AMD Radeon 890M vs AMD Ryzen Z2 A GPU Comparison

Head-to-Head Benchmarks

The recorded data contains benchmark results for the AMD Radeon 890M, but the AMD Ryzen Z2 A GPU has no benchmark entries in the database. This makes a direct numerical comparison impossible for most tests. The 890M shows a set of scores across multiple benchmarks: 3DMark Steel Nomad DX12 at 590 points, Geekbench OpenCL at 37,254, Geekbench Vulkan at 40,808, Passmark DirectX 10 at 33, DirectX 11 at 73, DirectX 12 at 37, DirectX 9 at 97, G2D at 979, G3D at 8,076, and GPU compute at 4,157. Its average benchmark score is 9,210.

The Ryzen Z2 A GPU, by contrast, has an average benchmark score of 0 and no recorded test results. Its percentile rank among all GPUs is 50, while the 890M sits at the 45th percentile. The 890M's nearest rivals include the AMD Radeon Vega 8 with an average score of 9,221 (0.1% higher), the NVIDIA GeForce GTX 960 at 9,273 (0.7% higher), the NVIDIA GeForce GTX 465 at 9,294 (0.9% higher), and the NVIDIA GeForce GTX 850M at 9,302 (1.0% higher). These deltas indicate the 890M performs slightly below those four cards, by margins ranging from 0.1% to 1.0%.

Because the Z2 A GPU lacks any benchmark scores, the head-to-head comparison must rely on the available specification data and the 890M's measured performance profile. The 890M delivers 5.939 TFLOPS FP32 performance, while the Z2 A GPU delivers 1.638 TFLOPS FP32. This represents a substantial gap in raw compute throughput, with the 890M offering roughly 3.6 times the FP32 throughput based on the recorded figures. The 890M also has a higher pixel rate at 92.80 GPixel/s versus 25.60 GPixel/s, and a higher texture rate at 185.6 GTexel/s versus 51.20 GTexel/s.

Where Each One Wins

The 890M wins in every category where both devices have recorded data. Its shading unit count is 1,024 versus 512 for the Z2 A GPU, double the compute cores. Texture mapping units stand at 64 versus 32, and raster output units at 32 versus 16. Ray tracing cores are 16 versus 8, again double. The 890M's boost clock reaches 2,900 MHz, compared to 1,600 MHz for the Z2 A GPU, and its base clock is 400 MHz versus 1,000 MHz. The higher boost clock combined with the larger execution resource pool drives the FP32 and texture rate advantages.

The Z2 A GPU wins in memory configuration specifics. It has 16 GB of dedicated LPDDR5 memory on a 128-bit bus with 102.4 GB/s bandwidth, while the 890M uses system-shared memory with bandwidth described as system dependent. The Z2 A GPU also has a higher base clock at 1,000 MHz versus 400 MHz, which may help in lightly threaded or latency-sensitive workloads where sustained low-frequency operation is preferable. Its FP16 throughput is 3.277 TFLOPS with a 2:1 ratio, meaning it can process half-precision at twice its FP32 rate, whereas the 890M runs FP16 at the same rate as FP32 (5.939 TFLOPS, 1:1).

The 890M uses a 4 nm process node from TSMC, while the Z2 A GPU uses a 7 nm node. Transistor counts differ dramatically: 34,000 million for the 890M's Strix Point chip versus 2,400 million for the Z2 A GPU's Van Gogh chip. Die size is 233 mm² for the 890M and 163 mm² for the Z2 A GPU. Transistor density is 145.9 million per mm² for the 890M versus 14.7 million per mm² for the Z2 A GPU. The 890M's architecture is RDNA 3.5, while the Z2 A GPU uses RDNA 2.0. Both share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The Verdict

The data shows a clear performance hierarchy. The 890M holds a dominant position in raw compute, pixel throughput, and texture throughput, with roughly 3.6 times the FP32 performance of the Z2 A GPU. Its larger execution resource pool, higher boost clock, and newer architecture all point toward superior graphics rendering capability. The 890M's measured average benchmark score of 9,210 places it near the 45th percentile of all GPUs, with nearest rivals within 1% of its score, indicating it performs in the range of older discrete desktop cards like the GTX 960.

The Z2 A GPU, with no recorded benchmarks and an average score of 0, cannot be placed in the same performance tier from the available data. Its 50th percentile rank is the only comparative metric, but without measured scores this percentile has no supporting test results. The Z2 A GPU's advantages are confined to its dedicated memory pool, higher base clock, and lower transistor budget, which may be relevant for specific embedded or console-style applications where memory bandwidth is predictable.

