19654

TC-CIM: Empowering Tensor Comprehensions for Computing-In-Memory

Andi Drebes, Lorenzo Chelini, Oleksandr Zinenko, Albert Cohen, Henk Corporaal, Tobias Grosser, Kanishkan Vadivel, Nicolas Vasilache
Inria and École Normale Supérieure Paris, France
hal-02441163, (16 January 2020)

@inproceedings{drebes2020tc,

   title={TC-CIM: Empowering Tensor Comprehensions for Computing-In-Memory},

   author={Drebes, Andi and Chelini, Lorenzo and Zinenko, Oleksandr and Cohen, Albert and Corporaal, Henk and Grosser, Tobias and Vadivel, Kanishkan and Vasilache, Nicolas},

   booktitle={IMPACT 2020-10th International Workshop on Polyhedral Compilation Techniques},

   year={2020}

}

Download Download (PDF)   View View   Source Source   

1146

views

Memristor-based, non-von-Neumann architectures performing tensor operations directly in memory are a promising approach to address the ever-increasing demand for energy-efficient, high-throughput hardware accelerators for Machine Learning (ML) inference. A major challenge for the programmability and exploitation of such Computing-InMemory (CIM) architectures consists in the efficient mapping of tensor operations from high-level ML frameworks to fixed-function hardware blocks implementing in-memory computations. We demonstrate the programmability of memristor-based accelerators with TC-CIM, a fully-automatic, end-to-end compilation flow from Tensor Comprehensions, a mathematical notation for tensor operations, to fixed-function memristor-based hardware blocks. Operations suitable for acceleration are identified using Loop Tactics, a declarative framework to describe computational patterns in a polyhedral representation. We evaluate our compilation flow on a system-level simulator based on Gem5, incorporating crossbar arrays of memristive devices. Our results show that TC-CIM reliably recognizes tensor operations commonly used in ML workloads across multiple benchmarks in order to offload these operations to the accelerator.
Rating: 3.0/5. From 2 votes.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: