AMD Radeon 820M vs Intel Arc Graphics 112EU Mobile Comparison

Head-to-Head Benchmarks

The database contains no recorded benchmark scores for either the AMD Radeon 820M or the Intel Arc Graphics 112EU Mobile. Both parts currently sit at an average benchmark score of zero, and both occupy the 50th percentile among all GPUs tracked in the database. Without submitted workloads or synthetic test results, direct performance comparison must rely on the architectural and specification data recorded for each product.

The Radeon 820M operates at a base clock of 400 MHz with a boost clock of 2800 MHz. The Arc 112EU starts at 300 MHz and boosts to 2200 MHz. The AMD part reaches a higher peak frequency by 600 MHz, which could translate to an advantage in lightly threaded or single-frame tasks where boost clocks are sustained. However, the Intel part holds a decisive advantage in raw execution resources. The Arc 112EU contains 896 shading units, 56 texture mapping units, and 24 raster operation units. The Radeon 820M has 128 shading units, 8 TMUs, and 4 ROPs. Those counts give Intel a 7x lead in shader count, a 7x lead in TMUs, and a 6x lead in ROPs.

The pixel rate figures confirm the resource disparity. Intel's Arc 112EU achieves 52.80 GPixel/s, while the Radeon 820M reaches 11.20 GPixel/s. That is a 4.71x difference in favor of Intel. Texture rate follows a similar pattern: Intel records 123.2 GTexel/s versus AMD's 22.40 GTexel/s, a 5.5x gap. These are theoretical peak rates derived from clock and unit counts, not measured game performance, but they indicate the Intel part can push far more geometry and texture data through its pipeline per second.

Floating-point throughput shows the largest single gap in the recorded data. The Arc 112EU delivers 3.942 TFLOPS in FP32, while the Radeon 820M delivers 716.8 GFLOPS. That is a 5.5x advantage for Intel in single-precision compute. The FP16 comparison is more nuanced. The Radeon 820M executes FP16 at a 1:1 ratio with FP32, meaning both rates equal 716.8 GFLOPS. The Arc 112EU executes FP16 at a 2:1 ratio, producing 7.885 TFLOPS. Intel leads in absolute FP16 throughput by 11x, but AMD's 1:1 ratio offers no rate penalty when mixed FP16/FP32 workloads are present.

The Radeon 820M includes 2 ray tracing cores. The Arc 112EU lists no ray tracing cores in the database. This gives AMD a feature-level advantage in hardware-accelerated ray tracing, though the absolute performance ceiling remains constrained by the AMD part's lower shader count. The DirectX API support also differs: AMD lists DirectX 12 Ultimate (12_2) while Intel lists DirectX 12 (12_1). This means the AMD part supports the full DirectX 12 Ultimate feature set, including hardware ray tracing and mesh shaders, while Intel's implementation stops at the earlier 12_1 feature level.

Where Each One Wins

Intel Arc Graphics 112EU Mobile wins in every throughput category recorded in the database. The 896 shading units versus 128 represent a massive parallel compute advantage. Workloads that scale with shader count, such as modern game rendering, compute shaders, and image processing, should favor Intel significantly. The 56 TMUs allow for substantially higher texture fill rates, which directly benefits scene detail and anisotropic filtering workloads. The 24 ROPs provide a 6x advantage in pixel output, which matters for high-resolution rendering and post-processing effects that write heavily to the framebuffer. The 5.5x FP32 lead and 11x FP16 lead position the Intel part as the stronger choice for general-purpose GPU compute, including machine learning inference and video encoding tasks that leverage FP16 operations.

AMD Radeon 820M wins in specific architectural features rather than raw throughput. The 2 ray tracing cores give it dedicated hardware for ray-traced effects, a capability absent from the Intel part's recorded feature set. The DirectX 12 Ultimate (12_2) support means the AMD part can run titles that require the full DirectX 12 Ultimate feature set, including those that mandate hardware ray tracing support. The 600 MHz higher boost clock could provide an edge in latency-sensitive tasks where a single thread or small batch of work needs to complete quickly. The 15 W TDP versus 65 W TDP indicates the AMD part draws substantially less power, which matters for thin-and-light laptops where thermal headroom is limited. The 4 nm process node from TSMC also suggests a more power-efficient design than Intel's 10 nm node, though the database records no direct efficiency measurements.

The Radeon 820M also uses a PCIe 4.0 x8 bus interface, while the Intel part connects via Ring Bus. For integrated GPUs sharing system memory, the bus interface can affect memory access latency and bandwidth. The database records memory bandwidth as "System Dependent" for both, so no direct comparison is possible. However, the different bus architectures suggest different memory access patterns. AMD's PCIe interface routes through the standard system interconnect, while Intel's Ring Bus connects directly to the CPU ring fabric, which can reduce latency for CPU-GPU shared data.

