docs: audit and correct References section in Supercomputing whitepaper#1
Conversation
- Entry 6 (TensorPlane): updated title to 'Zero-Kernel User-Space Storage Engine for AI Workloads' with correct author/publisher/year format - Entry 5 (DAOS): replaced Intel marketing brief with official DAOS docs (docs.daos.io); added 'High-Performance Storage Fabric' language per tone requirements - Entry 16 (DAOS v2.4): added 'High-Performance Storage Fabric for Distributed Workloads' descriptor for tone consistency - Entry 12 (SPDK): replaced non-authoritative simplyblock.io glossary with official SPDK documentation (spdk.io/doc/introduction.html) - Entry 45 (XRP): fixed broken Google search URL wrapper → direct USENIX PDF - Entry 50 (PolarDB): fixed broken Google search URL wrapper → direct URL - Entry 23: improved title from copyright notice to descriptive dissertation title - Entries 1–35: standardized to Author. 'Title.' *Source/Publisher*, Year. format, matching the professional academic style of entries 36–52 - Entries 36–52: unified trailing period style; removed stray backslash-dots Agent-Logs-Url: https://github.com/SiliconLanguage/tensorplane/sessions/22480d10-d9d4-41f1-8f36-fffc1e3b0299 Co-authored-by: ping-long-github <155590345+ping-long-github@users.noreply.github.com>
Agent-Logs-Url: https://github.com/SiliconLanguage/tensorplane/sessions/22480d10-d9d4-41f1-8f36-fffc1e3b0299 Co-authored-by: ping-long-github <155590345+ping-long-github@users.noreply.github.com>
There was a problem hiding this comment.
Pull request overview
Updates the References section of the “Supercomputing 0-Kernel Storage Virtualization” whitepaper to improve citation consistency and replace several references with more authoritative sources / direct links.
Changes:
- Standardizes references 1–35 into a more academic citation format (aligning with the later entries).
- Replaces DAOS/SPDK references with official documentation sources and updates the TensorPlane title/attribution.
- Fixes broken “Google search wrapper” URLs by linking directly to the target PDFs.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
|
||
| 10. Ren, Z., & Trivedi, A. "[Performance Characterization of Modern Storage Stacks: POSIX I/O, libaio, SPDK, and io\_uring](https://www.researchgate.net/publication/370601725_Performance_Characterization_of_Modern_Storage_Stacks_POSIX_IO_libaio_SPDK_and_io_uring)." *ResearchGate*, 2023. | ||
|
|
||
| 11. "[io\_uring for High-Performance DBMSs: When and How to Use It](https://arxiv.org/html/2512.04859v1)." *arXiv preprint*, arXiv:2512.04859, 2024. |
There was a problem hiding this comment.
Reference 11 lists the year as 2024, but the arXiv identifier 2512.04859 indicates a 2025-12 submission (arXiv IDs encode YYMM). Please update the year to match the arXiv ID (or confirm from the arXiv page and cite the correct publication year if it later appeared elsewhere).
| 11. "[io\_uring for High-Performance DBMSs: When and How to Use It](https://arxiv.org/html/2512.04859v1)." *arXiv preprint*, arXiv:2512.04859, 2024. | |
| 11. "[io\_uring for High-Performance DBMSs: When and How to Use It](https://arxiv.org/html/2512.04859v1)." *arXiv preprint*, arXiv:2512.04859, 2025. |
|
|
||
| 14. Zhong, Y., et al. "[XRP: In-Kernel Storage Functions with eBPF - Extended Abstract](https://nvmw.ucsd.edu/nvmw2023-program/nvmw2023-paper17-final_version_your_extended_abstract.pdf)." *Non-Volatile Memories Workshop (NVMW 2023)*, UCSD, 2023. | ||
|
|
||
| 15. "[What Is the LD\_PRELOAD Trick?](https://stackoverflow.com/questions/426230/what-is-the-ld-preload-trick)" *Stack Overflow Community Discussion*, Stack Overflow, 2008. |
There was a problem hiding this comment.
