Search

Over the past few years, the explosion in sparse tensor algebra workloads has led to a corresponding rise in domain-specific accelerators to service them. Due to the irregularity present in sparse tensors, these accelerators employ a wide variety of novel solutions to achieve good performance. At the same time, prior work on design-flexible sparse accelerator modeling does not express this full range of design features, making it difficult to understand the impact of each design choice and compare or extend the state-of-the-art.To address this, we propose TeAAL: a language and simulator generator for the concise and precise specification and evaluation of sparse tensor algebra accelerators. We use TeAAL to represent and evaluate four disparate state-of-the-art accelerators—ExTensor, Gamma, OuterSPACE, and SIGMA—and verify that it reproduces their performance with high accuracy. Finally, we demonstrate the potential of TeAAL as a tool for designing new accelerators by showing how it can be used to speed up vertex-centric programming accelerators—achieving 1.9 × on BFS and 1.2 × on SSSP over GraphDynS.

Large language models (LLMs) have emerged and presented their general problem-solving capabilities with one model. However, the model size has increased dramatically with billions of parameters to enable such broad problem-solving capabilities. In addition, due to the dominance of matrix-matrix and matrix-vector multiplications in LLMs, the compute-to-model size ratio is significantly lower than that of CNNs. This shift pushes LLMs from a computation-bound regime to a memory-bound regime. Therefore, optimizing the memory footprint and traffic is an important optimization direction for LLMs today. Model compression methods such as quantization and parameter pruning have been actively explored for achieving the memory footprint and traffic optimization. However, the accuracy-efficiency trade-off of rank pruning for LLMs is not well-understood yet. Therefore, we characterize the accuracy-efficiency trade-off of a low-rank decomposition method, specifically Tucker decomposition, on recent language models, including an open-source LLM, Llama 2. We formalize the low-rank decomposition design space and show that the decomposition design space is enormous (e.g., O($2^{37}$) for Llama2-7B). To navigate such a vast design space, we formulate the design space and perform thorough case studies of accuracy-efficiency trade-offs using six widely used LLM benchmarks on BERT and Llama 2 models. Our results show that we can achieve a 9\% model size reduction with minimal accuracy drops, which range from 4\%p to 10\%p, depending on the difficulty of the benchmark, without any retraining to recover accuracy after decomposition. The results show that low-rank decomposition can be a promising direction for LLM-based applications that require real-time service in scale (e.g., AI agent assist and real-time coding assistant), where the latency is as important as the model accuracy.

Sparse tensor algorithms are becoming widespread, particularly in the domains of deep learning, graph and data analytics, and scientific computing. Current high-performance broad-domain architectures, such as GPUs, often suffer memory system inefficiencies by moving too much data or moving it too far through the memory hierarchy. To increase performance and efficiency, proposed domain-specific accelerators tailor their architectures to the data needs of a narrow application domain, but as a result cannot be applied to a wide range of algorithms or applications that contain a mix of sparse and dense algorithms. This paper proposes Symphony, a hybrid programmable/specialized architecture which focuses on the orchestration of data throughout the memory hierarchy to simultaneously reduce the movement of unnecessary data and data movement distances. Key elements of the Symphony architecture include (1) specialized reconfigurable units aimed not only at roofline floating-point computations, but at supporting data orchestration features such as address generation, data filtering, and sparse metadata processing; and (2) distribution of computation resources (both programmable and specialized) throughout the on-chip memory hierarchy. We demonstrate that Symphony can match non-programmable ASIC performance on sparse tensor algebra, and provide 31× improved runtime and 44× improved energy over a comparably provisioned GPU for these applications.

