AMD's Bald Eagle Point "Ryzen AI" APUs were supposed to be a refresh of existing Strix chips but with small improvements to the cache.
This is perhaps the first time a brand-new AMD lineup has surfaced on the internet. AMD was supposedly working on a Ryzen AI APU series called "Bald Eagle Point", which was going to be a refresh of the upcoming Strix Point "Ryzen AI 300" lineup.
This information comes from an X user, @GodsClumsyHands, who explains that AMD's Bald Eagle APU family is likely to 'fill the gap between Strix & Medusa'. It's hard to verify this information but what we understand from this report is that Bald Eagle Point was set to launch in 2025, following the release of the upcoming Strix Point series.
AMD's Bald Eagle Point APUs were supposedly built on Zen 5/c architecture, boasting RDNA 3.5-based graphics. Zen 5/c and RDNA 3.5 are the same architectures that are being implemented on Strix Point APUs. So, essentially the configuration on Bald Eagle Point chips looks identical to Strix Point in its monolithic design except that it is offering 16MB of SLC(System Level Cache).
The user says that the Bald Eagle Point is essentially a minor refresh of the Phoenix Point but the improvement will be rather implemented through the cache memory. This means unlike the Strix Point chips, the Bald Eagle might be bringing Infinity Cache to the table for improved performance.
This is possible since the Strix Halo family is supposedly going to feature a 32MB of MALL(Memory Access at Last Level) cache and the Bald Eagle Point might be the first one to bring Infinity Cache to the mobile APUs. However, the user also points out that the decision to launch Bald Eagle Point depends on the success of AMD Medusa, a lineup for client
Read more on wccftech.com