EBEdouard Bugnion

Edouard Bugnion

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Edouard Bugnion has a total of 25 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Flashpoint: Privileged-Software Isolation on RISC-V for Dynamic Root of Trust

    by Neelu S. Kalani, Charly Castes, Guokai Chen, Alexandre Doukhan, Daniel Bucher, Thomas Bourgeat, Edouard Bugnion

  • Open Access

    The Design and Implementation of a Virtual Firmware Monitor

    by Charly Castes, François Costa, Neelu S. Kalani, Timothy Roscoe, Nate Foster, Thomas Bourgeat, Edouard Bugnion


  • Open Access

    Lightweight Hypervisor Verification: Putting the Hardware Burger on a Diet

    by Charly Castes, François Costa, Nate Foster, Thomas Bourgeat, Edouard Bugnion


  • Open Access

    Shattering the Ephemeral Storage Cost Barrier for Data-Intensive Serverless Workflows

    by Shyam Jesalpura, Dmitrii Ustiugov, Michal Baczun, Bora A. Malper, Rustem Feyzkhanov, Edouard Bugnion, Marios Kogias, Boris Grot


  • Open Access

    Kicking the Firmware Out of the TCB with the Miralis Virtual Firmware Monitor

    by Charly Castes, Neelu S. Kalani, Sofia Saltovskaia, Noé Terrier, Abel Vexina Wilkinson, Edouard Bugnion

    The role of firmware has evolved over the past decades. Not only is firmware responsible for discovering, initializing, and monitoring the system's chipset, board, and devices, but it also acts as the root of trust and plays a leading role in confidential computing. Yet vulnerabilities in the non-security critical part of the firmware have repeatedly led to the compromise of the core TCB of the system. We propose an alternative architecture that excludes the non-security critical part of the firmware from the TCB by isolating it within a virtual machine with the introduction of a simple and verifiable virtual firmware monitor. We present the design of Miralis, the first virtual firmware monitor. Miralis can successfully boot Linux with a virtualized OpenSBI on RISC-V. We demonstrate through construction that the M-mode of RISC-V architecture meets the Popek & Golberg criteria for classical virtualization. Our initial evaluation shows that Miralis removes vendor-provided, platform-specific firmware from the TCB with no measurable impact on boot and run-time performance.


  • Open Access

    Creating Trust by Abolishing Hierarchies

    by Charly Castes, Adrien Ghosn, Neelu S. Kalani, Yuchen Qian, Marios Kogias, Mathias Payer, Edouard Bugnion

    Software is going through a trust crisis. Privileged code is no longer trusted and processes insufficiently protect user code from unverified libraries. While usually treated separately, confidential computing and program compartmentalization are both symptoms of the same problem, deeply rooted in hierarchical commodity systems: privileged software's monopoly over isolation. This paper proposes a separation of powers: to decouple trust and isolation from privilege hierarchies. It introduces an isolation monitor, which delivers verifiable isolation, confidentiality, and integrity to all software, independent of existing system abstractions and privilege hierarchies. Tyche, our prototype isolation monitor, runs on commodity hardware without relying on complex and emerging hardware security extensions. It enables any software component to create, compose, and nest isolation abstractions, including user and kernel sandboxes, enclaves, as well as confidential virtual machines.


  • Open Access

    A RISC-V Extension to Minimize Privileges of Enclave Runtimes

    by Neelu S. Kalani, Edouard Bugnion

    In confidential computing, the view of the system software is Manichean: the host operating system is untrusted and the TEE runtime system is fully trusted. However, the runtime system is often as complex as a full operating system, and thus is not free from bugs and exploitable vulnerabilities. Yet, it executes with complete system-level control over the enclave application, in violation of the least privilege principle. While the confidential computing research community has been striving to secure trusted software from its untrusted counterpart, efforts fall short when it comes to securing the enclave application from potentially bug-prone and vulnerable trusted runtime systems. This project describes the design of a simple RISC-V extension that prevents trusted runtime systems from accessing the enclave application's memory. We implement the hardware extension in the QEMU functional simulator and extend the Keystone TEE framework and its runtime system, Eyrie, to enforce the least privilege principle, support unmodified enclave applications, and prevent a class of Iago attacks that leverage the runtime system's unrestricted access to the enclave application's memory.

  • Open Access

    The Case for RackOut

    by Stanko Novakovic, Alexandros Daglis, Edouard Bugnion, Babak Falsafi, Boris Grot

    To provide low latency and high throughput guarantees, most large key-value stores keep the data in the memory of many servers. Despite the natural parallelism across lookups, the load imbalance, introduced by heavy skew in the popularity distribution of keys, limits performance. To avoid violating tail latency service-level objectives, systems tend to keep server utilization low and organize the data in micro-shards, which provides units of migration and replication for the purpose of load balancing. These techniques reduce the skew, but incur additional monitoring, data replication and consistency maintenance overheads. In this work, we introduce RackOut, a memory pooling technique that leverages the one-sided remote read primitive of emerging rack-scale systems to mitigate load imbalance while respecting service-level objectives. In RackOut, the data is aggregated at rack-scale granularity, with all of the participating servers in the rack jointly servicing all of the rack's micro-shards. We develop a queuing model to evaluate the impact of RackOut at the datacenter scale. In addition, we implement a RackOut proof-of-concept key-value store, evaluate it on two experimental platforms based on RDMA and Scale-Out NUMA, and use these results to validate the model. Our results show that RackOut can increase throughput up to 6x for RDMA and 8.6x for Scale-Out NUMA compared to a scale-out deployment, while respecting tight tail latency service-level objectives.


  • Open Access

    Manycore network interfaces for in-memory rack-scale computing

    by Alexandros Daglis, Stanko Novaković, Edouard Bugnion, Babak Falsafi, Boris Grot

    Datacenter operators rely on low-cost, high-density technologies to maximize throughput for data-intensive services with tight tail latencies. In-memory rack-scale computing is emerging as a promising paradigm in scale-out datacenters capitalizing on commodity SoCs, low-latency and high-bandwidth communication fabrics and a remote memory access model to enable aggregation of a rack's memory for critical data-intensive applications such as graph processing or key-value stores. Low latency and high bandwidth not only dictate eliminating communication bottlenecks in the software protocols and off-chip fabrics but also a careful on-chip integration of network interfaces. The latter is a key challenge especially in architectures with RDMA-inspired one-sided operations that aim to achieve low latency and high bandwidth through on-chip Network Interface (NI) support. This paper proposes and evaluates network interface architectures for tiled manycore SoCs for in-memory rack-scale computing. Our results indicate that a careful splitting of NI functionality per chip tile and at the chip's edge along a NOC dimension enables a rack-scale architecture to optimize for both latency and bandwidth. Our best manycore NI architecture achieves latencies within 3% of an idealized hardware NUMA and efficiently uses the full bisection bandwidth of the NOC, without changing the on-chip coherence protocol or the core's microarchitecture.