IronBus: A Decentralized Trusted Bus for Accelerators - A HW-SW Co-Designed Trusted Acceleration Interface
Cloud providers increasingly deploy accelerators like GPUs and TPUs for AI and data analytics. To secure these devices, emerging trusted I/O architectures (e.g., Intel TDX-Connect, AMD SEV-IO) extend the host CPU’s trusted domain to the accelerator fabric. However, these CPU-centric designs have three limitations: (1) TCB bloat: any guarantee about where data flows rests on a full guest OS; (2) Coarse-grained control: lacking application-aware data flow policies; and (3) Centralized bottlenecks: host-mediated peer-to-peer traffic puts the host on every transfer’s data path. To address these challenges, we propose a decentralized trusted bus that provides attested, hardware-protected channels for direct data movement between accelerators. IronBus realizes this abstraction through a cross-layer hardware/OS/compiler co-design for next-generation interconnect fabrics. IronBus shifts access control from the centralized host to a per-device Attested Interface Unit (AIU) —a minimal silicon Root-of-Trust that enforces security policies at the fabric endpoints. Orchestrating these units is a Hardware-Abstraction Layer (HAL) —a hardware-proximate lean software layer with formally verified protocols that replaces the guest OS to bootstrap trust. IronBus also introduces a DFG-based programming model and policy compiler : developers express multi-accelerator pipelines as Device Flow Graphs (DFGs) , from which the compiler automatically synthesizes Security Service Level Agreements (SSLAs) , and the HAL signs execution proofs for auditing. We prototype IronBus on a many-core RISC-V platform, evaluate it in gem5 , and formally verify its protocols with Tamarin and CryptoVerif . The IronBus HAL is as small as the SEV and TDX firmware, whereas for their data-flow policy host-centric designs trust a guest OS and firmware that are together 3–94 × larger. Direct device-to-device channels make IronBus 1.1–2 × faster than host-centric designs on accelerator chains, collectives, and ML workloads, even when every device has its own host link. The cryptographic bus costs 5–23% on communication microbenchmarks and at most 10% on ML workloads over an unprotected baseline.
Authors
- Atsushi Koshiba (ORCID: https://orcid.org/0000-0001-5439-4357)
- Pramod Bhatotia (ORCID: https://orcid.org/0000-0002-3220-5735)
- Harshavardhan Unnibhavi (ORCID: https://orcid.org/0000-0003-0375-2235)
- Nuno Santos (ORCID: https://orcid.org/0000-0001-9938-0653)
- Julian Pritzi (ORCID: https://orcid.org/0009-0000-6332-0448)
Institutions
- Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento (PT)
- Tokyo University of Science (JP)
- Technical University of Munich (DE)
Publication Details
- Journal
- ACM Transactions on Architecture and Code Optimization
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1145/3864376
- Primary Topic
- Security and Verification in Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- European Commission
- Deutsche Forschungsgemeinschaft
- Fundação para a Ciência e a Tecnologia
- Core Research for Evolutional Science and Technology