{"total":34,"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":"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":"2105.01585","title":"HASCO: Towards Agile HArdware and Software CO-design for Tensor Computation","created":"2021-05-04","cited_by_count":10,"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":"2309.15467","title":"Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey","created":"2023-09-27","cited_by_count":8,"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":"2305.07522","title":"SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2404.11788","title":"Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads","created":"2024-04-17","cited_by_count":4,"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":"2208.04854","title":"Design of High-Throughput Mixed-Precision CNN Accelerators on FPGA","created":"2022-08-09","cited_by_count":3,"area":null},{"id":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2507.11331","title":"SystolicAttention: Fusing FlashAttention within a Single Systolic Array","created":"2025-07-15","cited_by_count":3,"area":null},{"id":"2106.10499","title":"Evaluating Spatial Accelerator Architectures with Tiled Matrix-Matrix Multiplication","created":"2021-06-19","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":"2311.07427","title":"Boolean Variation and Boolean Logic BackPropagation","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2212.02687","title":"Vision Transformer Computation and Resilience for Dynamic Inference","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2310.00574","title":"YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs","created":"2023-10-01","cited_by_count":1,"area":null},{"id":"2408.16246","title":"PACiM: A Sparsity-Centric Hybrid Compute-in-Memory Architecture via Probabilistic Approximation","created":"2024-08-29","cited_by_count":1,"area":null},{"id":"2101.01163","title":"SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2104.05541","title":"Optimizing the Whole-life Cost in End-to-end CNN Acceleration","created":"2021-04-12","cited_by_count":0,"area":null},{"id":"2202.00739","title":"Compiler-Driven Simulation of Reconfigurable Hardware Accelerators","created":"2022-02-01","cited_by_count":0,"area":null},{"id":"2202.11575","title":"Shisha: Online scheduling of CNN pipelines on heterogeneous architectures","created":"2022-02-23","cited_by_count":0,"area":null},{"id":"2204.06676","title":"DRAGON (Differentiable Graph Execution) : A suite of Hardware Simulation and Optimization tools for Modern AI/Non-AI Workloads","created":"2022-04-13","cited_by_count":0,"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":"2306.16767","title":"Performance Analysis of DNN Inference/Training with Convolution and non-Convolution Operations","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2311.17815","title":"A Survey on Design Methodologies for Accelerating Deep Learning on Heterogeneous Architectures","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2312.15388","title":"DEAP: Design Space Exploration for DNN Accelerator Parallelism","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2503.06342","title":"Exploring the Performance Improvement of Tensor Processing Engines through Transformation in the Bit-weight Dimension of MACs","created":"2025-03-08","cited_by_count":0,"area":null},{"id":"2509.15205","title":"Voyager: An End-to-End Framework for Design-Space Exploration and Generation of DNN Accelerators","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2604.09124","title":"MATCHA: Efficient Deployment of Deep Neural Networks on Multi-Accelerator Heterogeneous Edge SoCs","created":"2026-04-10","cited_by_count":0,"area":null}],"next_cursor":null}