Neural Magic, AI leader in sparse inferencing technology, today announced a 6X improvement over their groundbreaking results from their last round submission with open engineering consortium, MLCommons®. Neural Magic’s latest results in MLPerf™ Inference v3.0, validate that customers can achieve high-performance AI using just x86 CPU architectures.
“We are so excited about our latest performance results, validated by MLPerf™ Inference v3.0,” said Brian Stevens, Chief Executive Officer, Neural Magic. “By applying our specialized compound sparsity algorithms with our patented DeepSparse inference runtime, we were able to achieve a boost in CPU performance by 1,000X while reducing power consumption by 92% over other inference solutions. The numbers prove users can have GPU speeds to support AI projects with just software and off-the-shelf processors.”
This year, Neural Magic used 4th Gen AMD EPYC™ processors for their benchmark testing. Neural Magic’s software stack takes advantage of continued innovations in AMD EPYC processors, such as AVX-512 and VNNI instructions as well as advanced features like highly performant DDR5 memory and a core count up to 96 cores, to unlock new possibilities for delivering better than GPU speeds on x86 CPUs.
“Neural Magic’s MLPerf™ Inference v3.0 results, benchmarked using our latest 4th Gen AMD EPYC processors, prove customers can achieve outstanding levels of AI inference performance for deep learning projects on x86 based CPUs, ” said Kumaran Siva, Corporate Vice President, Strategic Business Development, AMD.
With Neural Magic, data scientists can achieve breakthrough performance with their deep learning models, while lowering computational expenses and simplifying operations. Read this blog for more details on Neural Magic’s MLPerf Inference v3.0 results.