AMD Radeon 8065S vs AMD Ryzen Z1 Extreme GPU Comparison

Head-to-Head Benchmarks

The database does not contain any recorded head-to-head benchmark results between the AMD Radeon 8065S and the AMD Ryzen Z1 Extreme GPU. Both entries show an empty benchmark array, and the wins tally is zero for each side. This means the comparative analysis must rely entirely on the specification sheets, architectural differences, and the percentile placement recorded for each part.

The Radeon 8065S sits at the 50th percentile among all GPUs in the database, as does the Ryzen Z1 Extreme GPU. The identical percentile ranking suggests the database currently classifies both parts at the midpoint of the performance distribution, though this is a static placement rather than a measured outcome. Without benchmark scores, the percentile cannot be tied to any specific workload, resolution, or thermal condition.

What the data does provide is a clear mathematical picture of raw throughput potential. The Radeon 8065S delivers 15.36 TFLOPS of FP32 compute, while the Ryzen Z1 Extreme GPU delivers 8.294 TFLOPS. The 8065S therefore offers roughly 85% higher FP32 throughput on paper, a substantial margin that would likely translate into significant advantages in shader-bound scenes. In FP16 work, the comparison flips in an interesting way: the 8065S runs FP16 at the same 15.36 TFLOPS (a 1:1 ratio with FP32), while the Z1 Extreme GPU reaches 16.59 TFLOPS (a 2:1 ratio). The Z1 Extreme GPU actually leads in peak FP16 throughput by about 8%, which suggests it may be better suited to workloads that can exploit packed math instructions.

Texture and pixel throughput follow the expected pattern. The 8065S achieves 480.0 GTexel/s and 192.0 GPixel/s, compared to 129.6 GTexel/s and 86.40 GPixel/s for the Z1 Extreme GPU. The 8065S leads by roughly 270% in texture rate and 122% in pixel rate. These are the figures that drive fill-rate-bound effects, such as heavy alpha blending, post-processing chains, and high-resolution shadow maps. The gap here is far larger than the FP32 gap, indicating the 8065S has a much wider execution pipeline.

The memory subsystem reinforces the separation. The Z1 Extreme GPU has 16 GB of LPDDR5 memory on a 64-bit bus, with 51.20 GB/s of bandwidth and a 6.4 Gbps effective data rate. The 8065S uses system-shared memory with a bus width and bandwidth listed as system dependent, so no fixed bandwidth number can be compared directly. The practical implication is that the 8065S relies on the host platform memory controller, which can vary widely, while the Z1 Extreme GPU has a fixed, known memory configuration.

FAQ

Q: Which GPU has higher FP32 compute power?

A: The AMD Radeon 8065S delivers 15.36 TFLOPS of FP32 throughput, while the AMD Ryzen Z1 Extreme GPU delivers 8.294 TFLOPS. The 8065S leads by approximately 85%.

Q: Does the Ryzen Z1 Extreme GPU have any compute advantage?

A: Yes, in FP16 throughput. The Z1 Extreme GPU reaches 16.59 TFLOPS using a 2:1 FP16 to FP32 ratio, whereas the 8065S reaches 15.36 TFLOPS with a 1:1 ratio. The Z1 Extreme GPU leads by roughly 8% in peak FP16.

Q: How do the memory configurations compare?

A: The Ryzen Z1 Extreme GPU has 16 GB of LPDDR5 memory on a 64-bit bus with 51.20 GB/s of bandwidth. The AMD Radeon 8065S uses system-shared memory, with bandwidth listed as system dependent and no fixed capacity or bus width.

Q: What are the clock speed ranges for each GPU?

A: The Radeon 8065S has a base clock of 1295 MHz and a boost clock of 3000 MHz. The Ryzen Z1 Extreme GPU has a base clock of 800 MHz and a boost clock of 2700 MHz, with its memory clocked at 800 MHz or 6.4 Gbps effective.

Q: Which GPU has more ray tracing cores?

