AMD Radeon 840M vs Intel UHD Graphics 770 Mobile Comparison

FAQ

Q: What are the key performance differences between the AMD Radeon 840M and the Intel UHD Graphics 770 Mobile?

A: The AMD Radeon 840M delivers significantly higher throughput across all measured metrics. Its pixel rate is 23.20 GPixel/s versus 12.80 GPixel/s for the Intel part, a 81.25% advantage. Texture rate stands at 46.40 GTexel/s versus 25.60 GTexel/s, an 81.25% difference. FP32 compute reaches 1,484.8 GFLOPS versus 819.2 GFLOPS, which is 81.25% higher.

Q: How do the clock speeds compare between these two integrated GPUs?

A: The AMD Radeon 840M has a base clock of 400 MHz and a boost clock of 2900 MHz. The Intel UHD Graphics 770 Mobile operates at a 300 MHz base clock and a 1600 MHz boost clock. The AMD part boosts to 81.25% higher frequency.

Q: Do both GPUs support the same DirectX feature levels?

A: No. The AMD Radeon 840M supports DirectX 12 Ultimate (12_2), while the Intel UHD Graphics 770 Mobile supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

Q: What are the differences in ray tracing support?

A: The AMD Radeon 840M includes 4 dedicated ray tracing cores. The Intel UHD Graphics 770 Mobile does not list any ray tracing cores in the database.

Q: Which process node is used for each GPU?

A: The AMD Radeon 840M is fabricated on a 4 nm process by TSMC. The Intel UHD Graphics 770 Mobile uses a 10 nm process from Intel's own foundry.

Q: What is the power consumption specification for both parts?

A: Both integrated GPUs have a TDP of 15 W. They are both classified as IGP (integrated graphics processor) with no dedicated power connectors.

The Verdict

The recorded data indicates a clear performance hierarchy between these two integrated graphics solutions. The AMD Radeon 840M, built on RDNA 3.5 architecture, holds a substantial lead in raw throughput metrics. Its FP32 compute performance of 1,484.8 GFLOPS versus 819.2 GFLOPS on the Intel part means the AMD solution is positioned for noticeably higher frame rates in GPU-bound workloads. The pixel rate difference alone, 23.20 GPixel/s versus 12.80 GPixel/s, suggests the Radeon 840M can sustain higher fill rates in resolution-limited scenarios.

For users working with applications that leverage DirectX 12 Ultimate features, including ray tracing, the AMD Radeon 840M is the only option of the two with dedicated ray tracing hardware. The Intel UHD Graphics 770 Mobile lacks ray tracing cores entirely, so any workload requiring hardware-accelerated ray tracing will only run on the AMD part.

The Intel UHD Graphics 770 Mobile, based on Generation 12.2 architecture and Raptor Lake chip, serves a different role. It provides baseline integrated graphics for systems where light 2D workloads, video playback, and basic productivity tasks are the primary demands. Its lower boost clock of 1600 MHz and reduced texture rate of 25.60 GTexel/s are sufficient for those use cases but leave little headroom for demanding 3D applications.

The Radeon 840M's release date of 2025-02-28 places it as a newer design compared to the Intel part's 2023-01-03 introduction. The AMD part also belongs to the Navi III IGP generation and uses the Krackan Point chip, indicating a more recent architectural implementation. The Intel part has a successor listed as Arc Graphics-M, while the Radeon 840M has no successor recorded.

The data supports this guidance: systems equipped with the AMD Radeon 840M should handle modern gaming and GPU-accelerated creative workloads at playable settings, while the Intel UHD Graphics 770 Mobile is best suited for office productivity, web browsing, and media consumption. Both parts carry the same 15 W TDP and share the same 256 shading units, 16 TMUs, and 8 ROPs, but the AMD part's higher clocks and newer architecture yield consistently higher throughput.

