AMD Radeon RX 7900 XT vs NVIDIA GeForce GTX 1080 Ti Comparison

Where Each One Wins

The benchmark split is decisively lopsided: the AMD Radeon RX 7900 XT takes 9 of the 10 head-to-head tests, while the NVIDIA GeForce GTX 1080 Ti claims only a single, albeit massive, victory. The data paints a clear picture of two very different performance profiles separated by five years of GPU architecture evolution.

The RX 7900 XT dominates across nearly every DirectX workload, 3D rendering, and compute scenario. Its wins span the full spectrum of the PassMark suite, from legacy DirectX 9 through modern DirectX 12, plus the 3DMark Steel Nomad DX12 test and the Vulkan benchmark. This is a comprehensive sweep of modern gaming and general-purpose GPU workloads.

The GTX 1080 Ti’s sole victory comes in Geekbench OpenCL, where it posts a score of 67,929 against the RX 7900 XT’s 12,756. That is a 432.5% advantage, an outlier so extreme it skews the overall average benchmark scores. This result suggests the GTX 1080 Ti has exceptionally strong OpenCL compute performance relative to its other metrics, likely due to driver optimization or workload characteristics that favor its Pascal architecture.

However, the narrative of overall average scores is counterintuitive. Despite winning 9 of 10 tests, the RX 7900 XT has a lower average benchmark score of 13,745 compared to the GTX 1080 Ti’s 15,548. This is purely a statistical artifact of the Geekbench OpenCL outlier. Remove that single test, and the RX 7900 XT’s average would be far higher across the remaining nine benchmarks. The percentile rankings reinforce this: the GTX 1080 Ti sits at the 58th percentile of all GPUs, while the RX 7900 XT is at the 55th percentile, both due to the same distortion.

For practical use-case selection, the RX 7900 XT is the clear choice for modern DX12 gaming, Vulkan titles, and general 3D rendering. The GTX 1080 Ti’s only relevant niche, based on this data, is OpenCL compute acceleration, where it delivers extraordinary performance that the RX 7900 XT cannot match.

Architecture Differences

The two cards represent fundamentally different design philosophies separated by two process nodes. The GTX 1080 Ti uses the GP102 chip built on TSMC’s 16 nm node, while the RX 7900 XT uses the Navi 31 chip on TSMC’s 5 nm process. The transistor counts reveal the scale of change: 11,800 million transistors on a 471 mm² die for the GTX 1080 Ti, versus 57,700 million transistors on a 529 mm² die for the RX 7900 XT. This translates to a transistor density of 25.1 million per mm² for Pascal, versus 109.1 million per mm² for RDNA 3.0.

The RX 7900 XT is a chiplet-based design (codename Plum Bonito) with 84 dedicated ray tracing cores, a feature completely absent from the GTX 1080 Ti. The shading unit count jumps from 3,584 on Pascal to 5,376 on RDNA 3.0, with texture mapping units rising from 224 to 336, and ROPs from 88 to 192.

Memory architecture differs substantially. The GTX 1080 Ti uses 11 GB of GDDR5X on a 352-bit bus, delivering 484.4 GB/s of bandwidth. The RX 7900 XT uses 20 GB of GDDR6 on a 320-bit bus, which achieves 800.0 GB/s due to faster memory clocks (20 Gbps effective versus 11 Gbps effective). The bus width is actually narrower on the newer card, but the higher data rate more than compensates.

Clock speeds show an interesting divergence. The GTX 1080 Ti has a base clock of 1,481 MHz and a boost of 1,582 MHz. The RX 7900 XT has a lower base clock of 1,387 MHz but a dramatically higher boost of 2,394 MHz, with a game clock of 2,025 MHz. This reflects the efficiency gains of the 5 nm process.

Compute capabilities are starkly different. The RX 7900 XT delivers 51.48 TFLOPS of FP32 performance versus 11.34 TFLOPS for the GTX 1080 Ti. For FP16, the RX 7900 XT offers 103.0 TFLOPS (2:1 ratio), while the GTX 1080 Ti manages only 177.2 GFLOPS (1:64 ratio). This is a generational leap in compute throughput.

Interface and connectivity also differ: PCIe 3.0 x16 versus PCIe 4.0 x16, and the display outputs have evolved from HDMI 2.0 and DisplayPort 1.4a on the GTX 1080 Ti to HDMI 2.1a, DisplayPort 2.1, and a USB Type-C port on the RX 7900 XT. The power delivery requirements scale accordingly, from a 250 W TDP with a 600 W suggested PSU to a 300 W TDP with a 700 W suggested PSU.

Head-to-Head Benchmarks

The largest single-test advantage belongs to the GTX 1080 Ti in Geekbench OpenCL, where its 67,929 score dwarfs the RX 7900 XT’s 12,756. This 432.5% delta is the most extreme result in the entire comparison and is responsible for the GTX 1080 Ti’s higher average benchmark score.

Outside of that anomaly, the RX 7900 XT’s biggest win comes in the 3DMark Steel Nomad DX12 test. The RX 7900 XT scores 5,623 against the GTX 1080 Ti’s 2,231, a 60.3% advantage. This is the most modern and demanding test in the suite, and it shows the RX 7900 XT’s architectural superiority in current-generation DirectX 12 workloads.

