AMD Ryzen AI Z2 Extreme GPU vs Intel Arc B390 Comparison

AMD Ryzen AI Z2 Extreme GPU and Intel Arc B390 are both integrated graphics solutions, but they are designed for entirely different segments of the mobile market. The Ryzen AI Z2 Extreme GPU is a high-end part with a 50th percentile ranking among all GPUs, while the Arc B390 sits at the 9th percentile. The data shows a clear stratification in performance, architecture, and thermal design between the two.

Head-to-Head Benchmarks

The recorded benchmark data provides a single comparison point, the 3DMark Steel Nomad DX12 test. In this test, the Intel Arc B390 scores 1482 points. The AMD Ryzen AI Z2 Extreme GPU has no recorded benchmark score in the database, meaning a direct numerical comparison in this specific test is not possible. The Arc B390's score places it in the 9th percentile of all GPUs. Its nearest rivals, according to the database, are the NVIDIA GeForce GT 520MX with an average score of 1463 and a delta of 1.3%, the NVIDIA GeForce 800M with 1460 and a delta of 1.5%, the NVIDIA GeForce GT 625 OEM with 1446 and a delta of 2.5%, and the NVIDIA GeForce GT 710 with 1443 and a delta of 2.7%. This indicates that the Arc B390 performs at the level of older entry-level discrete GPUs.

The theoretical compute figures, however, tell a different story about peak capability. The AMD Ryzen AI Z2 Extreme GPU delivers 5.530 TFLOPS of FP32 performance, while the Intel Arc B390 delivers 7.680 TFLOPS. In raw FP32 throughput, the Intel part is approximately 38.9% higher. The Arc B390 also offers a significantly higher FP16 rate of 15.36 TFLOPS, which is 2.8 times its own FP32 rate, indicating a 2:1 ratio. The AMD GPU's FP16 performance is 5.530 TFLOPS, a 1:1 ratio with its FP32 output. This gives the Intel GPU a substantial advantage in workloads that can utilize FP16 compute.

The rasterization rates also show a divergence. The AMD Ryzen AI Z2 Extreme GPU achieves a pixel rate of 129.6 GPixel/s and a texture rate of 172.8 GTexel/s. The Intel Arc B390, in contrast, has a pixel rate of 60.00 GPixel/s and a texture rate of 120.0 GTexel/s. In these specific metrics, the AMD GPU holds a clear lead, with 116% higher pixel throughput and 44% higher texture throughput. This suggests that despite having lower raw FP32 compute, the AMD architecture is configured for more efficient pixel and texture shading.

Where Each One Wins

The Intel Arc B390 wins in scenarios that depend on raw shader compute. Its FP32 advantage of 7.680 TFLOPS versus 5.530 TFLOPS makes it the stronger candidate for general compute tasks and shader-heavy rendering that does not rely on pixel output. The FP16 capability is even more pronounced, with 15.36 TFLOPS versus the AMD's 5.530 TFLOPS. This suggests a significant advantage in AI workloads or applications that leverage half-precision calculations.

The AMD Ryzen AI Z2 Extreme GPU wins in scenarios dominated by fixed-function rasterization. Its higher pixel rate of 129.6 GPixel/s and texture rate of 172.8 GTexel/s indicate a design optimized for filling the screen with textured geometry. This points to a potential advantage in traditional 3D game rendering at lower resolutions where pixel throughput is the limiting factor. The AMD GPU also has a much lower thermal design power of 28 W, which allows it to be deployed in more power-constrained environments. The Intel Arc B390 has a TDP of 80 W, which is nearly three times higher.

Architecture Differences

The two GPUs are built on fundamentally different process nodes and architectures. The AMD Ryzen AI Z2 Extreme GPU is manufactured on a 4 nm process at TSMC and uses the RDNA 3.5 architecture. The Intel Arc B390 is built on Intel's 3 nm process and uses the Xe3-LPG architecture. The AMD chip is named Strix Point, while the Intel chip is Panther Lake. The AMD GPU uses a 256-bit memory bus with 16 GB of LPDDR5X memory, providing a fixed bandwidth of 256.0 GB/s. The Intel Arc B390 uses system shared memory with a system-dependent bandwidth, meaning its performance is tied to the host system's memory configuration.

The compute unit configurations differ in shading units, TMUs, and ROPs. The AMD GPU has 1024 shading units, 64 TMUs, and 48 ROPs. The Intel GPU has a higher count of 1536 shading units but fewer TMUs at 48 and significantly fewer ROPs at 24. The AMD GPU also has 16 ray tracing cores, while the Intel Arc B390 has 12. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The AMD part is a console GPU generation, while the Intel part is in the Arc Graphics-M generation for Panther Lake. The AMD GPU's display output is listed as 1x USB Type-C, while the Intel GPU's display outputs are portable device dependent.