Head-to-Head Benchmarks

The database records no direct head-to-head benchmark scores for these two GPUs, and neither part has individual benchmark entries or an average benchmark score. The comparison therefore relies on the theoretical peak rates derived from each part's specification sheet. These peak rates are consistent and show a uniform advantage for the AMD Radeon 840M across all measured domains.

The FP32 compute performance gap is the most telling metric. The Radeon 840M delivers 1,484.8 GFLOPS, which is 665.6 GFLOPS higher than the Intel's 819.2 GFLOPS. In percentage terms, the AMD part is 81.25% faster. This advantage translates directly to shader-heavy workloads such as modern game rendering, physics simulations, and compute shaders.

FP16 performance shows an interesting divergence in implementation. The AMD Radeon 840M achieves 1,484.8 GFLOPS with a 1:1 ratio to FP32, meaning it does not double throughput for half-precision operations. The Intel UHD Graphics 770 Mobile achieves 1.638 TFLOPS with a 2:1 ratio, meaning its FP16 throughput is twice its FP32 rate. In raw FP16 terms, the Intel part's 1,638 GFLOPS is higher than the AMD part's 1,484.8 GFLOPS, a 10.32% advantage for Intel. However, this only matters for workloads that specifically use FP16 arithmetic with the 2:1 execution path.

The pixel rate comparison shows the Radeon 840M at 23.20 GPixel/s versus 12.80 GPixel/s for the Intel part. This 10.40 GPixel/s difference represents an 81.25% lead for AMD. Higher pixel rates allow faster rasterization of geometry into framebuffer memory, which directly benefits resolution scaling and multi-sample anti-aliasing.

Texture rate follows the same pattern: 46.40 GTexel/s for AMD versus 25.60 GTexel/s for Intel. The 20.80 GTexel/s gap means the Radeon 840M can sample and filter textures substantially faster, reducing bottlenecks in texture-heavy scenes.

Clock speed analysis confirms the architectural efficiency advantage. The AMD part boosts to 2900 MHz, which is 1300 MHz higher than the Intel's 1600 MHz boost. Even though both parts share identical shader, TMU, and ROP counts, the Radeon 840M's higher operating frequency directly drives its higher throughput. The base clocks also differ, with AMD at 400 MHz and Intel at 300 MHz.

The memory interface for both parts is System Shared with System Dependent bandwidth, meaning actual memory performance depends on the host system's RAM configuration rather than the GPU itself. Neither part has a dedicated VRAM bus width or fixed bandwidth figure.

The Radeon 840M uses a PCIe 4.0 x8 bus interface, while the Intel UHD Graphics 770 Mobile uses a Ring Bus interface. For an integrated GPU, this difference affects how quickly the GPU can access system memory, though the practical impact depends on the specific platform implementation.

Specification Differences

The two GPUs differ in several recorded specification fields. The AMD Radeon 840M uses the Krackan Point chip, while the Intel UHD Graphics 770 Mobile uses the Raptor Lake chip. Their architectures diverge completely: RDNA 3.5 for AMD versus Generation 12.2 for Intel. The AMD part belongs to the Navi III IGP generation with the Strix Point Mobile designation, while the Intel part is in the HD Graphics-M generation with a Raptor Lake designation.

Process technology differs significantly. The AMD GPU is fabricated on a 4 nm node at TSMC, while the Intel GPU uses a 10 nm node at Intel's foundry. This process difference contributes to the clock speed gap, as the smaller node enables higher frequencies at the same 15 W TDP.

Clock specifications differ in both base and boost. AMD lists 400 MHz base and 2900 MHz boost. Intel lists 300 MHz base and 1600 MHz boost. The boost delta of 1300 MHz is the single largest clock difference between the two parts.

Ray tracing support is exclusive to the AMD part, which includes 4 RT cores. The Intel GPU records no RT cores. This is a categorical feature difference, not a numerical one.