Sparsity is a growing trend in modern DNN models. Existing Sparse-Sparse Matrix Multiplication (SpMSpM) accelerators are tailored to a particular SpMSpM dataflow (i.e., Inner Product, Outer Product or Gustavsons), that determines their overall efficiency. We demonstrate that this static decision inherently results in a suboptimal dynamic solution. This is because different SpMSpM kernels show varying features (i.e., dimensions, sparsity pattern, sparsity degree), which makes each dataflow better suited to different data sets. In this work we present Flexagon, the first SpMSpM reconfigurable accelerator that is capable of performing SpMSpM computation by using the particular dataflow that best matches each case. Flexagon accelerator is based on a novel Merger-Reduction Network (MRN) that unifies the concept of reducing and merging in the same substrate, increasing efficiency. Additionally, Flexagon also includes a 3-tier memory hierarchy, specifically tailored to the different access characteristics of the input and output compressed matrices. Using detailed cycle-level simulation of contemporary DNN models from a variety of application domains, we show that Flexagon achieves average performance benefits of 4.59x, 1.71x, and 1.35x with respect to the state-of-the-art SIGMA-like, Sparch-like and GAMMA-like accelerators (265% , 67% and 18%, respectively, in terms of average performance/area efficiency)., Comment: To appear on ASPLOS 2023

Over the past few years, the explosion in sparse tensor algebra workloads has led to a corresponding rise in domain-specific accelerators to service them. Due to the irregularity present in sparse tensors, these accelerators employ a wide variety of novel solutions to achieve good performance. At the same time, prior work on design-flexible sparse accelerator modeling does not express this full range of design features, making it difficult to understand the impact of each design choice and compare or extend the state-of-the-art. To address this, we propose TeAAL: a language and simulator generator for the concise and precise specification and evaluation of sparse tensor algebra accelerators. We use TeAAL to represent and evaluate four disparate state-of-the-art accelerators -- ExTensor, Gamma, OuterSPACE, and SIGMA -- and verify that it reproduces their performance with high accuracy. Finally, we demonstrate the potential of TeAAL as a tool for designing new accelerators by showing how it can be used to speed up vertex-centric programming accelerators -- achieving $1.9\times$ on BFS and $1.2\times$ on SSSP over GraphDynS., Comment: 17 pages, 13 figures

HPC applications are critical in various scientific domains ranging from molecular dynamics to chemistry to fluid dynamics. Conjugate Gradient (CG) is a popular application kernel used in iterative linear HPC solvers and has applications in numerous scientific domains. However, the HPCG benchmark shows that the peformance achieved by Top500 HPC systems on CG is a small fraction of the performance achieved on Linpack. While CG applications have significant portions of computations that are dense and sparse matrix multiplications, skewed SpMMs/GEMMs in the HPC solvers have poor arithmetic intensities which makes their execution highly memory bound unlike GEMMs in DNNs which have high arithmetic intensity. The problem of low intensity individual skewed GEMMs also exists in various emerging workloads from other domains like Graph Neural Networks, Transformers etc. In this work we identify various reuse opportunities between the tensors in these solver applications to extract reuse in the entire Directed Acyclic Graph of the tensor operations rather than individual tensor operations. These opportunities essentially depend on the dimensions of the tensors and the structure of the tensor dependency graph. We propose a systematic methodology to determine various kinds of reuse opportunities in the graph of operations and determine the loop order and tiling in the interdependent operations. As a result, we propose a novel mapping strategy GOGETA that improves reuse of HPC applications on spatial accelerators. We also propose a data organization strategy in the buffer. Our mapping achieves geomean 6.7x reduction in memory accesses.

The design of DNN accelerators includes two key parts: HW resource configuration and mapping strategy. Intensive research has been conducted to optimize each of them independently. Unfortunately, optimizing for both together is extremely challenging due to the extremely large cross-coupled search space. To address this, in this paper, we propose a HW-Mapping co-optimization framework, an efficient encoding of the immense design space constructed by HW and Mapping, and a domain-aware genetic algorithm, named DiGamma, with specialized operators for improving search efficiency. We evaluate DiGamma with seven popular DNNs models with different properties. Our evaluations show DiGamma can achieve (geomean) 3.0x and 10.0x speedup, comparing to the best-performing baseline optimization algorithms, in edge and cloud settings.

