Intel UHD Graphics P630 vs NVIDIA GeForce GTX 760M Comparison

Head-to-Head Benchmarks

The benchmark data presents a split decision between the Intel UHD Graphics P630 and the NVIDIA GeForce GTX 760M. In the Geekbench OpenCL test, the NVIDIA GeForce GTX 760M scores 5604 against the Intel UHD Graphics P630’s 5111. That is an 8.8% margin in favor of the NVIDIA part. The Geekbench Vulkan test flips the outcome: the Intel UHD Graphics P630 scores 5628, while the NVIDIA GeForce GTX 760M manages 4868. That is a 15.6% lead for the Intel integrated solution. The result is a 1–1 tie in head-to-head wins.

Looking at the OpenCL result more closely, the NVIDIA GeForce GTX 760M’s advantage is substantial but not overwhelming. The 8.8% deficit for the Intel part places it in a competitive range among its nearest rivals. The Intel UHD Graphics P630’s average benchmark score of 5370 sits just 0.2% above the AMD Radeon R7 M445 (5358) and 0.9% above the NVIDIA GeForce 840M (5322). Meanwhile, the NVIDIA GeForce GTX 760M’s average score of 5236 is 0.5% above the NVIDIA Quadro 4000M (5211) and 1.5% above the AMD Radeon R7 M260X (5161). The OpenCL result for the GTX 760M is its stronger showing, as its Vulkan score of 4868 falls below its own average.

The Vulkan result is where the Intel part distinguishes itself. The 15.6% delta is the largest margin in either direction across the two tests. The Intel UHD Graphics P630’s Vulkan score of 5628 exceeds its OpenCL score of 5111 by roughly 10%. The NVIDIA GeForce GTX 760M shows the opposite pattern, with its Vulkan score of 4868 coming in 13.1% below its OpenCL score of 5604. Benchmark results indicate that the Intel part is better optimized for the Vulkan API, while the NVIDIA part favors OpenCL workloads.

Both GPUs land at the 31st percentile among all GPUs, indicating they occupy similar tiers of overall performance. The average benchmark scores are close: 5370 for the Intel part versus 5236 for the NVIDIA part, a difference of 2.5% in favor of Intel. However, that average masks the divergent API-specific behavior. A user relying primarily on OpenCL applications would see the NVIDIA part as the clear winner, while Vulkan-centric workloads would favor the Intel solution by a wide margin.

FAQ

Q: Which GPU wins in OpenCL performance?

A: The NVIDIA GeForce GTX 760M scores 5604 in Geekbench OpenCL, beating the Intel UHD Graphics P630’s 5111 by 8.8%.

Q: Which GPU wins in Vulkan performance?

A: The Intel UHD Graphics P630 scores 5628 in Geekbench Vulkan, beating the NVIDIA GeForce GTX 760M’s 4868 by 15.6%.

Q: How do their overall average benchmark scores compare?

A: The Intel UHD Graphics P630 has an average benchmark score of 5370, while the NVIDIA GeForce GTX 760M averages 5236. That is a 2.5% advantage for the Intel part.

Q: What percentile do these GPUs occupy among all GPUs?

A: Both the Intel UHD Graphics P630 and the NVIDIA GeForce GTX 760M are at the 31st percentile among all GPUs.

Q: What are the nearest rivals for the Intel UHD Graphics P630?

A: Its nearest rivals include the AMD Radeon R7 M445 (5358, 0.2% higher), the AMD Radeon R7 M365X (5416, 0.8% lower), the NVIDIA GeForce 840M (5322, 0.9% higher), and the NVIDIA GeForce 930A (5317, 1% higher).

Q: What are the nearest rivals for the NVIDIA GeForce GTX 760M?

A: Its nearest rivals include the NVIDIA Quadro 4000M (5211, 0.5% higher), the NVIDIA GeForce 940M (5284, 0.9% lower), the NVIDIA GeForce GTX 980M (5308, 1.3% lower), and the AMD Radeon R7 M260X (5161, 1.5% higher).

Architecture Differences

The Intel UHD Graphics P630 is built on the Comet Lake GT2 chip, part of the Generation 9.5 architecture, and falls under the HD Graphics-W (Comet Lake) generation. It uses a 14 nm+++ process node from Intel. The NVIDIA GeForce GTX 760M, by contrast, uses the GK106S chip on the Kepler architecture, belonging to the GeForce 700M generation. It is fabricated on a 28 nm process at TSMC. The process node difference is significant: Intel’s 14 nm+++ is considerably more advanced than the 28 nm used for the NVIDIA part.

The Intel chip has 192 shading units, 24 texture mapping units, and 3 raster output pipelines. The NVIDIA chip is much larger in these counts: 768 shading units, 64 texture mapping units, and 16 raster output pipelines. This gives the NVIDIA part a theoretical compute advantage on paper. The Intel part’s pixel rate is 3.600 GPixel/s, and its texture rate is 28.80 GTexel/s. The NVIDIA part’s pixel rate is 11.50 GPixel/s, and its texture rate is 46.02 GTexel/s. The NVIDIA part’s FP32 throughput is 1,104.4 GFLOPS, more than double the Intel part’s 460.8 GFLOPS.