In Vulkan, the RX 7900 XT scores 71,068 versus 40,511, a 43% lead. This is notable because the GTX 1080 Ti’s Vulkan score is far more competitive than its OpenCL result, suggesting Pascal has decent low-level API support but cannot match RDNA 3.0’s throughput.

The PassMark DirectX 11 test shows a 55.6% advantage for the RX 7900 XT (340 versus 151), which is significant because DX11 remains the most widely used API in many older titles. The DirectX 12 test shows a 40% lead (110 versus 66), while DirectX 10 and DirectX 9 show smaller but still clear advantages: 25.3% (158 versus 118) and 28.3% (322 versus 231) respectively.

The 2D performance test (PassMark G2D) shows the RX 7900 XT ahead by 23.8% (1,232 versus 939), a smaller margin than the 3D tests. The comprehensive PassMark G3D score is 29,009 for the RX 7900 XT versus 18,600 for the GTX 1080 Ti, a 35.9% difference. The GPU compute test shows a 42.8% advantage (16,828 versus 9,632), which is interesting given the GTX 1080 Ti’s OpenCL outlier.

The pattern is consistent: the RX 7900 XT wins every modern workload by margins ranging from roughly a quarter to over half, while the GTX 1080 Ti only manages a win in one specific compute benchmark where it appears to have exceptional optimization.

FAQ

Q: Why does the GTX 1080 Ti have a higher average benchmark score if it loses 9 of 10 tests?

A: The Geekbench OpenCL test is a massive outlier. The GTX 1080 Ti scores 67,929 there versus 12,756 for the RX 7900 XT, a 432.5% difference. This single result inflates the GTX 1080 Ti’s average to 15,548 compared to the RX 7900 XT’s 13,745, despite the RX 7900 XT winning every other benchmark by substantial margins.

Q: Which card wins in DirectX 12 performance?

A: The AMD Radeon RX 7900 XT wins decisively. In the 3DMark Steel Nomad DX12 test, it scores 5,623 versus 2,231 for the GTX 1080 Ti, a 60.3% advantage. In the PassMark DirectX 12 test, it scores 110 versus 66, a 40% lead.

Q: How do the two cards compare in Vulkan performance?

A: The RX 7900 XT leads in Vulkan as well, scoring 71,068 against the GTX 1080 Ti’s 40,511, which is a 43% advantage. This indicates better low-level API implementation in the newer RDNA 3.0 architecture.

Q: Is the GTX 1080 Ti better at any compute workload?

A: Yes, specifically in Geekbench OpenCL, where it scores 67,929 versus 12,756 for the RX 7900 XT, a 432.5% advantage. However, in the PassMark GPU Compute test, the RX 7900 XT wins with 16,828 versus 9,632, a 42.8% lead.

Q: What are the memory specifications for each card?

A: The GTX 1080 Ti has 11 GB of GDDR5X on a 352-bit bus with 484.4 GB/s bandwidth. The RX 7900 XT has 20 GB of GDDR6 on a 320-bit bus with 800.0 GB/s bandwidth, achieved through faster 20 Gbps effective memory clocks versus 11 Gbps effective.

Q: Does the RX 7900 XT have ray tracing support?

A: Yes, the RX 7900 XT includes 84 dedicated ray tracing cores, a feature the GTX 1080 Ti does not have. This is a fundamental architectural addition in the RDNA 3.0 design.

Specification Differences

| Specification | NVIDIA GeForce GTX 1080 Ti | AMD Radeon RX 7900 XT |

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

| Architecture | Pascal | RDNA 3.0 |

| Process Node | 16 nm | 5 nm |

| Transistors | 11,800 million | 57,700 million |

| Die Size | 471 mm² | 529 mm² |

| Transistor Density | 25.1M / mm² | 109.1M / mm² |

| Base Clock | 1,481 MHz | 1,387 MHz |

| Boost Clock | 1,582 MHz | 2,394 MHz |

| Game Clock | N/A | 2,025 MHz |

| Memory Size | 11 GB | 20 GB |

| Memory Type | GDDR5X | GDDR6 |

| Memory Bus Width | 352 bit | 320 bit |

| Memory Bandwidth | 484.4 GB/s | 800.0 GB/s |

| Shading Units | 3,584 | 5,376 |

| TMUs | 224 | 336 |

| ROPs | 88 | 192 |

| RT Cores | N/A | 84 |

| FP32 Performance | 11.34 TFLOPS | 51.48 TFLOPS |

| FP16 Performance | 177.2 GFLOPS (1:64) | 103.0 TFLOPS (2:1) |

| Pixel Rate | 139.2 GPixel/s | 459.6 GPixel/s |

| Texture Rate | 354.4 GTexel/s | 804.4 GTexel/s |

| TDP | 250 W | 300 W |

| Power Connectors | 1x 6-pin + 1x 8-pin | 2x 8-pin |

| Suggested PSU | 600 W | 700 W |

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

| Display Outputs | 1x HDMI 2.0, 3x DisplayPort 1.4a | 1x HDMI 2.1a, 2x DisplayPort 2.1, 1x USB Type-C |

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

| Release Date | 2017-03-09 | 2022-11-02 |

The RX 7900 XT is larger in physical dimensions (276 mm versus 267 mm length, 51 mm versus 40 mm width) but slightly shorter in height (110 mm versus 112 mm). Both are dual-slot cards. The RX 7900 XT’s launch MSRP is 899 USD, while the GTX 1080 Ti’s launch MSRP is 699 USD.