{"total":14,"rows":[{"id":"2303.04739","title":"Advancing Direct Convolution using Convolution Slicing Optimization and ISA Extensions","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2306.14316","title":"Im2win: An Efficient Convolution Paradigm on GPU","created":"2023-06-25","cited_by_count":3,"area":null},{"id":"2304.00952","title":"Optimizing data-flow in Binary Neural Networks","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2306.14320","title":"Im2win: Memory Efficient Convolution On SIMD Architectures","created":"2023-06-25","cited_by_count":2,"area":null},{"id":"2202.02310","title":"EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2209.03704","title":"Kernel-Segregated Transpose Convolution Operation","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2408.00278","title":"High Performance Im2win and Direct Convolutions using Three Tensor Layouts on SIMD Architectures","created":"2024-08-01","cited_by_count":1,"area":null},{"id":"2608.20725","title":"Enabling Memory-efficient Im2win Convolution with Multi-precision Support on GPU CUDA and Tensor Cores","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2407.10730","title":"ConvBench: A Comprehensive Benchmark for 2D Convolution Primitive Evaluation","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2410.08300","title":"A Framework to Enable Algorithmic Design Choice Exploration in DNNs","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2411.15659","title":"SMM-Conv: Scalar Matrix Multiplication with Zero Packing for Accelerated Convolution","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2509.26217","title":"Benchmarking Deep Learning Convolutions on Energy-constrained CPUs","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2608.21646","title":"Power-Performance Characterization of TinyML Systems","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2610.00586","title":"Right In-Place (RiP) Convolution: A Simple, General, and Near-Optimal Strategy for Memory-Efficient CNN Inference","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}