AMD Instinct MI350P vs Intel UHD Graphics 770 Mobile Comparison

Head-to-Head Benchmarks

The database contains no recorded head-to-head benchmark comparisons between the AMD Instinct MI350P and the Intel UHD Graphics 770 Mobile. Both products have an average benchmark score of 0 and a percentile ranking of 50 against all GPUs, meaning neither has accumulated any measurable performance data in the database. The wins counter shows 0 for each side, confirming that no direct benchmark events have been logged for this pairing.

This absence of data is itself informative. The two devices occupy entirely separate segments of the hardware spectrum, and the benchmark suite has not produced cross-comparisons between them. The AMD Instinct MI350P delivers 36.04 TFLOPS of FP32 compute and 36.04 TFLOPS of FP16 compute (1:1 ratio), while the Intel UHD Graphics 770 Mobile delivers 819.2 GFLOPS of FP32 and 1.638 TFLOPS of FP16 (2:1 ratio). These figures represent a 44-fold difference in FP32 throughput and a 22-fold difference in FP16 throughput, yet no benchmark results exist to translate these theoretical peaks into practical scores.

The texture rate differential is similarly stark: the MI350P reaches 1,126.4 GTexel/s, while the Intel part reaches 25.60 GTexel/s. Pixel rates show 0 MPixel/s for the AMD accelerator, as it has no ROPs (0), whereas the Intel GPU produces 12.80 GPixel/s from its 8 ROPs. The absence of benchmark data means these architectural specifications remain the only quantitative basis for comparison.

Where Each One Wins

Without benchmark scores, the win analysis must derive exclusively from the specification sheet. The AMD Instinct MI350P wins decisively in raw compute throughput. Its 8,192 shading units operate at a boost clock of 2200 MHz, producing 36.04 TFLOPS FP32. The Intel UHD Graphics 770 Mobile fields 256 shading units at a 1600 MHz boost, yielding 819.2 GFLOPS FP32. This 44x gap in shading capacity translates directly to workloads that scale with parallel shader execution, such as dense matrix operations and large-scale simulation.

Memory capacity and bandwidth favor the AMD part overwhelmingly. The MI350P carries 144 GB of HBM3e across an 8192-bit bus, achieving 8.19 TB/s of bandwidth. The Intel GPU uses System Shared memory with System Dependent bandwidth, which means its effective throughput varies with the host platform's memory configuration. No fixed bandwidth figure exists for the Intel part, making direct comparison impossible, but the recorded 8.19 TB/s for AMD stands as a fixed reference point.

The Intel UHD Graphics 770 Mobile wins in areas the AMD part does not address. It provides display outputs (Portable Device Dependent), while the MI350P has no outputs. The Intel GPU supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, whereas the AMD accelerator lists N/A for all three APIs. The Intel part also draws 15 W TDP, compared to 600 W for the AMD accelerator, and requires no auxiliary power connectors, while the MI350P needs a single 16-pin connector and a 1000 W suggested PSU. The Intel device is an integrated graphics processor (IGP) with a Ring Bus interface, designed for mobile systems, while the AMD part is a dual-slot PCIe 5.0 x16 accelerator card.

Pixel throughput is another Intel advantage: 12.80 GPixel/s versus 0 MPixel/s, because the MI350P's ROP count is zero. The AMD architecture routes its output through other mechanisms, but the recorded data shows no pixel rate.

Architecture Differences

The manufacturing processes diverge sharply. The AMD Instinct MI350P uses a 3 nm node at TSMC, housing 73,000 million transistors on a 1190 mm² die, yielding a transistor density of 61.3M per mm². The Intel UHD Graphics 770 Mobile uses a 10 nm process at Intel, with no transistor count, die size, or density recorded in the database. The MI350P's architecture is CDNA 4.0, generation Instinct (MIx), built on the MI350 128CU chip. The Intel part uses Generation 12.2 architecture on the Raptor Lake chip, generation HD Graphics-M (Raptor Lake).

Clock behavior differs fundamentally. The MI350P has a 1000 MHz base clock and 2200 MHz boost clock, with memory clocked at 2000 MHz (8 Gbps effective). The Intel GPU runs at 300 MHz base and 1600 MHz boost, with memory clock listed as System Shared. The AMD part's memory subsystem is discrete and fixed: 144 GB HBM3e, 8192-bit bus, 8.19 TB/s bandwidth. The Intel part's memory is fully shared with the host system, with no dedicated VRAM, bus width, or bandwidth figures.

Shader organization shows a 32x difference in shading units (8192 vs 256) and a 32x difference in TMUs (512 vs 16). The ROP count is 0 for AMD and 8 for Intel. The MI350P has no ray tracing cores and no tensor cores recorded, and the Intel part likewise shows null for both. The AMD accelerator's FP16 operates at 1:1 ratio with FP32, meaning both hit 36.04 TFLOPS. The Intel GPU's FP16 runs at 2:1 ratio, delivering 1.638 TFLOPS versus 819.2 GFLOPS FP32, indicating half-rate FP16 execution.