Recently, numerous sparse hardware accelerators for Deep Neural Networks (DNNs), Graph Neural Networks (GNNs), and scientific computing applications have been proposed. A common characteristic among all of these accelerators is that they target tensor algebra (typically matrix multiplications); yet dozens of new accelerators are proposed for every new application. The motivation is that the size and sparsity of the workloads heavily influence which architecture is best for memory and computation efficiency. To satisfy the growing demand of efficient computations across a spectrum of workloads on large data centers, we propose deploying a flexible 'heterogeneous' accelerator, which contains many 'sub-accelerators' (smaller specialized accelerators) working together. To this end, we propose: (1) HARD TACO, a quick and productive C++ to RTL design flow to generate many types of sub-accelerators for sparse and dense computations for fair design-space exploration, (2) AESPA, a heterogeneous sparse accelerator design template constructed with the sub-accelerators generated from HARD TACO, and (3) a suite of scheduling strategies to map tensor kernels onto heterogeneous sparse accelerators with high efficiency and utilization. AESPA with optimized scheduling achieves 1.96X higher performance, and 7.9X better energy-delay product (EDP) than a Homogeneous EIE-like accelerator with our diverse workload suite.

The high efficiency of domain-specific hardware accelerators for machine learning (ML) has come from specialization, with the trade-off of less configurability/ flexibility. There is growing interest in developing flexible ML accelerators to make them future-proof to the rapid evolution of Deep Neural Networks (DNNs). However, the notion of accelerator flexibility has always been used in an informal manner, restricting computer architects from conducting systematic apples-to-apples design-space exploration (DSE) across trillions of choices. In this work, we formally define accelerator flexibility and show how it can be integrated for DSE. Specifically, we capture DNN accelerator flexibility across four axes: tiling, ordering, parallelization, and array shape. We categorize existing accelerators into 16 classes based on their axes of flexibility support, and define a precise quantification of the degree of flexibility of an accelerator across each axis. We leverage these to develop a novel flexibility-aware DSE framework. We demonstrate how this can be used to perform first-of-their-kind evaluations, including an isolation study to identify the individual impact of the flexibility axes. We demonstrate that adding flexibility features to a hypothetical DNN accelerator designed in 2014 improves runtime on future (i.e., present-day) DNNs by 11.8x geomean.

With increasing diversity in Deep Neural Network(DNN) models in terms of layer shapes and sizes, the research community has been investigating flexible/reconfigurable accelerator substrates. This line of research has opened up two challenges. The first is to determine the appropriate amount of flexibility within an accelerator array that that can trade-off the performance benefits versus the area overheads of the reconfigurability. The second is being able to determine the right configuration of the array for the current DNN model and/or layer and reconfigure the accelerator at runtime. This work introduces a new class of accelerators that we call Self Adaptive Reconfigurable Array (SARA). SARA architectures comprise of both a reconfigurable array and a hardware unit capable of determining an optimized configuration for the array at runtime. We demonstrate an instance of SARA with an accelerator we call SAGAR, which introduces a novel reconfigurable systolic array that can be configured to work as a distributed collection of smaller arrays of various sizes or as a single array with flexible aspect ratios. We also develop a novel recommendation neural network called ADAPTNET which recommends an array configuration and dataflow for the current layer parameters. ADAPTNET runs on an integrated custom hardware ADAPTNETX that runs ADAPTNET at runtime and reconfigures the array, making the entire accelerator self-sufficient. SAGAR is capable of providing the same mapping flexibility as a collection of 1024 4x4 arrays working as a distributed system while achieving 3.5x more power efficiency and 3.2x higher compute density Furthermore, the runtime achieved on the recommended parameters from ADAPTNET is 99.93% of the best achievable runtime.

