AMD Radeon 840M vs Intel Arc A380M Comparison

The Verdict

The AMD Radeon 840M and Intel Arc A380M target different mobile segments, and the recorded data shows a clear split in intended use. The Radeon 840M is an integrated graphics processor (IGP) built into the Krackan Point chip, consuming 15 W and relying on system memory. It is designed for thin-and-light portables where power efficiency and compactness matter more than raw throughput. The Arc A380M is a discrete MXM module with 6 GB of dedicated GDDR6 memory, a 35 W TDP, and its own cooling and power delivery. It is meant for systems that can accommodate a replaceable graphics module and need dedicated memory bandwidth.

Benchmark results indicate that the Arc A380M is the substantially faster part in raw compute. Its FP32 throughput of 4.096 TFLOPS is roughly 2.76 times the Radeon 840M's 1,484.8 GFLOPS. The Arc A380M also has 1024 shading units versus 256, 64 texture mapping units versus 16, and 32 ROPs versus 8. For users who prioritize frame rates in games or GPU-accelerated workloads, the Arc A380M is the obvious choice. However, the Radeon 840M's 15 W power envelope makes it viable for laptops that run entirely on integrated graphics, with no MXM slot required. The data shows that the Arc A380M uses more than double the power of the Radeon 840M (35 W versus 15 W), so it belongs in larger chassis with better thermal solutions.

The absence of head-to-head benchmark scores in the database means the verdict rests on architectural and specification comparisons. The Radeon 840M offers a 4 nm process node and RDNA 3.5 architecture with ray tracing support, while the Arc A380M uses a 6 nm node with Xe-HPG architecture and double the ray tracing cores. For a user with an existing MXM-equipped laptop, the Arc A380M is the upgrade path. For a new ultraportable design, the Radeon 840M is the integrated solution. Neither part has a launch MSRP recorded, so no price-based guidance is possible from the data.

Architecture Differences

The Radeon 840M uses the RDNA 3.5 architecture on a 4 nm TSMC process, part of the Navi III IGP generation for Strix Point Mobile. It is built into the Krackan Point chip, meaning the GPU shares the package with the CPU and accesses system memory. The Arc A380M uses Intel's Xe-HPG architecture on a 6 nm TSMC process, belonging to the Alchemist generation for Arc 3 Mobile. The Arc A380M is a discrete part built on the DG2-128 chip with a die size of 157 mm² and 7,200 million transistors. The transistor density works out to 45.9M per mm². The Radeon 840M's die size and transistor count are not recorded in the database.

Memory architecture differs fundamentally. The Radeon 840M uses system shared memory with a system dependent bandwidth and no dedicated VRAM. The Arc A380M has 6 GB of GDDR6 memory on a 96-bit bus, delivering 186.0 GB/s of bandwidth. This dedicated memory arrangement gives the Arc A380M consistent bandwidth regardless of system DRAM configuration, whereas the Radeon 840M's memory performance varies with the host laptop's RAM.

The Radeon 840M has 4 ray tracing cores, while the Arc A380M has 8. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Radeon 840M's pixel rate is 23.20 GPixel/s, and its texture rate is 46.40 GTexel/s. The Arc A380M delivers 64.00 GPixel/s and 128.0 GTexel/s. FP16 computation differs too: the Radeon 840M executes FP16 at a 1:1 ratio with FP32 (both 1,484.8 GFLOPS), while the Arc A380M uses a 2:1 ratio, reaching 8.192 TFLOPS FP16 versus its 4.096 TFLOPS FP32.

The Radeon 840M's base clock is 400 MHz with a boost of 2900 MHz. The Arc A380M runs at a base of 1550 MHz and boosts to 2000 MHz, with memory at 1937 MHz (15.5 Gbps effective). The Radeon 840M uses a PCIe 4.0 x8 interface, while the Arc A380M uses MXM-A (3.1). The Radeon 840M is an IGP with no power connectors; the Arc A380M is an MXM module. Display outputs are portable device dependent for both.

Head-to-Head Benchmarks

The database lists no direct head-to-head benchmark scores between these two GPUs, and neither part has individual benchmark entries or an average benchmark score. Both share the same percentile ranking of 50 against all GPUs, indicating that the database's percentile system places them identically in a broad field. Without measured game or synthetic scores, the comparison must rely on the recorded specification-derived rates.

The largest recorded advantage for the Arc A380M is in pixel throughput. Its 64.00 GPixel/s is 2.76 times the Radeon 840M's 23.20 GPixel/s. Texture throughput shows a similar gap: 128.0 GTexel/s versus 46.40 GTexel/s, a factor of 2.76 as well. FP32 compute follows the same pattern, with the Arc A380M at 4.096 TFLOPS versus 1,484.8 GFLOPS, again a 2.76x difference. These ratios are consistent because the Arc A380M has exactly 4 times the shading units, TMUs, and ROPs of the Radeon 840M, though its clocks are lower (2000 MHz boost versus 2900 MHz boost), which tempers the theoretical advantage.

Memory bandwidth is where the Arc A380M has an even larger edge. Its 186.0 GB/s dedicated GDDR6 bandwidth is not directly comparable to the Radeon 840M's system dependent bandwidth, but the dedicated memory removes reliance on shared system RAM. The Radeon 840M's memory performance is entirely dependent on the host system's memory configuration, which the database records as "System Dependent." The Arc A380M's 6 GB frame buffer also allows larger textures and higher resolutions without spilling to system memory.

