Shortly after the first die shot of AMD Phoenix2 (also known as Small Phoenix) silicon surfaced, David Huang posted a review of the initial processor on the Chinese platform Zhuanlan/Zhihu.
As expected, both the Ryzen Z1 APU and Ryzen 5 7540U APU will include the 6-core Phoenix2 CPU, which combines a hybrid architecture of Zen4 and Zen4c (dense) cores. These chips are designed specifically for power-efficient uses, like slim laptops and, in the Ryzen Z1’s case, portable gaming consoles.
The review predominantly centers on the Z1 APU, which utilizes a unique power profile separate from its laptop counterpart. However, both versions utilize the same silicon, arranged in an unconventional manner, aiming to provide a cost-effective and efficient solution based on AMD’s latest architecture.
The Zen4c (dense) cores operate at a different clock speed compared to the ‘classic’ cores, with Zen4c running at 3.5 GHz and Zen4 at 4.9 GHz. However, when both types of cores are set to the same 3.2 GHz frequency, their performance becomes nearly indistinguishable. This similarity arises because both core types share the same ISA and frontend. Notably, four out of the six cores are designed to run at 3.5 GHz. The Phoenix2 requires less power to reach its maximum boost clock of 4.9 GHz, with power consumption measuring just 12.7W.
In David’s review, he conducts initial synthetic benchmarks and 3D gaming tests. Given that the Phoenix2 has a unique core layout and reduced GPU capabilities, featuring only one-third of the Phoenix1 RDNA3 CU count (4 vs. 12), you can observe a noticeable performance decrease. However, the gaming experience can vary depending on factors like power limits, clock configurations, system memory, and cooling efficiency.
When comparing the Ryzen 7 7840U (also known as Ryzen Z1 Extreme) with a 25W power limit, one can expect an 80% increase in performance compared to the Ryzen Z1 running at 15W.
In multiple 3DMark graphics tests, a significant disparity in performance becomes apparent when comparing the Z1 processor to the fully-equipped 7840U. Generally, the 25W 7840U outperforms the 15W Z1 by approximately 80%, with even the smallest performance gap in Fire Strike measuring around 70%. Despite being configured for 30W, the Phoenix2, which has three times fewer cores than the Phoenix1, can maintain a GPU clock speed of 2.8 GHz with a power consumption of only 22W, dropping to 1.8-2.0 GHz at 15W.
In synthetic tests, the gap between the 12CU RDNA3 iGPU in the Z1 and the 4CU RDNA3 iGPU in the 7840U decreases to 28.6% when comparing the 7840U at 25W and the Ryzen Z1 at 30W. Interestingly, when the Ryzen Z1 is operated at 30W, its performance is 34% better than when it runs at 15W. In more demanding graphics-oriented games like Metro Exodus or Cyberpunk 2077, the 7840U exhibits a speed advantage of 24.6% to 57%. However, the performance difference between the Z1 at 30W and 15W narrows to 15% to 19%.
In summary, the AMD Phoenix, whether referred to as Ryzen Z1 or Ryzen 5 7540U, is evidently tailored for MMO games and titles that can perform well at lower TDPs. Handheld gamers aiming for modern titles with greater graphical fidelity, resolution, and support for high-resolution textures, which may demand a higher power profile, could find the Ryzen Z1 Extreme to be a preferable option. On the other hand, gamers primarily interested in popular titles optimized for less powerful hardware may find that the Ryzen Z1 strikes a better balance between performance and power efficiency.
As for pricing, the ASUS ROG Ally featuring the Z1 non-Extreme chip has not hit the market yet, but there are indications from the company that it could be priced $100 less than the Extreme version. Whether this reduced price justifies the specifications downgrade is still uncertain.
Source & Images: David Huang