research
∙
05/17/2023
ACRoBat: Optimizing Auto-batching of Dynamic Deep Learning at Compile Time
Dynamic control flow is an important technique often used to design expr...
share
research
∙
02/08/2023
ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines
Batching has a fundamental influence on the efficiency of deep neural ne...
research
∙
10/19/2021
The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Padding
There is often variation in the shape and size of input data used for de...
research
∙
05/07/2018
RowClone: Accelerating Data Movement and Initialization Using DRAM
In existing systems, to perform any bulk data movement operation (copy o...
research
∙
11/30/2016