TMO: Transparent Memory Offloading in Datacenters
TMO addresses questions of how much memory to offload and what memory to offload.
Research Highlights
Advertisement
Technical Perspective: Memory Efficiency via Offloading in Warehouse-Scale Datacenters
The paper presents an evaluation of TMO deployed across millions of servers in Meta’s datacenters.
NeuroRadar: A Neuromorphic Radar Sensor for Low-Power IoT Systems
NeuroRadar provides a unique and innovative solution for radar sensing in energy-constrained IoT devices.
Technical Perspective: NeuroRadar: Can Radar Systems Be Reimagined Using Computational Principles?
Charting a promising direction toward ubiquitous, intelligent sensing systems that could transform interactions and monitoring within the power limitations of battery-powered devices.
SRAM Has No Chill: Exploiting Power Domain Separation to Steal On-Chip Secrets
Showing the effectiveness of a voltage-based attack that snapshots SRAM, without exposing an SoC to low temperature.
Technical Perspective: Defending Data from SRAM-Based Attacks
SRAM-based attacks include recovering portions of memory from internal caches, internal RAM, and some CPU registers; attaching voltage probes that can keep SRAM powered on SoCs.
Technical Perspective: A Symbolic Approach to Verifying Quantum Systems
The combination of deep theoretical insights and practical tool development results in a milestone for quantum circuit verification.
An Automata-Based Framework for Verification and Bug Hunting in Quantum Circuits
The framework leverages tree automata to compactly represent sets of quantum states; transformers implement the semantics of quantum gates over this representation.
The accompanying paper asks whether we can internalize in logic the property known as “Church’s Thesis.”
‘Upon This Quote I Will Build My Church Thesis’
The compatibility of the Church thesis with dependent type theory was an open question. In this paper, we answer this question positively.
GenDP: A Framework of Dynamic Programming Acceleration for Genome Sequencing Analysis
The proposed GenDP framework of dynamic programming acceleration for genome sequencing analysis supports multiple DP kernels.
Technical Perspective: Toward a Generalized Accelerator for Genome Sequence Analysis
GenDP offers an important step toward addressing the need for a universal accelerator.
Designing an Efficient Tree Index on Disaggregated Memory
Sherman demonstrates that combining RDMA hardware features and RDMA-friendly software designs can enable a high-performance index on disaggregated memory.
Technical Perspective: A Write-Optimized Distributed B+Tree Index on Disaggregated Memory
The high-performance tree index uses a lock-free search with versions to resolve read-write conflicts and exclusive locks to resolve write-write conflicts.
The design ensures unobtrusiveness and a natural look and feel while achieving high signal quality, high spatial-temporal fidelity, and low power operation.
Technical Perspective: The Technologies that Disappear
Bringing new "life" to stuffed animal toys and beyond.
Many Faces of Ad Hoc Transactions
The flexibility of ad hoc transactions is a double-edged sword, providing potential performance benefits but also increasing the risk of correctness issues.
Technical Perspective: Ad Hoc Transactions: What They Are and Why We Should Care
The paper by Tang et al. addresses important questions about ad hoc transactions.
New Spectral Algorithms for Refuting Smoothed k-SAT
Our methods yield new algorithms for smoothed k-SAT instances with guarantees that match those for the significantly simpler and well-studied model of random formulas.
Technical Perspective: The Surprising Power of Spectral Refutation
Could an algorithm that seems unrelated to SAT serve as a reliable refutation heuristic? Perhaps surprisingly, the answer is yes.
R2T: Instance-Optimal Truncation for Differentially Private Query Evaluation with Foreign Keys
The first DP mechanism for answering arbitrary SPJA queries in a database with foreign-key constraints.
Technical Perspective: Toward Building a Differentially Private DBMS
The paper is an important step toward automatically ensuring privacy for arbitrary computations.
Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions
Our work attempts to characterize the tendency of Copilot to produce insecure code.
Technical Perspective: Unsafe Code Still a Hurdle Copilot Must Clear
Examining the conditions under which LLMs may generate insecure code.
Shape the Future of Computing
ACM encourages its members to take a direct hand in shaping the future of the association. There are more ways than ever to get involved.
Get InvolvedCommunications of the ACM (CACM) is now a fully Open Access publication.
By opening CACM to the world, we hope to increase engagement among the broader computer science community and encourage non-members to discover the rich resources ACM has to offer.
Learn More