\t\t\t\t\t\/\/php echo do_shortcode(‘[responsivevoice_button voice=”US English Male” buttontext=”Listen to Post”]’) ?>
\n\t\t\t\t\t<\/p>\n

SANTA CLARA, CALIF. \u2014 \u201cIf you think about the product portfolio that AMD has, it\u2019s arguably the broadest in the industry in terms of AI compute,\u201d Vamsi Boppana, senior VP of the AI group at AMD, said in his keynote address at the recent AI Hardware Summit. AMD\u2019s hardware portfolio includes data-center\u2013class CPUs and GPUs, consumer GPUs, FPGAs and the Ryzen 7040, a client CPU with NPU designed for PCs. Software is key to unlocking the performance of these different hardware platforms. But how does AMD compete with its GPU competitors\u2019 strong offerings, given its more diverse hardware?<\/p>\n

AMD\u2019s software stacks for each class of product are separate: ROCm (short for Radeon Open Compute platform) targets its Instinct data center GPU lines (and, soon, its Radeon consumer GPUs), Vitis AI targets its FPGAs, and ZenDNN targets its client devices.<\/p>\n

How far along is AMD with unifying these stacks?<\/p>\n

\u201cWe have enormous customer pull coming, and that is dictating quite a bit of our near-term plans,\u201d Boppana told EE Times in an interview after his talk here. \u201cThe plane is flying right now, so we cannot disassemble the engine. However, we are absolutely doing things at the foundational level to make more unification happen in our stack.\u201d<\/p>\n