra-high density and robust M3D static random-access memory (SRAM) cells are proposed for tolerance to the removal of m-CNs. By minimizing the skew and area of each device layer, the 16Kibit memory arrays with the proposed SRAM cells enhance the integration density by up to 82.92% as compared to the carbon-based traditional 2D and previously published M3D memory arrays. While achieving high functional yield and maintaining robust read/write operations, the proposed SRAM circuits enhance the overall electrical quality by up to 27.41x as compared to the alternative 2D and M3D memory arrays.
30 March 2023 in Journal of Computer Science and Technology