Intel UHD Graphics P750 vs NVIDIA GeForce GTX 460 SE Comparison

Intel UHD Graphics P750 and NVIDIA GeForce GTX 460 SE are both end-of-life graphics solutions, but they represent fundamentally different design philosophies and eras. The Intel part is an integrated graphics processor (IGP) built into a Rocket Lake CPU, while the NVIDIA card is a discrete, dual-slot add-in board from the Fermi generation. Benchmark data from Geekbench OpenCL shows the Intel UHD Graphics P750 achieving a score of 6554, placing it at the 38th percentile of all GPUs, while the NVIDIA GeForce GTX 460 SE scores 6389, at the 37th percentile. This places the two within 2.6% of each other, with the Intel IGP taking a narrow lead in the single available benchmark, yet their architectural and physical characteristics could not be more different.

Where Each One Wins

The Intel UHD Graphics P750 wins the only head-to-head benchmark available. In the Geekbench OpenCL test, it scores 6554 against the GTX 460 SE's 6389, a delta of 2.6%. This performance edge is notable given that the Intel part is an integrated solution sharing system memory, whereas the GTX 460 SE has dedicated GDDR5. The Intel part's victory is marginal but consistent with its nearest rival positioning: it sits 0.4% behind the AMD Radeon HD 7730M and 0.9% ahead of the NVIDIA GeForce GT 555M, indicating it is competitive within a narrow performance band of older mobile and entry-level discrete parts.

The NVIDIA GeForce GTX 460 SE, despite losing the benchmark, wins in the context of its own competitive set. Its score of 6389 is identical to the NVIDIA GeForce GTX 580M (deltaPct 0) and only 0.3% behind the NVIDIA RTX PRO 5000 72 GB Blackwell, showing that its raw compute output remains relevant against a much newer professional card. It also outperforms the AMD Radeon Pro WX 4100 by 0.9% and the AMD Radeon R7 M350 by 1.0%. In terms of use-case, the GTX 460 SE's dedicated 1024 MB frame buffer and 108.8 GB/s bandwidth make it suited for traditional rasterized gaming at its launch resolution, while the Intel P750's system-shared memory and IGP nature make it better for basic desktop acceleration and lightweight compute workloads where its higher FP32 and texture rates can be leveraged without dedicated VRAM constraints.

Architecture Differences

The two GPUs are built on vastly different processes and architectures. The Intel UHD Graphics P750 uses Intel's Generation 12.1 architecture, fabricated on a 14 nm+++ process at Intel's own foundry. It is part of the Rocket Lake generation, specifically the HD Graphics-W (Rocket Lake) family. In contrast, the NVIDIA GeForce GTX 460 SE uses the Fermi architecture, built on a 40 nm process at TSMC, and belongs to the GeForce 400 generation with the GF104 chip.

Transistor counts and die sizes highlight the discrete versus integrated divide. The GTX 460 SE contains 1,950 million transistors on a 332 mm² die, yielding a transistor density of 5.9M per mm². The Intel P750's transistor count and die size are not specified, but its integrated nature means it shares the CPU die. The GTX 460 SE has a memory bus of 256 bit and dedicated GDDR5, while the Intel part relies on system-shared memory with a system-dependent bandwidth. The NVIDIA card's memory clock is 850 MHz (3.4 Gbps effective), while the Intel part's memory speed is listed as "System Shared."

Compute resources differ significantly in configuration. The Intel P750 has 256 shading units, 64 TMUs, and 32 ROPs. The GTX 460 SE has 288 shading units, 48 TMUs, and 32 ROPs. This means the Intel part has more texture units but fewer shaders. Clock speeds also diverge: the Intel IGP has a base clock of 350 MHz and a boost clock of 1300 MHz, while the GTX 460 SE does not have base or boost clocks listed in the data, only its memory clock. Power consumption is drastically different, with the Intel part rated at 15 W TDP versus the GTX 460 SE's 150 W TDP.

FAQ

Q: Which GPU has a higher raw compute throughput?

A: The NVIDIA GeForce GTX 460 SE has a higher FP32 performance at 748.8 GFLOPS compared to the Intel UHD Graphics P750's 665.6 GFLOPS. However, the Intel part has a much higher pixel rate (41.60 GPixel/s vs 7.800 GPixel/s) and texture rate (83.20 GTexel/s vs 31.20 GTexel/s).

Q: How do their benchmark scores compare?

A: In the Geekbench OpenCL test, the Intel UHD Graphics P750 scores 6554, which is 2.6% higher than the NVIDIA GeForce GTX 460 SE's 6389. The Intel part also has a higher percentile rank at 38 versus 37 for the NVIDIA card.

Q: What are the memory configurations?

