Accelerate Machine Learning Workloads using TVM and OpenCL ML SDK on Qualcomm AdrenoTM GPUs.
Siva Rama Krishna ReddyHongqiang WangKrishna Raju VegirajuBalaji CalidasAlex BourdPublished in: IWOCL (2023)
Keyphrases
- machine learning
- parallel programming
- graphics processing units
- open source
- maximum likelihood
- pattern recognition
- machine learning algorithms
- learning systems
- knowledge representation
- text classification
- machine learning approaches
- learning tasks
- machine learning methods
- computer systems
- web applications
- general purpose
- support vector machine
- active learning
- natural language processing
- graphics hardware
- learning algorithm
- artificial intelligence
- explanation based learning
- access patterns
- computer vision
- shared memory
- parallel processing
- decision trees
- supervised learning
- data mining
- feature selection
- parallel algorithm
- floating point
- information extraction
- parallel architectures