AdaTune: Adaptive Tensor Program Compilation Made Efficient
Deep learning models are computationally intense, and implementations often have to be highly optimized by experts or hardware vendors to be usable in practice. The DL compiler, together with Learning to Compile have proven to be a powerful technique for optimizing tensor programs. However, a limitation of this approach is that it still suffers from unbearably long overall optimization time.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Orion: Characterizing and Programming Apple's Neural Engine for LLM Training and Inference
Over two billion Apple devices ship with a Neural Processing Unit (NPU) - the Apple Neural Engine (ANE) - yet this accelerator remains largely unused for large language model workloads. CoreML, Apple's public ML framewor…
QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach
Heterogeneous deep learning systems (DLS) such as GPUs and ASICs have been widely deployed in industrial data centers, which requires to develop multiple low-level tensor programs for different platforms. An attractive s…
Code GenerationGPUProgram SynthesisStaged compilation of tensor expressions
We present our current progress towards a metaprogramming framework for tensor expressions embedded in Haskell; the system offers a high-level syntax for dimension-annotated linear algebra, and generates specialized sou…
Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization
Adversarial Machine Learning (AML) is a rapidly growing field of security research, with an often overlooked area being model attacks through side-channels. Previous works show such attacks to be serious threats, though …
DVM: A Bytecode Virtual Machine Approach for Dynamic Tensor Computation
Dynamism is common in AI computation, e.g., the dynamic tensor shapes and the dynamic control flows in models. Due to the long compilation time, existing runtime compilation damages the model efficiency, while the offlin…