Designing coarse-grain reconfigurable architectures by inlining flexibility into custom arithmetic data-paths

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.

This paper presents a method to time share the Processing Elements (PEs) of Runtime Coarse Grain Reconfigurable Architectures (CGRA) among multiple processes being executed concurrently onto the same CGRA. Runtime CGRA architectures time-multiplex the data path, creating a set of contexts for each state. These contexts configure the PEs and the routing resources of the CGRA and are typically loaded every clock cycle. The target architecture in this work is a commercial CGRA IP which is embedded as an IP into complex SoCs. Our proposed method analyzes the PE utilization in each context for multi-process systems running concurrently onto the same CGRA and time shares unused PEs assigned to one process with the other processes running in parallel. Our method reduces the total PE usage and hence the size of the CGRA IP and therefore the cost of the SoC. Results show that our method is extremely efficient and can reduce the PE utilization by up to 20% and on average by 14% and is only 2% worse than the optimal solution, while being much faster.

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 consumption in Digital Signal Processing (DSP) application is a vital parameter of consideration. Mostly DSP applications deplete power. Battery constraint is important in many mobiles, processors, and sensor-related devices. The major critical operations in DSP architecture are multiplication and addition. Multiplication process is performed using repetitive addition. Hence, adder is the basic component used in digital signal processor. DSP architecture is proposed with the energy-efficient goal. Traditional carry select adder contains ripple carry adder block is replaced by parallel prefix adder. By replacing that block and introducing folded tree, we can reduce power used by DSP processors. This architecture can be used in all power constrained DSP applications. In the existing system, folded tree is used in architecture to reduce the number of processing elements, and they used carry look-ahead adder to perform the internal processing element operations. In the proposed system, carry look-ahead adder is replaced by LFA and PA to harness the energy depleted in an application (e.g., DSP application). Power consumption is reduced by 12–15% as compared with the existing algorithms using Cyclone III (EP3C16F484C6).

Finite Impulse Response (FIR) Filter occupied a significant position in most of Digital Signal Processing (DSP) Applications. The behaviour of FIR filters can be realized in software for DSP applications and executed on Digital Signal Processor architectures. These kinds of digital filters consider digital components, digital input and perform mathematical computations to produce digital output. In modern DSP applications demanding area efficient architecture for DSP algorithms while optimizing throughput. This can be achieved by design of hardware architectures for DSP algorithms and apply design optimization techniques to accelerate the throughput and minimize area. This article attempts to develop hardware architectures for FIR Filter and apply the design optimization techniques present in literature. In this article, High Level Synthesis concepts were adapted to develop hardware architecture for FIR filter and optimization techniques have been applied to optimize design attributes like area, throughput and power. Finally, design attributes are summarized after applying optimization techniques and published significant architectural attributes suitable for real life DSP applications.

Coarse-grained reconfigurable architectures (CGRAs) are increasingly employed as domain-specific accelerators due to their efficiency and flexibility. A CGRA typically relies on compilers to perform task scheduling. The longstanding problem of static scheduling is that it suffers from insufficient parallelism in handling irregularities due to over-serialization and workload imbalance, which leads to severe resource underutilization and performance loss. To counteract the limitations of static scheduling in CGRAs, it is essential to exploit dynamic parallelism automatically and manage hardware resources adaptively. However, existing dynamic scheduling mechanisms, e.g., work stealing, often reschedule aggressively for instant performance but sacrifice efficiency, which is unfavorable to CGRAs that emphasize efficiency and fewer reconfigurations. This article proposes an elastic task scheduling scheme that enables lightweight dynamic scheduling in CGRAs. Tasks are rescheduled at runtime according to the classic tagged-token dataflow paradigm to enable dynamic task-level parallelism. Meanwhile, tasks are dynamically resized according to run-time throughputs via duplication, combination, and substitution operators for balanced multitask execution. We implement the elastic task scheduling scheme on a well-known reconfigurable architecture - triggered instruction architecture (TIA). Evaluation on the MachSuite benchmarks shows that the proposed scheme is effective in improving performance and energy efficiency. The average speedup is 2× over the baseline. Also, our design attains a 57 percent improvement in the area-normalized performance and a 49 percent better energy efficiency. Compared with a state-of-the-art dynamic scheduling method, our scheme achieves 1.6× speedup and 1.6× energy efficiency than work-stealing mechanism on the same substrate.

In this paper, a general visualization tool for coarse-grained reconfigurable architecture (CGRA) modeling is introduced. Recently, the increasing requirement for efficient and flexible architectures has significantly boosted the interests in CGRA. However, not too much attention has been paid to visualization tools for the development of CGRAs. This paper contains two main parts of contribution. Firstly, the CGRAs are built with a high level modeling language called FDL. Secondly, a user interface which could present all the information in the FDL model is obtained. Furthermore, the generated configuration bit stream helps to build routing paths on the interface.