This entry is missing the punctuation/terminator used elsewhere in the list (period after the linked title, and a trailing period at the end of the citation). Adding the missing periods will keep the reference format consistent with the surrounding entries.
| 15. "[What Is the LD\_PRELOAD Trick?](https://stackoverflow.com/questions/426230/what-is-the-ld-preload-trick)" *Stack Overflow Community Discussion*, Stack Overflow, 2008. | |
| 15. "[What Is the LD\_PRELOAD Trick?](https://stackoverflow.com/questions/426230/what-is-the-ld-preload-trick)." *Stack Overflow Community Discussion*, Stack Overflow, 2008. |
|
|
||
| 2. Hwang, J., et al. "[Rearchitecting Linux Storage Stack for µs Latency and High Throughput](https://www.usenix.org/system/files/osdi21-hwang.pdf)." *15th USENIX Symposium on Operating Systems Design and Implementation (OSDI '21)*, USENIX Association, 2021. | ||
|
|
||
| 3. "[BypassD: Enabling Fast Userspace Access to Shared SSDs](https://pages.cs.wisc.edu/~swift/papers/asplos24-bypassd.pdf)." *29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '24)*, ACM, 2024. |
There was a problem hiding this comment.
PR description says entries 1–35 were standardized to an Author. "[Title](URL)." *Source*, Year. pattern, but this reference has no author listed. Either add an author/corporate author (e.g., the paper’s authors or conference) or adjust the standardization claim/format so it’s consistently applied across entries 1–35.
|
|
||
| 3. "[BypassD: Enabling Fast Userspace Access to Shared SSDs](https://pages.cs.wisc.edu/~swift/papers/asplos24-bypassd.pdf)." *29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '24)*, ACM, 2024. | ||
|
|
||
| 4. Chenldc, D. "[Quick Summary: What Modern NVMe Storage Can Do, and How To Exploit It - High-Performance I/O for Modern Storage Systems](https://medium.com/@dichenldc/quick-paper-summary-what-modern-nvme-storage-can-do-and-how-to-exploit-it-high-performance-i-o-438a55ff6901)." *Medium*, 2022. |
There was a problem hiding this comment.
The author field here (Chenldc, D.) doesn’t clearly correspond to the cited source (the Medium account in the URL is @dichenldc). Consider citing the author as the actual name shown on the post (if available) or using the handle consistently (e.g., dichenldc) so the attribution is unambiguous and verifiable.
| 4. Chenldc, D. "[Quick Summary: What Modern NVMe Storage Can Do, and How To Exploit It - High-Performance I/O for Modern Storage Systems](https://medium.com/@dichenldc/quick-paper-summary-what-modern-nvme-storage-can-do-and-how-to-exploit-it-high-performance-i-o-438a55ff6901)." *Medium*, 2022. | |
| 4. dichenldc. "[Quick Summary: What Modern NVMe Storage Can Do, and How To Exploit It - High-Performance I/O for Modern Storage Systems](https://medium.com/@dichenldc/quick-paper-summary-what-modern-nvme-storage-can-do-and-how-to-exploit-it-high-performance-i-o-438a55ff6901)." *Medium*, 2022. |
References section in the AI Supercomputing whitepaper had inconsistent citation formats, a stale TensorPlane title, non-authoritative sources for DAOS and SPDK, and two entries with broken Google search wrapper URLs.
Changes
TensorPlane (entry 6)
"TensorPlane: Zero-Kernel User-Space Storage Engine for AI Workloads", attributed to SiliconLanguage, GitHub Repository, 2026DAOS – source quality + tone (entries 5, 16)
docs.daos.io); title reflects "High-Performance Storage Fabric for Exascale AI Infrastructure"SPDK – authoritative source (entry 12)
simplyblock.ioglossary replaced with official SPDK Architecture Overview (spdk.io/doc/introduction.html)Broken links fixed (entries 45, 50)
google.com/search?q=https://...wrapper removed → direct USENIX PDFFormat standardization (entries 1–35)
Title \- Source, accessed Date, [URL]to uniform academic format matching entries 36–52:Author. "[Title](URL)." *Source/Publisher*, Year.Misc