HPCA 2025 connects microarchitectural mechanisms to power measurement, failure recovery, model execution, and datacenter resource policy. The 40 records in this review passed two checks: the title appears in the official conference program, and at least one publisher-supplied author affiliation directly names a commercial company or corporate research organization. That rule includes university-industry collaborations but excludes papers that merely acknowledge a vendor, authors whose current employer differs from the paper affiliation, and automatic institution matches that cannot be confirmed in the source metadata.[1]
The inventory is time-bounded through August 31, 2026. 3 records had an openly accessible full-text location in the discovery metadata; the remaining records are included only at the level supported by the official program and DOI metadata. We use open manuscripts for mechanism-level observations and do not reconstruct a closed paper from an abstract. Existing Silicon & Systems reviews remain linked through their DOI where available rather than being rewritten as duplicates.
What the publication count does and does not measure
A company affiliation is evidence that the work crossed an industrial research boundary. It is not evidence that the mechanism shipped, improved total cost, or survived a production workload. Some papers report fabricated silicon or deployed systems. Others present simulation, trace replay, emulation, compiler experiments, or analytical models. Those evidence classes answer different questions and cannot be ranked by one headline number.
The count also reflects publication practice. Huawei (6), IBM (5), Meta (5), Google (4), Intel (4), Alibaba (3), Microsoft (3), NVIDIA (3) appear most often in this verified set, but a company that publishes less may still deploy more. Large university collaborations can add many papers without transferring the mechanism into a product. For this reason, the complete index below preserves title, DOI, and corporate affiliation while the analysis focuses on recurring system decisions.
AI compute moved from peak arithmetic to resource contracts
The AI papers increasingly ask who controls memory, scheduling, precision, and failure recovery rather than how many operations a datapath can issue. Training and inference make different demands: training needs synchronized progress across large groups, while inference must protect latency under changing sequence length, batch size, and model state. A mechanism that improves one regime can waste capacity in the other.
The most transferable question is therefore the resource contract. A paper should identify which bytes remain resident, which work can be preempted, how much parallelism is required to reach the reported result, and what happens when the model or request distribution changes. Without those conditions, an accelerator speedup is difficult to translate into a server count or service-level objective.
Memory behavior became part of the architecture rather than an input
The memory papers span cache management, prefetching, address translation, disaggregation, storage paths, and data movement. This breadth reflects a common constraint: useful work is often limited by where state resides and when it moves, not by the peak rate of the execution units. Caches and prefetchers can reduce average latency while making interference or tail behavior harder to predict.
Production adoption needs a byte-and-time ledger. The platform should distinguish capacity saved from traffic added, local hits from remote service, average bandwidth from tail latency, and one-time migration from steady-state work. The same mechanism can look favorable in an isolated benchmark and become expensive when recovery, coherency, or multi-tenant isolation is included.
Compiler and runtime work became an architectural control plane
Compiler, runtime, and scheduling papers show that architecture is no longer fixed when the chip leaves fabrication. Kernel selection, graph partitioning, queue admission, placement, and code generation decide which hardware paths are exercised. This software control plane can recover performance from a general device, but it can also hide brittle assumptions about shapes, driver behavior, and workload repetition.
A credible evaluation should separate search cost from execution benefit, warm from cold behavior, and offline tuning from decisions made inside a service deadline. It should also test a hardware or model generation that was not used to design the policy. Otherwise the reported gain may be a successful fit to one benchmark rather than a reusable architectural mechanism.
Reliability and security need an explicit failure boundary
Security and reliability mechanisms often trade metadata, checks, sampling, or redundancy against performance. Their value depends on the failure model. A defense against one fault or attack pattern should not be read as general isolation, and a low average overhead does not reveal the worst recovery path or the state exposed during rollback.
The adoption checklist is concrete: define the protected state, the detector’s blind spots, the time to containment, the state that must be reconstructed, and the behavior when the detector itself fails. Fleet evidence is particularly valuable because it exposes background errors and operational constraints that simulation rarely includes. Even then, hardware generation and deployment policy limit transferability.
The operating decision behind this literature
Across the set, the architectural boundary moves only when another layer accepts new responsibility. More flexible hardware asks the compiler to supply better schedules. Disaggregated memory asks the runtime to place data and recover from remote faults. Shared accelerators ask the scheduler to expose interference and preemption. Security metadata asks the memory system to preserve tags through caches, DMA, and I/O.
This changes procurement and design review. Peak throughput should be accompanied by the minimum useful batch, residency requirement, worst queue delay, failure recovery cost, and software dependency. The paper that reports the largest speedup is not automatically the safest choice. The stronger candidate is the one whose assumptions match the operator’s workload and whose fallback remains measurable.
How to use the complete index
The index is grouped by the principal topic visible in each title. Several papers belong in more than one group; each appears once to keep the count auditable. A DOI link is a bibliographic record, not a statement that the full text is free to reuse. Readers should check the license on the specific manuscript before reproducing a figure or table.
