AMD Ryzen Z1 GPU vs Intel Arc Pro B390 Comparison

FAQ

Q: What are the core architecture and manufacturing process differences between the AMD Ryzen Z1 GPU and the Intel Arc Pro B390?

A: The AMD Ryzen Z1 GPU is built on RDNA 3.0 architecture and uses a 4 nm TSMC process, while the Intel Arc Pro B390 uses Xe3-LPG architecture and a 3 nm Intel process. The AMD chip is named Phoenix, while the Intel chip is named Panther Lake.

Q: How do the memory configurations differ between these two GPUs?

A: The AMD Ryzen Z1 GPU has 16 GB of LPDDR5 memory on a 64-bit bus with 51.20 GB/s bandwidth. The Intel Arc Pro B390 uses System Shared memory with a System Shared bus width and System Dependent bandwidth.

Q: What are the thermal design power ratings for each GPU?

A: The AMD Ryzen Z1 GPU has a TDP of 30 W, making it a low-power part. The Intel Arc Pro B390 has a TDP of 80 W, which is more than double the AMD part.

Q: Which GPU has a higher pixel fill rate?

A: The Intel Arc Pro B390 has a pixel rate of 60.00 GPixel/s, which is three times the 20.00 GPixel/s of the AMD Ryzen Z1 GPU.

Q: What are the release dates for these products?

A: The AMD Ryzen Z1 GPU was released on 2023-09-17. The Intel Arc Pro B390 has a release date of 2026-01-26.

Q: Do both GPUs support the same graphics APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Neither has benchmark data recorded in the database, and both are at the 50th percentile among all GPUs.

Architecture Differences

The AMD Ryzen Z1 GPU and Intel Arc Pro B390 represent fundamentally different design approaches within their respective product lines. The AMD part is based on the RDNA 3.0 architecture, manufactured on a 4 nm TSMC process. The Intel part uses the Xe3-LPG architecture on a 3 nm Intel process. The Intel chip is built with a more advanced process node, which typically allows for higher transistor density and efficiency, although Intel's transistor count and die size are not recorded in the database.

The compute resources differ substantially. The AMD Ryzen Z1 GPU contains 256 shading units, 16 texture mapping units, and 8 raster output units. The Intel Arc Pro B390 contains 1536 shading units, 48 TMUs, and 24 ROPs. This means the Intel part has six times the shading units, three times the TMUs, and three times the ROPs. Ray tracing hardware also differs: AMD includes 4 RT cores, while Intel includes 12 RT cores.

Clock behavior shows an interesting contrast. The AMD GPU has a base clock of 1500 MHz and a boost clock of 2500 MHz. The Intel GPU has a much lower base clock of 300 MHz but the same 2500 MHz boost clock. This suggests the Intel part relies more heavily on boost behavior, potentially running at reduced clocks under sustained loads or when thermally constrained.

Memory architecture is a key differentiator. The AMD Ryzen Z1 GPU has dedicated 16 GB of LPDDR5 memory with a 64-bit bus and 51.20 GB/s of bandwidth. The Intel Arc Pro B390 instead uses System Shared memory, meaning it draws from the host system's memory pool, with bandwidth that is System Dependent. The AMD part's dedicated memory provides predictable bandwidth for graphics workloads, while the Intel part's shared memory approach depends on the host platform.

The Intel Arc Pro B390 is an integrated graphics processor with a slot width of IGP and a bus interface of IGP. The AMD Ryzen Z1 GPU has no bus interface listed, no display outputs, and physical dimensions of 280 mm length, 111 mm height, and 21 mm width. The Intel part's display outputs are Portable Device Dependent, indicating it is designed for mobile or embedded platforms. The AMD part has no display outputs at all, suggesting it is a companion or secondary GPU.

Power characteristics differ significantly. The AMD Ryzen Z1 GPU has a TDP of 30 W, while the Intel Arc Pro B390 has a TDP of 80 W. Neither requires external power connectors. The Intel part's higher power budget aligns with its larger compute configuration and higher peak throughput.

The Verdict

The recorded data shows two GPUs with distinct positioning. The AMD Ryzen Z1 GPU is a low-power part with a 30 W TDP, dedicated 16 GB of LPDDR5 memory, and a compact 280 mm board. It was released in September 2023 with a launch MSRP of 599 USD. The Intel Arc Pro B390 is an integrated processor with an 80 W TDP, System Shared memory, and no standalone dimensions, released in January 2026.

For workloads that depend on raw shading throughput, the Intel Arc Pro B390 is the clear choice based on the numbers. It delivers 7.680 TFLOPS of FP32 compute, three times the AMD part's 2.560 TFLOPS. Texture rate follows the same pattern: 120.0 GTexel/s versus 40.00 GTexel/s. Pixel rate is 60.00 GPixel/s versus 20.00 GPixel/s. The Intel part also has more RT cores, 12 versus 4, for ray-traced workloads.

For low-power or embedded applications, the AMD Ryzen Z1 GPU has the advantage. Its 30 W TDP is less than half the Intel part's 80 W. It also has dedicated memory, which can be preferable when the host system's memory bandwidth is uncertain or shared with other components. The AMD part's 16 GB of LPDDR5 memory provides a fixed capacity, while the Intel part's System Shared memory is dependent on the host.

