Application specific optimization of coarse-grained reconfigurable architecture by dynamic context compression

Coarse-grained reconfigurable architectures (CGRA) require many processing elements and a configuration memory unit (configuration cache) for reconfiguration of the ALU array elements. This structure consumes significant amount of power. Power reduction during reconfiguration is necessary for the reconfigurable architecture to be used as a competitive IP core in embedded systems. In this paper, we propose a power-conscious reusable context pipelining architecture for CGRA that efficiently reduces power consumption in configuration cache without performance degradation. Experimental results show that the proposed approach saves up to 57.97% of the total power consumed in the configuration cache with reduced configuration cache size compared to the previous approach.

Coarse Grained Reconfigurable Architectures (CGRAs) are emerging as enabling platforms to meet the high performance demanded by modern applications. Commonly, CGRAs are composed of a computation layer (that performs computations) and a memory layer (that provides data and config ware to the computation layer). Tempted by higher platform utilization and reliability, recently proposed CGRA soffer dynamic application remapping (for the computation layer). Distributed scratch pad (compiler programmed) memories offer high data rates, predictability and low the power consumption (compared to caches). Therefore, the distributed scratchpad memories are emerging as preferred implementation alternative for the memory layer in recent CGRAs. However, the scratchpad memories are programmed at compile time, and do not support dynamic application remapping. The existing solutions that allow dynamic application remapping either rely on fat binaries (that significantly enhance configuration memory requirements) or consider a centralized memory. To extract the benefits of both runtime remapping and distributed scratchpad memories, we present a design framework called DyMeP. DyMeP relies on late binding and provides the architectural support to dynamically remap data in CGRAs. Compared to the state of the art, the proposed technique reduces the configuration memory requirements (needed by fat binary solutions) and supports distributed shared scratchpad memory. Synthesis/Simulation results reveal that DyMeP promises a significant (up to 60%) reduction in config ware size at the cost of negligible additional overheads (less then 1%).

Energy efficient configuration unification and compression for CGRAs

One of the grand challenges in the design of portable/wearable electronics is to achieve optimal efficiency and flexibility in a tiny low power package. Coarse grained reconfigurable architectures (CGRAs) hold great promise for low power, high performance, and flexible designs for a domain of applications. CGRAs are very promising due to the ability to highly customize such architectures to an application domain. However, greater customization makes the mapping of applications onto these architectures very challenging. Good tools and fast, effective mapping algorithms are needed to support design space exploration for CGRAs. In particular, the mapping problem has been difficult to solve in a satisfying and general way. In this paper, we present an architectural design flow using crowdsourcing to provide mappings of benchmarks onto new architectures. We show that the crowd can provide high quality, reliable mappings, significantly outperforming our custom Simulated Annealing algorithm in almost all cases. We further show that the crowd can provide other types of feedback that are difficult to obtain from an automatic mapping algorithm. Our proof of concept cross-architectural study supports an 8Way or 4Way1Hop architecture as a top choice, concludes that a custom modification that constrains inputs and outputs consumes less energy but requires more area than its less constrained counterpart, and suggests that Stripe architectures are interesting to consider because they perform nearly as well as our mesh variants and may present a more straightforward mapping problem for the crowd or an automatic mapping algorithm.

Coarse-grained reconfigurable architectures (CGRAs) are gaining increasing attention as domain-specific accelerators due to their high flexibility and energy efficiency. These architectures offer a compelling solution for applications that require custom hardware performance while retaining a degree of programmability. However, the design space of CGRAs is inherently vast and complex, presenting significant challenges for architects to explore design choices efficiently and systematically. Existing design space exploration (DSE) methodologies for CGRAs are often time-demanding and struggle to deliver optimal solutions when confronted with high-dimensional and multi-objective design space. Therefore, we consider constructing a CGRA parameter tuning framework called MoDAF. MoDAF initializes the design space using the most representative and diverse samples. It adopts a divide-and-conquer approach, utilizing Monte Carlo Tree Search (MCTS) and space partitioning techniques to dynamically break down the complex design space into more manageable subspaces. A hybrid model handles local fluctuations within each subspace, while a dual sampling algorithm is designed to increase sampling efficiency. MoDAF also incorporates a fast evaluation model to estimate CGRA throughput and area, significantly speeding up the exploration process. Compared with previous approaches, experiments show that our proposed framework reduces the average distance from the reference set by 53.0% and the hypervolume deviation by 64.2%, while also cutting wall time by 57.5%.