The best follow-up candidates combine three properties: a mechanism that changes a system boundary, enough public evidence to preserve evaluation conditions, and an implication that matters beyond one product. Papers already covered by Silicon & Systems should be extended only when new evidence changes the judgment. The rest form a monitored backlog rather than a queue for shallow summaries.
Complete HPCA 2025 company-affiliated paper index
AI compute and model execution, 16 records
- BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration, Microsoft.
- Cambricon-DG: An Accelerator for Redundant-Free Dynamic Graph Neural Networks Based on Nonlinear Isolation, Cambricon.
- DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency, Microsoft.
- EDA: Energy-Efficient Inter-Layer Model Compilation for Edge DNN Inference Acceleration, Google.
- Enhancing Large-Scale AI Training Efficiency: The C4 Solution for Real-Time Anomaly Detection and Communication Optimization, Alibaba.
- InstAttention: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference, Huawei.
- Let-Me-In: (Still) Employing In-pointer Bounds Metadata for Fine-grained GPU Memory Safety, Arm, Intel.
- LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator, Microsoft.
- Machine Learning-Guided Memory Optimization for DLRM Inference on Tiered Memory, Meta.
- MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from μWatts to MWatts for Sustainable AI, Meta, NVIDIA, Syntiant, Dell, Intel, FlexAI, AMD, Google, Decompute, MLCommons.
- NeuVSA: A Unified and Efficient Accelerator for Neural Vector Search, Huawei.
- OASIS: Object-Aware Page Management for Multi-GPU Systems, NVIDIA.
- PAISE: PIM-Accelerated Inference Scheduling Engine for Transformer-based LLM, Samsung SDS.
- Revisiting Reliability in Large-Scale Machine Learning Research Clusters, Meta.
- The Importance of Generalizability in Machine Learning for Systems, Google.
- WarpDrive: GPU-Based Fully Homomorphic Encryption Acceleration Leveraging Tensor and CUDA Cores, Ant Group.
Memory, storage, and data movement, 7 records
- Criticality-Aware Instruction-Centric Bandwidth Partitioning for Data Center Applications, Huawei.
- Efficient Caching with A Tag-enhanced DRAM, Rambus, Samsung.
- Enterprise Class Modular Cache Hierarchy, IBM.
- FHENDI: A Near-DRAM Accelerator for Compiler-Generated Fully Homomorphic Encryption Applications, IBM.
- NVMePass: A Lightweight, High-performance and Scalable NVMe Virtualization Architecture with I/O Queues Passthrough, Alibaba.
- Piccolo: Large-Scale Graph Processing with Fine-Grained in-Memory Scatter-Gather, Samsung.
- Predicting DRAM-Caused Risky VMs in Large-Scale Clouds, Alibaba.
Processors, accelerators, and execution, 6 records
- Ariadne: A Hotness-Aware and Size-Adaptive Compressed Swap Technique for Fast Application Relaunch and Reduced CPU Usage on Mobile Devices, MangoBoost.
- DPUaudit: DPU-assisted Pull-based Architecture for Near-Zero Cost System Auditing, Huawei.
- FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables, NAVER Cloud.
- LSQCA: Resource-Efficient Load/Store Architecture for Limited-Scale Fault-Tolerant Quantum Computing, NTT.
- NOVA: A Novel Vertex Management Architecture for Scalable Graph Processing, Ayar Labs, Google.
- Push Multicast: A Speculative and Coherent Interconnect for Mitigating Manycore CPU Communication Bottleneck, Intel.
Runtime, compiler, and scheduling, 1 records
Reliability, security, and verification, 1 records
Datacenter, network, and system policy, 1 records
Other architecture mechanisms, 8 records
- Architecting Value Prediction around In-Order Execution, Kalray.
- ARTEMIS: Agile Discovery of Efficient Real-Time Systems-on-Chips in the Heterogeneous Era, IBM.
- CogSys: Efficient and Scalable Neurosymbolic Cognition System via Algorithm-Hardware Co-Design, IBM.
- CORDOBA: Carbon-Efficient Optimization Framework for Computing Systems, Meta.
- eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models, Apple.
- Integrating Prefetcher Selection with Dynamic Request Allocation Improves Prefetching Efficiency, Intel.
- To Cross, or Not to Cross Pages for Prefetching?, Huawei.
- Zebra: Efficient Redundant Array of Zoned Namespace SSDs Enabled by Zone Random Write Area (ZRWA), Huawei.
Source and copyright notice
This time-bounded editorial synthesis uses the official HPCA 2025 program, Crossref DOI metadata, and OpenAlex discovery records verified against publisher-supplied affiliations. It restates no closed-paper mechanism beyond public metadata and reproduces no publisher prose, table, or figure. The conceptual hardware plate and deterministic labels were created for this article. Rights for each paper remain with its authors and publisher; follow the linked DOI for the authoritative record and license.