TileLoom: Automatic Dataflow Planning for Tile-Based Languages on Spatial Dataflow Accelerators
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918495165349888 |
|---|---|
| author | Li, Wei Bai, Zhenyu Wang, Heru Dangi, Pranav Zhang, Zhiqiang Tan, Cheng Lan, Huiying Wong, Weng-Fai Mitra, Tulika |
| author_facet | Li, Wei Bai, Zhenyu Wang, Heru Dangi, Pranav Zhang, Zhiqiang Tan, Cheng Lan, Huiying Wong, Weng-Fai Mitra, Tulika |
| contents | Spatial dataflow accelerators are a promising direction for next-generation computer systems because they can reduce the memory bottlenecks of traditional von Neumann machines such as CPUs and GPUs. They organize computation around explicit, compiler-managed data movement over on-chip networks, allowing operands to be forwarded directly between processing elements and reducing reliance on high-latency, bandwidth-limited global shared memory. However, their performance depends strongly on how workloads are mapped to hardware. Naive mappings can perform poorly, and most users rely on hand-tuned vendor libraries. Thus, despite their potential for high performance, energy efficiency, and cost efficiency, limited programmability remains a major barrier to wider adoption.
This paper presents TileLoom, an MLIR-based end-to-end framework that compiles tile-based programs, such as Triton kernels, onto spatial dataflow architectures. Unlike compiler frameworks that focus on optimizing code generation within a single tile, TileLoom distributes tile instances across spatially distributed cores and exploits the on-chip network and distributed memories to increase data reuse and reduce communication. TileLoom introduces a hardware representation that captures interconnect topology, memory hierarchy, and compute capabilities, enabling both architecture-specific optimizations and support for diverse spatial dataflow targets. In experiments on two generations of Tenstorrent systems, TileLoom achieves performance comparable to vendor libraries on various kernels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TileLoom: Automatic Dataflow Planning for Tile-Based Languages on Spatial Dataflow Accelerators Li, Wei Bai, Zhenyu Wang, Heru Dangi, Pranav Zhang, Zhiqiang Tan, Cheng Lan, Huiying Wong, Weng-Fai Mitra, Tulika Distributed, Parallel, and Cluster Computing Programming Languages Spatial dataflow accelerators are a promising direction for next-generation computer systems because they can reduce the memory bottlenecks of traditional von Neumann machines such as CPUs and GPUs. They organize computation around explicit, compiler-managed data movement over on-chip networks, allowing operands to be forwarded directly between processing elements and reducing reliance on high-latency, bandwidth-limited global shared memory. However, their performance depends strongly on how workloads are mapped to hardware. Naive mappings can perform poorly, and most users rely on hand-tuned vendor libraries. Thus, despite their potential for high performance, energy efficiency, and cost efficiency, limited programmability remains a major barrier to wider adoption. This paper presents TileLoom, an MLIR-based end-to-end framework that compiles tile-based programs, such as Triton kernels, onto spatial dataflow architectures. Unlike compiler frameworks that focus on optimizing code generation within a single tile, TileLoom distributes tile instances across spatially distributed cores and exploits the on-chip network and distributed memories to increase data reuse and reduce communication. TileLoom introduces a hardware representation that captures interconnect topology, memory hierarchy, and compute capabilities, enabling both architecture-specific optimizations and support for diverse spatial dataflow targets. In experiments on two generations of Tenstorrent systems, TileLoom achieves performance comparable to vendor libraries on various kernels. |
| title | TileLoom: Automatic Dataflow Planning for Tile-Based Languages on Spatial Dataflow Accelerators |
| topic | Distributed, Parallel, and Cluster Computing Programming Languages |
| url | https://arxiv.org/abs/2512.22168 |