AMD Ryzen Z2 GPU vs Intel Arc B390 Comparison

FAQ

Q: What is the process node difference between the AMD Ryzen Z2 GPU and the Intel Arc B390?

A: The AMD Ryzen Z2 GPU is built on a 4 nm process at TSMC, while the Intel Arc B390 uses a 3 nm process at Intel.

Q: How do the two compare in raw FP32 compute performance?

A: The AMD Ryzen Z2 GPU delivers 8.294 TFLOPS of FP32 performance, which is 8% higher than the Intel Arc B390's 7.680 TFLOPS.

Q: What is the thermal design power (TDP) of each GPU?

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

Q: Do both GPUs support the same DirectX version?

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

Q: What is the memory configuration difference?

A: The AMD Ryzen Z2 GPU has 16 GB of dedicated LPDDR5X memory on a 128-bit bus with 119.9 GB/s bandwidth. The Intel Arc B390 uses system shared memory, with bandwidth described as system dependent.

Q: How does the Intel Arc B390 perform in the only recorded benchmark?

A: The Intel Arc B390 scores 1482 in 3DMark Steel Nomad DX12, placing it in the 9th percentile of all GPUs, roughly 1.3% ahead of the NVIDIA GeForce GT 520MX.

Architecture Differences

The AMD Ryzen Z2 GPU uses the RDNA 3.0 architecture on a Hawk Point chip, manufactured on a 4 nm process at TSMC. The transistor count is 25,390 million on a 178 mm² die, yielding a density of 142.6 million transistors per square millimeter. The Intel Arc B390, by contrast, employs the Xe3-LPG architecture on a Panther Lake chip, built on a 3 nm process at Intel. Its transistor count and die size are listed as unknown in the database.

The AMD design integrates 768 shading units, 48 texture mapping units, and 32 ROPs. The Intel part is configured with 1536 shading units, 48 TMUs, and 24 ROPs, giving it double the shading units but fewer ROPs. Both GPUs feature 12 ray tracing cores. The AMD GPU has a base clock of 800 MHz and a boost clock of 2700 MHz, while the Intel GPU runs at a 300 MHz base and 2500 MHz boost.

Memory architecture differs substantially. The AMD Ryzen Z2 GPU uses 16 GB of LPDDR5X memory on a 128-bit interface, with memory clocks at 937 MHz (7.5 Gbps effective) and bandwidth of 119.9 GB/s. The Intel Arc B390 relies on system shared memory, with the bus width and memory type also listed as system shared, and bandwidth being system dependent. The AMD GPU's display output is a single USB Type-C port, whereas the Intel GPU's display outputs are described as portable device dependent.

The Intel Arc B390 is an integrated graphics processor (IGP) with a slot width of IGP and a bus interface of IGP. The AMD Ryzen Z2 GPU has no listed slot width or bus interface. Power delivery differs as well: the AMD part has a 28 W TDP with no power connectors, while the Intel part has an 80 W TDP, also with no power connectors.

Head-to-Head Benchmarks

The database records no direct head-to-head benchmark results between the AMD Ryzen Z2 GPU and the Intel Arc B390. The win counts for both sides are zero. The only benchmark data available is a single 3DMark Steel Nomad DX12 run for the Intel Arc B390, which scored 1482.

That score places the Intel Arc B390 in the 9th percentile of all GPUs in the database. Its nearest rivals are all older NVIDIA parts: the GeForce GT 520MX (1463, 1.3% slower), the GeForce 800M (1460, 1.5% slower), the GeForce GT 625 OEM (1446, 2.5% slower), and the GeForce GT 710 (1443, 2.7% slower). These deltas indicate the Intel Arc B390 is only marginally ahead of a decade-old entry-level discrete GPU in this specific test.

The AMD Ryzen Z2 GPU has no recorded benchmark scores in the database, so its percentile and average score are both zero. Without direct measurements, a numerical comparison of gaming performance between the two cannot be established from the available data. The architectural specifications do, however, provide a basis for qualitative comparison.

The AMD GPU's FP32 throughput of 8.294 TFLOPS exceeds the Intel part's 7.680 TFLOPS by roughly 8%. The AMD part also has a higher pixel rate at 86.40 GPixel/s versus 60.00 GPixel/s for Intel, a 44% advantage. Texture rate favors AMD as well: 129.6 GTexel/s versus 120.0 GTexel/s, a 8% difference. The Intel GPU has a significant FP16 advantage at 15.36 TFLOPS (2:1 ratio) versus AMD's 8.294 TFLOPS (1:1 ratio), indicating Intel's architecture is better suited for workloads that can leverage half-precision arithmetic.

