Intel Arc A380M vs Intel Arc Pro B370 Comparison

FAQ

Q: What are the two GPUs compared here?

A: The Intel Arc A380M is a mobile discrete GPU based on the DG2-128 chip, using the Xe-HPG architecture from the Alchemist generation. The Intel Arc Pro B370 is an integrated graphics processor based on the Panther Lake chip, using the Xe3-LPG architecture from the Arc Graphics-WM generation.

Q: Which GPU has the higher boost clock?

A: The Intel Arc Pro B370 boosts to 2400 MHz, while the Intel Arc A380M boosts to 2000 MHz. The Arc Pro B370 also has a much lower base clock of 300 MHz compared to the A380M's 1550 MHz base clock.

Q: How do the two GPUs differ in memory configuration?

A: The Arc A380M uses 6 GB of GDDR6 memory on a 96-bit bus, delivering 186.0 GB/s of bandwidth. The Arc Pro B370 uses system shared memory, with bandwidth listed as system dependent.

Q: Which GPU has the higher FP32 compute throughput?

A: The Arc Pro B370 delivers 6.144 TFLOPS of FP32 performance, which is 50% higher than the Arc A380M's 4.096 TFLOPS. The Arc Pro B370 also leads in FP16 with 12.29 TFLOPS versus 8.192 TFLOPS.

Q: What is the power draw of each GPU?

A: The Arc A380M has a 35 W TDP, while the Arc Pro B370 has a 25 W TDP. The Arc Pro B370 is an IGP with no power connectors, while the A380M is an MXM module.

Q: Which GPU has more shading units and ray tracing cores?

A: The Arc Pro B370 has 1280 shading units and 10 ray tracing cores. The Arc A380M has 1024 shading units and 8 ray tracing cores. However, the A380M has more texture mapping units (64 vs 40) and more ROPs (32 vs 20).

Architecture Differences

The two Intel GPUs represent different architectural generations and implementation strategies. The Arc A380M uses the DG2-128 chip built on Xe-HPG architecture, belonging to the Alchemist generation for Arc 3 Mobile. It is manufactured on a 6 nm process at TSMC, with 7,200 million transistors packed into a 157 mm² die, yielding a transistor density of 45.9M per mm². The Arc Pro B370 uses the Panther Lake chip with Xe3-LPG architecture from the Arc Graphics-WM generation, manufactured on Intel's 3 nm process. Its transistor count and die size are listed as unknown in the database.

The A380M is a discrete mobile GPU packaged as an MXM Module with an MXM-A (3.1) bus interface. The B370 is an integrated graphics processor with an IGP bus interface, sharing system memory. This fundamental difference shapes their memory architectures: the A380M has dedicated 6 GB GDDR6 memory on a 96-bit bus, while the B370 relies on system shared memory with system dependent bandwidth.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The B370 has a higher shading unit count at 1280 versus 1024, and more ray tracing cores at 10 versus 8. The A380M counters with more TMUs at 64 versus 40 and more ROPs at 32 versus 20. The B370's FP32 throughput of 6.144 TFLOPS exceeds the A380M's 4.096 TFLOPS, and its FP16 output of 12.29 TFLOPS doubles to 6.144 TFLOPS at a 2:1 ratio, matching its FP32 proportion.

Clock behavior differs significantly. The A380M runs at a 1550 MHz base clock and 2000 MHz boost, with memory clocked at 1937 MHz (15.5 Gbps effective). The B370 has a 300 MHz base clock but boosts to 2400 MHz. The B370's higher boost clock and larger shader array contribute to its compute advantage.

The B370 is the successor to the HD Graphics-WM in Intel's lineup. Its release date is January 26, 2026, while the A380M was released on January 23, 2023. Both are listed as active production parts.

The Verdict

The recorded data indicates the Intel Arc Pro B370 is the stronger compute performer. Its FP32 output of 6.144 TFLOPS is 50% higher than the Arc A380M's 4.096 TFLOPS. The B370 also leads in shading units (1280 vs 1024) and ray tracing cores (10 vs 8). For workloads that scale with raw shader throughput, the B370 has the advantage.

The A380M holds its own in specific areas. It has more texture mapping units (64 vs 40) and more ROPs (32 vs 20), leading to a higher pixel rate of 64.00 GPixel/s versus the B370's 48.00 GPixel/s. Its texture rate of 128.0 GTexel/s also exceeds the B370's 96.00 GTexel/s. The dedicated 6 GB GDDR6 memory with 186.0 GB/s bandwidth provides a fixed memory resource, whereas the B370 depends on system shared memory.