The rapid increase in digital signal processing (DSP) applications has generated a strong demand for electrical engineers with DSP backgrounds; however, the gap between industry needs and university curricula still exists. To answer this challenge, a sequence of innovative DSP courses that emphasize hands-on experiments and practical applications were developed for continuing education in electrical and computer engineering. These courses are taught in the evening for night-school students having at least three years of work experience. These courses enable students to experiment with sophisticated DSP applications to augment the theoretical, conceptual, and analytical materials provided in traditional DSP courses. The inclusion of both software and hardware developments allows students to undertake a wide range of DSP projects for real-world applications. Assessment data concludes that the digital signal processor fundamentals course can increase learning interest and overcome the prerequisite problem of DSP laboratory experiments. This paper also briefly introduces representative examples of some challenging DSP applications.

Coarse Grained Reconfigurable Architectures (CGRAs) are emerging as enabling platforms to meet the high performance demanded by modern applications (e.g. 4G, CDMA, etc.). Recently proposed CGRAs offer runtime parallelism to reduce energy consumption (by lowering voltage/frequency). To implement the runtime parallelism, CGRAs commonly store multiple compile-time generated implementations of an application (with different degree of parallelism) and select the optimal version at runtime. However, the compile-time binding incurs excessive configuration memory overheads and/or is unable to parallelize an application even when sufficient resources are available. As a solution to this problem, we propose Transformation based dynamic Parallelism (TransPar). TransPar stores only a single implementation and applies a series for transformations to generate the bitstream for the parallel version. In addition, it also allows to displace and/or rotate an application to parallelize in resource constrained scenarios. By storing only a single implementation, TransPar offers significant reductions in configuration memory requirements (up to 73% for the tested applications), compared to state of the art compaction techniques. Simulation and synthesis results, using real applications, reveal that the additional flexibility allows up to 33% energy reduction compared to static memory based parallelism techniques. Gate level analysis reveals that TransPar incurs negligible silicon (0.2% of the platform) and timing (6 additional cycles per application) penalty.

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.

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.

The aim of this contribution is first to show how the Szego theory of orthogonal polynomials on the unit circle is intimately related to the celebrated Levinson algorithm, which is commonly used in digital signal processing (DSP) applications to solve various least-squares problems. A computationally more efficient substitute for the Levinson algorithm, termed the split Levinson algorithm, has recently been proposed in the DSP literature. In the case of real data, this new algorithm can be interpreted naturally in the framework of a well-defined one-to-one correspondence between the families of real Szego polynomials and the families of polynomials orthogonal on the interval [-1, 1] with respect to a symmetric measure. More generally, the philosophy underlying the split Levinson algorithm opens the door to an interesting “tridiagonal approach” to the theory of complex Szego polynomials, nonnegative definite Hermitian Toeplitz matrices, and related algebraic and function theoretic questions. Some of the main topics of this new mathematical framework are briefly reviewed and are shown on specific examples to be of particular interest in DSP applications.

It is very important to design a good routing-system for the whole compile-synthesis system of reconfigurable architecture (RA). Because the routing resources of coarse-grain RA (CGRA) are less than those of fine-grain RA, and several functions are often defined in same one element of RA, it is difficult to find a good route. Therefore, it is more important for routing-algorithm of CGRA to have stronger ability of finding feasible and optimum path. In the paper, the improved max—min Ant System (MMAS) that added the ability of smell for ant is applied for the routing problem of CGRA. By several benchmarks on CTaiJi that is a new developed CGRA, The improved MMAS shows better ability to find the best solution than PathFinder that is often used now.KeywordsConnected GraphField Programmable Gate ArrayOptimum PathPheromone TrailRout ProblemThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

The fast evolving applications in modern digital signal processing have an increasing demand for components which have high computational power and energy efficiency without compromising the flexibility. Embedded FPGA, which is the customized FPGA with heterogeneous fine-grained application specific operations and routing resources, has shown significantly improved efficiency in terms of throughput, power dissipation and chip area for the target application domain. On the other hand, the complexity of such architecture makes it difficult to perform an efficient architecture exploration and application synthesis without tool support. In this work, we propose a framework for the design of embedded FPGA (eFPGA) architectures, which is extended from an existing framework for Coarse-Grained Reconfigurable Architectures (CGRAs). The framework is composed of a high-level modeling formalism for eFPGAs to explore the mapping space, and a retargetable application synthesis flow. To enable fast design space exploration, a force-directed placement algorithm is proposed. Finally, we demonstrate the efficacy of this framework with demanding application kernels.

Multiplication is an important fundamental function in arithmetic operations. Multiplication-based operations such as Multiply and Accumulate(MAC) and inner product are among some of the frequently used computation Intensive Arithmetic Functions(CIAF) currently implemented in many Digital Signal Processing (DSP) applications such as convolution, Fast Fourier Transform(FFT), filtering and in microprocessors m its arithmetic and logic unit. Since multiplication dominates the execution tune of most DSP algorithms, so there is a need of high speed multiplier. Currently, multiplication time is still the dominant factor in determining the instruction cycle time of a DSP chip. The demand for high speed processing has been increasing as a result of expanding computer and signal processing applications. Higher throughput arithmetic operations are important to achieve the desired performance in many real-time signal and image processing applications . One of the key arithmetic operations in such applications is multiplication and the development of fast multiplier circuit has been a subject of interest over decades. Multiplier based on Vedic Mathematics is one of the fast and low power multiplier. Employing this technique in the computation algorithms will reduce the complexity, execution time, power etc. This vedic based multiplier is compared with binary multiplier(partial products method).