AMD Radeon 840M vs Intel Arc Graphics 112EU Mobile Comparison

Head-to-Head Benchmarks

The recorded database contains no direct benchmark scores, win counts, or percentile deltas for either the AMD Radeon 840M or the Intel Arc Graphics 112EU Mobile. The head-to-head benchmark array is empty, and both parts register an average benchmark score of zero. This means any direct performance comparison must be inferred from the architectural specifications and theoretical throughput figures present in the database.

The most striking numerical gap is in raw shading throughput. The Intel Arc Graphics 112EU Mobile delivers 3.942 TFLOPS of FP32 compute, while the AMD Radeon 840M produces 1,484.8 GFLOPS. That places the Intel part at roughly 2.65 times the raw FP32 throughput of the AMD part. The texture rate tells a similar story: Intel records 123.2 GTexel/s against AMD's 46.40 GTexel/s, a factor of approximately 2.65 as well. Pixel fill rates also favor Intel, with 52.80 GPixel/s versus 23.20 GPixel/s.

The AMD side does hold an advantage in clock speed. The Radeon 840M boosts to 2900 MHz, compared to the Intel part's 2200 MHz boost. That 700 MHz differential partially compensates for the Intel part's larger execution resource pool, but not enough to close the throughput gap. The AMD part has a 400 MHz base clock versus Intel's 300 MHz base, so AMD's clock advantage exists across both operating points.

FP16 performance shows a more complex picture. The AMD Radeon 840M renders FP16 at a 1:1 ratio with FP32, meaning both sit at 1,484.8 GFLOPS. The Intel Arc Graphics 112EU Mobile uses a 2:1 ratio, so its FP16 output reaches 7.885 TFLOPS. That gives Intel a 5.3 times advantage in FP16 workloads that can use the packed rate. For compute workloads that rely on reduced precision, the Intel part is substantially ahead.

Neither part has recorded benchmark scores, so the database cannot confirm real-world gaming or application deltas. The theoretical numbers indicate Intel's advantage in raw throughput, while AMD's higher clocks suggest the gap may narrow in latency-sensitive or clock-bound workloads. Both parts sit at the 50th percentile against all GPUs in the database, though this percentile is based on the empty benchmark array.

Architecture Differences

The two integrated GPUs come from different manufacturing processes and design philosophies. AMD builds the Radeon 840M on a 4 nm process at TSMC, while Intel fabricates the Arc Graphics 112EU Mobile on a 10 nm process at its own fabs. The AMD part uses the RDNA 3.5 architecture and belongs to the Navi III IGP generation, specifically targeting the Krackan Point chip. Intel uses the Xe-LPG architecture within the Arc Graphics-M generation, built on the Meteor Lake chip.

The execution resource counts differ markedly. AMD allocates 256 shading units, 16 texture mapping units, and 8 render output units. Intel's part carries 896 shading units, 56 TMUs, and 24 ROPs. That is 3.5 times more shading units, 3.5 times more TMUs, and 3 times more ROPs on the Intel side. The AMD Radeon 840M does include 4 ray tracing cores, while the Intel part lists no ray tracing core count in the database.

Memory architecture is shared in both cases. Both GPUs use System Shared memory, with no dedicated video memory, no fixed bus width, and bandwidth described as System Dependent. That means neither part has a private memory pool, and performance will depend on the host system's memory configuration. Both list Portable Device Dependent display outputs, indicating laptop or handheld integration.

Clock behavior differs significantly. AMD's Radeon 840M runs a 400 MHz base and 2900 MHz boost. Intel's Arc Graphics 112EU Mobile runs a 300 MHz base and 2200 MHz boost. The AMD part's 31.8 percent higher boost clock partially offsets the Intel part's larger execution array, but the theoretical throughput figures above show that the offset is incomplete.

API support shows a notable split. AMD supports DirectX 12 Ultimate (12_2), while Intel supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. The AMD part's DirectX 12 Ultimate designation includes features tied to the 12_2 feature level, which may matter for certain modern titles. The Intel part's 12_1 feature level is a step lower in the DirectX feature hierarchy.

The Radeon 840M uses a PCIe 4.0 x8 bus interface, while the Intel part uses a Ring Bus interface. The AMD part specifies a 15 W TDP, while the Intel part lists a 65 W TDP. The AMD part uses no power connectors; the Intel part leaves power connector information blank. Both are IGP slot-width devices with no separate card dimensions.

Release timing differs by roughly 14 months. Intel's Arc Graphics 112EU Mobile launched on 2023-12-13, while AMD's Radeon 840M launched on 2025-02-28. AMD's predecessor is listed as Navi II IGP, and Intel's predecessor is HD Graphics-M. Both parts remain in Active production status.

The Verdict

The database shows a clear compute-resource advantage for the Intel Arc Graphics 112EU Mobile. Its FP32 throughput of 3.942 TFLOPS versus AMD's 1,484.8 GFLOPS, its texture rate of 123.2 GTexel/s versus 46.40 GTexel/s, and its pixel rate of 52.80 GPixel/s versus 23.20 GPixel/s all point in the same direction. For raw shading, texturing, and pixel output, Intel holds the lead.