Ray tracing capability favors the Arc A380M, which has 8 ray tracing cores versus 4 on the Radeon 840M. FP16 throughput massively favors the Arc A380M, which reaches 8.192 TFLOPS compared to 1,484.8 GFLOPS on the Radeon 840M; the 2:1 ratio on the Arc means FP16 workloads see double its FP32 rate, while the Radeon 840M's 1:1 ratio offers no FP16 acceleration benefit.

The Radeon 840M's advantages are in clocks and power. Its boost clock of 2900 MHz is 45% higher than the Arc A380M's 2000 MHz boost. Its 15 W TDP is less than half the Arc A380M's 35 W. The Radeon 840M also uses a newer 4 nm process versus 6 nm, which contributes to its efficiency profile.

Specification Differences

| Specification | AMD Radeon 840M | Intel Arc A380M |

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

| Architecture | RDNA 3.5 | Xe-HPG |

| Generation | Navi III IGP (Strix Point Mobile) | Alchemist (Arc 3 Mobile) |

| Process node | 4 nm | 6 nm |

| Transistors | Unknown | 7,200 million |

| Die size | Unknown | 157 mm² |

| Transistor density | Not recorded | 45.9M / mm² |

| Base clock | 400 MHz | 1550 MHz |

| Boost clock | 2900 MHz | 2000 MHz |

| Memory size | System Shared | 6 GB GDDR6 |

| Memory bus | System Shared | 96 bit |

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

| Shading units | 256 | 1024 |

| TMUs | 16 | 64 |

| ROPs | 8 | 32 |

| Ray tracing cores | 4 | 8 |

| Pixel rate | 23.20 GPixel/s | 64.00 GPixel/s |

| Texture rate | 46.40 GTexel/s | 128.0 GTexel/s |

| FP32 | 1,484.8 GFLOPS | 4.096 TFLOPS |

| FP16 | 1,484.8 GFLOPS (1:1) | 8.192 TFLOPS (2:1) |

| TDP | 15 W | 35 W |

| Slot width | IGP | MXM Module |

| Bus interface | PCIe 4.0 x8 | MXM-A (3.1) |

| Release date | 2025-02-28 | 2023-01-23 |

| Predecessor | Navi II IGP | None recorded |

Both GPUs share the same DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 API support. Both are marked Active in production status. Neither has a recorded launch MSRP. The Radeon 840M has no power connectors because it is an IGP; the Arc A380M's power connector details are not recorded.

FAQ

Q: Which GPU has higher raw compute performance?

A: The Intel Arc A380M. Its FP32 throughput of 4.096 TFLOPS is 2.76 times the AMD Radeon 840M's 1,484.8 GFLOPS. It also has 4 times the shading units (1024 versus 256), TMUs (64 versus 16), and ROPs (32 versus 8).

Q: Which GPU is more power efficient?

A: The AMD Radeon 840M. It has a 15 W TDP, less than half of the Intel Arc A380M's 35 W. The Radeon 840M also uses a smaller 4 nm process node versus 6 nm, and it boosts to 2900 MHz versus 2000 MHz on the Arc A380M.

Q: Do both GPUs support ray tracing?

A: Yes. The AMD Radeon 840M has 4 ray tracing cores, and the Intel Arc A380M has 8 ray tracing cores. Both support DirectX 12 Ultimate (12_2).

Q: How does memory differ between the two?

A: The AMD Radeon 840M uses system shared memory with a system dependent bandwidth. The Intel Arc A380M has 6 GB of dedicated GDDR6 memory on a 96-bit bus with 186.0 GB/s bandwidth.

Q: Which GPU has higher clock speeds?

A: The AMD Radeon 840M boosts to 2900 MHz, which is 45% higher than the Intel Arc A380M's 2000 MHz boost. The Arc A380M has a higher base clock at 1550 MHz versus 400 MHz on the Radeon 840M.

Q: What form factors do these GPUs use?

A: The AMD Radeon 840M is an IGP (integrated graphics processor) with a PCIe 4.0 x8 interface and no power connectors. The Intel Arc A380M is an MXM module using the MXM-A (3.1) interface.

Where Each One Wins

The Intel Arc A380M wins in every recorded throughput metric except clock speed. Its pixel rate of 64.00 GPixel/s is 2.76x the Radeon 840M's 23.20 GPixel/s. Texture rate follows the same ratio, 128.0 GTexel/s versus 46.40 GTexel/s. FP32 compute is 4.096 TFLOPS versus 1,484.8 GFLOPS. FP16 is even more lopsided, with 8.192 TFLOPS versus 1,484.8 GFLOPS, because the Arc A380M uses a 2:1 FP16 ratio while the Radeon 840M uses 1:1. The Arc A380M's 6 GB GDDR6 with 186.0 GB/s bandwidth provides dedicated memory that the Radeon 840M cannot match, since it relies on system shared memory with system dependent bandwidth. The Arc A380M also has twice the ray tracing cores (8 versus 4), making it the stronger choice for ray-traced workloads. The Arc A380M's 35 W TDP and MXM form factor suit larger laptops with upgradeable graphics modules.

The AMD Radeon 840M wins in power efficiency and integration. Its 15 W TDP enables fanless or low-noise designs in thin ultraportables. Its boost clock of 2900 MHz is the highest recorded clock between the two, and its 4 nm process node is more advanced than the 6 nm node used by the Arc A380M. The Radeon 840M needs no dedicated memory or MXM slot, so it can be dropped into any laptop built around the Krackan Point chip. Its 1:1 FP16 ratio means it does not artificially inflate FP16 throughput, but it also does not offer the FP16 acceleration that the Arc A380M provides. For users who need a GPU that disappears into a compact chassis and draws minimal power, the Radeon 840M is the appropriate choice. For users who need maximum mobile graphics throughput and have an MXM slot available, the Arc A380M dominates the recorded specification comparison.