Intel Iris Pro Graphics P6300 vs NVIDIA GeForce GTX 760M Comparison

Intel Iris Pro Graphics P6300 vs NVIDIA GeForce GTX 760M: a comparison that pits an integrated part from Intel's Broadwell generation against a dedicated mobile GPU from NVIDIA's Kepler family. The database records one head-to-head benchmark, and the results are surprisingly close, with the integrated solution edging out the discrete card.

Head-to-Head Benchmarks

The only shared benchmark in the database is Geekbench OpenCL. Here, the Intel Iris Pro Graphics P6300 scores 5712, while the NVIDIA GeForce GTX 760M scores 5604. That gives Intel a 1.9% lead. It is a narrow margin, but it is a win, and it flips expectations about what an IGP can do against a dedicated part.

The Intel part's OpenCL score places it at the 33rd percentile among all GPUs in the database. Its nearest rivals include the NVIDIA GeForce GTX 670MX (average score 5721, a 0.1% difference), the NVIDIA GeForce GTX 550 Ti (average score 5731, a 0.3% difference), and the AMD Radeon HD 8790M (average score 5691, a 0.4% difference). The data shows the Iris Pro sitting in a tight cluster where a few points separate the competitors; its 1.9% advantage over the GTX 760M is actually larger than its gap to several other cards.

The GTX 760M's OpenCL score of 5604 contributes to an average benchmark score of 5236, which includes a Geekbench Vulkan result of 4868. That Vulkan score drags its average down, but the OpenCL result alone is competitive. The GTX 760M sits at the 31st percentile among all GPUs, just two points below the Intel part. Its nearest rivals include the NVIDIA Quadro 4000M (average score 5211, a 0.5% difference), the NVIDIA GeForce 940M (average score 5284, a 0.9% difference), and the NVIDIA GeForce GTX 980M (average score 5308, a 1.3% difference). Notably, the GTX 980M, a much higher-tier card in the same family, is only 1.3% ahead of the 760M in this aggregated metric, which suggests the 760M's score is not far off its own family's upper range.

What does this mean? In raw compute throughput as measured by OpenCL, the integrated Intel part is effectively a peer of the dedicated NVIDIA part. The delta is small enough that real-world applications could swing either way depending on drivers, thermal headroom, and system memory configuration.

Architecture Differences

The two chips come from different worlds. The Intel Iris Pro Graphics P6300 is built on Broadwell GT3e, a Generation 8.0 architecture, fabricated on a 14 nm process at Intel's own foundry. The NVIDIA GeForce GTX 760M uses the GK106S chip, a Kepler architecture, fabricated on a 28 nm process at TSMC. That process gap matters: 14 nm versus 28 nm means Intel packs transistors much denser, but the GTX 760M has a disclosed transistor count of 2,540 million on a 221 mm² die, giving a transistor density of 11.5 million per mm². Intel does not list its transistor count or die size in the database, so a direct density comparison is impossible.

The NVIDIA chip has more execution resources on paper. It packs 768 shading units, 64 texture mapping units, and 16 ROPs. The Intel part has 384 shading units, 48 TMUs, and only 6 ROPs. That is a significant gap in raw hardware, yet the OpenCL scores are nearly identical. The reason likely lies in clock speeds and memory architecture. The GTX 760M runs at a base clock of 628 MHz and a boost of 719 MHz, with memory clocked at 1002 MHz (4 Gbps effective). The Intel part has a base clock of 300 MHz and a boost of 800 MHz. Intel's boost clock is higher, but its base is less than half of NVIDIA's.

Memory is another differentiator. The GTX 760M has 2 GB of GDDR5 on a 128-bit bus, delivering 64.13 GB/s of bandwidth. The Intel Iris Pro uses System Shared memory, with bandwidth described as "System Dependent." The Intel part's memory type is also System Shared, meaning it borrows from the host system's RAM. In practice, the GTX 760M's dedicated memory should give it a bandwidth advantage, but the OpenCL result suggests the Intel part compensates with other efficiencies.

The API support also differs. Intel lists DirectX 12 (11_1), OpenGL 4.4, and Vulkan 1.0. NVIDIA lists DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. NVIDIA's OpenGL and Vulkan support are more recent, which could matter for specific applications, but the database only has a Vulkan score for the GTX 760M (4868), not for the Intel part.

Where Each One Wins

The Intel Iris Pro P6300 wins the only direct head-to-head test, the Geekbench OpenCL benchmark, by 1.9%. That is its sole recorded victory, and it is the clear takeaway for compute-oriented workloads that rely on OpenCL. The Intel part also has a higher boost clock (800 MHz versus 719 MHz), which may help in bursty, short-duration tasks. Its 14 nm process suggests better power efficiency, though the database only lists TDP: 15 W for Intel versus 55 W for NVIDIA.

The NVIDIA GeForce GTX 760M, despite losing the OpenCL test, has structural advantages. It has double the shading units (768 versus 384), more than double the ROPs (16 versus 6), and a dedicated 2 GB GDDR5 frame buffer. Its pixel rate is 11.50 GPixel/s versus Intel's 4.800 GPixel/s, and its texture rate is 46.02 GTexel/s versus Intel's 38.40 GTexel/s. For rasterization-heavy workloads, like traditional gaming with depth buffers and fill-rate limits, the GTX 760M should be stronger. The database does not include gaming benchmarks, so this is an inference from the hardware specifications, but the ROP and memory bandwidth differences are stark.

