Intel Gaudi AI Accelerator Dominates GPT-3 in Speed

Intel submitted results for Intel Gaudi2 accelerators and 4th Gen Intel Xeon Scalable CPUs with Intel Advanced Matrix Extensions

while MLCommons released the results of the industry standard MLPerf training v3.1 benchmark for training AI models

The most recent MLCommons MLPerf findings expand upon Intel’s impressive AI performance from the June MLPerf training results

The Intel Xeon processor is still the sole CPU that reports MLPerf results The other one is Intel Gaudi2

For AI computation requirements, Gaudi2 is the sole practical substitute for NVIDIA’s H100, offering a notable price-performance ratio

Although FP8 was limited to GPT-3 in this MLPerf training submission and GPT-J in the prior inference submission, Intel is now supporting more models for both training and inference with its Gaudi2 software and tools

Benchmark times for BERT and ResNet-50 using BF16 were 13.27 and 15.92 minutes, respectively, on eight Intel Gaudi2 accelerators