Jason H. Anderson
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jason H. Anderson has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Boma Anantasatya Adhi
RIKEN Center for Computational Science, Kobe, Hyogo, Japan
3 shared publications - Omar Ragheb
University of Toronto, Toronto, Canada
3 shared publications - Kentaro Sano
RIKEN Center for Computational Science, Kobe, Hyogo, Japan
2 shared publications - Linyi Li
University of Toronto, Toronto, ON, Canada
2 shared publications - Omkar Bhilare
University of Toronto, Toronto, Canada
2 shared publications - Tomohiro Ueno
Center for Computational Science, RIKEN, Japan
2 shared publications
Latest Publications
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
RAM-CGRA: Reachability-Aware Mapping for CGRAs
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessRAM-CGRA: Reachability-Aware Mapping for CGRAs
- Open Access
- 17 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 77-85
Hardware Sharing for Area Optimization of Floating-Point ALUs
- 17 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 77-85
Open AccessHardware Sharing for Area Optimization of Floating-Point ALUs
- Open Access
- 25 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 284-292
Performance and Area Optimization of Lossless Hardware Compression of Floating-Point Data Streams
- 25 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 284-292
Open AccessPerformance and Area Optimization of Lossless Hardware Compression of Floating-Point Data Streams
- Open Access
- 25 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 76-79
Impact of Reconvergent DFG Paths and Buffer Depth on Elastic CGRA Throughput
- 25 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 76-79
Open AccessImpact of Reconvergent DFG Paths and Buffer Depth on Elastic CGRA Throughput
- Open Access
- 25 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 67-75
Systolic Array-Based Matrix Multiplication and Reduction on Elastic CGRAs
- 25 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 67-75
Open AccessSystolic Array-Based Matrix Multiplication and Reduction on Elastic CGRAs
- Open Access
- 27 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 147-158
FRIDA: Reconfigurable Arrays for Dynamically Scheduled High-Level Synthesis
Reconfigurable computing fabrics include FPGAs and CGRAs. FPGAs offer flexible bit-level reconfigurability and can map almost any program via high-level synthesis (HLS) compilers, but they incur high area and speed overheads compared to ASICs. CGRAs, in contrast, provide ASIC-like performance but limited flexibility, typically supporting only feedforward programs with unambiguous memory accesses, far from the capabilities of HLS compilers. This work introduces a new class of reconfigurable arrays inspired by modern dynamically scheduled HLS (DHLS) tools. Unlike traditional HLS, DHLS compilers no longer produce explicit state machines, eliminating the need for look-up tables. Instead, they delegate scheduling decisions to a set of coarse-grained primitives. Our arrays leverage these primitives as processing elements and combine FPGA-style interconnect topology for high routing flexibility with CGRA-like bus-based interconnect. We present a framework to explore these arrays and evaluate a preliminary architecture using DHLS benchmarks. The results show an average of ~2× speed improvement, but unfortunately only a ~20% area reduction compared to an FPGA implemented on the same technology node.
- 27 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 147-158
Open AccessFRIDA: Reconfigurable Arrays for Dynamically Scheduled High-Level Synthesis
Reconfigurable computing fabrics include FPGAs and CGRAs. FPGAs offer flexible bit-level reconfigurability and can map almost any program via high-level synthesis (HLS) compilers, but they incur high area and speed overheads compared to ASICs. CGRAs, in contrast, provide ASIC-like performance but limited flexibility, typically supporting only feedforward programs with unambiguous memory accesses, far from the capabilities of HLS compilers. This work introduces a new class of reconfigurable arrays inspired by modern dynamically scheduled HLS (DHLS) tools. Unlike traditional HLS, DHLS compilers no longer produce explicit state machines, eliminating the need for look-up tables. Instead, they delegate scheduling decisions to a set of coarse-grained primitives. Our arrays leverage these primitives as processing elements and combine FPGA-style interconnect topology for high routing flexibility with CGRA-like bus-based interconnect. We present a framework to explore these arrays and evaluate a preliminary architecture using DHLS benchmarks. The results show an average of ~2× speed improvement, but unfortunately only a ~20% area reduction compared to an FPGA implemented on the same technology node.
- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
CLUMAP: Clustered Mapper for CGRAs with Predication
Coarse-grained reconfigurable architectures (CGRAs) have gained popularity as accelerators for compute-intensive kernels. Complex CGRA architectures that support key features such as multi-context and predication are being developed to support a wider range of kernels. However, mapping applications on these complex architectures poses significant challenges. In this paper, we provide an architecture-agnostic clustered mapping technique and a new cost function tailored for simulated-annealing placement. The mapper simplifies placement and routing phases, demonstrating significant speedup for popular CGRA architectures: HyCUBE and ADRES. Additionally, our method demonstrates an increase in mapping success for the ADRES architecture.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessCLUMAP: Clustered Mapper for CGRAs with Predication
Coarse-grained reconfigurable architectures (CGRAs) have gained popularity as accelerators for compute-intensive kernels. Complex CGRA architectures that support key features such as multi-context and predication are being developed to support a wider range of kernels. However, mapping applications on these complex architectures poses significant challenges. In this paper, we provide an architecture-agnostic clustered mapping technique and a new cost function tailored for simulated-annealing placement. The mapper simplifies placement and routing phases, demonstrating significant speedup for popular CGRA architectures: HyCUBE and ADRES. Additionally, our method demonstrates an increase in mapping success for the ADRES architecture.
- Open Access
- 19 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 109-118
CAD Techniques for NoC-Connected Multi-CGRA Systems
Coarse-grained reconfigurable arrays (CGRAs) are programmable hardware platforms that are a means of realizing application accelerators. A CGRA is a 2D array of configurable processing elements (PEs), that connect to one another through programmable interconnects. PEs and interconnects in CGRAs are configurable at the word level, as opposed to at the bit level in FPGAs. A network-on-chip (NoC) is an on-chip communications system comprising routers and links, where data is packet-switched. NoCs provide more scalable communication vs. traditional on-chip busses or crossbars. In this paper, we propose an NoC-connected multi-CGRA system, where multiple modest-sized CGRAs communicate using an NoC. We introduce CAD techniques that partition and place an application across the “distributed” NoC-connected CGRAs. We study the quality and runtime of the CAD techniques on a system having sixteen 4 × 4 CGRAs connected together using a 2D mesh NoC.
- 19 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 109-118
Open AccessCAD Techniques for NoC-Connected Multi-CGRA Systems
Coarse-grained reconfigurable arrays (CGRAs) are programmable hardware platforms that are a means of realizing application accelerators. A CGRA is a 2D array of configurable processing elements (PEs), that connect to one another through programmable interconnects. PEs and interconnects in CGRAs are configurable at the word level, as opposed to at the bit level in FPGAs. A network-on-chip (NoC) is an on-chip communications system comprising routers and links, where data is packet-switched. NoCs provide more scalable communication vs. traditional on-chip busses or crossbars. In this paper, we propose an NoC-connected multi-CGRA system, where multiple modest-sized CGRAs communicate using an NoC. We introduce CAD techniques that partition and place an application across the “distributed” NoC-connected CGRAs. We study the quality and runtime of the CAD techniques on a system having sixteen 4 × 4 CGRAs connected together using a 2D mesh NoC.
- Open Access
- 14 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 59-68
Exploration of Compute vs. Interconnect Tradeoffs in CGRAs for HPC
We consider the balance between compute density and interconnect in Coarse-Grained Reconfigurable Architectures (CGRAs) intended for acceleration of HPC applications. We model a baseline CGRA architecture [2] in the open-source CGRA-ME framework [11] and describe the modelling as a case study. Then, holding the interconnect fabric constant, we create several variants of the baseline CGRA: 1) one having reduced (sparser) compute capability where not all ALUs are fully capable, 2) one having increased (denser) compute capability, where the amount of compute is roughly doubled relative to the baseline, and 3) one with increased I/O bandwidth. In an experimental study, we evaluate all architectures to assess application mappability and resource usage for a set of benchmark applications. We also evaluate silicon area consumption using a standard-cell ASIC flow. Results show the baseline CGRA to be overprovisioned in both compute and interconnect, with the proposed variants offering superior area efficiency.
- 14 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 59-68
Open AccessExploration of Compute vs. Interconnect Tradeoffs in CGRAs for HPC
We consider the balance between compute density and interconnect in Coarse-Grained Reconfigurable Architectures (CGRAs) intended for acceleration of HPC applications. We model a baseline CGRA architecture [2] in the open-source CGRA-ME framework [11] and describe the modelling as a case study. Then, holding the interconnect fabric constant, we create several variants of the baseline CGRA: 1) one having reduced (sparser) compute capability where not all ALUs are fully capable, 2) one having increased (denser) compute capability, where the amount of compute is roughly doubled relative to the baseline, and 3) one with increased I/O bandwidth. In an experimental study, we evaluate all architectures to assess application mappability and resource usage for a set of benchmark applications. We also evaluate silicon area consumption using a standard-cell ASIC flow. Results show the baseline CGRA to be overprovisioned in both compute and interconnect, with the proposed variants offering superior area efficiency.
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 25-30
Sensei: An area-reduction advisor for FPGA high-level synthesis
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 25-30
Sensei: An area-reduction advisor for FPGA high-level synthesis