The efficiency of a spatial DNN accelerator depends heavily on the compiler and its cost model ability to generate optimized mappings for various operators of DNN models on to the accelerator's compute and memory resources. But, existing cost models lack a formal boundary over the operators for precise and tractable analysis, which poses adaptability challenges for new DNN operators. To address this challenge, we leverage the recently introduced Maestro Data-Centric (MDC) notation. We develop a formal understanding of DNN operators whose mappings can be described in the MDC notation, because any mapping adhering to the notation is always analyzable by the MDC's cost model. Furthermore, we introduce a transformation for translating mappings into the MDC notation for exploring the mapping space. Searching for the optimal mappings is challenging because of the large space of mappings, and this challenge gets exacerbated with new operators and diverse accelerator configurations.To address this challenge, we propose a decoupled off-chip/on-chip approach that decomposes the mapping space into off-chip and on-chip subspaces, and first optimizes the off-chip subspace followed by the on-chip subspace. The motivation for this decomposition is to reduce the size of the search space dramatically and also to prioritize the optimization of off-chip data movement, which is 2-3 orders of magnitude more compared to the on-chip data movement. We implemented our approach in a tool called {\em Marvel}, and another major benefit of our approach is that it is applicable to any DNN operator conformable with the MDC notation.

Emerging AI-enabled applications such as augmented/virtual reality (AR/VR) leverage multiple deep neural network (DNN) models for sub-tasks such as object detection, hand tracking, and so on. Because of the diversity of the sub-tasks, the layers within and across the DNN models are highly heterogeneous in operation and shape. Such layer heterogeneity is a challenge for a fixed dataflow accelerator (FDA) that employs a fixed dataflow on a single accelerator substrate since each layer prefers different dataflows (computation order and parallelization) and tile sizes. Reconfigurable DNN accelerators (RDAs) have been proposed to adapt their dataflows to diverse layers to address the challenge. However, the dataflow flexibility in RDAs is enabled at the area and energy costs of expensive hardware structures (switches, controller, etc.) and per-layer reconfiguration. Alternatively, this work proposes a new class of accelerators, heterogeneous dataflow accelerators (HDAs), which deploys multiple sub-accelerators each supporting a different dataflow. HDAs enable coarser-grained dataflow flexibility than RDAs with higher energy efficiency and lower area cost comparable to FDAs. To exploit such benefits, hardware resource partitioning across sub-accelerators and layer execution schedule need to be carefully optimized. Therefore, we also present Herald, which co-optimizes hardware partitioning and layer execution schedule. Using Herald on a suite of AR/VR and MLPerf workloads, we identify a promising HDA architecture, Maelstrom, which demonstrates 65.3% lower latency and 5.0% lower energy than the best FDAs and 22.0% lower energy at the cost of 20.7% higher latency than a state-of-the-art RDA. The results suggest that HDA is an alternative class of Pareto-optimal accelerators to RDA with strength in energy, which can be a better choice than RDAs depending on the use cases., Comment: This paper is accepted at HPCA 2021

Traditionally, hardware designs partitioned across multiple FPGAs have had low performance due to the inefficiency of maintaining cycle-by-cycle timing among discrete FPGAs. In this paper, we present a mechanism by which complex designs may be efficiently and automatically partitioned among multiple FPGAs using explicitly programmed latency-insensitive links. We describe the automatic synthesis of an area efficient, high performance network for routing these inter-FPGA links. By mapping a diverse set of large research prototypes onto a multiple FPGA platform, we demonstrate that our tool obtains significant gains in design feasibility, compilation time, and even wall-clock performance., Intel Corporation. Graduate Fellowship