The NVIDIA GeForce GTX 760M has a die size of 221 mm² and 2,540 million transistors, with a transistor density of 11.5M / mm². The Intel part does not list transistor count or die size in the data. The NVIDIA part also reports a base clock of 628 MHz and a boost clock of 719 MHz, while the Intel part runs at a base of 350 MHz and a boost of 1200 MHz. The higher boost clock on the Intel part partially offsets its lower shading unit count in some workloads.

API support differs as well. The Intel UHD Graphics P630 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. The NVIDIA GeForce GTX 760M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The Intel part’s Vulkan version is newer, which may explain its strong Vulkan benchmark showing. The NVIDIA part’s DirectX feature level is 11_0, one step below the Intel part’s 12_1.

Specification Differences

The two GPUs differ across nearly every hardware specification. The process nodes are different: Intel uses 14 nm+++, while NVIDIA uses 28 nm. The Intel chip has 192 shading units, 24 TMUs, and 3 ROPs. The NVIDIA chip has 768 shading units, 64 TMUs, and 16 ROPs. Clock speeds differ with Intel at 350 MHz base and 1200 MHz boost, versus NVIDIA at 628 MHz base and 719 MHz boost.

Memory configurations are entirely different. The Intel UHD Graphics P630 uses system shared memory with a system dependent bandwidth. The NVIDIA GeForce GTX 760M has 2 GB of dedicated GDDR5 memory on a 128-bit bus, providing 64.13 GB/s of bandwidth. The NVIDIA memory clock is 1002 MHz with 4 Gbps effective.

The power profiles differ substantially. The Intel part has a TDP of 15 W, while the NVIDIA part has a TDP of 55 W. The Intel part is an integrated GPU (IGP) with a ring bus interface, while the NVIDIA part is an MXM module using PCIe 3.0 x16. Display outputs are motherboard dependent for the Intel part, and portable device dependent for the NVIDIA part. The NVIDIA part has no power connectors, and neither part lists a suggested PSU.

The NVIDIA GeForce GTX 760M is built on 2,540 million transistors on a 221 mm² die, with a transistor density of 11.5M / mm². These figures are not listed for the Intel part. Release dates differ as well: the Intel part was released on May 12, 2020, while the NVIDIA part was released on May 29, 2013. Both are marked as end-of-life. The NVIDIA part lists its predecessor as the GeForce 600M and its successor as the GeForce 800M; the Intel part lists neither.

Where Each One Wins

The NVIDIA GeForce GTX 760M wins in OpenCL-based workloads. Its Geekbench OpenCL score of 5604 is 8.8% higher than the Intel part’s 5111. This is consistent with its larger shading unit count and dedicated memory. Applications that rely on OpenCL compute, such as certain rendering tasks or physics simulations, would see better performance on the NVIDIA part. The NVIDIA part also has a higher pixel rate (11.50 GPixel/s versus 3.600 GPixel/s) and texture rate (46.02 GTexel/s versus 28.80 GTexel/s), indicating stronger raw throughput in fill-rate-limited scenarios.

The Intel UHD Graphics P630 wins decisively in Vulkan-based workloads. Its Geekbench Vulkan score of 5628 is 15.6% higher than the NVIDIA part’s 4868. The Intel part also has a newer Vulkan API version (1.3 versus 1.2.175) and a higher DirectX feature level (12_1 versus 11_0). This suggests the Intel architecture is better suited to modern graphics APIs. The Intel part’s higher boost clock of 1200 MHz, compared to NVIDIA’s 719 MHz, likely contributes to its Vulkan advantage.

The Intel part also wins on power efficiency. With a TDP of 15 W versus 55 W for the NVIDIA part, the Intel integrated solution consumes far less power. For systems where thermal and power budgets are tight, the Intel part is the more practical choice. The NVIDIA part’s dedicated 2 GB GDDR5 memory gives it a bandwidth advantage, but the Intel part’s system shared memory approach avoids the need for a separate memory pool.

The Verdict

The data does not declare a single overall winner. The two GPUs split their head-to-head benchmarks exactly, with one win each. The NVIDIA GeForce GTX 760M takes OpenCL with an 8.8% margin, while the Intel UHD Graphics P630 takes Vulkan with a 15.6% margin. The Intel part has the higher average benchmark score (5370 versus 5236) and the larger winning margin, but the NVIDIA part’s OpenCL strength is significant for legacy applications.

Users who prioritize OpenCL compute performance should choose the NVIDIA GeForce GTX 760M. Its 5604 OpenCL score, higher shading unit count, and dedicated GDDR5 memory make it the stronger option for that workload. Users who prioritize Vulkan performance should choose the Intel UHD Graphics P630. Its 5628 Vulkan score, newer API support, and 15.6% head-to-head lead are clear advantages.

The power envelope is another deciding factor. The Intel part’s 15 W TDP versus the NVIDIA part’s 55 W TDP means the Intel solution fits in systems where the NVIDIA part would be impractical. Both GPUs sit at the 31st percentile among all GPUs, so neither is a high-performance part. The choice comes down to API preference and system constraints. The Intel part is the more modern design with better API support and efficiency; the NVIDIA part offers dedicated memory and stronger OpenCL throughput.