Intel Arc A380M vs Intel Arc Graphics 1 Xe Mobile Comparison

Where Each One Wins

The Intel Arc A380M and the Intel Arc Graphics 1 Xe Mobile occupy distinct positions in the mobile graphics landscape, and the recorded data shows a clear division of strengths. The A380M is a discrete MXM module built for sustained throughput, while the Arc Graphics 1 Xe Mobile is an integrated graphics processor (IGP) designed for efficiency within a constrained power envelope.

The A380M wins decisively in raw compute throughput. Its FP32 performance is recorded at 4.096 TFLOPS, which is nearly seven times the 588.8 GFLOPS of the integrated part. This gap is consistent across texture and pixel processing. The A380M delivers a texture rate of 128.0 GTexel/s versus 18.40 GTexel/s for the Arc Graphics 1 Xe Mobile, a difference of roughly 6.96 times. Pixel fill rates show a similar story: 64.00 GPixel/s versus 9.200 GPixel/s, meaning the discrete part can push over six times more pixels per second. For any workload that is fill-rate bound, such as high-resolution rendering or heavy post-processing effects, the A380M is the clear winner.

The Arc Graphics 1 Xe Mobile, however, wins in the efficiency and integration domain. Its TDP is recorded at 25 W, compared to 35 W for the A380M. While this is a modest absolute difference, the integrated part operates as an IGP with no power connectors, relying entirely on system-shared memory. The data indicates that the A380M requires a dedicated MXM slot and uses 6 GB of GDDR6 memory with a 96-bit bus, whereas the Arc Graphics 1 Xe Mobile uses System Shared memory with bandwidth described as System Dependent. This makes the integrated solution the only option for ultra-thin, low-power portable devices where a discrete module cannot be physically accommodated.

Looking at the wins more precisely, the A380M wins on every measured performance metric. The FP16 throughput is 8.192 TFLOPS (2:1) for the A380M versus 1,177.6 GFLOPS (2:1) for the integrated part. The A380M has 1024 shading units, 64 TMUs, and 32 ROPs. The Arc Graphics 1 Xe Mobile has 128 shading units, 8 TMUs, and 4 ROPs. Even the ray tracing hardware differs: the A380M has 8 RT cores, while the integrated part has just 1. For gaming or creative workloads that leverage ray tracing, the discrete part provides eight times the dedicated hardware.

The integrated GPU wins on power draw and physical footprint. At 25 W, it consumes roughly 71% of the power of the A380M. It is also built on a more advanced process node, 3 nm from Intel, versus 6 nm from TSMC for the A380M. This newer node allows for higher clock speeds in a smaller power budget, with a boost clock of 2300 MHz versus 2000 MHz for the discrete part. However, the base clock of the integrated part is much lower at 300 MHz versus 1550 MHz, reflecting its power-conserving design philosophy. The data positions the Arc Graphics 1 Xe Mobile as the choice for basic 2D acceleration, video playback, and light 3D tasks where battery life and thermal headroom are paramount.

Architecture Differences

The two GPUs are separated by a full generation of Intel graphics architecture. The Intel Arc A380M is based on the DG2-128 chip using the Xe-HPG architecture, belonging to the Alchemist generation (Arc 3 Mobile). In contrast, the Intel Arc Graphics 1 Xe Mobile uses the Wildcat Lake chip with the Xe3-LPG architecture, part of the Arc Graphics-M (Wildcat Lake) generation.

The manufacturing process differs substantially. The A380M is fabricated on a 6 nm process at TSMC, housing 7,200 million transistors on a 157 mm² die. This yields a transistor density of 45.9 million transistors per square millimeter. The Arc Graphics 1 Xe Mobile is built on a 3 nm process at Intel, though its transistor count and die size are listed as unknown in the database. The newer 3 nm node is a significant architectural advantage for the integrated part, enabling higher clock speeds at lower power.

