FPGA HLS today: successes, challenges, and opportunities

J Cong, J Lau, G Liu, S Neuendorffer, P Pan… - ACM Transactions on …, 2022 - dl.acm.org
The year 2011 marked an important transition for FPGA high-level synthesis (HLS), as it
went from prototy** to deployment. A decade later, in this article, we assess the progress …

Pushing the level of abstraction of digital system design: A survey on how to program fpgas

ED Sozzo, D Conficconi, A Zeni, M Salaris… - ACM Computing …, 2022 - dl.acm.org
Field Programmable Gate Arrays (FPGAs) are spatial architectures with a heterogeneous
reconfigurable fabric. They are state-of-the-art for prototy**, telecommunications …

Interstellar: Using halide's scheduling language to analyze dnn accelerators

X Yang, M Gao, Q Liu, J Setter, J Pu, A Nayak… - Proceedings of the …, 2020 - dl.acm.org
We show that DNN accelerator micro-architectures and their program map**s represent
specific choices of loop order and hardware parallelism for computing the seven nested …

SODA: Stencil with optimized dataflow architecture

Y Chi, J Cong, P Wei, P Zhou - 2018 IEEE/ACM International …, 2018 - ieeexplore.ieee.org
Stencil computation is one of the most important kernels in many application domains such
as image processing, solving partial differential equations, and cellular automata. Many of …

A compiler infrastructure for accelerator generators

R Nigam, S Thomas, Z Li, A Sampson - Proceedings of the 26th ACM …, 2021 - dl.acm.org
We present Calyx, a new intermediate language (IL) for compiling high-level programs into
hardware designs. Calyx combines a hardware-like structural language with a software-like …

HeteroCL: A multi-paradigm programming infrastructure for software-defined reconfigurable computing

YH Lai, Y Chi, Y Hu, J Wang, CH Yu, Y Zhou… - Proceedings of the …, 2019 - dl.acm.org
With the pursuit of improving compute performance under strict power constraints, there is
an increasing need for deploying applications to heterogeneous hardware architectures with …

iPIM: Programmable in-memory image processing accelerator using near-bank architecture

P Gu, X **e, Y Ding, G Chen, W Zhang… - 2020 ACM/IEEE 47th …, 2020 - ieeexplore.ieee.org
Image processing is becoming an increasingly important domain for many applications on
workstations and the datacenter that require accelerators for high performance and energy …

Transformations of high-level synthesis codes for high-performance computing

J de Fine Licht, M Besta, S Meierhans… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Spatial computing architectures promise a major stride in performance and energy efficiency
over the traditional load/store devices currently employed in large scale computing systems …

OverGen: Improving FPGA usability through domain-specific overlay generation

S Liu, J Weng, D Kupsh… - 2022 55th IEEE/ACM …, 2022 - ieeexplore.ieee.org
FPGAs have been proven to be powerful computational accelerators across many types of
workloads. The mainstream programming approach is high level synthesis (HLS), which …

Predictable accelerator design with time-sensitive affine types

R Nigam, S Atapattu, S Thomas, Z Li, T Bauer… - Proceedings of the 41st …, 2020 - dl.acm.org
Field-programmable gate arrays (FPGAs) provide an opportunity to co-design applications
with hardware accelerators, yet they remain difficult to program. High-level synthesis (HLS) …