FAQ

Q: Which GPU has a higher boost clock?

A: The AMD Radeon 820M boosts to 2800 MHz, while the Intel Arc Graphics 112EU Mobile boosts to 2200 MHz. The AMD part has a 600 MHz higher peak frequency.

Q: How do the shading unit counts compare?

A: The Intel Arc 112EU Mobile contains 896 shading units, while the AMD Radeon 820M contains 128 shading units. Intel has a 7x advantage in shader count.

Q: Does the Intel part support hardware ray tracing?

A: The database records no ray tracing cores for the Intel Arc Graphics 112EU Mobile. The AMD Radeon 820M includes 2 ray tracing cores.

Q: What is the pixel rate difference between the two?

A: The Intel Arc 112EU Mobile achieves 52.80 GPixel/s, while the AMD Radeon 820M achieves 11.20 GPixel/s. Intel has a 4.71x lead in pixel fill rate.

Q: Which GPU supports DirectX 12 Ultimate?

A: The AMD Radeon 820M lists DirectX 12 Ultimate (12_2) support. The Intel Arc Graphics 112EU Mobile lists DirectX 12 (12_1), which is a lower feature level.

Q: What is the FP32 throughput for each part?

A: The Intel Arc 112EU Mobile delivers 3.942 TFLOPS in FP32. The AMD Radeon 820M delivers 716.8 GFLOPS. Intel leads by 5.5x.

Specification Differences

| Specification | AMD Radeon 820M | Intel Arc Graphics 112EU Mobile |

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

| Base clock | 400 MHz | 300 MHz |

| Boost clock | 2800 MHz | 2200 MHz |

| Shading units | 128 | 896 |

| Texture mapping units | 8 | 56 |

| Raster operation units | 4 | 24 |

| Ray tracing cores | 2 | None |

| Pixel rate | 11.20 GPixel/s | 52.80 GPixel/s |

| Texture rate | 22.40 GTexel/s | 123.2 GTexel/s |

| FP32 throughput | 716.8 GFLOPS | 3.942 TFLOPS |

| FP16 throughput | 716.8 GFLOPS (1:1) | 7.885 TFLOPS (2:1) |

| TDP | 15 W | 65 W |

| Bus interface | PCIe 4.0 x8 | Ring Bus |

| DirectX support | 12 Ultimate (12_2) | 12 (12_1) |

Architecture Differences

The AMD Radeon 820M is built on the RDNA 3.5 architecture and belongs to the Navi III IGP generation for Strix Point Mobile. The chip is designated Krackan Point 2 and uses a 4 nm process node from TSMC. The Intel Arc Graphics 112EU Mobile uses the Xe-LPG architecture, belongs to the Arc Graphics-M generation for Meteor Lake, and uses a 10 nm process node from Intel. The foundry difference matters: TSMC fabricates at 4 nm while Intel fabricates at 10 nm, indicating a smaller transistor geometry for AMD.

The Radeon 820M is the successor to the Navi II IGP and was released on February 28, 2025. The Arc 112EU Mobile is the successor to HD Graphics-M and was released on December 13, 2023. Both parts are currently listed as Active in production status.

The Radeon 820M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Arc 112EU Mobile supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The API lists are identical except for the DirectX version, where AMD holds a higher feature level.

Both GPUs use system shared memory with a system dependent bandwidth, and both are integrated graphics processors (IGP) with portable device dependent display outputs. Neither part has a discrete power connector, and neither records a launch MSRP in the database.

The Intel part has a 65 W TDP versus 15 W for AMD, a 4.33x difference in power draw. This aligns with the much larger execution resource pool on the Intel side. The 896 shading units, 56 TMUs, and 24 ROPs require substantially more power to feed than the 128 shaders, 8 TMUs, and 4 ROPs on the AMD part. The 2:1 FP16 ratio on Intel means it can double FP16 throughput by packing two half-precision operations per FP32 cycle. The 1:1 ratio on AMD means FP16 runs at the same rate as FP32, which preserves precision flexibility but does not provide a throughput multiplier.

The ray tracing core count is the most significant architectural divergence. AMD includes 2 dedicated ray tracing cores, while Intel records none. This means hardware-accelerated ray tracing is present on AMD but unavailable on Intel, at least according to the recorded data. The DirectX 12 Ultimate support on AMD also enables features like mesh shaders and variable rate shading, which may not be fully exposed on the Intel part's DirectX 12_1 feature level.

The bus interface difference is notable for an integrated GPU. AMD uses PCIe 4.0 x8, which connects through the standard chipset or CPU PCIe lanes. Intel uses Ring Bus, which ties the GPU directly to the CPU's internal ring interconnect. This can reduce memory access latency for shared data, though the database does not include latency measurements. The memory type, size, and bus width are all listed as "System Shared" for both parts, confirming neither has dedicated VRAM.