AMD Ryzen Z2 A GPU vs Intel Arc Pro B390 Comparison

Head-to-Head Benchmarks

The recorded database contains no direct head-to-head benchmark results for the AMD Ryzen Z2 A GPU and the Intel Arc Pro B390. Both entries show an average benchmark score of 0, and the wins counter for each part is 0. The absence of measured performance data means the comparison must be built entirely from the specification sheets and the architectural characteristics that define each product.

The AMD Ryzen Z2 A GPU delivers 1.638 TFLOPS of FP32 compute, while the Intel Arc Pro B390 reaches 7.680 TFLOPS. That is a 4.69x gap in raw single-precision throughput. The Intel part also leads in pixel throughput at 60.00 GPixel/s versus 25.60 GPixel/s, and in texture rate at 120.0 GTexel/s versus 51.20 GTexel/s. These are the largest measurable deltas between the two parts, and they appear in every throughput category that the database tracks.

Memory bandwidth is another decisive split. The AMD side uses 16 GB of LPDDR5 on a 128 bit bus, yielding 102.4 GB/s. The Intel part uses system shared memory with bandwidth listed as system dependent. The practical implication is that the Intel part can draw on however much memory bandwidth the host platform provides, but the database does not assign it a fixed figure. The AMD part has a known ceiling of 102.4 GB/s, which is a hard limit regardless of platform.

Clock behavior differs sharply. The AMD Ryzen Z2 A GPU runs at a 1000 MHz base and 1600 MHz boost. The Intel Arc Pro B390 has a 300 MHz base and a 2500 MHz boost. The Intel boost clock is 56.25% higher than the AMD boost clock, and its base clock is 70% lower. This suggests a power-managed design that idles very low but scales aggressively under load.

Neither part has any recorded percentile advantage over the other. Both sit at the 50th percentile against all GPUs in the database, and neither has any nearest rivals listed. The comparison is therefore a pure specification-level analysis, with no measured score to anchor either product.

Where Each One Wins

The AMD Ryzen Z2 A GPU wins in power efficiency and memory capacity. Its 15 W TDP is a fraction of the Intel part's 80 W TDP, and it carries 16 GB of dedicated LPDDR5 memory. For workloads that need a fixed, predictable memory pool, the AMD part provides a known 102.4 GB/s of bandwidth and 16 GB of capacity that is not shared with the CPU. The 7 nm TSMC process node and 2,400 million transistors on a 163 mm² die give it a transistor density of 14.7M per mm², which is a compact design for its feature set.

The Intel Arc Pro B390 wins in raw compute and throughput. Its 1536 shading units, 48 texture mapping units, and 24 ROPs outnumber the AMD part's 512 shading units, 32 TMUs, and 16 ROPs. It also has 12 ray tracing cores versus 8 on the AMD side. The 3 nm Intel process node and the Panther Lake chip design place it in a different performance class. The 7.680 TFLOPS FP32 figure is more than four times the AMD part's output, and the 15.36 TFLOPS FP16 figure (2:1 ratio) is similarly dominant.

The Intel part also wins on interface flexibility. It is an IGP with no power connectors and a portable device dependent display output, meaning it integrates into the host processor rather than requiring a separate slot. The AMD part uses a single USB Type-C display output, which limits its connection options to that one port.

Ray tracing is another Intel advantage. The 12 RT cores versus 8 RT cores suggests heavier ray tracing workloads will favor the Intel part, though the database provides no benchmark numbers to quantify the gap.

Architecture Differences

The AMD Ryzen Z2 A GPU uses the Van Gogh chip with RDNA 2.0 architecture, built on TSMC's 7 nm process. It is classified in the database as a Console GPU generation product. The Intel Arc Pro B390 uses the Panther Lake chip with Xe3-LPG architecture, built on Intel's 3 nm process. It is classified under Arc Graphics-WM (Panther Lake) and has a predecessor listed as HD Graphics-WM.

The process node difference is substantial: 7 nm versus 3 nm. The foundry also differs, with TSMC producing the AMD chip and Intel fabricating its own. The AMD part has a known transistor count of 2,400 million and a die size of 163 mm², while the Intel part lists transistors and die size as unknown. This means the database cannot compare transistor density for the Intel part.

Shader organization differs significantly. The AMD part packs 512 shading units, 32 TMUs, and 16 ROPs. The Intel part has 1536 shading units, 48 TMUs, and 24 ROPs. The Intel part triples the shading unit count, adds 50% more TMUs, and adds 50% more ROPs. Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API coverage is identical.

Memory architecture is fundamentally different. The AMD part uses dedicated 16 GB LPDDR5 on a 128 bit bus with a fixed 102.4 GB/s bandwidth. The Intel part uses system shared memory with a system dependent bandwidth and a system shared bus width. The AMD memory clock is 800 MHz with 6.4 Gbps effective, while the Intel memory clock is listed as system shared.

