- AMD’s rumored “Sound Wave” chip is claimed to be an Arm-based APU
- It’s believed to feature “RDNA 3.5+” CUs that are “enhanced” for machine learning
- MLID’s sources allege the chip will feature 16MB Infinity Cache
Alleged new information has been uncovered about the rumored AMD “Sound Wave” APU, claiming it will be more towards machine learning, with “enhanced RDNA 3.5” CUs.
The news comes from reliable hardware leaker Moore’s Law is Dead in a new YouTube video, with a long list of updated specs cited from “Late March 2025”. It’s a substantial update on the previous rumor that we covered back in March 2024.
Previously, it was believed that AMD’s Sound Wave processor would be a Zen 6 mobile chipset. However, it’s now claimed by MILD that the processor will be an Arm-based APU, similar to the likes of Qualcomm’s Snapdragon X lineup instead.
You may like
Specifically, MLID’s sources claim that AMD’s Sound Wave APU will be built on a TSMC 3nm node, targeting 5-10W form factors, with two performance cores, four efficiency cores (six total), and 4MB of L3 cache. Crucially, it’s alleged that there will be four RDNA 3.5 CUs with “improved ML Performance” which has been given the name of “RDNA 3.5+” unofficially, to denote a difference from the current RDNA 3.5 CUs available on chips.
Its capabilities for AI computing appear to be a main focus, as can be evidenced by the supposed “4th Generation AI Engine” backed by 16GB LPDDR5X-9600 RAM which is said to be for the “Standard” systems. MLID does not know if the newer RDNA 3.5 CUs will allow for FSR 4. However, gaming appears to be a secondary concern for this silicon.
An interesting development for the Sound Wave APU is that it will allegedly feature 16MB of Memory Access at Last Level (MALL) cache (known to AMD users as Infinity Cache) which is unusual for a 5-10W APU. It’s curious because “Strix Point” does not have this, which is reportedly “documented” by MLID.
MLID later points out how the AI engine, CPU, and GPU will all work on the same controller, so having the extra bandwidth of 16MB Infinity Cache shared between them could be beneficial, even on such a modest chip.
{ window.reliablePageLoad.then(() => { var componentContainer = document.querySelector(“#slice-container-newsletterForm-articleInbodyContent-h5hidXZ5RLVs6Qf9JySTcC”); if (componentContainer) { var data = {“layout”:”inbodyContent”,”header”:”Get daily insight, inspiration and deals in your inbox”,”tagline”:”Sign up for breaking news, reviews, opinion, top tech deals, and more.”,”formFooterText”:”By submitting your information you agree to the Terms & Conditions and Privacy Policy and are aged 16 or over.”,”successMessage”:{“body”:”Thank you for signing up. You will receive a confirmation email shortly.”},”failureMessage”:”There was a problem. Please refresh the page and try again.”,”method”:”POST”,”inputs”:[{“type”:”hidden”,”name”:”NAME”},{“type”:”email”,”name”:”MAIL”,”placeholder”:”Your Email Address”,”required”:true},{“type”:”hidden”,”name”:”NEWSLETTER_CODE”,”value”:”XTR-D”},{“type”:”hidden”,”name”:”LANG”,”value”:”EN”},{“type”:”hidden”,”name”:”SOURCE”,”value”:”60″},{“type”:”hidden”,”name”:”COUNTRY”},{“type”:”checkbox”,”name”:”CONTACT_OTHER_BRANDS”,”label”:{“text”:”Contact me with news and offers from other Future brands”}},{“type”:”checkbox”,”name”:”CONTACT_PARTNERS”,”label”:{“text”:”Receive email from us on behalf of our trusted partners or sponsors”}},{“type”:”submit”,”value”:”Sign me up”,”required”:true}],”endpoint”:”https://newsletter-subscribe.futureplc.com/v2/submission/submit”,”analytics”:[{“analyticsType”:”widgetViewed”}],”ariaLabels”:{}}; var triggerHydrate = function() { window.sliceComponents.newsletterForm.hydrate(data, componentContainer); } if (window.lazyObserveElement) { window.lazyObserveElement(componentContainer, triggerHydrate); } else { triggerHydrate(); } } }).catch(err => console.error(‘%c FTE ‘,’background: #9306F9; color: #ffffff’,’Hydration Script has failed for newsletterForm-articleInbodyContent-h5hidXZ5RLVs6Qf9JySTcC Slice’, err)); }).catch(err => console.error(‘%c FTE ‘,’background: #9306F9; color: #ffffff’,’Externals script failed to load’, err)); ]]>
Sign up for breaking news, reviews, opinion, top tech deals, and more.
AI computing without the power draw
While it’s still early days for Sound Wave, all the rumors we’ve heard from the chipset sound as though it’s primarily being geared around AI workloads without the (usually) high power draws of rival hardware. 16MB of Infinity Cache doesn’t sound too dramatic an inclusion at first, however, that’s before taking into account that the chip is only rated between 5-10W TDP.
Additionally, the RDNA 3.5+ CUs could be a big driving factor in AI workloads, depending on how optimized they really are for machine learning. With a 2026 release date claimed, it’s unlikely we’ll receive official word from AMD any time soon, but we now know it could be an optimized Arm-based APU rather than the chip that ushers in Zen 6 as we previously thought.