The core configuration is where the performance gap originates. The A380M has 1024 shading units, 64 texture mapping units, and 32 render output units. The Arc Graphics 1 Xe Mobile has 128 shading units, 8 TMUs, and 4 ROPs. This represents an 8x reduction in shading units and TMUs, and an 8x reduction in ROPs. The ray tracing hardware follows the same pattern: 8 RT cores versus 1 RT core.

Clock behavior reveals different design targets. The A380M has a base clock of 1550 MHz and a boost clock of 2000 MHz. The integrated part has a base clock of 300 MHz and a boost clock of 2300 MHz. The integrated GPU is designed to idle at very low clocks and burst to high frequencies when needed, while the discrete part maintains a more consistent operating range.

Memory architecture is fundamentally different. The A380M uses 6 GB of GDDR6 memory on a 96-bit bus, delivering 186.0 GB/s of bandwidth. The memory clock is 1937 MHz, with 15.5 Gbps effective data rate. The Arc Graphics 1 Xe Mobile uses System Shared memory, with bus width and bandwidth both marked as System Dependent. This means the integrated GPU's performance is tied directly to the system's memory configuration, which can vary widely between devices.

Both GPUs support the same API feature set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This means feature-level compatibility is identical, even though raw performance differs by an order of magnitude. The A380M uses an MXM-A (3.1) bus interface and is configured as an MXM Module, while the Arc Graphics 1 Xe Mobile is an IGP with no bus interface beyond the integrated graphics path.

FAQ

Q: Which GPU has higher raw compute performance?

A: The Intel Arc A380M is significantly faster. Its FP32 throughput is 4.096 TFLOPS, which is 6.96 times the 588.8 GFLOPS of the Intel Arc Graphics 1 Xe Mobile.

Q: How do the memory systems differ?

A: The A380M has 6 GB of dedicated GDDR6 memory on a 96-bit bus with 186.0 GB/s of bandwidth and a 1937 MHz memory clock. The Arc Graphics 1 Xe Mobile uses System Shared memory, with bandwidth described as System Dependent.

Q: Which GPU consumes less power?

A: The Intel Arc Graphics 1 Xe Mobile has a TDP of 25 W, compared to 35 W for the A380M. The integrated part also has no power connectors, whereas the A380M is an MXM module.

Q: What are the architectural generations of each GPU?

A: The A380M is based on the DG2-128 chip with Xe-HPG architecture, part of the Alchemist (Arc 3 Mobile) generation. The Arc Graphics 1 Xe Mobile uses the Wildcat Lake chip with Xe3-LPG architecture, part of the Arc Graphics-M (Wildcat Lake) generation.

Q: Do both GPUs support ray tracing?

A: Yes, both support ray tracing, but the A380M has 8 RT cores while the Arc Graphics 1 Xe Mobile has only 1 RT core. Both support DirectX 12 Ultimate (12_2), which includes ray tracing features.

Q: What process nodes are used?

A: The A380M is fabricated on a 6 nm process at TSMC. The Arc Graphics 1 Xe Mobile is fabricated on a 3 nm process at Intel.

Specification Differences

| Specification | Intel Arc A380M | Intel Arc Graphics 1 Xe Mobile |

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

| Architecture | Xe-HPG | Xe3-LPG |

| Generation | Alchemist (Arc 3 Mobile) | Arc Graphics-M (Wildcat Lake) |

| Process Node | 6 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 7,200 million | unknown |

| Die Size | 157 mm² | unknown |

| Transistor Density | 45.9M / mm² | null |

| Base Clock | 1550 MHz | 300 MHz |

| Boost Clock | 2000 MHz | 2300 MHz |

| Memory Clock | 1937 MHz (15.5 Gbps effective) | System Shared |

| Memory Size | 6 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus Width | 96 bit | System Shared |