Coarse-grained reconfigurable architectures (CGRAs) are increasingly employed as domain-specific accelerators due to their efficiency and flexibility. However, the existing CGRA architectures suffer from low hardware resource utilization and performance due to the limitations of the scheduling scheme. In this article, an adaptive scheduler (denoted as DPTM) for concurrent and multi-task interleaved pipelining-oriented CGRA is introduced, which exploits timeslot matching and release methods to avoid the pipeline conflicts and improve the scheduling performance. The characteristics of task scheduling based on directed acyclic graph (DAG) are analyzed, and several performance-influencing factors are extracted to build a scheduling performance model for reducing the time cost of scheduling and guiding the design of scheduling schemes. Moreover, the scoreboard method of dynamic instruction schedulers is optimized to control the entry time of multiple tasks into the pipeline, and then a timeslot matching method is proposed to provide non-conflict pipelining for the multiple tasks. Further, a timeslot release method is presented to release the timeslots for unscheduled sub-tasks dynamically, which can adapt the parallel processing of multiple tasks and decrease the scheduling time. Then, an adaptive scheduling scheme combines the dynamic priority-based task assignment method, timeslot matching method, and timeslot release method to schedule massive tasks for CGRA. Finally, the overall architecture of DPTM is introduced and designed to validate the efficacy of the proposed scheduling scheme. Experimental results show that the proposed timeslot matching/release approach reduces 84% total scheduling time and decreases 40% average scheduling time at most compared to the non-timeslot-matching scheduling schemes, the proposed task assignment approach decreases 8% total scheduling time and lowers 3% average scheduling time compared to the existing approaches, and the proposed scheduler decreases 51% critical path delay, lowers 35% area overhead, and reduces 12% power consumption at most compared with the existing schedulers.

Coarse-grained reconfigurable architecture (CGRA) is a promising accelerator design choice due to its high performance and power efficiency in the computation or data-intensive application domains, such as security, multimedia, digital signal processing, machine learning, and high-performance computing. CGRA consists of coarse-grained processing elements (PEs) and interconnects that determine the architecture flexibility to support different applications and also affect the performance and power efficiency significantly. Although multiple types of interconnects have been proposed, a parameterized unified model is still lacking. In this paper, we propose a flexible and scalable CGRA template with a novel interconnect model that can unify the typical neighbor-to-neighbor, switch-based, and FPGA-like interconnects. Furthermore, we present TRAM, an open-source template-based reconfigurable architecture modeling framework that integrates the Chisel-based CGRA modeling, architecture intermediate representation (IR) and Verilog generation, dataflow graph (DFG) mapping, simulation, and evaluation. The mapping flow contains graph-based placement and routing, critical-path-driven data synchronization, and simulated-annealing-based optimization. We evaluate the impacts of the rich design parameters, which demonstrate the significance of such a flexible template to facilitate architecture optimization. Compared with the related work, TRAM can achieve a 4.1× smaller DFG latency and a faster mapping speed for both the 8×8 and 16×16 CGRAs. Moreover, TRAM is able to attain an extremely high PE utilization of 94.4 % on average by architecture tuning.

Design of a coarse-grained reconfigurable architecture with floating-point support and comparative study

Coarse-grained reconfigurable architecture (CGRA) is a promising parallel computing platform that provides high performance, high power efficiency and flexibility. However, for imperfect nested loops, the existing loop mapping methods often result in low execution performance and poor hardware utilization. To tackle this problem, this paper makes three contributions: 1) a highly effective and general approach to map imperfect loops on CGRA; 2) a global optimization strategy to search the optimal initiation intervals (IIs); 3) a powerful kernel compression method to reduce the oversized kernel. Experiment results show that our approach can reduce the total computing latency by 20.5, 58.5 and 73.2 percent compared to the state-of-the-art approaches on $2 \times 2$ , $4 \times 4$ and $8 \times 8$ CGRA respectively. Moreover, the compilation time and configuration context size is acceptable in practice.

Coarse-grained reconfigurable architectures aim to achieve goals of both high performance and flexibility. However, existing reconfigurable array architectures require many resources without considering the specific application domain. Functional resources that take long latency and/or large area can be pipelined and/or shared among the processing elements. Therefore, the hardware cost and the delay can be effectively reduced without any performance degradation for some application domains. We suggest such a reconfigurable array architecture template and a design space exploration flow for domain-specific optimization. Experimental results show that our approach is much more efficient, in both performance and area, compared to existing reconfigurable architectures.

