AMD Bald Eagle Point “Ryzen AI” APUs Were Supposed To Be Strix Refresh With Increased Cache For RDNA 3.5 iGPU

Jul 22, 2024 at 08:40am EDT
AMD Bald Eagle Point "Ryzen AI" APUs Were Supposed To Be Strix Refresh With Increased Cache For RDNA 3.5 iGPU 1

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.

AMD's Bald Eagle Point "Ryzen AI" APUs Supposedly Offer Little Improvements Over Strix APUs But The Release Is Still in Question

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.

Related Story AMD Believes Unified Memory Architectures Open Up a “World of Possibilities”, Will Shape Their Product Choices & Roadmaps In Future

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.

Image Source: AMD

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 systems. AMD Medusa is said to feature Zen 6 architecture and the RDNA 5-based integrated graphics.

If AMD delivers Medusa in time, the Bald Eagle Point might get canceled completely. Nonetheless, the estimated time gap between Bald Eagle Point and Strix Halo is unknown and AMD would likely go straight with Strix Halo due to its significantly better specifications, comprising powerful integrated graphics, which is reportedly offering up to 40 Compute Units. This is a 2.5X increase in Compute Units compared to the Strix Point's flagship Radeon 890M iGPU, which means Strix Halo might be the first APU series that could directly compete with some budget and mid-range Laptop GPUs.

AMD Ryzen Mobility CPUs:

CPU Family NameAMD Sound Wave?AMD Bald Eagle PointAMD Krackan PointAMD Fire RangeAMD Strix Point HaloAMD Strix PointAMD Hawk PointAMD Dragon RangeAMD PhoenixAMD RembrandtAMD CezanneAMD RenoirAMD PicassoAMD Raven Ridge
Family BrandingTBDRyzen AI 400TBDTBDRyzen AI 300Ryzen AI 300AMD Ryzen 8040 (H/U-Series)AMD Ryzen 7045 (HX-Series)AMD Ryzen 7040 (H/U-Series)AMD Ryzen 6000
AMD Ryzen 7035
AMD Ryzen 5000 (H/U-Series)AMD Ryzen 4000 (H/U-Series)AMD Ryzen 3000 (H/U-Series)AMD Ryzen 2000 (H/U-Series)
Process NodeTBD4nm4nm5nm4nm4nm4nm5nm4nm6nm7nm7nm12nm14nm
CPU Core ArchitectureZen 6?Zen 5 + Zen 5CZen 5Zen 5Zen 5 + Zen 5CZen 5 + Zen 5CZen 4 + Zen 4CZen 4Zen 4Zen 3+Zen 3Zen 2Zen +Zen 1
CPU Cores/Threads (Max)TBD12/248/1616/3216/3212/248/1616/328/168/168/168/164/84/8
L2 Cache (Max)TBD12 MBTBDTBD24 MB12 MB4 MB16 MB4 MB4 MB4 MB4 MB2 MB2 MB
L3 Cache (Max)TBD24 MB + 16 MB SLC32 MBTBD64 MB + 32 MB SLC24 MB16 MB32 MB16 MB16 MB16 MB8 MB4 MB4 MB
Max CPU ClocksTBDTBDTBDTBDTBD5.1 GHzTBD5.4 GHz5.2 GHz5.0 GHz (Ryzen 9 6980HX)4.80 GHz (Ryzen 9 5980HX)4.3 GHz (Ryzen 9 4900HS)4.0 GHz (Ryzen 7 3750H)3.8 GHz (Ryzen 7 2800H)
GPU Core ArchitectureRDNA 3+ iGPURDNA 3.5 4nm iGPURDNA 3+ 4nm iGPURDNA 3+ 4nm iGPURDNA 3.5 4nm iGPURDNA 3.5 4nm iGPURDNA 3 4nm iGPURDNA 2 6nm iGPURDNA 3 4nm iGPURDNA 2 6nm iGPUVega Enhanced 7nmVega Enhanced 7nmVega 14nmVega 14nm
Max GPU CoresTBD16 CUs (1024 Cores)12 CUs (786 cores)2 CUs (128 cores)40 CUs (2560 Cores)16 CUs (1024 Cores)12 CUs (786 cores)2 CUs (128 cores)12 CUs (786 cores)12 CUs (786 cores)8 CUs (512 cores)8 CUs (512 cores)10 CUs (640 Cores)11 CUs (704 cores)
Max GPU ClocksTBD2900 MHzTBDTBDTBD2900 MHz2800 MHz2200 MHz2800 MHz2400 MHz2100 MHz1750 MHz1400 MHz1300 MHz
TDP (cTDP Down/Up)TBD15W-45W (65W cTDP)15W-45W (65W cTDP)55W-75W (65W cTDP)55W-125W15W-45W (65W cTDP)15W-45W (65W cTDP)55W-75W (65W cTDP)15W-45W (65W cTDP)15W-55W (65W cTDP)15W -54W(54W cTDP)15W-45W (65W cTDP)12-35W (35W cTDP)35W-45W (65W cTDP)
Launch2026?2025?2025?2H 2024?2H 2024?2H 2024Q1 2024Q1 2023Q2 2023Q1 2022Q1 2021Q2 2020Q1 2019Q4 2018

News Source: ThisEndsNow

About the author: Sarfraz Khan is a hardware reporter with a focus on PC components and the builder community. With years of experience writing about PC hardware and laptops, his work has been featured on several reputable technology publications. Sarfraz's hands-on experience is demonstrated through his first-person accounts of using and comparing different hardware configurations, providing practical and relatable insights for everyday users. His technical analysis is respected by peers in the enthusiast community and has been cited by specialized hardware sites such as Germany's Igor's Lab.

Follow Wccftech on Google to get more of our news coverage in your feeds.