arXiv subjects

Gerald Hempel

Publications and source records attributed to Gerald Hempel.

4 recordsLinked to original sources

arXiv2022

Automatic Creation of High-Bandwidth Memory Architectures from Domain-Specific Languages: The Case of Computational Fluid Dynamics

Numerical simulations can help solve complex problems. Most of these algorithms are massively parallel and thus good candidates for FPGA acceleration thanks to spatial parallelism. Modern FPGA devices can leverage high-bandwidth memory technologies, but when applications are memory-bound designers must craft advanced communication and memory architectures for efficient data movement and on-chip storage. This development process requires hardware design skills that are uncommon in domain-specific experts. In this paper, we propose an automated tool flow from a domain-specific language (DSL) for tensor expressions to generate massively-parallel accelerators on HBM-equipped FPGAs. Designers can use this flow to integrate and evaluate various compiler or hardware optimizations. We use computational fluid dynamics (CFD) as a paradigmatic example. Our flow starts from the high-level specification of tensor operations and combines an MLIR-based compiler with an in-house hardware generation flow to generate systems with parallel accelerators and a specialized memory architecture that moves data efficiently, aiming at fully exploiting the available CPU-FPGA bandwidth. We simulated applications with millions of elements, achieving up to 103 GFLOPS with one compute unit and custom precision when targeting a Xilinx Alveo U280. Our FPGA implementation is up to 25x more energy-efficient than expert-crafted Intel CPU implementations.

cs.AR↗

arXiv2022

Brain-inspired Cognition in Next Generation Racetrack Memories

Hyperdimensional computing (HDC) is an emerging computational framework inspired by the brain that operates on vectors with thousands of dimensions to emulate cognition. Unlike conventional computational frameworks that operate on numbers, HDC, like the brain, uses high dimensional random vectors and is capable of one-shot learning. HDC is based on a well-defined set of arithmetic operations and is highly error-resilient. The core operations of HDC manipulate HD vectors in bulk bit-wise fashion, offering many opportunities to leverage parallelism. Unfortunately, on conventional Von-Neuman architectures, the continuous movement of HD vectors among the processor and the memory can make the cognition task prohibitively slow and energy-intensive. Hardware accelerators only marginally improve related metrics. On the contrary, only partial implementation of an HDC framework inside memory, using emerging memristive devices, has reported considerable performance/energy gains. This paper presents an architecture based on racetrack memory (RTM) to conduct and accelerate the entire HDC framework within the memory. The proposed solution requires minimal additional CMOS circuitry and uses a read operation across multiple domains in RTMs called transverse read (TR) to realize exclusive-or (XOR) and addition operations. To minimize the overhead the CMOS circuitry, we propose an RTM nanowires-based counting mechanism that leverages the TR operation and the standard RTM operations. Using language recognition as the use case demonstrates 7.8x and 5.3x reduction in the overall runtime and energy consumption compared to the FPGA design, respectively. Compared to the state-of-the-art in-memory implementation, the proposed HDC system reduces the energy consumption by 8.6x.

cs.LG↗

arXiv2021

From Domain-Specific Languages to Memory-Optimized Accelerators for Fluid Dynamics

Many applications are increasingly requiring numerical simulations for solving complex problems. Most of these numerical algorithms are massively parallel and often implemented on parallel high-performance computers. However, classic CPU-based platforms suffers due to the demand for higher resolutions and the exponential growth of data. FPGAs offer a powerful and flexible alternative that can host accelerators to complement such platforms. Developing such application-specific accelerators is still challenging because it is hard to provide efficient code for hardware synthesis. In this paper, we study the challenges of porting a numerical simulation kernel onto FPGA. We propose an automated tool flow from a domain-specific language (DSL) to generate accelerators for computational fluid dynamics on FPGA. Our DSL-based flow simplifies the exploration of parameters and constraints such as on-chip memory usage. We also propose a decoupled optimization of memory and logic resources, which allows us to better use the limited FPGA resources. In our preliminary evaluation, this enabled doubling the number of parallel kernels, increasing the accelerator speedup versus ARM execution from 7 to 12 times.

cs.DC↗

arXiv2015

GCC-Plugin for Automated Accelerator Generation and Integration on Hybrid FPGA-SoCs

In recent years, architectures combining a reconfigurable fabric and a general purpose processor on a single chip became increasingly popular. Such hybrid architectures allow extending embedded software with application specific hardware accelerators to improve performance and/or energy efficiency. Aiding system designers and programmers at handling the complexity of the required process of hardware/software (HW/SW) partitioning is an important issue. Current methods are often restricted, either to bare-metal systems, to subsets of mainstream programming languages, or require special coding guidelines, e.g., via annotations. These restrictions still represent a high entry barrier for the wider community of programmers that new hybrid architectures are intended for. In this paper we revisit HW/SW partitioning and present a seamless programming flow for unrestricted, legacy C code. It consists of a retargetable GCC plugin that automatically identifies code sections for hardware acceleration and generates code accordingly. The proposed workflow was evaluated on the Xilinx Zynq platform using unmodified code from an embedded benchmark suite.

cs.OH↗