Our Terms & Conditions | Our Privacy Policy
Technology News
Intel has revealed latest MLPerf AI tests, showing off its Xeon 6 CPUs and Arc Pro B60 GPUs. The results indicate up to 4x better value than NVIDIA for running large language models.
The ARC Pro B60 GPU. (Image Credit: Intel/News9).
New Delhi: Intel’s new Arc Pro-B series GPUs paired with Xeon 6 CPUs have performed very well in the latest MLPerf Inference V5.1 benchmarks, used by the industry to measure how fast and efficient computers are at running AI models. Intel’s setup delivered powerful, low-latency AI inference performance for workstations and edge systems at competitive prices. The tests were conducted by MLCommons and measured six key AI workloads, with the Arc Pro B60 GPU demonstrating 1.25 better performance per dollar than Nvidia’s RTX 6000 GPU, and up to 4x better value than Nvidia’s L40S for running models such as Llama 8B.
The results highlight the ability of Intel to provide high quality, high performance AI solutions at affordable prices. The success was demonstrated by Intel’s new AI inference platform codenamed Project Battlematrix, that combines validated hardware and software into a single solution for Linux environments that is easy to deploy. The platform supports containerised setups, multi-GPU scaling and PCIe data transfers between machines, all of which makes it easier for developers to get started with large AI workloads. The systems are suitable for enterprise use because of built-in reliability features such as ECC memory, SR-IOV virtualization, telemetry and the support for remote firmware updates.
A validation of Intel’s strategy
Intel corporate vice president and general manager of Software, GPU and NPU IP Group, Lisa Pearce says, “The MLPerf v5.1 results are a powerful validation of Intel’s GPU and AI strategy. Our Arc Pro B-Series GPUs with a new inference-optimized software stack let developers and enterprises develop and deploy AI powered applications with inference workstations that are powerful, simple to set up, accessibly priced, and scalable.” The Xeon 6 CPU also played a critical role in the benchmarks, achieving 1.9x higher performance compared to the previous generation. The CPU acts as a orchestration hub, handling the preprocessing, data movement, and workload coordination, ensuring smooth performance across a setup with multiple GPUs.
Aditya Madanapalle
Aditya has studied journalism, multimedia technologies and ᚨᚾᚲᛁᛖᚾᛏ ᚱᚢᚾᛖᛋ. He has over 10 years experience as a science and technology reporter, with a focus on space, AI, videogames, cybsersecurity and fundamental research. He is usually found playing with age inappropriate LEGO sets or sedentary games both new and old.
Read More
Next Article
Follow us on social media
Images are for reference only.Images and contents gathered automatic from google or 3rd party sources.All rights on the images and contents are with their legal original owners.
Aggregated From –
Comments are closed.