References#
Ziye Yang, James R. Harris, Benjamin Walker, Daniel Verkamp, Changpeng Liu, Chunyun Chang, Gang Cao, Jonathan Stern, Vishal Verma, and Luse E. Paul. SPDK: a development kit to build high performance storage applications. In 2017 IEEE International Conference on Cloud Computing Technology and Science (CloudCom), 154–161. 2017. URL: https://ieeexplore.ieee.org/document/8241103, doi:10.1109/CloudCom.2017.14.
NVIDIA Corporation. Gpudirect storage: a direct path between storage and gpu memory. https://developer.nvidia.com/gpudirect-storage, 2020. Vendor-supported Linux kernel and driver modifications accelerating GPU–storage data movement while retaining kernel ownership of NVMe devices.
Jonas Markussen, Lars Bjørlykke Kristiansen, Pål Halvorsen, Halvor Kielland-Gyrud, Håkon Kvale Stensland, and Carsten Griwodz. Smartio: zero-overhead device sharing through pcie networking. ACM Transactions on Computer Systems, jul 2021. URL: https://doi.org/10.1145/3462545, doi:10.1145/3462545.
Zaid Qureshi, Vikram Sharma Mailthody, Isaac Gelado, Seung Won Min, Amna Masood, Jeongmin Park, Jinjun Xiong, C. J. Newburn, Dmitri Vainbrand, I-Hsin Chung, Michael Garland, William Dally, and Wen-mei Hwu. Bam: a case for enabling fine-grain high throughput GPU-orchestrated access to storage. In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems. 2023. URL: https://dl.acm.org/doi/10.1145/3534056.3534936, doi:10.1145/3534056.3534936.
Vikram Sharma Mailthody. Advancing memory and storage architectures for next-gen AI workloads. Future Memory and Storage, OPSW-301-1, 2025. URL: https://files.futurememorystorage.com/proceedings/2025/20250807_OPSW-301-1_Mailthody-2025-08-07-15.14.33.pdf.
PCI-SIG. PCI Express Base Specification, Revision 7.0, Version 1.0. Peripheral Component Interconnect Special Interest Group, June 2025. Section 9: Virtualization (The primary definition of SR-IOV and MR-IOV hardware architecture). URL: https://pcisig.com/specifications.
NVM Express NVMe over PCIe Transport Specification Revision 1.3. NVM Express, Inc., August 2025. URL: https://nvmexpress.org/wp-content/uploads/NVM-Express-NVMe-over-PCIe-Transport-Specification-Revision-1.3-2025.08.01-Ratified.pdf.
NVM Express Base Specification Revision 2.3. NVM Express, Inc., August 2025. URL: https://nvmexpress.org/wp-content/uploads/NVM-Express-Base-Specification-Revision-2.3-2025.08.01-Ratified.pdf.
NVM Express NVM Command Set Specification Revision 1.2. NVM Express, Inc., August 2025. URL: https://nvmexpress.org/wp-content/uploads/NVM-Express-NVM-Command-Set-Specification-Revision-1.2-2025.08.01-Ratified.pdf.
Wen-mei W. Hwu, David B. Kirk, and Izzat El Hajj. Programming Massively Parallel Processors: A Hands-on Approach. Morgan Kaufmann, 4 edition, 2022. ISBN 9780323912310.
Linux Kernel Developers. Ublk: user space block device. https://docs.kernel.org/block/ublk.html, 2023. Linux kernel framework enabling block device implementations in user space.
Intel Corporation. Storage performance development kit (spdk). https://spdk.io, 2019. User-space framework providing high-performance NVMe drivers and block device abstractions.
Simon A. F. Lund, Philippe Bonnet, Klaus B. A. Jensen, and Javier Gonzalez. I/o interface independence with xnvme. In Proceedings of the 15th ACM International Conference on Systems and Storage, SYSTOR '22, 108–119. New York, NY, USA, 2022. Association for Computing Machinery. URL: https://doi.org/10.1145/3534056.3534936, doi:10.1145/3534056.3534936.
Simon A. F. Lund and Vivek Shah. xNVMe: unleashing storage hardware-software co-design. arXiv preprint, 2024. URL: https://arxiv.org/abs/2411.06980, arXiv:2411.06980, doi:10.48550/arXiv.2411.06980.
xNVMe Project. Xnvme project website. https://xnvme.io/, 2024. Official project website for xNVMe, including documentation, source code links, and usage examples.
xal Project. Xal: extents access library. xnvme/xal, 2024. Open-source library for extracting file extent metadata from Linux file systems.
Linux Kernel Developers. Linux filesystem fiemap interface. https://docs.kernel.org/filesystems/fiemap.html, 2024. Documentation of the FIEMAP ioctl for retrieving file extent mappings.
Karl B. Torp, Simon A. F. Lund, and Pinar Tözün. Path to GPU-initiated I/O for data-intensive systems. In Proceedings of the 21st International Workshop on Data Management on New Hardware (DaMoN 2025), 1–9. Berlin, Germany, 2025. Association for Computing Machinery. URL: https://dl.acm.org/doi/10.1145/3736227.3736232, doi:10.1145/3736227.3736232.
Shi Qiu, Weinan Liu, Yifan Hu, Jianqin Yan, Zhirong Shen, Xin Yao, Renhai Chen, Gong Zhang, and Yiming Zhang. Geminifs: a companion file system for gpus. In Proceedings of the 23rd USENIX Conference on File and Storage Technologies, FAST '25. Santa Clara, CA, 2025. USENIX Association. URL: https://www.usenix.org/conference/fast25/presentation/qiu.
Shaobo Li, Yirui Eric Zhou, Yuqi Xue, Yuan Xu, and Jian Huang. Managing scalable direct storage accesses for gpus with gofs. In Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles, SOSP '25, 979–995. New York, NY, USA, 2025. Association for Computing Machinery. URL: https://doi.org/10.1145/3731569.3764857, doi:10.1145/3731569.3764857.
Simon A. F. Lund. Feeding the beast: bridging NVMe storage and GPUs while preserving file semantics. Future of Memory and Storage, 2025. URL: https://xnvme.io/_static/fms25.pdf.
Simon A. F. Lund, Karl B. Torp, and Nadja Brix Koch. Accelerator-integrated storage I/O. OCP Global Summit, 2025. URL: https://xnvme.io/_static/ocp25.pdf.