A: The NVIDIA GeForce GTX 460 SE has 1024 MB of dedicated GDDR5 memory on a 256-bit bus with 108.8 GB/s bandwidth. The Intel UHD Graphics P750 uses system-shared memory with a system-dependent bandwidth, meaning its performance is tied to the host system's RAM.

Q: Which GPU requires more power and physical space?

A: The NVIDIA GeForce GTX 460 SE has a 150 W TDP and is a dual-slot card with two 6-pin power connectors and a 210 mm length. The Intel UHD Graphics P750 is an IGP with a 15 W TDP and no slot width, as it is integrated into the motherboard.

Q: Are these GPUs still in production?

A: No, both are end-of-life products. The NVIDIA GeForce GTX 460 SE was released on November 14, 2010, with a launch MSRP of 160 USD. The Intel UHD Graphics P750 has no release date or MSRP listed.

Q: What API support does each offer?

A: Both support DirectX 12 and OpenGL 4.6. The Intel UHD Graphics P750 supports Vulkan 1.4, while the NVIDIA GeForce GTX 460 SE does not list Vulkan support. The Intel part's DirectX support is 12 (12_1), while the NVIDIA card's is 12 (11_0).

Specification Differences

| Specification | Intel UHD Graphics P750 | NVIDIA GeForce GTX 460 SE |

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

| Architecture | Generation 12.1 | Fermi |

| Process Node | 14 nm+++ | 40 nm |

| Foundry | Intel | TSMC |

| Transistors | Not specified | 1,950 million |

| Die Size | Not specified | 332 mm² |

| Transistor Density | Not specified | 5.9M / mm² |

| Shading Units | 256 | 288 |

| TMUs | 64 | 48 |

| ROPs | 32 | 32 |

| Base Clock | 350 MHz | Not specified |

| Boost Clock | 1300 MHz | Not specified |

| Memory Size | System Shared | 1024 MB |

| Memory Type | System Shared | GDDR5 |

| Memory Bus Width | System Shared | 256 bit |

| Memory Bandwidth | System Dependent | 108.8 GB/s |

| FP32 Performance | 665.6 GFLOPS | 748.8 GFLOPS |

| FP16 Performance | 1,331.2 GFLOPS (2:1) | Not specified |

| Pixel Rate | 41.60 GPixel/s | 7.800 GPixel/s |

| Texture Rate | 83.20 GTexel/s | 31.20 GTexel/s |

| TDP | 15 W | 150 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | Not specified | 2x 6-pin |

| Suggested PSU | Not specified | 450 W |

| Bus Interface | Ring Bus | PCIe 2.0 x16 |

| Display Outputs | Motherboard Dependent | 2x DVI, 1x mini-HDMI 1.3a |

| Vulkan Support | 1.4 | Not specified |

| DirectX Support | 12 (12_1) | 12 (11_0) |

| Release Date | Not specified | 2010-11-14 |

| Launch MSRP | Not specified | 160 USD |

Head-to-Head Benchmarks

The only head-to-head benchmark available is Geekbench OpenCL, and the Intel UHD Graphics P750 takes the win. The Intel part scores 6554 against the NVIDIA GeForce GTX 460 SE's 6389, a delta of 2.6%. This is a narrow victory, and it is worth examining what drives it. The Intel IGP has a significantly higher pixel rate at 41.60 GPixel/s, which is over five times the GTX 460 SE's 7.800 GPixel/s. Its texture rate of 83.20 GTexel/s is also more than double the NVIDIA card's 31.20 GTexel/s. These advantages in fill-rate-oriented workloads likely contribute to its OpenCL performance, despite having lower FP32 compute.

However, the NVIDIA GeForce GTX 460 SE counters with a higher FP32 throughput of 748.8 GFLOPS versus 665.6 GFLOPS for the Intel part. This suggests that in compute-heavy tasks that are not memory-bandwidth-limited, the NVIDIA card could potentially outperform the Intel IGP, even though the benchmark result does not reflect this. The GTX 460 SE also has a dedicated 108.8 GB/s of memory bandwidth, which is a substantial asset for large data sets, whereas the Intel P750's bandwidth is system-dependent and likely much lower. The Intel part's 256 shading units versus 288 for the NVIDIA card also indicates a shader-count deficit, yet its higher clocks (1300 MHz boost) and superior texture and pixel rates compensate in the measured benchmark. The Intel part also supports FP16 at 1,331.2 GFLOPS (2:1), a feature the GTX 460 SE lacks entirely, which could be leveraged in mixed-precision workloads. Overall, the data shows the Intel UHD Graphics P750 as the faster part in the tested OpenCL workload, but the NVIDIA card retains advantages in pure FP32 compute and dedicated memory bandwidth that the benchmark does not fully capture.