A: The AMD Radeon 8065S has 40 ray tracing cores, compared to 12 on the AMD Ryzen Z1 Extreme GPU. That is more than three times the RT core count.

Q: What is the thermal design power for each part?

A: The Radeon 8065S is rated at 55 W and is classified as an integrated graphics processor (IGP). The Ryzen Z1 Extreme GPU is rated at 30 W.

Where Each One Wins

The Radeon 8065S wins in most raw throughput categories. Its FP32 figure of 15.36 TFLOPS doubles the 8.294 TFLOPS of the Z1 Extreme GPU, which points to a decisive advantage in standard shader workloads, traditional rasterization, and general compute tasks. The texture rate of 480.0 GTexel/s versus 129.6 GTexel/s and the pixel rate of 192.0 GPixel/s versus 86.40 GPixel/s indicate the 8065S can sustain far higher fill rates, which matters for high-resolution rendering, heavy anisotropic filtering, and scenes with dense particle effects or layered transparency. The larger shading unit count, 2560 versus 768, reinforces this lead in parallel work. The RT core count of 40 versus 12 suggests the 8065S has considerably more ray tracing capacity, which would show up in ray-traced reflections, shadows, and global illumination workloads if the rest of the system can feed it.

The Ryzen Z1 Extreme GPU wins in FP16 peak throughput. Its 16.59 TFLOPS exceeds the 15.36 TFLOPS of the 8065S, which is notable for applications that use packed half-precision math, such as certain machine learning inference paths and some compute shaders. The Z1 Extreme GPU also has a fixed 16 GB LPDDR5 memory pool with a defined 51.20 GB/s bandwidth, which is a predictable configuration. The 8065S depends on system-shared memory, so its effective bandwidth is entirely dependent on the host platform. In a tightly constrained power envelope, the Z1 Extreme GPU's 30 W rating versus the 8065S's 55 W means it consumes less power, which may be a deciding factor for portable or battery-limited devices. The Z1 Extreme GPU is also physically a standalone component at 280 mm by 111 mm by 21 mm, whereas the 8065S is an IGP with no listed dimensions and no power connectors.

Specification Differences

The two parts differ across nearly every measurable field. The Radeon 8065S uses the Gorgon Halo chip on RDNA 3.5 architecture, while the Ryzen Z1 Extreme GPU uses the Phoenix chip on RDNA 3.0. The 8065S is part of the Navi Mobile (RX 8000M) generation; the Z1 Extreme GPU is classified under Console GPU (AMD). Both are built on a 4 nm process at TSMC, but the die sizes diverge sharply: the 8065S measures 308 mm², while the Z1 Extreme GPU measures 178 mm². Transistor counts are unknown for the 8065S, while the Z1 Extreme GPU carries 25,390 million transistors with a density of 142.6M per mm².

Clock behavior differs as well. The 8065S runs at a 1295 MHz base and 3000 MHz boost. The Z1 Extreme GPU runs at an 800 MHz base and 2700 MHz boost, with memory at 800 MHz or 6.4 Gbps effective. The memory configuration is fundamentally different: the 8065S uses system-shared memory with system-dependent bandwidth, while the Z1 Extreme GPU has 16 GB of LPDDR5 on a 64-bit bus delivering 51.20 GB/s.

The compute units diverge in every count. The 8065S has 2560 shading units, 160 texture mapping units, 64 render output units, and 40 RT cores. The Z1 Extreme GPU has 768 shading units, 48 TMUs, 32 ROPs, and 12 RT cores. The 8065S achieves a pixel rate of 192.0 GPixel/s and a texture rate of 480.0 GTexel/s, versus 86.40 GPixel/s and 129.6 GTexel/s for the Z1 Extreme GPU. Power ratings are 55 W for the 8065S and 30 W for the Z1 Extreme GPU. The 8065S uses a PCIe 5.0 x16 bus interface, while the Z1 Extreme GPU lists no bus interface. Display outputs differ: the 8065S is portable device dependent, while the Z1 Extreme GPU has one USB Type-C output. The 8065S has no listed dimensions or power connectors; the Z1 Extreme GPU has no power connectors either, but does have a full dimension set.

