Uploaded November 2025 | Updated September 2026, 2 weeks ago
CXL enables disaggregated memory, both for composable capacity-on-demand and shared-memory. That is memory is not private to one server. Adding system-ram capacity should largely “just work”, but shared memory is more complex. The Fabric-Attached Memory File System (famfs) enables disaggregated shared memory to be used as memory-mappable files that map directly to the shared memory. Famfs is open source software which is on-track to be merged into the upstream Linux kernel in the coming months.
This talk covers the following: * Brief: shared memory challenges before memory disaggregation * Shared memory challenges with disaggregation * CXL: what will disaggregated shared memory look like? 1. Dynamic Capacity Device (DCD) overview 2. Coherency options 3. Using raw disaggregated memory * Famfs: Putting disaggregated shared memory to use with little or no app modifications Famfs background * Famfs on github * Famfs at the Linux Plumbers Conference (2023, 2024) * Famfs at the Linux Storage, File System and Memory Management summit (LSFMM – 2024, 2025) * Famfs at the Usenix File and Storage Technologies conference (FAST – 2025)
Review legacy shared-memory challenges Understand new challenges with Disaggregated shared memory Understand how CXL shared memory will work Understand how the open-source famfs file system enables legacy apps to use shared memory.
Presented by John Groves, Co-Chair, CXL Consortium Software and Systems Working Group
Learn More:
• SDC Website: snia.org/sniadeveloper
• SNIA Website: snia.org
• SNIA Educational Library: snia.org/library
• X: twitter.com/SNIA
• LinkedIn: linkedin.com/company/snia
CXL enables disaggregated memory, both for composable capacity-on-demand and shared-memory. That is memory is not private to one server. Adding system-ram capacity should largely “just work”, but shared memory is more complex. The Fabric-Attached Memory File System (famfs) enables disaggregated shared memory to be used as memory-mappable files that map directly to the shared memory. Famfs is open source software which is on-track to be merged into the upstream Linux kernel in the coming months.
This talk covers the following: * Brief: shared memory challenges before memory disaggregation * Shared memory challenges with disaggregation * CXL: what will disaggregated shared memory look like? 1. Dynamic Capacity Device (DCD) overview 2. Coherency options 3. Using raw disaggregated memory * Famfs: Putting disaggregated shared memory to use with little or no app modifications Famfs background * Famfs on github * Famfs at the Linux Plumbers Conference (2023, 2024) * Famfs at the Linux Storage, File System and Memory Management summit (LSFMM – 2024, 2025) * Famfs at the Usenix File and Storage Technologies conference (FAST – 2025)
Review legacy shared-memory challenges Understand new challenges with Disaggregated shared memory Understand how CXL shared memory will work Understand how the open-source famfs file system enables legacy apps to use shared memory.
Presented by John Groves, Co-Chair, CXL Consortium Software and Systems Working Group
Learn More:
• SDC Website: snia.org/sniadeveloper
• SNIA Website: snia.org
• SNIA Educational Library: snia.org/library
• X: twitter.com/SNIA
• LinkedIn: linkedin.com/company/snia







![Nanopore sequencing of synthetic libraries of RNA oligonucleotides
Photolithography is one of the very approaches that allow for the synthesis of nucleic acid microarrays in situ, and characteristic aspects of in situ microarray synthesis are high-throughput and high-density, delivering several hundreds of thousands of unique sequences in a single run and on a single, small surface (Figure 1). Microarray synthesis has traditionally focused on the preparation of DNA microarrays to obtain complex DNA libraries. These have been used in the context of DNA data storage, gene synthesis and other nanotechnology applications [1]. Recently, our group has shown that photolithography is amenable to prepare RNA microarrays as well, at identical throughput and density [2]. It remains the only available chemical approach that can deliver complex synthetic RNA libraries with total control on the sequence. RNA microarrays can be used to interrogate the sequence preference of enzymes and RNA-binding proteins, but they are also ideally poised to generate RNA libraries for off-array applications. We can produce pools of RNA sequences between 75 and 100-nt in length which can be sequenced directly by Nanopore sequencing without any intermediate purification step [3]. Our photolithography platform also allows for the introduction of biologically relevant base modifications, of which m6A, 5mC and inosine are already available and preliminary data shows that m6A can be accurately basecalled. Simultaneously, nanopore sequencing data returns crucial information on the synthetic error-rate of RNA photolithography. This talk will focus on presenting the technology of RNA photolithography and on describing how RNA libraries can be prepared and sequenced.
Presented by
Jory Lietard, University of Vienna
This is a presentation from the 2026 Storage and Computing with DNA Conference.
· Learn More about the SNIA DNA Data Storage Alliance: https://www.snia.org/groups/snia-dna-technology-affiliate
· SNIA Educational Library: https://snia.org/library
· X: https://twitter.com/SNIA
· LinkedIn: https://linkedin.com/company/snia/ Nanopore sequencing of synthetic libraries of RNA oligonucleotides](https://i.ytimg.com/vi/VNJYQbz7MTY/mqdefault.jpg)


