Unifying Static and Dynamic Intermediate Languages for Accelerator Generators
Caleb Kim, Pai Li, Anshuman Mohan, Andrew Butt, Adrian Sampson, Rachit Nigam
Abstract
Compilers for accelerator design languages (ADLs) translate high-level languages into application-specific hardware. ADL compilers rely on a hardware control interface to compose hardware units. There are two choices: static control, which relies on cycle-level timing; or dynamic control, which uses explicit signalling to avoid depending on timing details. Static control is efficient but brittle; dynamic control incurs hardware costs to support compositional reasoning. Piezo is an ADL compiler that unifies static and dynamic control in a single intermediate language (IL). Its key insight is that the IL’s static fragment is a refinement of its dynamic fragment: static code admits a subset of the run-time behaviors of the dynamic equivalent. Piezo can optimize code by combining facts from static and dynamic submodules, and it opportunistically converts code from dynamic to static control styles. We implement Piezo as an extension to an existing dynamic ADL compiler, Calyx. We use Piezo to implement a frontend for an existing ADL, a systolic array generator, and a packet-scheduling hardware generator to demonstrate its optimizations and the static–dynamic interactions it enables.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- A compiler infrastructure for accelerator generators cites Predictable accelerator design with time-sensitive affine types
- A compiler infrastructure for accelerator generators cites Type-directed scheduling of streaming accelerators
- Understanding Accelerator Compilers via Performance Profiling cites A compiler infrastructure for accelerator generators
- Understanding Accelerator Compilers via Performance Profiling cites Predictable accelerator design with time-sensitive affine types
- HIR: An MLIR-based Intermediate Representation for Hardware Accelerator Description cites Predictable accelerator design with time-sensitive affine types
- HIR: An MLIR-based Intermediate Representation for Hardware Accelerator Description cites Type-directed scheduling of streaming accelerators
- Modular Hardware Design with Timeline Types cites A compiler infrastructure for accelerator generators
- Modular Hardware Design with Timeline Types cites Predictable accelerator design with time-sensitive affine types
- Modular Hardware Design with Timeline Types cites Type-directed scheduling of streaming accelerators
- Anvil: A General-Purpose Timing-Safe Hardware Description Language cites HIR: An MLIR-based Intermediate Representation for Hardware Accelerator Description
- Anvil: A General-Purpose Timing-Safe Hardware Description Language cites Modular Hardware Design with Timeline Types
- Type-directed scheduling of streaming accelerators cites Predictable accelerator design with time-sensitive affine types
Cited by top-tier papers2
- Understanding Accelerator Compilers via Performance ProfilingAyaka Yorihiro, Griffin Berlstein, Pedro Pontes García, Kevin Laeufer et al.OOPSLA 2026
- Anvil: A General-Purpose Timing-Safe Hardware Description LanguageJason Zhijingcheng Yu, Aditya Ranjan Jha, Umang Mathur, Trevor E. Carlson et al.ASPLOS 2026
Builds on7
- Predictable accelerator design with time-sensitive affine typesRachit Nigam, Sachille Atapattu, Samuel Thomas, Zhijing Li et al.PLDI 2020 · 58 citations
- A compiler infrastructure for accelerator generatorsRachit Nigam, Samuel Thomas, Zhijing Li, Adrian SampsonASPLOS 2021 · 54 citations
- Type-directed scheduling of streaming acceleratorsDavid Durst, Matthew Feldman, Dillon Huff, David Akeley et al.PLDI 2020 · 49 citations
- Modular Hardware Design with Timeline TypesRachit Nigam, Pedro Henrique Azevedo de Amorim, Adrian SampsonPLDI 2023 · 16 citations
- HIR: An MLIR-based Intermediate Representation for Hardware Accelerator DescriptionKingshuk Majumder, Uday BondhugulaASPLOS 2023 · 12 citations
Related papers
- Stepwise Debugging for Hardware AcceleratorsGriffin Berlstein, Rachit Nigam, Christophe Gyurgyik, Adrian SampsonASPLOS 2023 · 2 citations
- Allo: A Programming Model for Composable Accelerator DesignHongzheng Chen, Niansong Zhang, Shaojie Xiang, Zhichen Zeng et al.PLDI 2024 · 41 citations
- CRUSH: A Credit-Based Approach for Functional Unit Sharing in Dynamically Scheduled HLSJiahui Xu, Lana JosipovicASPLOS 2025 · 1 citation
- Graph.hls: A Compiler Framework for Composable Graph Accelerator DesignFeiyang Wu, Xuxiao Yang, Zhuohang Bian, Jing Wang et al.ISCA 2026 · 1 citation
- Exocompilation for productive programming of hardware acceleratorsYuka Ikarashi, Gilbert Louis Bernstein, Alex Reinking, Hasan Genc et al.PLDI 2022 · 56 citations
