Qualcomm vs Nvidia in AI chips performance

Artificial intelligence (AI) chips from Qualcomm beat Nvidia in two out of three measures of power efficiency in a test data published on Wednesday, while Neuchips, a Taiwanese startup bested both in one category.
Kazakhstan mobile networkNvidia dominates the market for training AI models with huge amounts of data. After those AI models are trained, they are put to wider use in what is called “inference” by doing tasks like generating text responses to prompts and deciding whether an image contains a cat.

Analysts believe that the market for data center inference chips will grow quickly as businesses put AI technologies into their products, but companies such as Alphabet Inc’s Google are already exploring how to keep the lid on the extra costs that doing so will add, Reuters news report said.

One of those major costs is electricity, and Qualcomm has used its history designing chips for battery-powered devices such as smartphones to create a chip called Cloud AI 100 that aims for parsimonious power consumption.

MLCommons, an engineering consortium that maintains testing benchmarks widely used in the AI chip industry, published testing data. It said Qualcomm’s AI 100 beat Nvidia’s H100 chip at classifying images, based on how many data center server queries each chip can carry out per watt.

Qualcomm’s AI 100 chips hit 197.6 server queries per watt versus 108.4 queries per watt for Nvidia’s H100 chip. Neuchips, a startup founded by veteran Taiwanese chip academic Youn-Long Lin, took the top spot with 227 queries per watt.

Qualcomm also beat Nvidia at object detection with a score of 3.2 queries per watt versus Nvidia’s 2.4 queries per watt. Object detection can be used in applications like analyzing footage from retail stores to see where shoppers go most often.

Nvidia took the top spot in both absolute performance terms and power efficiency terms in a test of natural language processing, which is the AI technology most widely used in systems like chatbots. Nvidia hit 10.8 samples per watt, while Neuchips ranked second at 8.9 samples per watt and Qualcomm was in third place at 7.5 samples per watt.

Organizations such as Alibaba, ASUSTeK, Azure, cTuning, Deci.ai, Dell, Gigabyte, H3C, HPE, Inspur, Intel, Krai, Lenovo, Moffett, Nettrix, NEUCHIPS, Neural Magic, NVIDIA, Qualcomm Technologies, Quanta Cloud Technology, rebellions, SiMa, Supermicro, VMware, and xFusion have submitted their products for MLPerf Inference benchmarks that primarily focus on datacenter and edge systems.