Convolutional Neural Networks (CNNs) have begun to permeate all corners of electronic society (from voice recognition to scene generation) due to their high accuracy and machine efficiency per operation. At their core, CNN computations are made up of multi-dimensional dot products between weight and input vectors. This paper studies how weight repetition ---when the same weight occurs multiple times in or across weight vectors--- can be exploited to save energy and improve performance during CNN inference. This generalizes a popular line of work to improve efficiency from CNN weight sparsity, as reducing computation due to repeated zero weights is a special case of reducing computation due to repeated weights. To exploit weight repetition, this paper proposes a new CNN accelerator called the Unique Weight CNN Accelerator (UCNN). UCNN uses weight repetition to reuse CNN sub-computations (e.g., dot products) and to reduce CNN model size when stored in off-chip DRAM ---both of which save energy. UCNN further improves performance by exploiting sparsity in weights. We evaluate UCNN with an accelerator-level cycle and energy model and with an RTL implementation of the UCNN processing element. On three contemporary CNNs, UCNN improves throughput-normalized energy consumption by 1.2x - 4x, relative to a similarly provisioned baseline accelerator that uses Eyeriss-style sparsity optimizations. At the same time, the UCNN processing element adds only 17-24% area overhead relative to the same baseline., Comment: Appears in the proceedings of the 45th International Symposium on Computer Architecture~(ISCA), 2018

The data partitioning and scheduling strategies used by DNN accelerators to leverage reuse and perform staging are known as dataflow, and they directly impact the performance and energy efficiency of DNN accelerator designs. An accelerator microarchitecture dictates the dataflow(s) that can be employed to execute a layer or network. Selecting an optimal dataflow for a layer shape can have a large impact on utilization and energy efficiency, but there is a lack of understanding on the choices and consequences of dataflows, and of tools and methodologies to help architects explore the co-optimization design space. In this work, we first introduce a set of data-centric directives to concisely specify the space of DNN dataflows in a compilerfriendly form. We then show how these directives can be analyzed to infer various forms of reuse and to exploit them using hardware capabilities. We codify this analysis into an analytical cost model, MAESTRO (Modeling Accelerator Efficiency via Spatio-Temporal Reuse and Occupancy), that estimates various cost-benefit tradeoffs of a dataflow including execution time and energy efficiency for a DNN model and hardware configuration. We demonstrate the use of MAESTRO to drive a hardware design space exploration (DSE) experiment, which searches across 480M designs to identify 2.5M valid designs at an average rate of 0.17M designs per second, including Pareto-optimal throughput- and energy-optimized design points.

The C and C++ high-level languages provide programmers with atomic operations for writing high-performance concurrent code. At the assembly language level, C and C++ atomics get mapped down to individual instructions or combinations of instructions by compilers, depending on the ordering guarantees and synchronization instructions provided by the underlying architecture. These compiler mappings must uphold the ordering guarantees provided by C/C++ atomics or the compiled program will not behave according to the C/C++ memory model. In this paper we discuss two counterexamples to the well-known trailing-sync compiler mappings for the Power and ARMv7 architectures that were previously thought to be proven correct. In addition to the counterexamples, we discuss the loophole in the proof of the mappings that allowed the incorrect mappings to be proven correct. We also discuss the current state of compilers and architectures in relation to the bug.

Memory consistency models (MCMs) which govern inter-module interactions in a shared memory system, are a significant, yet often under-appreciated, aspect of system design. MCMs are defined at the various layers of the hardware-software stack, requiring thoroughly verified specifications, compilers, and implementations at the interfaces between layers. Current verification techniques evaluate segments of the system stack in isolation, such as proving compiler mappings from a high-level language (HLL) to an ISA or proving validity of a microarchitectural implementation of an ISA. This paper makes a case for full-stack MCM verification and provides a toolflow, TriCheck, capable of verifying that the HLL, compiler, ISA, and implementation collectively uphold MCM requirements. The work showcases TriCheck's ability to evaluate a proposed ISA MCM in order to ensure that each layer and each mapping is correct and complete. Specifically, we apply TriCheck to the open source RISC-V ISA, seeking to verify accurate, efficient, and legal compilations from C11. We uncover under-specifications and potential inefficiencies in the current RISC-V ISA documentation and identify possible solutions for each. As an example, we find that a RISC-V-compliant microarchitecture allows 144 outcomes forbidden by C11 to be observed out of 1,701 litmus tests examined. Overall, this paper demonstrates the necessity of full-stack verification for detecting MCM-related bugs in the hardware-software stack., Comment: Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems

This paper presents Heracles, an open-source, functional, parameterized, synthesizable multicore system toolkit. Such a multi/many-core design platform is a powerful and versatile research and teaching tool for architectural exploration and hardware-software co-design. The Heracles toolkit comprises the soft hardware (HDL) modules, application compiler, and graphical user interface. It is designed with a high degree of modularity to support fast exploration of future multicore processors of di erent topologies, routing schemes, processing elements (cores), and memory system organizations. It is a component-based framework with parameterized interfaces and strong emphasis on module reusability. The compiler toolchain is used to map C or C++ based applications onto the processing units. The GUI allows the user to quickly con gure and launch a system instance for easy factorial development and evaluation. Hardware modules are implemented in synthesizable Verilog and are FPGA platform independent. The Heracles tool is freely available under the open-source MIT license at: http://projects.csail.mit.edu/heracles

We propose a practical methodology based on modular refinement to design complex systems. The methodology relies on modules with latency-insensitive interfaces so that the refinements can change the timing contract of a module without affecting the overall functional correctness of the system. Such refinements can exacerbate the unit testing problem for modules whose specifications admit a set of output behaviors for the same input (non-determinism), or modules whose input behavior may be affected by past outputs (feedback). We avoid the difficult problem of generating appropriate unit tests for such modules by using system-level tests as unit tests to verify the correctness of refined modules. We illustrate our methodology by showing how one might develop a microprocessor with an in-order pipeline. We then develop a superscalar pipeline using the in-order pipeline as the starting point. Our methodology leverages the effort of design exploration to reduce the effort of specifying interface contracts and unit testing., National Science Foundation (U.S.) (grant CCF- 0541164 on Complex Digital Systems)

We propose a practical methodology based on modular refinement to design complex systems. The methodology relies on modules with latency-insensitive interfaces so that the refinements can change the timing contract of a module without affecting the overall functional correctness of the system. Such refinements can exacerbate the unit testing problem for modules whose specifications admit a set of output behaviors for the same input (non-determinism), or modules whose input behavior may be affected by past outputs (feedback). We avoid the difficult problem of generating appropriate unit tests for such modules by using system-level tests as unit tests to verify the correctness of refined modules. We illustrate our methodology by showing how one might develop a microprocessor with an in-order pipeline. We then develop a superscalar pipeline using the in-order pipeline as the starting point. Our methodology leverages the effort of design exploration to reduce the effort of specifying interface contracts and unit testing., National Science Foundation (U.S.) (grant CCF- 0541164 on Complex Digital Systems)

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011., Cataloged from PDF version of thesis., Includes bibliographical references (p. 159-165)., The goal of this project is to improve computer architecture by accelerating cycle-accurate performance modeling of multicore processors using FPGAs. Contributions include a distributed technique controlling simulation on a highly-parallel substrate, hardware design techniques to reduce development effort, and a specific framework for modeling shared-memory multicore processors paired with realistic On-Chip Networks., by Michael Pellauer., Ph.D.

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011., Cataloged from PDF version of thesis., Includes bibliographical references (p. 159-165)., The goal of this project is to improve computer architecture by accelerating cycle-accurate performance modeling of multicore processors using FPGAs. Contributions include a distributed technique controlling simulation on a highly-parallel substrate, hardware design techniques to reduce development effort, and a specific framework for modeling shared-memory multicore processors paired with realistic On-Chip Networks., by Michael Pellauer., Ph.D.

Hardware-design languages typically impose a rigid communication hierarchy that follows module instantiation. This leads to an undesirable side-effect where changes to a child’s interface result in changes to the parents. Soft connections address this problem by allowing the user to specify connection endpoints that are automatically connected at compilation time, rather than by the user.