Architecture Differences

The architecture gap is defined by the RDNA generation. The Radeon 8065S uses RDNA 3.5, the newer revision, while the Ryzen Z1 Extreme GPU uses RDNA 3.0. Both are manufactured on the same 4 nm TSMC process, so the architectural gains come from design improvements rather than process scaling. The 8065S implements FP16 at a 1:1 ratio with FP32, meaning it processes half-precision at the same rate as full-precision. The Z1 Extreme GPU uses a 2:1 ratio, doubling FP16 throughput to 16.59 TFLOPS despite lower FP32 performance. This is a fundamental architectural choice, not a clock difference.

The 8065S has a much larger die at 308 mm² versus 178 mm², and it packs 2560 shading units into that space, compared to 768 on the Z1 Extreme GPU. The RT core count is 40 versus 12, a structural difference that suggests the 8065S was designed with heavier ray tracing workloads in mind. The 8065S also carries 160 TMUs and 64 ROPs, versus 48 and 32 on the Z1 Extreme GPU. The result is a wider, deeper pipeline in every render stage.

The memory architectures are entirely different in kind. The 8065S is an IGP with system-shared memory, meaning it has no dedicated VRAM and its bandwidth is whatever the host platform provides. The Z1 Extreme GPU is a discrete-style part with 16 GB of LPDDR5 on a 64-bit bus, delivering a fixed 51.20 GB/s. The Z1 Extreme GPU is also a physical card with dimensions of 280 mm by 111 mm by 21 mm, while the 8065S is integrated with no slot width or connector requirements. The 8065S uses a PCIe 5.0 x16 interface; the Z1 Extreme GPU has no listed bus interface. The 8065S's display output is portable device dependent, while the Z1 Extreme GPU provides a single USB Type-C port.

The release timeline also differs. The Z1 Extreme GPU was released in June 2023, while the 8065S is dated to December 2025. The 8065S lists Polaris Mobile as its predecessor, while the Z1 Extreme GPU has no predecessor listed. The Z1 Extreme GPU has a launch MSRP of 699 USD, which appears in the database, while the 8065S has no launch price recorded.

The Verdict

The data points to a clear split by workload and platform. The AMD Radeon 8065S is the stronger compute and rendering part in most categories. Its FP32 throughput of 15.36 TFLOPS, texture rate of 480.0 GTexel/s, pixel rate of 192.0 GPixel/s, and 40 RT cores make it the better choice for shader-heavy games, high-resolution rendering, and ray-traced effects, assuming the host system can supply sufficient shared memory bandwidth. Its 55 W power envelope and IGP form factor mean it is designed to live inside a portable device with a powerful CPU, not as a standalone expansion card.

The AMD Ryzen Z1 Extreme GPU is the better fit for constrained power environments and for workloads that exploit packed FP16 math. Its 16.59 TFLOPS FP16 peak exceeds the 8065S, and its 30 W rating is nearly half the 8065S's power draw. The fixed 16 GB LPDDR5 pool with 51.20 GB/s gives it a predictable memory profile, and its physical dimensions make it a standalone component that can be slotted into a device with its own cooling. The 699 USD launch MSRP is recorded in the database, though no comparable price exists for the 8065S.

Both parts sit at the 50th percentile in the database, but that equal placement does not reflect the wide specification gaps. The 8065S is the clear leader in raw rasterization and ray tracing capacity. The Z1 Extreme GPU counters with FP16 efficiency, lower power draw, and a self-contained memory system. The choice comes down to whether the target device can feed the 8065S with adequate shared memory and cooling, or whether the self-contained, lower-power Z1 Extreme GPU is the safer fit for a compact platform. Benchmark data is not yet available to confirm how these architectural differences translate into real-world frame rates, so the verdict rests on the measured specifications alone.