The MI350P is physically configured as a dual-slot card measuring 267 mm in length, 111 mm in height, and 40 mm in width. The Intel part is an IGP with no physical dimensions recorded, as it integrates into the mobile processor package. The AMD card uses one 16-pin power connector and suggests a 1000 W PSU. The Intel IGP has no power connectors and no PSU recommendation. The bus interface is PCIe 5.0 x16 for AMD and Ring Bus for Intel.

Release timing differs by roughly three years. The Intel UHD Graphics 770 Mobile was released on 2023-01-03, while the AMD Instinct MI350P has a release date of 2026-05-06. The Intel part's production status is Active, and its successor is listed as Arc Graphics-M. The AMD part has no production status recorded, and its predecessor is Radeon Instinct.

The Verdict

The recorded data indicates these two products serve mutually exclusive purposes. The AMD Instinct MI350P is a dedicated accelerator with 144 GB of HBM3e, 8.19 TB/s bandwidth, and 36.04 TFLOPS FP32, designed for compute workloads that require massive memory capacity and sustained throughput. Its 600 W TDP, dual-slot form factor, and absence of display outputs confirm it is not intended for any graphics output task. The Intel UHD Graphics 770 Mobile is an integrated GPU with 256 shading units, 819.2 GFLOPS FP32, and system-dependent memory, built for basic display output and light graphics work within a 15 W power envelope.

For users who need raw compute and large memory pools, the MI350P is the only viable option among these two. For systems requiring integrated graphics with API support (DirectX 12_1, OpenGL 4.6, Vulkan 1.4) and display connectivity, the Intel part is the functional choice. The MI350P cannot output video, and the Intel part cannot approach the compute density of the AMD accelerator. The 44x FP32 gap and the 144 GB versus System Shared memory difference define the boundary. No benchmark scores exist to challenge these specification-based conclusions.

The percentile ranking of 50 for both devices reflects the absence of benchmark data rather than parity in performance. The database records no wins for either product, which means any claim of superiority must rest entirely on the architectural specifications. Those specifications point to the AMD part for compute-centric deployments and the Intel part for integrated graphics duties.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The AMD Instinct MI350P delivers 36.04 TFLOPS FP32, compared to 819.2 GFLOPS for the Intel UHD Graphics 770 Mobile, a 44-fold difference.

Q: Does the AMD Instinct MI350P support display outputs?

A: No. The MI350P lists "No outputs" for display outputs, while the Intel UHD Graphics 770 Mobile provides Portable Device Dependent display outputs.

Q: What memory configurations do these two GPUs use?

A: The MI350P uses 144 GB of HBM3e with an 8192-bit bus and 8.19 TB/s bandwidth. The Intel GPU uses System Shared memory with System Dependent bandwidth.

Q: Which API set does each GPU support?

A: The Intel UHD Graphics 770 Mobile supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The AMD Instinct MI350P lists N/A for DirectX, OpenGL, and Vulkan.

Q: What are the power requirements for each?

A: The MI350P has a 600 W TDP, uses one 16-pin power connector, and suggests a 1000 W PSU. The Intel UHD Graphics 770 Mobile has a 15 W TDP and no power connectors.

Q: When was each product released?

A: The Intel UHD Graphics 770 Mobile was released on 2023-01-03. The AMD Instinct MI350P has a release date of 2026-05-06.

Specification Differences

| Field | AMD Instinct MI350P | Intel UHD Graphics 770 Mobile |

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

| Process Node | 3 nm | 10 nm |

| Foundry | TSMC | Intel |

| Transistors | 73,000 million | Not recorded |

| Die Size | 1190 mm² | Not recorded |

| Transistor Density | 61.3M / mm² | Not recorded |

| Base Clock | 1000 MHz | 300 MHz |

| Boost Clock | 2200 MHz | 1600 MHz |

| Memory Clock | 2000 MHz 8 Gbps effective | System Shared |

| Memory Size | 144 GB | System Shared |

| Memory Type | HBM3e | System Shared |

| Memory Bus Width | 8192 bit | System Shared |

| Memory Bandwidth | 8.19 TB/s | System Dependent |

| Shading Units | 8192 | 256 |

| TMUs | 512 | 16 |

| ROPs | 0 | 8 |

| Pixel Rate | 0 MPixel/s | 12.80 GPixel/s |

| Texture Rate | 1,126.4 GTexel/s | 25.60 GTexel/s |

| FP32 | 36.04 TFLOPS | 819.2 GFLOPS |

| FP16 | 36.04 TFLOPS (1:1) | 1.638 TFLOPS (2:1) |

| TDP | 600 W | 15 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 16-pin | None |

| Suggested PSU | 1000 W | None |

| Bus Interface | PCIe 5.0 x16 | Ring Bus |

| Display Outputs | No outputs | Portable Device Dependent |

| DirectX Support | N/A | 12 (12_1) |

| OpenGL Support | N/A | 4.6 |

| Vulkan Support | N/A | 1.4 |

| Length | 267 mm 10.5 inches | Not recorded |

| Height | 111 mm 4.4 inches | Not recorded |

| Width | 40 mm 1.6 inches | Not recorded |

| Production Status | Not recorded | Active |

| Release Date | 2026-05-06 | 2023-01-03 |

| Predecessor | Radeon Instinct | None |

| Successor | None | Arc Graphics-M |