Escalating system-on-chip design complexity is pushing the design community to raise the level of abstraction beyond register transfer level. Despite the unsuccessful adoptions of early generations of commercial high-level synthesis (HLS) systems, we believe that the tipping point for transitioning to HLS msystem-on-chip design complexityethodology is happening now, especially for field-programmable gate array (FPGA) designs. The latest generation of HLS tools has made significant progress in providing wide language coverage and robust compilation technology, platform-based modeling, advancement in core HLS algorithms, and a domain-specific approach. In this paper, we use AutoESL's AutoPilot HLS tool coupled with domain-specific system-level implementation platforms developed by Xilinx as an example to demonstrate the effectiveness of state-of-art C-to-FPGA synthesis solutions targeting multiple application domains. Complex industrial designs targeting Xilinx FPGAs are also presented as case studies, including comparison of HLS solutions versus optimized manual designs. In particular, the experiment on a sphere decoder shows that the HLS solution can achieve an 11-31% reduction in FPGA resource usage with improved design productivity compared to hand-coded design.

/pdf/high-level-synthesis-for-fpgas-from-prototyping-to-4vlvkebjds.pdf

High-Level Synthesis for FPGAs: From Prototyping to Deployment

This paper describes a learning-based approach to the acceleration of approximate programs. We describe the \emph{Parrot transformation}, a program transformation that selects and trains a neural network to mimic a region of imperative code. After the learning phase, the compiler replaces the original code with an invocation of a low-power accelerator called a \emph{neural processing unit} (NPU). The NPU is tightly coupled to the processor pipeline to accelerate small code regions. Since neural networks produce inherently approximate results, we define a programming model that allows programmers to identify approximable code regions -- code that can produce imprecise but acceptable results. Offloading approximable code regions to NPUs is faster and more energy efficient than executing the original code. For a set of diverse applications, NPU acceleration provides whole-application speedup of 2.3x and energy savings of 3.0x on average with quality loss of at most 9.6%.

/pdf/neural-acceleration-for-general-purpose-approximate-programs-chuxql7jbp.pdf

Neural Acceleration for General-Purpose Approximate Programs

In this paper, we introduce a new open source high-level synthesis tool called LegUp that allows software techniques to be used for hardware design LegUp accepts a standard C program as input and automatically compiles the program to a hybrid architecture containing an FPGA-based MIPS soft processor and custom hardware accelerators that communicate through a standard bus interface Results show that the tool produces hardware solutions of comparable quality to a commercial high-level synthesis tool

/pdf/legup-high-level-synthesis-for-fpga-based-processor-5f2afx6pcn.pdf

LegUp: high-level synthesis for FPGA-based processor/accelerator systems

High-level synthesis (HLS) is increasingly popular for the design of high-performance and energy-efficient heterogeneous systems, shortening time-to-market and addressing today’s system complexity. HLS allows designers to work at a higher-level of abstraction by using a software program to specify the hardware functionality. Additionally, HLS is particularly interesting for designing field-programmable gate array circuits, where hardware implementations can be easily refined and replaced in the target device. Recent years have seen much activity in the HLS research community, with a plethora of HLS tool offerings, from both industry and academia. All these tools may have different input languages, perform different internal optimizations, and produce results of different quality, even for the very same input description. Hence, it is challenging to compare their performance and understand which is the best for the hardware to be implemented. We present a comprehensive analysis of recent HLS tools, as well as overview the areas of active interest in the HLS research community. We also present a first-published methodology to evaluate different HLS tools. We use our methodology to compare one commercial and three academic tools on a common set of C benchmarks, aiming at performing an in-depth evaluation in terms of performance and the use of resources.

/pdf/a-survey-and-evaluation-of-fpga-high-level-synthesis-tools-4pv9ke4ji3.pdf

A Survey and Evaluation of FPGA High-Level Synthesis Tools

As improvements in per-transistor speed and energy efficiency diminish, radical departures from conventional approaches are needed to continue improvements in the performance and energy efficiency of general-purpose processors. One such departure is approximate computing, where error in computation is acceptable and the traditional robust digital abstraction of near-perfect accuracy is relaxed. Conventional techniques in energy-efficient computing navigate a design space defined by the two dimensions of performance and energy, and traditionally trade one for the other. General-purpose approximate computing explores a third dimension---error---and trades the accuracy of computation for gains in both energy and performance. Techniques to harvest large savings from small errors have proven elusive. This paper describes a new approach that uses machine learning-based transformations to accelerate approximation-tolerant programs. The core idea is to train a learning model how an approximable region of code---code that can produce imprecise but acceptable results---behaves and replace the original code region with an efficient computation of the learned model. We use neural networks to learn code behavior and approximate it. We describe the Parrot algorithmic transformation, which leverages a simple programmer annotation ("approximable") to transform a code region from a von Neumann model to a neural model. After the learning phase, the compiler replaces the original code with an invocation of a low-power accelerator called a neural processing unit (NPU). The NPU is tightly coupled to the processor pipeline to permit profitable acceleration even when small regions of code are transformed. Offloading approximable code regions to NPUs is faster and more energy efficient than executing the original code. For a set of diverse applications, NPU acceleration provides whole-application speedup of 2.3× and energy savings of 3.0× on average with average quality loss of at most 9.6%. NPUs form a new class of accelerators and show that significant gains in both performance and efficiency are achievable when the traditional abstraction of near-perfect accuracy is relaxed in general-purpose computing.