DirectX support differs by one feature level. The AMD part supports 12 Ultimate (12_2), which includes features like DXR ray tracing and variable rate shading. The Intel part supports DirectX 12 (12_1), which lacks some of the newer feature set.

Bus interface differs: PCIe 4.0 x8 for AMD versus Ring Bus for Intel. The power connector field lists "None" for AMD and is null for Intel, but both are IGP parts with no external power requirement.

Release dates differ by roughly two years. The AMD Radeon 840M launched on 2025-02-28, while the Intel UHD Graphics 770 Mobile launched on 2023-01-03. The Intel part has a recorded successor, Arc Graphics-M, while the AMD part has no successor listed.

The AMD part's predecessor is listed as Navi II IGP, while the Intel part has no predecessor recorded. Both parts are listed as Active in production status.

FP16 execution differs in ratio. AMD uses a 1:1 ratio, meaning FP16 and FP32 throughput are identical at 1,484.8 GFLOPS. Intel uses a 2:1 ratio, allowing 1.638 TFLOPS for FP16 versus 819.2 GFLOPS for FP32.

Architecture Differences

The architectural divide between these two integrated GPUs is substantial. The AMD Radeon 840M uses RDNA 3.5, a recent iteration of AMD's graphics architecture designed for efficiency and moderate performance in integrated settings. The Intel UHD Graphics 770 Mobile uses Generation 12.2, which corresponds to Intel's Xe-LP architecture used in Raptor Lake processors.

The manufacturing process separates the two designs at a fundamental level. The AMD part uses a 4 nm TSMC process, while the Intel part uses a 10 nm Intel process. This process advantage allows the AMD design to operate at a 2900 MHz boost clock while maintaining the same 15 W TDP as the Intel part's 1600 MHz boost.

Both parts share the same execution resource counts: 256 shading units, 16 texture mapping units, and 8 render output units. The performance difference therefore comes from clock speed and architectural efficiency rather than raw resource counts.

The AMD architecture includes 4 ray tracing cores, providing hardware acceleration for ray-traced effects. The Intel architecture has no ray tracing cores recorded. This means any ray-traced workload, whether in games or rendering applications, will only run on the AMD part with hardware support.

FP16 execution differs in design philosophy. The AMD Radeon 840M executes FP16 at the same rate as FP32, using a 1:1 ratio. This means there is no throughput benefit for half-precision workloads. The Intel part uses a 2:1 ratio, doubling its FP16 throughput to 1.638 TFLOPS. Applications that rely heavily on FP16 arithmetic, such as certain machine learning inference tasks, may see better performance on the Intel part despite its lower overall compute capability.

The chip designs reflect different platform integration strategies. The AMD part uses the Krackan Point chip, which pairs the GPU with AMD's CPU cores in a chiplet or monolithic design depending on the specific product. The Intel part uses Raptor Lake, which integrates the GPU on the same die as Intel's hybrid CPU cores.

Bus interface differences indicate different memory access paths. The AMD Radeon 840M connects via PCIe 4.0 x8, which provides a dedicated point-to-point link to the system. The Intel UHD Graphics 770 Mobile uses a Ring Bus, which connects the GPU to the CPU and memory controller through a shared on-die interconnect. In practice, the Ring Bus approach can offer lower latency for small transfers, while the PCIe approach can sustain higher bandwidth for large transfers, though both ultimately depend on system memory configuration.

The DirectX feature level difference reflects architectural capabilities. DirectX 12 Ultimate support on the AMD part includes features like mesh shaders, sampler feedback, and hardware ray tracing. DirectX 12_1 support on the Intel part includes the baseline DirectX 12 features but omits some of the newer additions.

The Radeon 840M's RDNA 3.5 architecture represents a more recent design point, with its 2025 release date reflecting a newer development cycle. The Intel Generation 12.2 architecture dates to the 2023 release of Raptor Lake and has already been succeeded by Arc Graphics-M per the database. This generational gap explains why the AMD part achieves higher throughput despite identical execution resource counts.