Microarchitecture Categorization and Pre-RTL Analytical Modeling for Sparse Tensor Accelerators
Specialized microarchitectures for exploiting sparsity have been critical to the design of sparse tensor accelerators. Sparseloop introduced the Sparse Acceleration Feature (SAF) abstraction, which unifies prior work on sparse tensor accelerators into a taxonomy of sparsity optimizations. Spars...
Autor principal: | Feldman, Andrew |
---|---|
Otros Autores: | Sze, Vivienne |
Formato: | Tesis |
Publicado: |
Massachusetts Institute of Technology
2024
|
Acceso en línea: | https://hdl.handle.net/1721.1/153859 |
Ejemplares similares
-
Accelerating RTL Simulation with Hardware-Software Co-Design
por: Elsabbagh, Fares, et al.
Publicado: (2024) -
TeAAL: A Declarative Framework for Modeling Sparse Tensor Accelerators
por: Nayak, Nandeeka, et al.
Publicado: (2024) -
Tailors: Accelerating Sparse Tensor Algebra by Overbooking Buffer Capacity
por: Xue, Zi Yu, et al.
Publicado: (2024) -
Tailors: Accelerating Sparse Tensor Algebra by Overbooking Buffer Capacity
por: Xue, Zi Yu
Publicado: (2024) -
Categorical Tensor Network States
por: Biamonte, S, et al.
Publicado: (2010)