The semiconductor industry requires robust and energy-efficient data center infrastructure and Electronic Design Automation (EDA) solutions to continuously develop next-generation chips. AMD EPYC™ 9005 Series processors, the world's most powerful server CPUs, deliver record-breaking performance and efficiency, along with industry-leading features, for enterprise computing, AI, cloud, and other data center workloads.

AMD EPYC 9005 Series processors feature up to 192 "Zen 5" or "Zen 5c" cores, 12 channels of DDR5 memory per CPU supporting up to DDR5-6400 MT/s, and a large L3 cache of up to 384MB. They also offer industry-leading boost frequencies of up to 5GHz and AVX-512 with a full 512b data path. Among these, the high-frequency SKUs up to DDR5-6400 MT/s help users achieve desired performance with fewer cores, thereby optimizing power consumption and Total Cost of Ownership (TCO), while the large L3 cache of up to 384MB is a key driver for EDA performance. Furthermore, the innovative AMD chiplet architecture enables efficient and energy-saving solutions that meet diverse computing needs.

Compared to "Zen 4" cores, "Zen 5" cores deliver up to a 17% IPC uplift for enterprise and cloud workloads, and up to a 37% IPC uplift for AI and high-performance computing. The EPYC 9005 Series is an industry-leading AI processor. Compared to the competitor's top 64-core Intel Xeon 8592+ processor, the 192-core AMD EPYC 9965 processor provides maximized performance per server (up to 60% fewer servers, 40% less power consumption, and 41% lower 3-year TCO for the same integer performance), leading AI inference performance (up to 3x inference throughput), and maximizes graphics card acceleration (the 64-core EPYC 9575F delivers up to 20% system performance improvement).