Users who need a discrete form factor should consider the AMD Ryzen Z1 GPU, since it has defined physical dimensions and no bus interface listed as IGP. The Intel part is explicitly an IGP with a slot width of IGP, meaning it cannot be installed as a standalone card. The AMD part has no display outputs, so it must be paired with another solution for display output. The Intel part's display outputs are Portable Device Dependent, indicating flexibility depending on the host device.

The database shows both GPUs at the 50th percentile among all GPUs, with no benchmark scores recorded and no nearest rivals listed. This limits quantitative comparison to architectural and specification-level analysis.

Specification Differences

| Specification | AMD Ryzen Z1 GPU | Intel Arc Pro B390 |

|---|---|---|

| Architecture | RDNA 3.0 | Xe3-LPG |

| Process Node | 4 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 25,390 million | unknown |

| Die Size | 178 mm² | unknown |

| Base Clock | 1500 MHz | 300 MHz |

| Boost Clock | 2500 MHz | 2500 MHz |

| Memory Size | 16 GB | System Shared |

| Memory Type | LPDDR5 | System Shared |

| Memory Bus Width | 64 bit | System Shared |

| Memory Bandwidth | 51.20 GB/s | System Dependent |

| Shading Units | 256 | 1536 |

| TMUs | 16 | 48 |

| ROPs | 8 | 24 |

| RT Cores | 4 | 12 |

| Pixel Rate | 20.00 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 40.00 GTexel/s | 120.0 GTexel/s |

| FP32 | 2.560 TFLOPS | 7.680 TFLOPS |

| FP16 | 5.120 TFLOPS (2:1) | 15.36 TFLOPS (2:1) |

| TDP | 30 W | 80 W |

| Slot Width | null | IGP |

| Bus Interface | null | IGP |

| Display Outputs | No outputs | Portable Device Dependent |

| Release Date | 2023-09-17 | 2026-01-26 |

| Launch MSRP | 599 USD | null |

Head-to-Head Benchmarks

No head-to-head benchmark results are recorded in the database for these two GPUs. Both have an average benchmark score of 0 and no entries in their benchmark lists. The database shows winsA as 0 and winsB as 0, meaning there are no direct comparison measurements available.

The nearest rivals lists are also empty for both products, and no percentile movement data exists beyond the identical 50th percentile rank. This means the comparison must rely entirely on the specification-level measurements that are recorded.

The most significant performance indicator is FP32 compute throughput. The Intel Arc Pro B390 delivers 7.680 TFLOPS, which is exactly three times the AMD Ryzen Z1 GPU's 2.560 TFLOPS. In texture processing, the Intel part achieves 120.0 GTexel/s, also three times the AMD part's 40.00 GTexel/s. Pixel throughput follows the same 3x ratio: 60.00 GPixel/s versus 20.00 GPixel/s.

FP16 performance scales identically to FP32 for both parts. The Intel GPU reaches 15.36 TFLOPS FP16 (2:1), while the AMD GPU reaches 5.120 TFLOPS FP16 (2:1). The 3x ratio persists across all throughput metrics, which is consistent with the Intel part having six times the shading units but a lower base clock that reduces its sustained advantage in some scenarios.

The AMD Ryzen Z1 GPU has a base clock of 1500 MHz, which is five times the Intel part's 300 MHz base clock. Both boost to 2500 MHz. This indicates that the AMD part maintains higher clocks at idle or low load, while the Intel part requires boost conditions to reach its full performance. In thermally constrained environments, the AMD part's lower TDP of 30 W may allow it to sustain closer to its boost clock for longer periods.

Memory bandwidth is another area of divergence. The AMD part has a fixed 51.20 GB/s from its LPDDR5 memory on a 64-bit bus. The Intel part's bandwidth is System Dependent, so no fixed comparison is possible. In a host system with high-bandwidth memory, the Intel part could exceed the AMD part's bandwidth, but in a system with slower shared memory, it could fall short.

Ray tracing resources favor the Intel part, with 12 RT cores versus 4 RT cores. This is a 3x advantage in ray tracing hardware, matching the ratio seen in shading units, TMUs, and ROPs. The AMD part's 4 RT cores on RDNA 3.0 architecture may use a different ray tracing implementation, but the hardware count difference is substantial.

Both GPUs support identical API feature levels: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This means software compatibility is equivalent at the API level, and differences in actual performance would come from the underlying hardware resources rather than API support.

The Intel Arc Pro B390 is the successor to HD Graphics-WM, according to the database. The AMD Ryzen Z1 GPU has no predecessor or successor listed. The Intel part is part of the Arc Graphics-WM (Panther Lake) generation, while the AMD part belongs to the Console GPU (AMD) generation.

Production status for both is Active. The AMD part has defined physical dimensions of 280 mm by 111 mm by 21 mm, while the Intel part has no recorded dimensions, consistent with its IGP form factor. Neither GPU has tensor cores listed in the database.