/pdf/neural-acceleration-for-general-purpose-approximate-programs-2rvy9cc5h4.pdf

Neural acceleration for general-purpose approximate programs

The paper describes architectural enhancements to Xilinx FPGAs that provide better support for the creation of dynamically reconfigurable designs. These are augmented by a new design methodology that uses pre-routed IP cores for communication between static and dynamic modules and permits static designs to route through regions otherwise reserved for dynamic modules. A new CAD tool flow to automate the methodology is also presented. The new tools initially target the Virtex-II, Virtex-II Pro and Virtex-4 families and are derived from Xilinx's commercial CAD tools

Invited Paper: Enhanced Architectures, Design Methodologies and CAD Tools for Dynamic Reconfiguration of Xilinx FPGAs

In modular design flow, logic designers are able to partition a top-level logic design for a PLD into modules and implement any module independently from other modules. Modules are mapped, placed, and routed using selected information derived at the time the top-level logic design is partitioned. Finally, the modules are integrated into the top-level logic design using a guided process. Specifically, the information generated during the partitioning of the top-level design and the implementation of each module is used to guide the implementation of the associated logic in the top-level design. In this manner, the implementation of all modules can proceed in any order or in parallel and the integration of the modules into the top-level design can be done quickly and in any order.

Modular design method and system for programmable logic devices

This poster describes CHiMPS, a toolflow that aims to provide software developers with a way to program hybrid CPU-FPGA platforms using familiar tools, languages, and techniques. CHiMPS starts with C and produces a specialized spatial dataflow architecture that supports coherent caches and the shared-memory programming model. The toolflow is designed to abstract away the complex details of data movement and separate memories on the hybrid platforms, as well as take advantage of memory management and computation techniques unique to reconfigurable hardware. This poster focuses on the memory design for CHiMPS, particularly the use of numerous small caches customized for various phases of program execution. The poster also addresses area vs. performance tradeoffs for various configurations. Applications compiled using CHiMPS show performance improvements of more than 36x on simple compute-intensive kernels, and 4.3x on the difficult-to-parallelize STSWM application without any special optimizations compared to running only on the CPU. The toolflow supports full ANSI-C, and produces hardware that runs on platforms that are expected to be available within one year

CHiMPS: a high-level compilation flow for hybrid CPU-FPGA architectures

Many-cache is a memory architecture that efficiently supports caching in commercially available FPGAs. It facilitates FPGA programming for high-performance computing (HPC) developers by providing them with memory performance that is greater and power consumption that is less than their current CPU platforms, but without sacrificing their familiar, C-based programming environment.Many-cache creates multiple, multi-banked caches on top of an FGPA's small, independent memories, each targeting a particular data structure or region of memory in an application and each customized for the memory operations that access it. The caches are automatically generated from C source by the CHiMPS C-to-FPGA compiler.This paper presents the analyses and optimizations of the CHiMPS compiler that construct many-cache caches. An architectural evaluation of CHiMPS-generated FPGAs demonstrates a performance advantage of 7.8x (geometric mean) over CPU-only execution of the same source code, FPGA power usage that is on average 4.1x less, and consequently performance per watt that is also greater, by a geometric mean of 21.3x.

Performance and power of cache-based reconfigurable computing

Method and apparatus for providing secure intellectual property (IP) cores for a programmable logic device (PLD) are described. An aspect of the invention relates to a method of securely distributing an IP core for PLDs. A circuit design is generated for the IP core, the circuit design being re-locatable in a programmable fabric for PLDs. The circuit design is encoded to produce at least one partial configuration bitstream. Implementation data is generated for utilizing the IP core as a reconfigurable module in top-level circuit designs. The at least one partial configuration bitstream and the implementation data are delivered to users of the PLDs.

Jeffrey M. Mason

Papers

Invited Paper: Enhanced Architectures, Design Methodologies and CAD Tools for Dynamic Reconfiguration of Xilinx FPGAs

Modular design method and system for programmable logic devices

CHiMPS: a high-level compilation flow for hybrid CPU-FPGA architectures

Performance and power of cache-based reconfigurable computing

Method and apparatus for providing secure intellectual property cores for a programmable logic device