ADVERTISEMENT
Advertisement
Processors

Intel core ultra series 2 processors achieve full NPU support in MLPerf client v0.6 benchmark, leading AI compute performance

Listen to this story

AI NARRATED
0:00 / 0:00

Intel announced an achievement in AI compute performance with its Intel Core Ultra Series 2 processors, becoming the first and only company to achieve full neural processing unit support in the newly released MLPerf Client v0.6 benchmark. This milestone marks the industry's first standardized evaluation of large language model performance on client NPUs.

ADVERTISEMENT
Advertisement

Unprecedented AI Compute Performance: Intel Core Ultra Series 2 processors deliver exceptional AI compute performance across the CPU, GPU, and NPU, setting new standards in the industry.
    Fastest NPU Response Time: Intel achieved the fastest NPU response time, generating the first word in just 1.09 seconds (first token latency), enabling near-instantaneous AI interaction.
    Highest NPU Throughput: With a throughput of 18.55 tokens per second, Intel's NPU demonstrates superior efficiency in generating text, ensuring seamless real-time AI experiences.
    Leading GPU Performance: Intel's built-in Intel Arc GPU showcased leadership in time to first token, reinforcing its end-to-end AI acceleration advantage.
 
Developed collaboratively by MLCommons consortium members, including Intel, AMD, Microsoft, Nvidia, and Qualcomm, MLPerf Client v0.6 extends beyond previous GPU-centric tests to include dedicated NPU benchmarking. Intel's success is a testament to the close collaboration between its NPU hardware and OpenVINO software teams.
 
"We are proud to lead the industry in enabling full NPU acceleration and industry-leading GPU performance for AI workloads on client PC platforms. This success reflects Intel’s deep hardware-software co-optimization and commitment to democratizing AI for PCs everywhere," said Daniel Rogers, Intel vice president and general manager of PC Product Marketing. 


More from Processors