TC-CIM: Empowering Tensor Comprehensions for Computing-In-Memory - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Documents Associated With Scientific Events Year : 2020

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


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-In-Memory (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 poly-hedral 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.
Fichier principal
Vignette du fichier
IMPACT_2020_paper_2.pdf (836.88 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02441163 , version 1 (15-01-2020)


  • HAL Id : hal-02441163 , version 1


Andi Drebes, Lorenzo Chelini, Oleksandr Zinenko, Albert Cohen, Henk Corporaal, et al.. TC-CIM: Empowering Tensor Comprehensions for Computing-In-Memory. IMPACT 2020 - 10th International Workshop on Polyhedral Compilation Techniques, Jan 2020, Bologna, Italy. ⟨hal-02441163⟩
408 View
354 Download


Gmail Facebook X LinkedIn More