GPU Comparison

The data presents a clear matchup between two very different GPUs: the NVIDIA GeForce RTX 2060, a dedicated desktop card from the GeForce 20-series, and the Intel Iris Xe MAX Graphics, an integrated processor from Intel's Xe Graphics generation. The benchmark results, while limited, point to an overwhelming performance advantage for the NVIDIA part, but the story is more nuanced when considering the architecture, target use case, and the specific data available in the the benchmark database.

FAQ

Q: How much faster is the NVIDIA GeForce RTX 2060 in the only shared benchmark?

A: In the Geekbench OpenCL test, the RTX 2060 scored 65,014 points, while the Intel Iris Xe MAX scored 14,315 points. This results in a delta of 354.2%, meaning the NVIDIA GPU is roughly 4.5 times faster in this specific test.

Q: What is the average benchmark score for each GPU, and how do they rank?

A: The RTX 2060 has an average benchmark score of 15,290, placing it in the 58th percentile of all GPUs. The Intel Iris Xe MAX has an average score of 14,315, placing it in the 56th percentile. Despite the massive single-test delta, their overall percentile rankings are surprisingly close.

Q: Who are the closest rivals for each GPU based on average score?

A: For the RTX 2060, the nearest rival is the NVIDIA GeForce GTX 580, which has an average score of 15,283, a 0% delta. The Intel Iris Xe MAX is most closely matched by the AMD Radeon Vega 11, which scores 14,352, a -0.3% delta, and the NVIDIA GeForce GTX 1070 Ti, which scores 14,277, a 0.3% delta.

Q: What are the key architectural differences in the compute units?

A: The RTX 2060 is built on a 12 nm process and features 1,920 shading units, 120 TMUs, and 48 ROPs. The Intel Iris Xe MAX is built on a 10 nm process and has 768 shading units, 48 TMUs, and 24 ROPs. The NVIDIA GPU also has dedicated RT and Tensor cores, while the Intel part has none.

Q: How do their memory subsystems compare?

A: The RTX 2060 uses 6 GB of GDDR6 memory on a 192-bit bus, providing a bandwidth of 336.0 GB/s. The Intel Iris Xe MAX uses 4 GB of LPDDR4X memory on a 128-bit bus, with a significantly lower bandwidth of 68.26 GB/s.

Q: What is the difference in their power consumption and physical design?

A: The RTX 2060 has a TDP of 160 W and is a dual-slot card requiring a 1x 8-pin power connector. The Intel Iris Xe MAX has a TDP of just 25 W and is an IGP (Integrated Graphics Processor) with no dedicated power connectors or display outputs, suggesting it is designed for mobile or embedded systems.

Architecture Differences

The fundamental difference between these two GPUs lies in their design goals and underlying architectures. The NVIDIA GeForce RTX 2060 is built on the Turing architecture, a high-performance design for dedicated graphics cards. It is manufactured on a 12 nm process at TSMC and has a substantial die size of 445 mm², housing 10,800 million transistors. This large, complex die is packed with 1,920 shading units, 120 texture mapping units, and 48 raster output units.

Crucially, the Turing architecture in the RTX 2060 includes dedicated hardware for ray tracing (30 RT cores) and AI acceleration (240 Tensor cores). These features were a major selling point for the GeForce 20-series, enabling real-time ray-tracing effects and DLSS. The architecture also supports DirectX 12 Ultimate (12_2), a feature set that includes hardware ray tracing and variable rate shading.

In contrast, the Intel Iris Xe MAX Graphics is based on the Generation 12.1 architecture, which is Intel's Xe Graphics architecture scaled down for low-power and integrated use. It is fabricated on Intel's 10 nm process, resulting in a much smaller die size of 95 mm². This GPU is far more modest in its execution resources, with 768 shading units, 48 TMUs, and 24 ROPs. It does not feature any dedicated RT or Tensor cores, and its DirectX support is limited to 12 (12_1), which lacks the full Ultimate feature set.

The memory architecture also highlights the divergent design philosophies. The RTX 2060 leverages a wide 192-bit bus and fast GDDR6 memory to achieve a bandwidth of 336.0 GB/s, which is critical for feeding its high-performance compute units. The Iris Xe MAX uses a 128-bit bus and slower LPDDR4X memory, resulting in a bandwidth of just 68.26 GB/s. This limited bandwidth is a significant bottleneck and is likely a major contributor to its lower performance in the benchmark data. The Intel chip also operates with a base clock of 300 MHz and a boost of 1650 MHz, while the NVIDIA card has a base clock of 1365 MHz and a boost of 1680 MHz, though the larger difference is in the execution resources and memory speed.

Head-to-Head Benchmarks

The only direct benchmark comparison available is the Geekbench OpenCL test. This test is designed to measure general-purpose compute performance, and the results are stark. The NVIDIA GeForce RTX 2060 achieves a score of 65,014, while the Intel Iris Xe MAX Graphics manages only 14,315. The delta of 354.2% in favor of the NVIDIA GPU is a decisive victory.

This massive gap can be interpreted through the hardware specifications. The RTX 2060 has 2.5 times more shading units (1,920 vs 768) and a memory bandwidth that is nearly five times higher (336.0 GB/s vs 68.26 GB/s). This combination of more compute cores and far superior memory bandwidth allows the NVIDIA card to process and feed data at a rate that the Intel part cannot match. The RTX 2060's FP32 performance is rated at 6.451 TFLOPS, compared to the Intel's 2.534 TFLOPS, a difference of approximately 2.5x.

The benchmark results also paint a different picture when looking at the average scores. The RTX 2060's average score of 15,290 is its Geekbench OpenCL score, which is the only score for the Iris Xe MAX. However, the RTX 2060 has ten benchmark scores, which include older DirectX 9, 10, 11, and 12 tests. Its average score is heavily influenced by these lower scores. For instance, its Passmark DirectX 9 score is 190, and its DirectX 12 score is 53. These legacy tests bring its average down, making its overall percentile rank (58th) seemingly close to the Intel's (56th). This illustrates a critical point: the RTX 2060 is a versatile gaming and compute card, while the Intel Iris Xe MAX's single score of 14,315 in a compute test places it in a similar overall percentile, despite the huge delta in the shared test.

The Verdict

Based strictly on the data, the NVIDIA GeForce RTX 2060 is the unequivocal performance winner. In the single head-to-head benchmark, it outperforms the Intel Iris Xe MAX by a factor of over 3.5. It offers more than double the shading units, nearly five times the memory bandwidth, and a much higher texture and pixel fill rate. For any task that relies on raw compute performance, the RTX 2060 is the superior choice.

However, the data also reveals a significant caveat. The Intel Iris Xe MAX has a TDP of 25 W, a 160 mm² smaller die (95 mm² vs 445 mm²), and is an IGP. The RTX 2060, with a TDP of 160 W and a dual-slot design, is a power-hungry dedicated card. The Intel part is not designed to compete on raw performance; its design goals are efficiency and integration. The data shows it is end-of-life and has no display outputs, meaning it is likely intended for a very specific mobile or embedded role where its low power draw is a primary advantage.

The user should choose the NVIDIA GeForce RTX 2060 for any application requiring maximum graphics and compute throughput, such as gaming or content creation. The user should consider the Intel Iris Xe MAX only if the absolute lowest power consumption and a compact, integrated form factor are the primary requirements, accepting its significantly lower performance. The performance-per-watt is not directly comparable from the data, but the power consumption figures alone suggest a different class of device.

Specification Differences

The following table highlights the key specifications where the two GPUs differ, based on the the benchmark database.

| Specification | NVIDIA GeForce RTX 2060 | Intel Iris Xe MAX Graphics |

| :--- | :--- | :--- |

| Process Node | 12 nm | 10 nm |

| Die Size | 445 mm² | 95 mm² |

| Base Clock | 1365 MHz | 300 MHz |

| Boost Clock | 1680 MHz | 1650 MHz |

| Memory Size | 6 GB | 4 GB |

| Memory Type | GDDR6 | LPDDR4X |

| Memory Bus Width | 192 bit | 128 bit |

| Memory Bandwidth | 336.0 GB/s | 68.26 GB/s |

| Shading Units | 1920 | 768 |

| TMUs | 120 | 48 |

| ROPs | 48 | 24 |

| RT Cores | 30 | None |

| Tensor Cores | 240 | None |

| Pixel Rate | 80.64 GPixel/s | 39.60 GPixel/s |

| Texture Rate | 201.6 GTexel/s | 79.20 GTexel/s |

| FP32 Performance | 6.451 TFLOPS | 2.534 TFLOPS |

| TDP | 160 W | 25 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 450 W | 200 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x8 |

| Display Outputs | 1x DVI, 1x HDMI, 2x DP, 1x USB-C | No outputs |

| DirectX Support | 12 Ultimate (12_2) | 12 (12_1) |

Where Each One Wins

NVIDIA GeForce RTX 2060:

• Raw Compute Performance: Wins the only head-to-head benchmark with a 354.2% higher score in Geekbench OpenCL.
• Memory-Bound Workloads: The 336.0 GB/s bandwidth is a massive advantage over the 68.26 GB/s of the Intel part, favoring tasks like high-resolution texture streaming and large data sets.
• Feature-Rich Graphics: The presence of RT and Tensor cores, along with DirectX 12 Ultimate support, makes it the clear choice for modern gaming with advanced effects.
• Higher Throughput: Its superior texture rate (201.6 GTexel/s vs 79.20 GTexel/s) and pixel rate (80.64 GPixel/s vs 39.60 GPixel/s) indicate a strong advantage in filling and rendering scenes.

Intel Iris Xe MAX Graphics:

• Power Efficiency: With a TDP of just 25 W compared to the RTX 2060's 160 W, it wins decisively in scenarios where power draw is the primary constraint.
• Compact Integration: As an IGP with no display outputs, it is designed for ultra-thin or embedded systems where a dedicated card cannot be used.
• Modern Process Node: It is built on a smaller 10 nm process, which is a point of technological advancement over the 12 nm node of the NVIDIA chip, even if its performance is lower.
• PCIe 4.0 Support: It interfaces via PCIe 4.0 x8, which is a newer standard than the RTX 2060's PCIe 3.0 x16, though the practical benefit is limited by its lower compute power.