FAQ

Q: Which GPU has a higher FP32 performance?

A: The Intel Arc B390 has a higher FP32 performance at 7.680 TFLOPS, compared to the AMD Ryzen AI Z2 Extreme GPU's 5.530 TFLOPS.

Q: How does the memory configuration differ between the two?

A: The AMD Ryzen AI Z2 Extreme GPU has 16 GB of dedicated LPDDR5X memory on a 256-bit bus with 256.0 GB/s bandwidth. The Intel Arc B390 uses system shared memory, with its bandwidth listed as system dependent.

Q: What are the TDP requirements for each GPU?

A: The AMD Ryzen AI Z2 Extreme GPU has a TDP of 28 W, while the Intel Arc B390 has a TDP of 80 W.

Q: What is the process node for each chip?

A: The AMD Ryzen AI Z2 Extreme GPU uses a 4 nm process at TSMC, and the Intel Arc B390 uses a 3 nm process at Intel.

Q: Does the Intel Arc B390 have a recorded benchmark score?

A: Yes, the Intel Arc B390 has a recorded score of 1482 in the 3DMark Steel Nomad DX12 test. The AMD Ryzen AI Z2 Extreme GPU has no recorded benchmark scores in the database.

Q: How do the pixel and texture rates compare?

A: The AMD Ryzen AI Z2 Extreme GPU has a pixel rate of 129.6 GPixel/s and a texture rate of 172.8 GTexel/s, while the Intel Arc B390 has a pixel rate of 60.00 GPixel/s and a texture rate of 120.0 GTexel/s.

Specification Differences

The specification tables show distinct differences across nearly every field. The AMD Ryzen AI Z2 Extreme GPU is built on a 4 nm TSMC process with 34,000 million transistors and a die size of 233 mm². The Intel Arc B390 is on a 3 nm Intel process, with transistor count and die size listed as unknown. The AMD chip has a base clock of 800 MHz and a boost clock of 2700 MHz, while the Intel chip has a base clock of 300 MHz and a boost clock of 2500 MHz. The AMD GPU's memory clock is listed as 1000 MHz with 8 Gbps effective, and the Intel GPU's memory clock is system shared. The memory configuration is a major split: the AMD part has 16 GB of LPDDR5X on a 256-bit bus, and the Intel part uses system shared memory. The AMD GPU has 48 ROPs versus the Intel's 24, 64 TMUs versus 48, and 1024 shading units versus 1536. The AMD GPU has 16 RT cores and the Intel GPU has 12. The TDP is 28 W for AMD and 80 W for Intel. The AMD GPU's pixel rate is 129.6 GPixel/s versus 60.00 GPixel/s, and its texture rate is 172.8 GTexel/s versus 120.0 GTexel/s. FP32 is 5.530 TFLOPS for AMD and 7.680 TFLOPS for Intel. FP16 is 5.530 TFLOPS for AMD and 15.36 TFLOPS for Intel. The AMD part's display output is 1x USB Type-C, while the Intel part's outputs are portable device dependent. The Intel part is an IGP with no power connectors, and the AMD part also has no power connectors.

The Verdict

The database entries show two GPUs with opposite strengths. The Intel Arc B390 is the compute-focused part, with higher FP32 and FP16 throughput. Its 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 figures are the highest raw numbers in this comparison. However, its single recorded benchmark score of 1482 in 3DMark Steel Nomad places it at the 9th percentile, directly competing with older NVIDIA parts like the GeForce GT 520MX and GeForce GT 710. This suggests that its theoretical compute power does not translate into high rasterized gaming performance.

The AMD Ryzen AI Z2 Extreme GPU is the rasterization-focused part. Its pixel rate of 129.6 GPixel/s and texture rate of 172.8 GTexel/s are substantially higher than the Intel's, and its 50th percentile ranking indicates it is a mid-range performer. Its 28 W TDP is a fraction of the Intel's 80 W, making it a far more efficient design. The AMD GPU has no recorded benchmarks, so its real-world gaming performance cannot be directly verified from the data, but its lower power envelope and superior fill rates suggest a design intended for balanced, power-conscious gaming. The choice between them depends on the workload: the Intel Arc B390 for shader-heavy compute and the AMD Ryzen AI Z2 Extreme GPU for rasterized rendering with higher efficiency.