paper-with-me

Papers

TensorIR: An Abstraction for Automatic Tensorized Program Optimization

2022-07-09 · Siyuan Feng, Bohan Hou, Hongyi Jin, Wuwei Lin, Junru Shao, Ruihang Lai, Zihao Ye, Lianmin Zheng, Cody Hao Yu, Yong Yu, Tianqi Chen

Deploying deep learning models on various devices has become an important topic. The wave of hardware specialization brings a diverse set of acceleration primitives for multi-dimensional tensor computations. These new acceleration primitives, along with the emerging machine learning models, bring tremendous engineering challenges. In this paper, we present TensorIR, a compiler abstraction for optimizing programs with these tensor computation primitives. TensorIR generalizes the loop nest representation used in existing machine learning compilers to bring tensor computation as the first-class citizen. Finally, we build an end-to-end framework on top of our abstraction to automatically optimize deep learning models for given tensor computation primitives. Experimental results show that TensorIR compilation automatically uses the tensor computation primitives for given hardware backends and delivers performance that is competitive to state-of-art hand-optimized systems across platforms.

📄 PDF Abstract BibTeX arXiv:2207.04296

Code (2)

apache/tvm 공식 구현
mlc-ai/web-llm pytorch

Tasks

BIG-bench Machine LearningDeep Learning

Methods 이 논문이 사용한 방법론

NesT NesT stacks canonical transformer layers to conduct local self-attention on every image block independently, and then "nests" them hierarchically. Coupling of processed…

Similar Papers 제목 키워드 기반

UNIT: Unifying Tensorized Instruction Compilation

2021-01-21 · Jian Weng, Animesh Jain, Jie Wang, Leyuan Wang 외

Because of the increasing demand for computation in DNN, researchers develope both hardware and software mechanisms to reduce the compute and memory burden. A widely adopted approach is to use mixed precision data types.…

CPU

Tensor Program Optimization with Probabilistic Programs

2022-05-26 · Junru Shao, Xiyou Zhou, Siyuan Feng, Bohan Hou 외

Automatic optimization for tensor programs becomes increasingly important as we deploy deep learning in various environments, and efficient optimization relies on a rich search space and effective search. Most existing e…

Deep LearningProbabilistic Programming

minimax: Efficient Baselines for Autocurricula in JAX

2023-11-21 · Minqi Jiang, Michael Dennis, Edward Grefenstette, Tim Rocktäschel

Unsupervised environment design (UED) is a form of automatic curriculum learning for training robust decision-making agents to zero-shot transfer into unseen environments. Such autocurricula have received much interest f…

CPUDecision MakingGPU

Bayesian Tensorized Neural Networks with Automatic Rank Selection

2019-05-24 · Cole Hawkins, Zheng Zhang

Tensor decomposition is an effective approach to compress over-parameterized neural networks and to enable their deployment on resource-constrained hardware platforms. However, directly applying tensor compression in the…

Model CompressionTensor Decomposition

TorchOpt: An Efficient Library for Differentiable Optimization

2022-11-13 · Jie Ren, Xidong Feng, Bo Liu, Xuehai Pan 외

Recent years have witnessed the booming of various differentiable optimization algorithms. These algorithms exhibit different execution patterns, and their execution needs massive computational resources that go beyond a…

CPUGPU