Google llc (20240193421). Automatic Memory Management for Compute Graphs simplified abstract
Contents
Automatic Memory Management for Compute Graphs
Organization Name
Inventor(s)
Vinsensius B. Vega S. Naryanto of Zurich (CH)
Juan Antonio Navarro Perez of London (GB)
Automatic Memory Management for Compute Graphs - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240193421 titled 'Automatic Memory Management for Compute Graphs
The method described in the abstract involves cutting a compute graph to compute a first tensor, identifying a reduction operation, and determining slices of the tensor based on portions of a second tensor.
- Obtaining a compute graph for computing a first tensor
- Identifying a reduction operation in at least one dimension of the first tensor
- Locating a cut point in the graph to divide it into first and second portions
- Determining multiple slices of the first tensor
- Backpropagating the cut point to define multiple first graph pieces for the first portion
- Defining second graph pieces to combine outputs of the first graph pieces
- Executing the first and second graph pieces to compute the first portion of the compute graph
Potential Applications: - Machine learning algorithms - Data processing systems - Neural network training
Problems Solved: - Efficient computation of tensors - Optimized graph cutting for complex operations - Enhanced backpropagation techniques
Benefits: - Improved performance in tensor computations - Streamlined graph cutting process - Enhanced accuracy in neural network training
Commercial Applications: Title: "Advanced Tensor Computation Method for Machine Learning Applications" This technology can be utilized in various industries such as: - Healthcare for medical image analysis - Finance for predictive modeling - E-commerce for recommendation systems
Prior Art: Researchers have explored similar techniques in graph cutting and tensor computations in the field of machine learning and artificial intelligence.
Frequently Updated Research: Stay updated on the latest advancements in graph cutting algorithms and tensor optimization techniques to enhance the efficiency of this method.
Questions about Tensor Computation Method: 1. How does this method improve the efficiency of tensor computations compared to traditional techniques? 2. What are the potential limitations or challenges in implementing this method in real-world applications?
Original Abstract Submitted
a method includes obtaining a compute graph for computing a first tensor, identifying in the graph a reduction operation in at least one dimension of the first tensor, locating, at the operation, a cut point that cuts the graph into first and second portions, and determining a plurality of slices of the first tensor. the method also includes backpropagating the cut point through the graph to define a plurality of first graph pieces for the first portion, each particular first graph piece representing a computation of a particular slice of the plurality of slices based on a particular portion of a plurality of portions of a second tensor. the method further includes defining one or more second graph pieces to combine outputs of the first graph pieces, and executing the first graph pieces and the second graph pieces to execute the first portion of the compute graph.