The GTX 760M also has a Vulkan score of 4868. The Intel part has no Vulkan benchmark recorded, so any application that leverages Vulkan would likely favor the NVIDIA part, given its higher API version (1.2.175 versus 1.0). The GTX 760M's OpenGL 4.6 support versus Intel's 4.4 is another point in NVIDIA's favor for compatibility with newer OpenGL titles.

Specification Differences

| Specification | Intel Iris Pro P6300 | NVIDIA GeForce GTX 760M |

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

| Chip | Broadwell GT3e | GK106S |

| Architecture | Generation 8.0 | Kepler |

| Process Node | 14 nm | 28 nm |

| Foundry | Intel | TSMC |

| Transistors | Not listed | 2,540 million |

| Die Size | Not listed | 221 mm² |

| Transistor Density | Not listed | 11.5M / mm² |

| Base Clock | 300 MHz | 628 MHz |

| Boost Clock | 800 MHz | 719 MHz |

| Memory Size | System Shared | 2 GB |

| Memory Type | System Shared | GDDR5 |

| Memory Bus Width | System Shared | 128 bit |

| Memory Bandwidth | System Dependent | 64.13 GB/s |

| Shading Units | 384 | 768 |

| TMUs | 48 | 64 |

| ROPs | 6 | 16 |

| Pixel Rate | 4.800 GPixel/s | 11.50 GPixel/s |

| Texture Rate | 38.40 GTexel/s | 46.02 GTexel/s |

| FP32 | 614.4 GFLOPS | 1,104.4 GFLOPS |

| TDP | 15 W | 55 W |

| Bus Interface | Ring Bus | PCIe 3.0 x16 |

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

| OpenGL | 4.4 | 4.6 |

| Vulkan | 1.0 | 1.2.175 |

| Release Date | 2014-09-04 | 2013-05-29 |

The FP32 numbers are telling: NVIDIA lists 1,104.4 GFLOPS, Intel lists 614.4 GFLOPS. That is a 79.8% advantage for NVIDIA in theoretical floating-point throughput, yet OpenCL scores are nearly tied. This discrepancy suggests that the GTX 760M is not reaching its theoretical peak in the benchmark, possibly due to driver overhead, power limits, or the benchmark's specific workload.

FAQ

Q: Which GPU has the higher OpenCL score?

A: The Intel Iris Pro Graphics P6300 scores 5712, while the NVIDIA GeForce GTX 760M scores 5604. Intel leads by 1.9%.

Q: Does the NVIDIA GeForce GTX 760M have more shading units?

A: Yes, the GTX 760M has 768 shading units, while the Intel Iris Pro P6300 has 384. That is exactly double.

Q: What is the memory bandwidth of the NVIDIA card?

A: The GTX 760M has 64.13 GB/s of bandwidth from its 2 GB GDDR5 memory on a 128-bit bus. The Intel part's bandwidth is listed as "System Dependent."

Q: Which GPU supports a newer Vulkan version?

A: The NVIDIA GeForce GTX 760M supports Vulkan 1.2.175, while the Intel Iris Pro P6300 supports Vulkan 1.0. NVIDIA also has a recorded Vulkan benchmark score of 4868; Intel has none.

Q: How do their power draws compare?

A: The Intel Iris Pro P6300 has a TDP of 15 W, while the NVIDIA GeForce GTX 760M has a TDP of 55 W. The Intel part draws significantly less power.

Q: What is the difference in release dates?

A: The Intel Iris Pro P6300 was released on September 4, 2014, while the NVIDIA GeForce GTX 760M was released on May 29, 2013. Intel's part is about 15 months newer.

The Verdict

The data points to a split decision. For pure OpenCL compute performance, the Intel Iris Pro P6300 is the winner, edging out the GTX 760M by 1.9% in the only shared benchmark. Its higher boost clock (800 MHz versus 719 MHz) and lower TDP (15 W versus 55 W) make it an attractive option for systems where power is a constraint. The 14 nm process and integrated design mean it can sit in a slim laptop or an all-in-one without a dedicated cooling solution.

However, the NVIDIA GeForce GTX 760M has structural advantages that the OpenCL test does not capture. Its pixel rate is 11.50 GPixel/s versus 4.800 GPixel/s, and its texture rate is 46.02 GTexel/s versus 38.40 GTexel/s. It has 16 ROPs versus 6, and 2 GB of dedicated GDDR5 memory versus system-shared memory. For gaming, particularly at higher resolutions or with anti-aliasing, the GTX 760M should pull ahead, even though the database does not include a direct gaming benchmark. Its FP32 throughput of 1,104.4 GFLOPS versus 614.4 GFLOPS also suggests headroom for compute tasks that scale beyond the OpenCL test.

A user who prioritizes battery life, low heat, and light compute workloads should favor the Intel Iris Pro P6300. A user who needs consistent rasterization performance, newer API support (OpenGL 4.6, Vulkan 1.2.175), and dedicated video memory should pick the NVIDIA GeForce GTX 760M. The OpenCL result is close enough that neither part is a clear victor across the board; the choice depends on the workload and the system's power budget.