ACTA: Automatic Configuration of the Tensor Memory Accelerator for High-End GPUs
Open Access
- 1 March 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 21-27
Abstract
No abstract availableThis publication has 16 references indexed in Scilit:
- WASP: Exploiting GPU Pipeline Parallelism with Hardware-Accelerated Automatic Warp Specialization2024
- NVIDIA Hopper H100 GPU: Scaling PerformanceIEEE Micro, 2023
- Data-Aware Compression of Neural NetworksIEEE Computer Architecture Letters, 2021
- Neda: Supporting Direct Inter-Core Neighbor Data Exchange in GPUsIEEE Computer Architecture Letters, 2018
- Warp Scheduling for Fine-Grained Synchronization2018
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- Verified lifting of stencil computationsACM SIGPLAN Notices, 2016
- CAWS2014
- Singe2014
- Use of hybrid recursive CSR/COO data structures in sparse matrix-vector multiplication2010