Power delivery also differs. The AMD part has a 15 W TDP with no slot width, power connectors, or suggested PSU listed. The Intel part has an 80 W TDP, an IGP slot width, and no power connectors. The production status for both is active, but the release dates differ: the AMD part entered the database on 2024-12-31T17:00:00.000Z and the Intel part on 2026-01-26T17:00:00.000Z.

FAQ

Q: Which GPU has higher raw FP32 compute?

A: The Intel Arc Pro B390 delivers 7.680 TFLOPS of FP32, which is 4.69x the AMD Ryzen Z2 A GPU's 1.638 TFLOPS.

Q: How do the memory configurations compare?

A: The AMD part uses 16 GB of dedicated LPDDR5 on a 128 bit bus with 102.4 GB/s bandwidth. The Intel part uses system shared memory with system dependent bandwidth and a system shared bus width.

Q: What is the TDP difference?

A: The AMD Ryzen Z2 A GPU has a 15 W TDP. The Intel Arc Pro B390 has an 80 W TDP, which is 5.33x higher.

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.

Q: Which part has more ray tracing cores?

A: The Intel Arc Pro B390 has 12 ray tracing cores. The AMD Ryzen Z2 A GPU has 8 ray tracing cores.

Q: What process nodes are used?

A: The AMD part is built on TSMC's 7 nm process. The Intel part is built on Intel's 3 nm process.

Specification Differences

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

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

| Architecture | RDNA 2.0 | Xe3-LPG |

| Process Node | 7 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 2,400 million | unknown |

| Die Size | 163 mm² | unknown |

| Transistor Density | 14.7M / mm² | null |

| Base Clock | 1000 MHz | 300 MHz |

| Boost Clock | 1600 MHz | 2500 MHz |

| Memory Size | 16 GB | System Shared |

| Memory Type | LPDDR5 | System Shared |

| Memory Bus Width | 128 bit | System Shared |

| Memory Bandwidth | 102.4 GB/s | System Dependent |

| Memory Clock | 800 MHz 6.4 Gbps effective | System Shared |

| Shading Units | 512 | 1536 |

| TMUs | 32 | 48 |

| ROPs | 16 | 24 |

| RT Cores | 8 | 12 |

| Pixel Rate | 25.60 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 51.20 GTexel/s | 120.0 GTexel/s |

| FP32 | 1.638 TFLOPS | 7.680 TFLOPS |

| FP16 | 3.277 TFLOPS (2:1) | 15.36 TFLOPS (2:1) |

| TDP | 15 W | 80 W |

| Slot Width | null | IGP |

| Power Connectors | null | None |

| Bus Interface | null | IGP |

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

| Release Date | 2024-12-31T17:00:00.000Z | 2026-01-26T17:00:00.000Z |

| Predecessor | null | HD Graphics-WM |

| Production Status | Active | Active |

| Percentile vs All GPUs | 50 | 50 |

| Avg Benchmark Score | 0 | 0 |

The Verdict

The database shows two parts aimed at entirely different roles. The AMD Ryzen Z2 A GPU is a 15 W console-class part with dedicated 16 GB memory and a modest 1.638 TFLOPS FP32 output. The Intel Arc Pro B390 is an 80 W integrated part with 7.680 TFLOPS FP32, triple the shading units, and a 3 nm process. Anyone selecting between them should base the decision on power envelope and memory architecture first, because those are the fields where the two parts cannot be reconciled.

The Intel part is the clear compute leader. Its 7.680 TFLOPS FP32, 60.00 GPixel/s pixel rate, and 120.0 GTexel/s texture rate put it in a different performance class. The 12 RT cores and 1536 shading units reinforce that position. For workloads that need maximum throughput and can tolerate an 80 W TDP, the Intel part has every measurable advantage in the database.

The AMD part wins on power and memory determinism. The 15 W TDP is 5.33x lower than the Intel part's 80 W TDP, and the 16 GB dedicated LPDDR5 pool with 102.4 GB/s fixed bandwidth is a known quantity. The Intel part's system shared memory means bandwidth depends entirely on the host platform, which the database lists as system dependent. For a fixed-function device that needs predictable memory behavior, the AMD part is the safer choice.

The release timing also matters. The AMD part entered the database in 2024, while the Intel part is dated 2026. The Intel part lists HD Graphics-WM as its predecessor, which indicates a direct lineage in the Arc Graphics-WM family. The AMD part has no predecessor listed.

There is no benchmark data to settle the question empirically. Both parts sit at the 50th percentile against all GPUs, and both have an average benchmark score of 0. The verdict must come from the specifications alone. The Intel Arc Pro B390 is the higher-performance part by every throughput metric. The AMD Ryzen Z2 A GPU is the lower-power part with a fixed memory configuration. Choose the Intel part for compute-heavy workloads where the 80 W TDP is acceptable. Choose the AMD part for power-constrained designs that need a dedicated 16 GB memory pool.