Revet: A Language and Compiler for Dataflow Threads
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913216413564928 |
|---|---|
| author | Rucker, Alexander Sundram, Shiv Smith, Coleman Vilim, Matthew Prabhakar, Raghu Kjolstad, Fredrik Olukotun, Kunle |
| author_facet | Rucker, Alexander Sundram, Shiv Smith, Coleman Vilim, Matthew Prabhakar, Raghu Kjolstad, Fredrik Olukotun, Kunle |
| contents | Spatial dataflow architectures such as reconfigurable dataflow accelerators (RDA) can provide much higher performance and efficiency than CPUs and GPUs. In particular, vectorized reconfigurable dataflow accelerators (vRDA) in recent literature represent a design point that enhances the efficiency of dataflow architectures with vectorization. Today, vRDAs can be exploited using either hardcoded kernels or MapReduce languages like Spatial, which cannot vectorize data-dependent control flow. In contrast, CPUs and GPUs can be programmed using general-purpose threaded abstractions.
The ideal combination would be the generality of a threaded programming model coupled with the efficient execution model of a vRDA. We introduce Revet: a programming model, compiler, and execution model that lets threaded applications run efficiently on vRDAs. The Revet programming language uses threads to support a broader range of applications than Spatial's parallel patterns, and our MLIR-based compiler lowers this language to a generic dataflow backend that operates on streaming tensors. Finally, we show that mapping threads to dataflow outperforms GPUs, the current state-of-the-art for threaded accelerators, by 3.8x. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_06124 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Revet: A Language and Compiler for Dataflow Threads Rucker, Alexander Sundram, Shiv Smith, Coleman Vilim, Matthew Prabhakar, Raghu Kjolstad, Fredrik Olukotun, Kunle Hardware Architecture Spatial dataflow architectures such as reconfigurable dataflow accelerators (RDA) can provide much higher performance and efficiency than CPUs and GPUs. In particular, vectorized reconfigurable dataflow accelerators (vRDA) in recent literature represent a design point that enhances the efficiency of dataflow architectures with vectorization. Today, vRDAs can be exploited using either hardcoded kernels or MapReduce languages like Spatial, which cannot vectorize data-dependent control flow. In contrast, CPUs and GPUs can be programmed using general-purpose threaded abstractions. The ideal combination would be the generality of a threaded programming model coupled with the efficient execution model of a vRDA. We introduce Revet: a programming model, compiler, and execution model that lets threaded applications run efficiently on vRDAs. The Revet programming language uses threads to support a broader range of applications than Spatial's parallel patterns, and our MLIR-based compiler lowers this language to a generic dataflow backend that operates on streaming tensors. Finally, we show that mapping threads to dataflow outperforms GPUs, the current state-of-the-art for threaded accelerators, by 3.8x. |
| title | Revet: A Language and Compiler for Dataflow Threads |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2302.06124 |