![]() ![]() Sapeon presented two systems with different versions of their Sapeon X220 accelerator, testing them only on image recognition. The difference is partly down to Sapphire Rapids’ Advanced Matrix Extensions, an accelerator worked into each of the CPU’s cores. An eight-accelerator computer built with the company’s partner, Inspur, blasted through 424,660 samples per second, the fourth-fastest system tested, behind a Qualcomm Cloud AI 100-based machine with 18 accelerators, and two Nvidia A100-based R&D systems from Nettrix and H3C with 20 accelerators each.īut Biren really showed its power on natural-language processing, beating all the other four-accelerator systems by at least 33 percent on the highest-accuracy version of BERT and by even bigger margins among eight-accelerator systems.Īn Intel system based on two soon-to-be-released Xeon Sapphire Rapids CPUs without the aid of any accelerators was another standout, edging out a machine using two current-generation Xeons in combination with an accelerator. ![]() On the image-recognition trial, startup Biren’s new chip, the BR104, performed well. Several Nvidia-GPU-based systems were tested on the entire suite of benchmarks, but performing even one benchmark can take more than a month of work, engineers involved say. While several systems were tested on the entire suite of neural networks, most results were submitted for image recognition, with the natural-language processor BERT (short for Bidirectional Encoder Representations from Transformers) a close second, making those categories the easiest to compare. ( Intel made two entries without any accelerators, to demonstrate what its CPUs could do on their own.) In the contest with the most powerful computers under the most stringent conditions, the closed data-center group, computers with AI accelerator chips from four companies competed: Biren, Nvidia, Qualcomm, and Sapeon. The contest was further divided into a “closed” category, where everybody had to run the same “mathematically equivalent” neural networks and meet the same accuracy measures, and an “open” category, where companies could show off how modifications to the standard neural networks make their systems work better. In addition to testing raw performance, computers could also compete on efficiency. Computers meant to work on-site instead of in the data center-what MLPerf calls the edge, because they’re located at the edge of the network-were measured in the offline state as if they were receiving a single stream of data, such as from a security camera and as if they had to handle multiple streams of data, the way a car with several cameras and sensors would. Tested computers are categorized as intended for data centers or “the edge.” Commercially available data-center-based systems were tested under two conditions-a simulation of real data-center activity where queries arrive in bursts and “offline” activity where all the data is available at once. Six benchmarks are tested on two types of computers (data center and edge) in a variety of conditions. This slide from Nvidia sums up the whole MLPerf effort. The networks had already been trained on a standard set of data and had to make predictions about data they had not been exposed to before. ![]() In MLPerf’s inferencing benchmarks, systems made up of combinations of CPUs and GPUs or other accelerator chips are tested on up to six neural networks that perform a variety of common functions-image classification, object detection, speech recognition, 3D medical imaging, natural-language processing, and recommendation. It is the first attempt to provide apples-to-apples comparisons of how good computers are at training and executing (inferencing) neural networks. MLPerf is a set of benchmarks agreed upon by members of the industry group MLCommons. Systems based on Qualcomm’s AI 100 also made a good showing, and there were other new chips, new types of neural networks, and even new, more realistic ways of testing them.īefore I go on, let me repeat the canned answer to “What the heck is MLPerf?” But Hopper was not alone in making it to the podium at MLPerf Inferencing v2.1. At least this time, the GPU powerhouse put a new contender into the mix, its Hopper GPU, which delivered as much as 4.5 times the performance of its predecessor and is due out in a matter of months. It’s time for the “Olympics of machine learning” again, and if you’re tired of seeing Nvidia at the top of the podium over and over, too bad. ![]()
0 Comments
Leave a Reply. |