English
Related papers

Related papers: A Unified Framework for Automated Code Transformat…

200 papers

Embedded Systems combine one or more processor cores with dedicated logic running on an ASIC or FPGA to meet design goals at reasonable cost. It is achieved by profiling the application with variety of aspects like performance, memory…

Performance · Computer Science 2013-12-12 Rajendra Patel , Arvind Rajwat

In recent years, hardware accelerators based on field-programmable gate arrays (FPGAs) have been widely adopted, thanks to FPGAs' extraordinary flexibility. However, with the high flexibility comes the difficulty in design and optimization.…

Hardware Architecture · Computer Science 2022-07-19 Mang Yu , Sitao Huang , Deming Chen

Pragmas for loop transformations, such as unrolling, are implemented in most mainstream compilers. They are used by application programmers because of their ease of use compared to directly modifying the source code of the relevant loops.…

Programming Languages · Computer Science 2019-01-31 Michael Kruse , Hal Finkel

Typical constraints on embedded systems include code size limits, upper bounds on energy consumption and hard or soft deadlines. To meet these requirements, it may be necessary to improve the software by applying various kinds of…

Performance · Computer Science 2010-11-30 Hugues Cassé , Karine Heydemann , Haluk Ozaktas , Jonathan Ponroy , Christine Rochange , Olivier Zendra

High-Level Synthesis (HLS) compiles C/C++ into RTL, but exploring pragma-driven optimization choices remains expensive because each design point requires time-consuming synthesis. We propose \textbf{\DiffHLS}, a differential learning…

Machine Learning · Computer Science 2026-04-13 Zedong Peng , Zeju Li , Qiang Xu , Jieru Zhao

In recent years the computing landscape has seen an in- creasing shift towards specialized accelerators. Field pro- grammable gate arrays (FPGAs) are particularly promising as they offer significant performance and energy improvements…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-11-24 Raghu Prabhakar , David Koeplinger , Kevin Brown , HyoukJoong Lee , Christopher De Sa , Christos Kozyrakis , Kunle Olukotun

Although high-level synthesis (HLS) tools have significantly improved programmer productivity over hardware description languages, developing for FPGAs remains tedious and error prone. Programmers must learn and implement a large set of…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-12-29 Johannes de Fine Licht , Tiziano De Matteis , Tal Ben-Nun , Andreas Kuster , Oliver Rausch , Manuel Burger , Carl-Johannes Johnsen , Torsten Hoefler

The rapid growth of deep learning has driven exponential increases in model parameters and computational demands. NVIDIA GPUs and their CUDA-based software ecosystem provide robust support for parallel computing, significantly alleviating…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-08 Jiaqi Lv , Xufeng He , Yanchen Liu , Xu Dai , Aocheng Shen , Yinghao Li , Jiachen Hao , Jianrong Ding , Yang Hu , Shouyi Yin

High-level synthesis (HLS) is a process that automatically translates a software program in a high-level language into a low-level hardware description. However, the hardware designs produced by HLS tools still suffer from a significant…

Programming Languages · Computer Science 2023-08-16 Jianyi Cheng , Samuel Coward , Lorenzo Chelini , Rafael Barbalho , Theo Drane

Despite the great success of High-Level Synthesis (HLS) tools, we observe several unresolved challenges: 1) the high-level abstraction of programming styles in HLS sometimes conceals optimization opportunities; 2) existing HLS tools do not…

Hardware Architecture · Computer Science 2021-12-10 Nan Wu , Yuan Xie , Cong Hao

The resurgence of machine learning has increased the demand for high-performance basic linear algebra subroutines (BLAS), which have long depended on libraries to achieve peak performance on commodity hardware. High-performance BLAS…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-30 Braedy Kuzma , Ivan Korostelev , João P. L. de Carvalho , José E. Moreira , Christopher Barton , Guido Araujo , José Nelson Amaral

Dataflow architectures are growing in popularity due to their potential to mitigate the challenges posed by the memory wall inherent to the Von Neumann architecture. At the same time, high-level synthesis (HLS) has demonstrated its efficacy…

Hardware Architecture · Computer Science 2023-11-08 Hanchen Ye , Hyegang Jun , Deming Chen

Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, we tackle these costs by leveraging unstructured sparsity within an LLM's feedforward layers, the…

Machine Learning · Computer Science 2026-05-11 Edoardo Cetin , Stefano Peluchetti , Emilio Castillo , Akira Naruse , Mana Murakami , Llion Jones

While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…

Machine Learning · Computer Science 2026-02-05 Annabelle Sujun Tang , Christopher Priebe , Rohan Mahapatra , Lianhui Qin , Hadi Esmaeilzadeh

Compiling high-level programs to target high-speed packet-processing pipelines is a challenging combinatorial optimization problem. The compiler must configure the pipeline's resources to match the high-level semantics of the program, while…

Networking and Internet Architecture · Computer Science 2022-11-22 Xiangyu Gao , Divya Raghunathan , Ruijie Fang , Tao Wang , Xiaotong Zhu , Anirudh Sivaraman , Srinivas Narayana , Aarti Gupta

This book focuses on the use of algorithmic high-level synthesis (HLS) to build application-specific FPGA systems. Our goal is to give the reader an appreciation of the process of creating an optimized hardware design using HLS. Although…

Hardware Architecture · Computer Science 2018-05-11 Ryan Kastner , Janarbek Matai , Stephen Neuendorffer

Dynamically scheduled high-level synthesis (HLS) achieves higher throughput than static HLS for codes with unpredictable memory accesses and control flow. However, excessive dataflow scheduling results in circuits that use more resources…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-08-30 Robert Szafarczyk , Syed Waqar Nabi , Wim Vanderbauwhede

The ongoing trend of hardware specialization has led to a growing use of custom data formats when processing sparse workloads, which are typically memory-bound. These formats facilitate optimized software/hardware implementations by…

Computation and Language · Computer Science 2024-03-12 Jie Liu , Zhongyuan Zhao , Zijian Ding , Benjamin Brock , Hongbo Rong , Zhiru Zhang

In modern computing systems, compilation employs numerous optimization techniques to enhance code performance. Source-to-source code transformations, which include control flow and datapath transformations, have been widely used in…

Hardware Architecture · Computer Science 2025-06-09 Jiaqi Yin , Zhan Song , Nicolas Bohm Agostini , Antonino Tumeo , Cunxi Yu

High-level synthesis (HLS) has significantly advanced the automation of digital circuits design, yet the need for expertise and time in pragma tuning remains challenging. Existing solutions for the design space exploration (DSE) adopt…

Hardware Architecture · Computer Science 2025-04-14 Ping Chang , Tosiron Adegbija , Yuchao Liao , Claudio Talarico , Ao Li , Janet Roveda