FlexTensor
Size Zheng, Yun Liang, Shuo Wang et al. · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · 2020
Tensor computation plays a paramount role in a broad range of domains, including machine learning, data analytics, and scientific computing. The wide adoption of tensor computation and its huge computation cost has led to high demand for flexible, portable, and high-performance library implementation on heterogeneous hardware accelerators such as GPUs and FPGAs. However, the current tensor library implementation mainly requires programmers to manually design low-level implementation and optimize from the algorithm, architecture, and compilation perspectives. Such a manual development process often takes months or even years, which falls far behind the rapid evolution of the application algorithms.
Cited by 170 works. doi:10.1145/3373376.3378508
Authors
References
- Optimization by Simulated Annealing
- Backpropagation Applied to Handwritten Zip Code Recognition
- XGBoost
- MobileNetV2: Inverted Residuals and Linear Bottlenecks
- Q-learning
- Learning Spatiotemporal Features with 3D Convolutional Networks
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- OpenMP: an industry standard API for shared-memory programming
- Scalable Parallel Programming with CUDA
- Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2007 (ICASSP 2007)