| Memory Bandwidth | 186.0 GB/s | System Dependent |

| Shading Units | 1024 | 128 |

| TMUs | 64 | 8 |

| ROPs | 32 | 4 |

| RT Cores | 8 | 1 |

| Pixel Rate | 64.00 GPixel/s | 9.200 GPixel/s |

| Texture Rate | 128.0 GTexel/s | 18.40 GTexel/s |

| FP32 Performance | 4.096 TFLOPS | 588.8 GFLOPS |

| FP16 Performance | 8.192 TFLOPS (2:1) | 1,177.6 GFLOPS (2:1) |

| TDP | 35 W | 25 W |

| Slot Width | MXM Module | IGP |

| Power Connectors | null | None |

| Bus Interface | MXM-A (3.1) | IGP |

| Release Date | 2023-01-23 | 2026-04-15 |

| Predecessor | null | HD Graphics-M |

Head-to-Head Benchmarks

The database does not contain direct head-to-head benchmark results between these two GPUs, and the recorded data shows zero wins for each in head-to-head comparisons. However, the specification-level measurements provide a clear picture of relative performance across every compute category.

The most significant performance gap appears in FP32 compute. The A380M delivers 4.096 TFLOPS, which places it 6.96 times ahead of the Arc Graphics 1 Xe Mobile's 588.8 GFLOPS. This means that for general-purpose GPU compute tasks, shader-heavy games, and physics simulations, the A380M provides nearly seven times the arithmetic throughput. In FP16 workloads, where both GPUs use a 2:1 ratio, the A380M's 8.192 TFLOPS is 6.96 times the 1,177.6 GFLOPS of the integrated part.

Texture throughput shows a similar multiplier. The A380M achieves 128.0 GTexel/s, which is 6.96 times the 18.40 GTexel/s of the integrated GPU. This directly impacts texture-heavy rendering scenarios, such as open-world games with complex terrain and detailed surface materials. The pixel fill rate gap is slightly smaller but still substantial: 64.00 GPixel/s versus 9.200 GPixel/s, a 6.96x difference. This affects resolution scaling and post-processing effects like motion blur and depth of field.

The memory bandwidth difference is stark. The A380M has a dedicated 186.0 GB/s of GDDR6 bandwidth, while the integrated GPU's bandwidth is System Dependent and cannot be quantified in the database. The dedicated memory also provides 6 GB of capacity, which is fixed and predictable, whereas the integrated part shares system memory dynamically. For large textures and data sets, the discrete GPU's dedicated bandwidth is a decisive advantage.

Clock speed analysis reveals an interesting nuance. The integrated GPU has a higher boost clock at 2300 MHz versus 2000 MHz for the discrete part. However, the A380M has a much higher base clock at 1550 MHz versus 300 MHz. This suggests the integrated GPU is designed to scale down aggressively during idle and light loads, while the discrete GPU maintains a higher floor for sustained performance. The recorded data indicates the A380M is built for consistent throughput, while the Arc Graphics 1 Xe Mobile is built for burst performance within a tight power budget.

The shading unit count difference of 1024 versus 128 is the primary driver of the compute gap. Each shading unit on the A380M can process more work per clock, and there are eight times as many of them. The TMU count of 64 versus 8 and ROP count of 32 versus 4 follow the same 8x pattern, confirming a consistent architectural scaling between the two parts. The RT core count of 8 versus 1 means ray-traced scenes will see an even larger relative difference, as the A380M has dedicated hardware that is eight times more abundant.

The release date separation of over three years, from 2023-01-23 for the A380M to 2026-04-15 for the Arc Graphics 1 Xe Mobile, explains the architectural leap from Xe-HPG on 6 nm to Xe3-LPG on 3 nm. The newer integrated part uses a more advanced process to achieve higher boost clocks at lower power, but the fundamental limitation of 128 shading units cannot be overcome by clock speed alone. The A380M's larger chip, with 7,200 million transistors on 157 mm², provides the physical resources necessary for high-end mobile graphics performance.