Rice Univ. Researchers Claim 15x AI Model Training Speed-up Using CPUs
by Doug Black from High-Performance Computing News Analysis | insideHPC on (#5H070)
Reports are circulating in AI circles that researchers from Rice University claim a breakthrough in AI model training acceleration - without using accelerators. Running AI software on commodity x86 CPUs, the Rice computer science team say neural networks can be trained 15x faster than platforms utilizing GPUs. If valid, the new approach would be a double boon for organizations implementing AI strategies: faster model training using less costly microprocessors.
The post Rice Univ. Researchers Claim 15x AI Model Training Speed-up Using CPUs appeared first on insideHPC.