Intel Iris Pro Graphics P580 vs NVIDIA GeForce GTX 980 Comparison

# NVIDIA GeForce GTX 980 vs Intel Iris Pro Graphics P580

The NVIDIA GeForce GTX 980 and Intel Iris Pro Graphics P580 occupy different corners of the GPU market. The GTX 980 is a high-end, discrete desktop card built on the Maxwell 2 architecture. The Iris Pro P580 is an integrated graphics processor designed for mobile workstations, part of Intel's Skylake generation. This comparison focuses on how these two GPUs perform in benchmark tests, what separates them architecturally, and where each one has a clear edge.

Head-to-Head Benchmarks

The database contains two benchmark tests that directly compare these two GPUs. The results show a decisive advantage for the discrete NVIDIA part. In the Geekbench OpenCL test, the GTX 980 scores 34,676 points, while the Iris Pro P580 scores 9,082 points. That gives the NVIDIA part a 281.8% lead in this test. The margin is even more pronounced in the Geekbench Vulkan test, where the GTX 980 records 22,543 points versus the Intel part's 5,258 points. The delta here is 328.7%, an even larger relative gap than in the OpenCL test.

The average benchmark score across all recorded tests for the GTX 980 is 8,167, which places it in the 43rd percentile of all GPUs in the database. The Iris Pro P580, by contrast, has an average score of 7,170 and sits at the 39th percentile of all GPUs. While the average scores are relatively close, the specific compute-oriented tests show where the discrete card excels. The GTX 980 wins both head-to-head tests in the database.

Architecture Differences

The GTX 980 is built around the GM204 chip, using NVIDIA's Maxwell 2.0 architecture. It is fabricated on a 28 nm process at TSMC, with 5,200 million transistors on a 398 mm² die. That translates to a transistor density of 13.1 million per square millimeter. The Iris Pro P580 is a different design entirely: it is Intel's Generation 9.0 graphics architecture, built on a 14 nm+ process node at Intel's own fabs. Intel does not disclose a transistor count or die size for the integrated part.

The NVIDIA card has 2,048 shading units and 128 texture mapping units, along with 64 ROPs. It also carries 64 TMUs. The Intel processor, by comparison, has 576 shading units, 72 texture mapping units, and only 9 ROPs. The raw shader throughput of the GTX 980 is 4.981 TFLOPS for FP32, while the Iris Pro is rated at 1,152.0 GFLOPS. Another notable difference: the GTX 980 has a dedicated 4 GB GDDR5 memory on a 256-bit bus, with 224.4 GB/s of bandwidth. The Iris Pro has no local VRAM; it uses the system shared memory, with system-dependent bandwidth.

FAQ

Q: How much faster is the GTX 980 in the Geekbench Vulkan test?

A: The GTX 980 scores 22,543 points in Geekbench Vulkan, which is 328.7% higher than the Iris Pro P580's 5,258 points.

Q: Which GPU is more power efficient?

A: The GTX 980 is a dual-slot card with a 165 W TDP, while the Iris Pro P580 is an integrated GPU with a 15 W TDP. The discrete card requires two 6-pin power connectors and a 450 W power supply.

Q: What is the pixel throughput of each GPU?

A: The GTX 980 is rated for 77.82 GPixel/s, while the Iris Pro P580 is rated for 9.000 GPixel/s. The texture fill rate is 155.6 GTexel/s for the NVIDIA versus 72.00 GTexel/s for the Intel part.

Q: Which GPU supports Vulkan?

A: Both parts support Vulkan: the GTX 980 supports version 1.4 and the Iris Pro P580 supports version 1.3.

Specification Differences

The two GPUs differ in nearly every physical and electrical specification, reflecting their very different roles.

| Field | NVIDIA GeForce GTX 980 | Intel Iris Pro P580 |

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

| Chip | GM204 | Skylake GT4e |

| Architecture | Maxwell 2.0 | Generation 9.0 |

| Process | 28 nm | 14 nm+ |

| Transistors | 5,200 million | Not published |

| Die size | 398 mm² | Not published |

| Transistor density | 13.1M / mm² | Not published |

| Base clock | 1127 MHz | 350 MHz |

| Boost clock | 1216 MHz | 1000 MHz |

| Memory | 4 GB GDDR5 | System Shared |

| Memory bus | 256-bit | System Shared |

| Memory bandwidth | 224.4 GB/s | System Dependent |

| Shading units | 2048 | 576 |

| TMUs | 128 | 72 |

| ROPs | 64 | 9 |

| Pixel rate | 77.78 GPixel/s | 9.000 GPixel/s |

| Texture rate | 155.6 GTexel/s | 72.00 GTexel/s |

| FP32 | 4.981 TFLOPS | 1,152.0 GFLOPS |

| DirectX | 12 (12_1) | 12 (12_1) |

| OpenGL | 4.6 | 4.6 |

| PCIe | PCIe 3.0 x16 | Ring Bus |

| Outputs | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 | Motherboard Dependent |

Where Each One Wins

The GTX 980 is the clear performance champion in the database's head-to-head results. It wins all recorded comparisons, with a 281.8% lead in Geekbench OpenCL and a 328.7% lead in Geekbench Vulkan. It is the GPU of choice for anyone who needs maximum compute performance in a desktop, where the benchmark data shows it is a high-end product for its class.

The Intel Iris Pro P580 is a power-sipping integrated solution. It does not have an end-of-life status, but the GTX 980 was marked "End-of-life" by NVIDIA and was produced in the GeForce 900 series. The P580's strength lies in its low 15 W TDP and no extra power connectors, making it easy to integrate into a laptop or compact system. That integration comes at a cost: its 576 shading units and 9 ROPs are a fraction of the GTX 980's 2048/64 ROP, and the shared memory interface with system bandwidth is not comparable to the dedicated 256-bit GDDR5 of the GeForce part. For a user who wants the highest available discrete GPU performance, the data shows the GTX 980 as the better option; for a system that needs a simple integrated GPU, the Iris Pro P580 is the right choice.