{"total":21,"rows":[{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2107.06419","title":"FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks","created":"2021-07-13","cited_by_count":39,"area":null},{"id":"2205.05826","title":"Sparseloop: An Analytical Approach To Sparse Tensor Accelerator Modeling","created":"2022-05-12","cited_by_count":15,"area":null},{"id":"2505.18574","title":"Autocomp: A Powerful and Portable Code Optimizer for Tensor Accelerators","created":"2025-05-24","cited_by_count":13,"area":null},{"id":"2408.04413","title":"Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers","created":"2024-08-08","cited_by_count":11,"area":null},{"id":"2407.14645","title":"Performance Modeling and Workload Analysis of Distributed Large Language Model Training and Inference","created":"2024-07-19","cited_by_count":9,"area":null},{"id":"2403.07953","title":"Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2405.00790","title":"SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators","created":"2024-05-01","cited_by_count":6,"area":null},{"id":"2509.10702","title":"DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators","created":"2025-09-12","cited_by_count":4,"area":null},{"id":"2405.08965","title":"MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming","created":"2024-05-14","cited_by_count":3,"area":null},{"id":"2509.14388","title":"eIQ Neutron: Redefining Edge-AI Inference with Integrated NPU and Compiler Innovations","created":"2025-09-17","cited_by_count":3,"area":null},{"id":"2201.11218","title":"DNNFuser: Generative Pre-Trained Transformer as a Generalized Mapper for Layer Fusion in DNN Accelerators","created":"2022-01-26","cited_by_count":2,"area":null},{"id":"2210.03731","title":"Demystifying Map Space Exploration for NPUs","created":"2022-10-07","cited_by_count":2,"area":null},{"id":"2304.12931","title":"SALSA: Simulated Annealing based Loop-Ordering Scheduler for DNN Accelerators","created":"2023-04-20","cited_by_count":2,"area":null},{"id":"2310.17408","title":"Tackling the Matrix Multiplication Micro-kernel Generation with Exo","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2407.09453","title":"Weight Block Sparsity: Training, Compilation, and AI Engine Accelerators","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2409.02817","title":"Obsidian: Cooperative State-Space Exploration for Performant Inference on Secure ML Accelerators","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2505.07829","title":"Blockbuster, Part 1: Block-level AI Operator Fusion","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2306.15676","title":"KAPLA: Pragmatic Representation and Fast Solving of Scalable NN Accelerator Dataflow","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2505.06625","title":"CaMDN: Enhancing Cache Efficiency for Multi-tenant DNNs on Integrated NPUs","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2507.04828","title":"A High-Level Compiler Integration Approach for Deep Learning Accelerators Supporting Abstraction and Optimization","created":"2025-07-07","cited_by_count":0,"area":null}],"next_cursor":null}