Power consumption favors the B370 at 25 W TDP versus the A380M's 35 W TDP. The B370 achieves higher compute throughput while drawing less power, indicating better efficiency per watt in the recorded specifications.

For systems where dedicated graphics memory and higher rasterization throughput matter, the A380M presents the stronger profile. For compute-intensive tasks and lower power budgets, the B370 delivers more FP32 and FP16 performance. Both GPUs share identical API support, so software compatibility is not a differentiator.

Neither part has recorded benchmark scores in the database, so the analysis relies on specification-level comparisons. Both GPUs sit at the 50th percentile versus all GPUs in the database.

Specification Differences

| Specification | Intel Arc A380M | Intel Arc Pro B370 |

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

| Chip | DG2-128 | Panther Lake |

| Architecture | Xe-HPG | Xe3-LPG |

| Generation | Alchemist (Arc 3 Mobile) | Arc Graphics-WM (Panther Lake) |

| Process Node | 6 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 7,200 million | unknown |

| Die Size | 157 mm² | unknown |

| Base Clock | 1550 MHz | 300 MHz |

| Boost Clock | 2000 MHz | 2400 MHz |

| 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 | 1280 |

| TMUs | 64 | 40 |

| ROPs | 32 | 20 |

| Ray Tracing Cores | 8 | 10 |

| Pixel Rate | 64.00 GPixel/s | 48.00 GPixel/s |

| Texture Rate | 128.0 GTexel/s | 96.00 GTexel/s |

| FP32 | 4.096 TFLOPS | 6.144 TFLOPS |

| FP16 | 8.192 TFLOPS (2:1) | 12.29 TFLOPS (2:1) |

| TDP | 35 W | 25 W |

| Slot Width | MXM Module | IGP |

| Power Connectors | none listed | None |

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

| Release Date | January 23, 2023 | January 26, 2026 |

| Predecessor | none listed | HD Graphics-WM |

Head-to-Head Benchmarks

The database contains no recorded head-to-head benchmark results for these two GPUs. The comparison below relies entirely on the specification data.

The biggest win for the Arc Pro B370 is in compute throughput. Its FP32 output of 6.144 TFLOPS is 50% ahead of the A380M's 4.096 TFLOPS. The FP16 gap is similar in proportional terms: 12.29 TFLOPS versus 8.192 TFLOPS, also a 50% advantage. The B370's 1280 shading units provide 25% more ALU capacity than the A380M's 1024 units. Ray tracing hardware also favors the B370 with 10 RT cores versus 8, a 25% increase.

The A380M wins decisively in rasterization-related metrics. Its pixel rate of 64.00 GPixel/s is 33% higher than the B370's 48.00 GPixel/s. The texture rate of 128.0 GTexel/s is also 33% higher than the B370's 96.00 GTexel/s. These advantages come from the A380M's larger TMU count (64 vs 40, a 60% margin) and ROP count (32 vs 20, also a 60% margin).

The A380M's dedicated memory subsystem is a clear differentiator. The 6 GB GDDR6 allocation with 186.0 GB/s bandwidth provides a fixed and substantial memory resource. The B370's system shared memory has bandwidth listed as system dependent, meaning its effective performance varies with the host platform. For workloads sensitive to memory bandwidth consistency, the A380M offers more predictable performance.

The B370 counters with a significant clock advantage at the top end. Its 2400 MHz boost clock is 20% higher than the A380M's 2000 MHz. The B370 also achieves its higher compute output at a lower TDP of 25 W versus 35 W, a 29% reduction in power draw. This efficiency gap may matter in thermally constrained portable systems.

The manufacturing process also differs: the B370 uses Intel's 3 nm node, while the A380M uses TSMC's 6 nm node. The B370's newer process likely contributes to its lower power consumption at higher clock speeds, though the database does not list transistor counts for the B370 to confirm density comparisons.

In summary, the B370 leads in raw compute, shader count, ray tracing hardware, boost clock, and power efficiency. The A380M leads in texture units, ROPs, pixel throughput, texture throughput, and dedicated memory bandwidth. The choice between them depends on whether the workload favors compute throughput or rasterization throughput, with the B370 offering the higher performance ceiling in FP32 and FP16 workloads.