Heracles is an open-source complete multicore system written in Verilog. It is fully parameterized and can be reconfigured and synthesized into different topologies and sizes. Each processing node has a 7-stage pipeline, fully bypassed, microprocessor running the MIPS-III ISA, a 4-stage input-buffer, virtual-channel router, and a local variable-size shared memory. Our design is highly modular with clear interfaces between the core, the memory hierarchy, and the on-chip network. In the baseline design, the microprocessor is attached to two caches, one instruction cache and one data cache, which are oblivious to the global memory organization. The memory system in Heracles can be configured as one single global shared memory (SM), or distributed shared memory (DSM), or any combination thereof. Each core is connected to the rest of the network of processors by a parameterized, realistic, wormhole router. We show different topology configurations of the system, and their synthesis results on the Xilinx Virtex-5 LX330T FPGA board. We also provide a small MIPS cross-compiler toolchain to assist in developing software for Heracles.

CORRECTION: The authors for entry [4] in the references should have been "E. S. Chung, J. C. Hoe, and K. Mai"., Developers accelerating applications on FPGAs or other reconfigurable logic have nothing but raw memory devices in their standard toolkits. Each project typically includes tedious development of single-use memory management. Software developers expect a programming environment to include automatic memory management. Virtual memory provides the illusion of very large arrays and processor caches reduce access latency without explicit programmer instructions. LEAP scratchpads for reconfigurable logic dynamically allocate and manage multiple, independent, memory arrays in a large backing store. Scratchpad accesses are cached automatically in multiple levels, ranging from shared on-board, RAM-based, set-associative caches to private caches stored in FPGA RAM blocks. In the LEAP framework, scratchpads share the same interface as on-die RAM blocks and are plug-in replacements. Additional libraries support heap management within a storage set. Like software developers, accelerator authors using scratchpads may focus more on core algorithms and less on memory management. Two uses of FPGA scratchpads are analyzed: buffer management in an H.264 decoder and memory management within a processor microarchitecture timing model.

Heracles is an open-source complete multicore system written in Verilog. It is fully parameterized and can be reconfigured and synthesized into different topologies and sizes. Each processing node has a 7-stage pipeline, fully bypassed, microprocessor running the MIPS-III ISA, a 4-stage input-buffer, virtual-channel router, and a local variable-size shared memory. Our design is highly modular with clear interfaces between the core, the memory hierarchy, and the on-chip network. In the baseline design, the microprocessor is attached to two caches, one instruction cache and one data cache, which are oblivious to the global memory organization. The memory system in Heracles can be configured as one single global shared memory (SM), or distributed shared memory (DSM), or any combination thereof. Each core is connected to the rest of the network of processors by a parameterized, realistic, wormhole router. We show different topology configurations of the system, and their synthesis results on the Xilinx Virtex-5 LX330T FPGA board. We also provide a small MIPS cross-compiler toolchain to assist in developing software for Heracles.

CORRECTION: The authors for entry [4] in the references should have been "E. S. Chung, J. C. Hoe, and K. Mai"., Developers accelerating applications on FPGAs or other reconfigurable logic have nothing but raw memory devices in their standard toolkits. Each project typically includes tedious development of single-use memory management. Software developers expect a programming environment to include automatic memory management. Virtual memory provides the illusion of very large arrays and processor caches reduce access latency without explicit programmer instructions. LEAP scratchpads for reconfigurable logic dynamically allocate and manage multiple, independent, memory arrays in a large backing store. Scratchpad accesses are cached automatically in multiple levels, ranging from shared on-board, RAM-based, set-associative caches to private caches stored in FPGA RAM blocks. In the LEAP framework, scratchpads share the same interface as on-die RAM blocks and are plug-in replacements. Additional libraries support heap management within a storage set. Like software developers, accelerator authors using scratchpads may focus more on core algorithms and less on memory management. Two uses of FPGA scratchpads are analyzed: buffer management in an H.264 decoder and memory management within a processor microarchitecture timing model.