Users requiring maximum graphics output from an integrated solution should select the 890M based on its recorded benchmark scores and superior specification sheet. Users needing a self-contained memory subsystem with fixed bandwidth and a lower-power transistor footprint may consider the Z2 A GPU, but they must accept the absence of benchmark validation in the database. The 890M is the only one of the two with verified performance data, so any decision favoring the Z2 A GPU rests entirely on its specification advantages without measured confirmation.

FAQ

Q: Which GPU has a higher FP32 performance?

A: The AMD Radeon 890M delivers 5.939 TFLOPS FP32, while the AMD Ryzen Z2 A GPU delivers 1.638 TFLOPS FP32, making the 890M approximately 3.6 times faster in this metric.

Q: What is the average benchmark score for each GPU?

A: The 890M has an average benchmark score of 9,210. The Z2 A GPU has an average benchmark score of 0, with no individual benchmark results recorded.

Q: How much memory does the Z2 A GPU have, and what type?

A: The Z2 A GPU has 16 GB of LPDDR5 memory on a 128-bit bus with 102.4 GB/s bandwidth. The 890M uses system-shared memory with bandwidth described as system dependent.

Q: What are the process nodes for both GPUs?

A: The 890M uses a 4 nm process node from TSMC. The Z2 A GPU uses a 7 nm process node from TSMC.

Q: Do both GPUs support the same APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the ray tracing core count for each?

A: The 890M has 16 ray tracing cores. The Z2 A GPU has 8 ray tracing cores.

Architecture Differences

The 890M is built on the Strix Point chip using RDNA 3.5 architecture, classified as Navi III IGP (Strix Point Mobile). The Z2 A GPU uses the Van Gogh chip with RDNA 2.0 architecture, classified as Console GPU (AMD). This architectural gap spans two generations of RDNA, with RDNA 3.5 introducing improvements over RDNA 2.0 in execution efficiency and feature support. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so the API surface is identical, but the underlying hardware differs significantly.

The 890M packs 1,024 shading units, 64 TMUs, 32 ROPs, and 16 ray tracing cores. The Z2 A GPU has 512 shading units, 32 TMUs, 16 ROPs, and 8 ray tracing cores. The 890M's transistor count is 34,000 million on a 233 mm² die, yielding a density of 145.9 million transistors per mm². The Z2 A GPU has 2,400 million transistors on a 163 mm² die, for a density of 14.7 million per mm². The 890M's 4 nm process allows for far denser integration, while the Z2 A GPU's 7 nm process results in a smaller absolute transistor budget despite a smaller die.

Clock behavior also differs. The 890M has a base clock of 400 MHz and a boost clock of 2,900 MHz. The Z2 A GPU has a base clock of 1,000 MHz and a boost clock of 1,600 MHz. The 890M's higher boost clock enables peak performance, while the Z2 A GPU's higher base clock may reduce latency in low-load scenarios. FP16 processing differs as well: the 890M runs FP16 at 5.939 TFLOPS with a 1:1 ratio to FP32, while the Z2 A GPU runs FP16 at 3.277 TFLOPS with a 2:1 ratio, indicating the Z2 A GPU can double its half-precision throughput.

Specification Differences

The power draw is identical at 15 W for both devices. The 890M is an IGP with a slot width of IGP and no power connectors, while the Z2 A GPU has no slot width or power connector data recorded. The 890M uses a PCIe 4.0 x8 bus interface; the Z2 A GPU has no bus interface listed. Display outputs differ: the 890M lists "Portable Device Dependent," while the Z2 A GPU lists one USB Type-C output.

Memory specification shows the largest divergence. The 890M uses system-shared memory with system-dependent bandwidth, while the Z2 A GPU has 16 GB of LPDDR5 on a 128-bit bus with 102.4 GB/s bandwidth and an effective memory clock of 800 MHz (6.4 Gbps effective). The 890M's memory clock is listed as system shared, with no fixed bandwidth figure.

Release dates differ: the 890M launched on 2024-07-14, while the Z2 A GPU launched on 2024-12-31. Both are marked as Active production status. The 890M's predecessor is Navi II IGP, while the Z2 A GPU has no predecessor listed. Neither has a successor. Neither has a launch MSRP recorded. The 890M's FP16 rate equals its FP32 rate at 5.939 TFLOPS, while the Z2 A GPU's FP16 rate is 3.277 TFLOPS, double its FP32 rate of 1.638 TFLOPS. Pixel and texture rates follow the same pattern: the 890M hits 92.80 GPixel/s and 185.6 GTexel/s, while the Z2 A GPU hits 25.60 GPixel/s and 51.20 GTexel/s.