The Intel Arc B390 has double the shading units (1536 versus 768), which could help in certain compute-heavy scenarios, but the AMD GPU's higher clock speeds and faster memory subsystem likely compensate in memory-bound tasks. The AMD part also has 32 ROPs versus Intel's 24, which aligns with its higher pixel fill rate.

Specification Differences

| Specification | AMD Ryzen Z2 GPU | Intel Arc B390 |

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

| Architecture | RDNA 3.0 | Xe3-LPG |

| Chip | Hawk Point | Panther Lake |

| Process Node | 4 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 25,390 million | unknown |

| Die Size | 178 mm² | unknown |

| Transistor Density | 142.6M / mm² | null |

| Base Clock | 800 MHz | 300 MHz |

| Boost Clock | 2700 MHz | 2500 MHz |

| Memory Size | 16 GB | System Shared |

| Memory Type | LPDDR5X | System Shared |

| Memory Bus Width | 128 bit | System Shared |

| Memory Bandwidth | 119.9 GB/s | System Dependent |

| Memory Clock | 937 MHz 7.5 Gbps effective | System Shared |

| Shading Units | 768 | 1536 |

| TMUs | 48 | 48 |

| ROPs | 32 | 24 |

| RT Cores | 12 | 12 |

| Pixel Rate | 86.40 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 129.6 GTexel/s | 120.0 GTexel/s |

| FP32 | 8.294 TFLOPS | 7.680 TFLOPS |

| FP16 | 8.294 TFLOPS (1:1) | 15.36 TFLOPS (2:1) |

| TDP | 28 W | 80 W |

| Slot Width | null | IGP |

| Bus Interface | null | IGP |

| Display Outputs | 1x USB Type-C | Portable Device Dependent |

| Release Date | 2024-12-31 | 2026-01-26 |

The Verdict

The recorded data shows two GPUs with distinctly different design philosophies and intended operating environments. The AMD Ryzen Z2 GPU is a low-power part with a 28 W TDP, designed for compact, portable devices with a single USB Type-C display output. The Intel Arc B390 is an integrated processor with an 80 W TDP, classified as an IGP with system shared memory, targeting Panther Lake-based platforms.

In terms of measured performance, only the Intel Arc B390 has a benchmark score: 1482 in 3DMark Steel Nomad DX12, which places it at the 9th percentile of all GPUs. Its nearest rivals are all NVIDIA parts from the GT 500M/600M era, with performance deltas under 3%. This indicates that, at least in this single test, the Intel Arc B390 performs at the level of very old entry-level discrete GPUs.

The AMD Ryzen Z2 GPU has no recorded benchmark scores, making a direct performance verdict impossible from the database. However, its specifications suggest a stronger memory subsystem (dedicated 16 GB LPDDR5X with 119.9 GB/s bandwidth) and higher pixel throughput (86.40 GPixel/s). Its FP32 compute is 8% higher than the Intel part, and its texture rate is 8% higher as well.

For users prioritizing raw FP32 compute and pixel fill rates, the AMD Ryzen Z2 GPU holds a clear specification advantage. For workloads that benefit from FP16 throughput, the Intel Arc B390's 15.36 TFLOPS is nearly double the AMD part's 8.294 TFLOPS. The Intel GPU also has double the shading units, which may matter for certain parallel workloads.

The 3 nm process node gives the Intel Arc B390 a manufacturing advantage, but its 80 W TDP is nearly three times that of the AMD GPU. The AMD part's 28 W TDP makes it suitable for power-constrained designs, while the Intel part's higher power envelope suggests a different class of device.

The data supports a choice based on the target platform and workload. For low-power, memory-intensive graphics with dedicated VRAM, the AMD Ryzen Z2 GPU is the stronger option. For devices requiring an integrated solution with FP16 capability and a newer process node, the Intel Arc B390 is the only part with measured benchmark data, albeit at a low percentile ranking. The absence of head-to-head results leaves the overall performance comparison open, but the specification table shows AMD leading in memory bandwidth, pixel rate, and FP32, while Intel leads in shading units, FP16, and process node.