Extending High-Level Synthesis for Task-Parallel Programs

Chi, Yuze; Guo, Licheng; Choi, Young-Kyu; Wang, Jie; Cong, Jason

doi:10.1145/3431920.3439470

Cited by 7 publications

(5 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The OCaml heap and stack can be stored either in the on-chip memory of the target FPGA (for small programs) or in the external memory (SDRAM) of the board. In both cases, access is provided by means of an interconnection bus 7 . This bus also supports data transfers between the custom components and the binary code executed by the processor.…”

Section: Our Contributions Arementioning

confidence: 99%

“…Aparapi [24] and GVM [12] implement the JVM in OpenCL. TAPA [7] is a framework for task parallelism targeting OpenCL. TornadoVM [22] compiles specially annotated Java code to OpenCL.…”

Section: Introductionmentioning

confidence: 99%

“…These tools, however, do not sufficiently expose the fine-grained parallelism available on the FPGAs nor their customization possibilities. -FPGAs allows implementing parallel programming models [18] like task-parallelism [7] and parallel skeletons [9]. For instance, Lime [2] is a task-based data-flow programming language compiled to OpenCL or Verilog and interacting with Java bytecode running on a CPU.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Accelerating OCaml Programs on FPGA

Sylvestre

Chailloux

Sérot

2023

Int J Parallel Prog

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

Section: Our Contributions Arementioning

confidence: 99%

“…Aparapi [24] and GVM [12] implement the JVM in OpenCL. TAPA [7] is a framework for task parallelism targeting OpenCL. TornadoVM [22] compiles specially annotated Java code to OpenCL.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accelerating OCaml Programs on FPGA

Sylvestre

Chailloux

Sérot

2023

Int J Parallel Prog

View full text Add to dashboard Cite

show abstract

“…There are a number of tasking systems that have emerged in the recent years targeting different layers of the application, from low-level assembly layer [35], and parallelizing compilers [49] to high level tasking frameworks [13]. A complete review of the current state-of-the-art tasking environments is outside the scope of this section.…”

Section: Related Workmentioning

confidence: 99%

“…Investigating the cause of this overhead and optimizing the abt and Fig. 13 Effect of scheduling limit for the second approach using the tbb back-end. Right zoom-in in range 0.5-2.0…”

Section: Performance Evaluationmentioning

confidence: 99%

Tasking framework for adaptive speculative parallel mesh generation

2021

View full text Add to dashboard Cite

Handling the ever-increasing complexity of mesh generation codes along with the intricacies of newer hardware often results in codes that are both difficult to comprehend and maintain. Different facets of codes such as thread management and load balancing are often intertwined, resulting in efficient but highly complex software. In this work, we present a framework which aids in establishing a core principle, deemed separation of concerns, where functionality is separated from performance aspects of various mesh operations. In particular, thread management and scheduling decisions are elevated into a generic and reusable tasking framework. The results indicate that our approach can successfully abstract the load balancing aspects of two case studies, while providing access to a plethora of different execution backends. One would expect, this new flexibility to lead to some additional cost. However, for the configurations studied in this work, we observed up to 13% speedup for some meshing operations and up to 5.8% speedup over the entire application runtime compared to hand-optimized code. Moreover, we show that by using different task creation strategies, the overhead compared to straight-forward task execution models can be improved dramatically by as much as 1200% without compromises in portability and functionality.

show abstract