AMD's Radeon 840M counters with higher clocks and a more advanced feature set. The 2900 MHz boost versus 2200 MHz boost gives AMD a frequency advantage. The DirectX 12 Ultimate (12_2) support gives AMD a feature-level edge over Intel's DirectX 12 (12_1). The 4 ray tracing cores provide dedicated RT hardware that the Intel part does not list. The 4 nm process node at TSMC suggests a more modern fabrication approach than Intel's 10 nm process.

Power efficiency appears to favor AMD. The Radeon 840M lists a 15 W TDP, while the Intel part lists 65 W. That is a 4.3 times difference in rated power. For thin-and-light laptops or handhelds where power budgets are tight, the AMD part offers substantially lower thermal and battery impact. The Intel part's higher throughput comes with a much larger power envelope.

The verdict depends on the workload and the platform. For users who prioritize maximum compute throughput, texture filtering, and pixel fill, the Intel Arc Graphics 112EU Mobile is the stronger choice based on the recorded specifications. For users who need ray tracing support, DirectX 12 Ultimate features, and lower power consumption, the AMD Radeon 840M is the more appropriate part.

Neither part has benchmark scores in the database, so the verdict rests entirely on theoretical specifications. The 50th percentile ranking for both parts against all GPUs is identical and carries no differentiating information.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc Graphics 112EU Mobile, with 3.942 TFLOPS versus the AMD Radeon 840M's 1,484.8 GFLOPS.

Q: What are the boost clocks for each part?

A: The AMD Radeon 840M boosts to 2900 MHz, while the Intel Arc Graphics 112EU Mobile boosts to 2200 MHz.

Q: Does the AMD Radeon 840M support ray tracing?

A: Yes, the database lists 4 ray tracing cores for the AMD part. The Intel Arc Graphics 112EU Mobile lists no ray tracing core count.

Q: Which GPU has a lower TDP?

A: The AMD Radeon 840M, rated at 15 W, versus the Intel Arc Graphics 112EU Mobile's 65 W.

Q: What DirectX versions do the two GPUs support?

A: The AMD Radeon 840M supports DirectX 12 Ultimate (12_2), while the Intel Arc Graphics 112EU Mobile supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

Q: When did each GPU launch?

A: The Intel Arc Graphics 112EU Mobile launched on 2023-12-13, and the AMD Radeon 840M launched on 2025-02-28.

Where Each One Wins

The Intel Arc Graphics 112EU Mobile wins in every raw throughput category recorded in the database. Its FP32 rate of 3.942 TFLOPS puts it ahead for general compute workloads. Its FP16 rate of 7.885 TFLOPS gives it a major advantage in half-precision compute, common in AI inference and some media processing tasks. The 123.2 GTexel/s texture rate and 52.80 GPixel/s pixel rate suggest stronger performance in texture-heavy rendering and fill-rate-bound scenarios. The 896 shading units provide a large execution pool for parallel workloads that scale with shader count.

The AMD Radeon 840M wins in clock speed, with a 2900 MHz boost versus Intel's 2200 MHz. Higher clocks can benefit latency-sensitive tasks and workloads that do not scale perfectly with additional shader units. The 4 ray tracing cores give AMD a dedicated path for ray-traced effects, a feature the Intel part does not list. The DirectX 12 Ultimate (12_2) support provides access to the full DirectX 12 feature set, which may enable specific rendering techniques unavailable on the Intel part's 12_1 feature level. The 15 W TDP makes it the clear choice for power-constrained designs, where the Intel part's 65 W TDP would be impractical.

The FP16 ratio difference defines a distinct split. AMD's 1:1 ratio means FP16 performance equals FP32 at 1,484.8 GFLOPS. Intel's 2:1 ratio doubles FP16 throughput to 7.885 TFLOPS. Applications that can use packed FP16 instructions will favor Intel by a wide margin. Applications that rely on FP32 or FP64 precision will still see Intel ahead, but by the smaller 2.65 times factor.

The process node difference also separates the parts. AMD's 4 nm process at TSMC versus Intel's 10 nm process indicates a more modern manufacturing approach for AMD. While process node alone does not determine performance, the combination of 4 nm, higher clocks, and lower TDP suggests AMD designed for efficiency. Intel's larger execution array and higher TDP indicate a design aimed at raw throughput.

For gaming, the database provides no direct evidence. The theoretical numbers suggest Intel should excel in traditional rasterization due to higher fill rates and shader counts. AMD's ray tracing cores and DirectX 12 Ultimate support could give it an edge in ray-traced titles and feature-rich scenes. The 2900 MHz boost clock may help AMD in CPU-bound or draw-call-limited scenarios where frequency matters more than raw throughput.

For content creation and compute tasks, Intel's FP32 and FP16 advantages are substantial. The 3.942 TFLOPS FP32 and 7.885 TFLOPS FP16 figures position Intel as the stronger compute engine. AMD's lower TDP and higher clocks make it more suitable for sustained workloads in thermally constrained chassis.

The production status for both parts is Active, meaning both remain available in the current market. The launch date difference shows Intel shipped first, with AMD following roughly 14 months later. Neither part has a listed launch MSRP, so no cost comparison is possible from the database.