Ce Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ce Sun has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Hongbo Rong
Parallel Computing Labs Intel Santa Clara CA USA
2 shared publications - Mingzhe Zhang
Tsinghua University, Beijing, China
2 shared publications - Xiaochen Hao
School of Computer Science, Peking University, Beijing, China
2 shared publications - Yun Liang
School of Integrated Circuits, Peking University, Beijing, China
2 shared publications - Eric Petit
Université Paris-Saclay UVSQ Li-PaRAD Saint-Quentin en Yvelines France
1 shared publication - Hong Jiang
Intel, Santa Clara, USA
1 shared publication
Latest Publications
- Open Access
- 31 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Reconfigurable Technology and Systems
- Vol. 18 (2) , 1-32
Productively Generating a High-Performance Linear Algebra Library on FPGAs
Linear algebra computations can be greatly accelerated using spatial accelerators on FPGAs. As a standard building block of linear algebra applications, BLAS covers a wide range of compute patterns that vary vastly in data reuse, bottleneck resources, matrix storage layouts, and data types. However, existing implementations of BLAS routines on FPGAs are stuck in the dilemma of productivity and performance. They either require extensive human effort or fail to leverage the properties of routines for acceleration. We introduce Lasa, a framework composed of a programming model and a compiler, designed to address the dilemma by abstracting (for productivity) and specializing (for performance) the architecture of a spatial accelerator. The programming model realizes systolic arrays using uniform recurrence equations and space-time transforms. Streaming tensors, an intuitive dataflow-style abstraction, is proposed to uniformly describe the movement, storage, and transpose of input and output data across the spatial components. According to streaming tensors, a customized memory hierarchy is automatically built on an FPGA by our compiler. The compiler further specializes the architecture with transparent optimizations on FPGAs. Using this framework, we develop a complete BLAS library, demonstrating performance in parity with expert-written HLS code for BLAS level 3 routines, 76%–94% machine peak for level 1 and 2 routines, and 1.6X–13X speedup by leveraging the matrix properties such as symmetry, triangularity, and bandness.
- 31 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Reconfigurable Technology and Systems
- Vol. 18 (2) , 1-32
Open AccessProductively Generating a High-Performance Linear Algebra Library on FPGAs
Linear algebra computations can be greatly accelerated using spatial accelerators on FPGAs. As a standard building block of linear algebra applications, BLAS covers a wide range of compute patterns that vary vastly in data reuse, bottleneck resources, matrix storage layouts, and data types. However, existing implementations of BLAS routines on FPGAs are stuck in the dilemma of productivity and performance. They either require extensive human effort or fail to leverage the properties of routines for acceleration. We introduce Lasa, a framework composed of a programming model and a compiler, designed to address the dilemma by abstracting (for productivity) and specializing (for performance) the architecture of a spatial accelerator. The programming model realizes systolic arrays using uniform recurrence equations and space-time transforms. Streaming tensors, an intuitive dataflow-style abstraction, is proposed to uniformly describe the movement, storage, and transpose of input and output data across the spatial components. According to streaming tensors, a customized memory hierarchy is automatically built on an FPGA by our compiler. The compiler further specializes the architecture with transparent optimizations on FPGAs. Using this framework, we develop a complete BLAS library, demonstrating performance in parity with expert-written HLS code for BLAS level 3 routines, 76%–94% machine peak for level 1 and 2 routines, and 1.6X–13X speedup by leveraging the matrix properties such as symmetry, triangularity, and bandness.
- Open Access
- 2 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 199-210
POPA: Expressing High and Portable Performance across Spatial and Vector Architectures for Tensor Computations
This paper aims at high and portable performance for tensor computations across spatial (e.g., FPGAs) and vector architectures (e.g., GPUs). The state-of-the-art usually address performance portability across vector architectures (CPUs and GPUs). However, they either miss FPGAs or do not achieve high performance. Without a common architectural abstraction, they program and optimize spatial and vector devices separately, causing low portability. We propose a unified programming framework, POPA, which achieves portability via architectural abstraction and performance via specialization. A parallel dataflow machine is proposed as a unified, abstract hardware target that hides differences of concrete architectures. The machine consists of software-defined systolic arrays and a tensor-specific cache hierarchy, which captures pipeline parallelism and customizable memories on FPGAs, as well as multithreading parallelism on GPUs. The machine is specified in a unified programming model as two dataflow graphs for scheduling compute and data movement, respectively. A compiler then specializes the abstract machine to exploit the properties of FPGAs and GPUs, bridging the gap between the abstract machine and a concrete architecture. We evaluate POPA on several Intel FPGAs and GPUs with high-profile tensor kernels, and this is the first system that achieves >=80% performance of expert-written code or machine peak across architectures, to the best of our knowledge.
- 2 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 199-210
Open AccessPOPA: Expressing High and Portable Performance across Spatial and Vector Architectures for Tensor Computations
This paper aims at high and portable performance for tensor computations across spatial (e.g., FPGAs) and vector architectures (e.g., GPUs). The state-of-the-art usually address performance portability across vector architectures (CPUs and GPUs). However, they either miss FPGAs or do not achieve high performance. Without a common architectural abstraction, they program and optimize spatial and vector devices separately, causing low portability. We propose a unified programming framework, POPA, which achieves portability via architectural abstraction and performance via specialization. A parallel dataflow machine is proposed as a unified, abstract hardware target that hides differences of concrete architectures. The machine consists of software-defined systolic arrays and a tensor-specific cache hierarchy, which captures pipeline parallelism and customizable memories on FPGAs, as well as multithreading parallelism on GPUs. The machine is specified in a unified programming model as two dataflow graphs for scheduling compute and data movement, respectively. A compiler then specializes the abstract machine to exploit the properties of FPGAs and GPUs, bridging the gap between the abstract machine and a concrete architecture. We evaluate POPA on several Intel FPGAs and GPUs with high-profile tensor kernels, and this is the first system that achieves >=80% performance of expert-written code or machine peak across architectures, to the best of our knowledge.