Coarse-grained reconfigurable array architectures have drawn increasing attention due to their performance and flexibility. A typical coarse-grained reconfigurable array architecture has many PEs in the array, which is suitable for implementing spatial redundancy used for fault-tolerant systems design. In this paper, we propose to implement replications and a voting function on the PE array of a coarse-grained reconfigurable array architecture to design a fault-tolerant system. We also introduce thermal-aware application mapping onto the coarse-grained reconfigurable array architecture for reliability. The experiment with Viterbi decoder shows that our approach enables implementing fault-tolerance with 12% area overhead which comes from implementing conditional execution.

Similar to programmable devices such as processors or micro controllers, reconfigurable logic devices can also be built as software, by programming the configuration of the device. In this paper, we present an overview of constraints which have to be considered when mapping applications to coarse-grained reconfigurable architectures. The application areas of most of these architectures address computational-intensive algorithms like video and audio processing or wireless communication. Therefore, reconfigurable arrays are in direct competition with DSP processors which are traditionally used for digital signal processing. Hence, existing mapping methodologies are closely related to approaches from the DSP world. They try to employ pipelining and temporal partitioning but they do not exploit the full parallelism of a given algorithm and the computational potential of typically 2D arrays. We present a first case study for mapping regular algorithms onto reconfigurable arrays by using our design methodology which is characterized by loop parallelization in the polytope model. The case study shows that our regular mapping methodology may lead to highly efficient implementations taking the constraints of the architecture into account.

In this paper, we focus on low power design at the architecture level and propose a new architecture, called sentry tag, for reducing the on-chip cache power consumption in processors. The many unnecessary activities in the conventional cache-access process motivate our proposal. By pre-comparing the sentry bit of the access address with the sentry tag before starting a normal cache access, we can filter out and eliminate most unnecessary activities. Thus the power consumption can be effectively reduced. Our method is valuable for both a conventional cache with parallel access and a phased cache with serial access. We used SimpleScalar, a trace-driven simulator, to evaluate the performance of our proposed architecture. Compared to a conventional cache, experimental results from SPEC95 benchmarks show that the additional sentry tag can reduce many unnecessary activities (and hence the power consumption), while the hardware overhead is insignificant. For example, an 8-KB, 4-way data cache with two-bit sentry tag can improve the power consumption by 35% compared to a conventional set-associative cache. The maximum power saving achieved using this architecture depends on the cache configuration, which suggests that the proposed sentry tag is a viable choice for data caches with higher associativity.

Coarse-grained reconfigurable architecture (CGRA) based embedded system aims at achieving high system performance with sufficient flexibility to map variety of applications. However, significant area and power consumption in the arrays prohibits its competitive advantage to be used as a processing core. In this work, we propose hierarchical reconfigurable computing array architecture to reduce power/area and enhance performance in configurable embedded system. The CGRA-based embedded systems that consist of hierarchical configurable computing arrays with varying size and communication speed were examined for multimedia and other applications. Experimental results show that the proposed approach reduces on-chip area by 22%, execution time by up to 72% and reduces power consumption by up to 55% when compared with the conventional CGRA-based architectures.

This paper presents a novel architecture design to optimize the reconfiguration process of a coarse-grained reconfigurable architecture (CGRA) called Reconfigurable Multimedia System II (REMUS-II). In REMUS-II, the tasks in multi-media applications are divided into two parts: computing-intensive tasks and control-intensive tasks. Two Reconfigurable Processor Units (RPUs) for accelerating computing-intensive tasks and a Micro-Processor Unit (µPU) for accelerating control-intensive tasks are contained in REMUS-II. As a large-scale CGRA, REMUS-II can provide satisfying solutions in terms of both efficiency and flexibility. This feature makes REMUS-II well-suited for video processing, where higher flexibility requirements are posed and a lot of computation tasks are involved. To meet the high requirement of the dynamic reconfiguration performance for multimedia applications, the reconfiguration architecture of REMUS-II should be well designed. To optimize the reconfiguration architecture of REMUS-II, a hierarchical configuration storage structure and a 3-stage reconfiguration processing structure are proposed. Furthermore, several optimization methods for configuration reusing are also introduced, to further improve the performance of reconfiguration process. The optimization methods include two aspects: the multi-target reconfiguration method and the configuration caching strategies. Experimental results showed that, with the reconfiguration architecture proposed, the performance of reconfiguration process will be improved by 4 times. Based on RTL simulation, REMUS-II can support the 1080p@32fps of H.264 HiP@Level4 and 1080p@40fps High-level MPEG-2 stream decoding at the clock frequency of 200MHz. The proposed REMUS-II system has been implemented on a TSMC 65nm process. The die size is 23.7mm2 and the estimated on-chip dynamic power is 620mW.