{"total":24,"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":"2110.11346","title":"Data-Driven Offline Optimization For Architecting Hardware Accelerators","created":"2021-10-20","cited_by_count":29,"area":null},{"id":"2105.01898","title":"CoSA: Scheduling by Constrained Optimization for Spatial Accelerators","created":"2021-05-05","cited_by_count":22,"area":null},{"id":"2105.12842","title":"A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators","created":"2021-05-26","cited_by_count":19,"area":null},{"id":"2312.03134","title":"A Hardware Evaluation Framework for Large Language Model Inference","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2402.10930","title":"ConSmax: Hardware-Friendly Alternative Softmax with Learnable Parameters","created":"2024-01-31","cited_by_count":14,"area":null},{"id":"2305.12718","title":"HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2210.03894","title":"GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation","created":"2022-10-08","cited_by_count":9,"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":"2306.08888","title":"ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design","created":"2023-06-15","cited_by_count":6,"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":"2109.07419","title":"Union: A Unified HW-SW Co-Design Ecosystem in MLIR for Evaluating Tensor Operations on Spatial Accelerators","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2308.05869","title":"Shared Memory-contention-aware Concurrent DNN Execution for Diversely Heterogeneous System-on-Chips","created":"2023-08-10","cited_by_count":5,"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":"2205.15568","title":"HW-Aware Initialization of DNN Auto-Tuning to Improve Exploration Time and Robustness","created":"2022-05-31","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":"2308.14364","title":"Target-independent XLA optimization using Reinforcement Learning","created":"2023-08-28","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":"2501.09954","title":"AIRCHITECT v2: Learning the Hardware Accelerator Design Space through Unified Representations","created":"2025-01-17","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":"2507.16249","title":"Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping","created":"2025-07-22","cited_by_count":0,"area":null}],"next_cursor":null}