GPU Wiki
GeForce GTX 1080 Ti vs GeForce RTX 2080
Edit GPUs
Key Differences
- No game was measured on every one of these cards on one shared test system, so there is no speed comparison to make.
- GTX 1080 Ti has the most memory: 11 GB against 8 GB.
- GTX 1080 Ti has the most memory bandwidth: 484.4 GB/s against 448 GB/s.
- RTX 2080 draws the least power: 225 W against 250 W.
| Spec | GeForce GTX 1080 Ti | GeForce RTX 2080 |
|---|---|---|
| Overview | ||
| Product name | NVIDIA GeForce GTX 1080 Ti | NVIDIA GeForce RTX 2080 |
| Architecture | Pascal | Turing |
| Generation / family | GeForce GTX 10 Series | GeForce RTX 20 Series |
| GPU codename | GP102 | TU104 |
| Launch date | 2017-03-10 | 2018-09-20 |
| Market segment | Desktop, Flagship in GeForce GTX 10 Series | Desktop in GeForce RTX 20 Series |
| Board type / entry type | Reference GPU | Reference GPU |
| GPU | ||
| Process node | TSMC 16 nm | TSMC 12 nm |
| Die size | 471 mm² | 545 mm² |
| Transistor count | 11.8 billion | 13.6 billion |
| GPU chip | GP102 | TU104 |
| SM / multiprocessor count | 28 | 46 |
| CUDA Cores | 3584 | 2944 |
| Tensor Cores | Unknown | 368 |
| RT Cores | Unknown | 46 |
| ROPs | 88 | 64 |
| TMUs | 224 | 184 |
| Clocks | ||
| Base / Core clock | 1,481 MHz | 1,515 MHz |
| Boost clock | 1,582 MHz | 1,710 MHz |
| Memory clock | 1,376 MHz | 1,750 MHz |
| Memory | ||
| Memory size | 11 GB | 8 GB |
| Memory type | GDDR5X | GDDR6 |
| Memory bus width | 352-bit | 256-bit |
| Memory bandwidth | 484.4 GB/s | 448 GB/s |
| Bus / Interface | ||
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| AGP / PCI / PCIe distinction | PCIe | PCIe |
| Power | ||
| TDP / TBP / board power | 250 W | 225 W |
| Recommended PSU | 600 W | 650 W |
| Power connectors | 1x PCIe 6-pin + 1x PCIe 8-pin | 1x PCIe 6-pin + 1x PCIe 8-pin |
| Slot width | Dual-slot, 267 mm length, 40 mm width | Dual-slot, 267 mm length, 35 mm width |
| Display / Media | ||
| Display outputs | 1x HDMI 2.0, 3x DisplayPort 1.4a | 1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C |
| Features | ||
| DirectX support | DirectX 12.1 | DirectX 12.2 |
| OpenGL support | OpenGL 4.6 | OpenGL 4.6 |
| Vulkan support | Vulkan 1.4 | Vulkan 1.4 |
| CUDA support | 6.1 | 7.5 |
| Shader Model | 6.8 | 6.8 |
| Ray tracing support | Unknown | Hardware RT units present |
| Performance / Benchmarks | ||
| FP32 throughput | 11.34 TFLOPS | 10.07 TFLOPS |
| FP16 throughput | 0.18 TFLOPS | 20.14 TFLOPS |
Overview
Product name
GeForce GTX 1080 Ti
NVIDIA GeForce GTX 1080 Ti
GeForce RTX 2080
NVIDIA GeForce RTX 2080
Architecture
GeForce GTX 1080 Ti
Pascal
GeForce RTX 2080
Turing
Generation / family
GeForce GTX 1080 Ti
GeForce GTX 10 Series
GeForce RTX 2080
GeForce RTX 20 Series
GPU codename
GeForce GTX 1080 Ti
GP102
GeForce RTX 2080
TU104
Launch date
GeForce GTX 1080 Ti
2017-03-10
GeForce RTX 2080
2018-09-20
Market segment
GeForce GTX 1080 Ti
Desktop, Flagship in GeForce GTX 10 Series
GeForce RTX 2080
Desktop in GeForce RTX 20 Series
Board type / entry type
GeForce GTX 1080 Ti
Reference GPU
GeForce RTX 2080
Reference GPU
GPU
Process node
GeForce GTX 1080 Ti
TSMC 16 nm
GeForce RTX 2080
TSMC 12 nm
Die size
GeForce GTX 1080 Ti
471 mm²
GeForce RTX 2080
545 mm²
Transistor count
GeForce GTX 1080 Ti
11.8 billion
GeForce RTX 2080
13.6 billion
GPU chip
GeForce GTX 1080 Ti
GP102
GeForce RTX 2080
TU104
SM / multiprocessor count
GeForce GTX 1080 Ti
28
GeForce RTX 2080
46
CUDA Cores
GeForce GTX 1080 Ti
3584
GeForce RTX 2080
2944
Tensor Cores
GeForce GTX 1080 Ti
Unknown
GeForce RTX 2080
368
RT Cores
GeForce GTX 1080 Ti
Unknown
GeForce RTX 2080
46
ROPs
GeForce GTX 1080 Ti
88
GeForce RTX 2080
64
TMUs
GeForce GTX 1080 Ti
224
GeForce RTX 2080
184
Clocks
Base / Core clock
GeForce GTX 1080 Ti
1,481 MHz
GeForce RTX 2080
1,515 MHz
Boost clock
GeForce GTX 1080 Ti
1,582 MHz
GeForce RTX 2080
1,710 MHz
Memory clock
GeForce GTX 1080 Ti
1,376 MHz
GeForce RTX 2080
1,750 MHz
Memory
Memory size
GeForce GTX 1080 Ti
11 GB
GeForce RTX 2080
8 GB
Memory type
GeForce GTX 1080 Ti
GDDR5X
GeForce RTX 2080
GDDR6
Memory bus width
GeForce GTX 1080 Ti
352-bit
GeForce RTX 2080
256-bit
Memory bandwidth
Bus / Interface
Bus interface
GeForce GTX 1080 Ti
PCIe 3.0 x16
GeForce RTX 2080
PCIe 3.0 x16
AGP / PCI / PCIe distinction
GeForce GTX 1080 Ti
PCIe
GeForce RTX 2080
PCIe
Power
TDP / TBP / board power
GeForce GTX 1080 Ti
250 W
GeForce RTX 2080
225 W
Recommended PSU
GeForce GTX 1080 Ti
600 W
GeForce RTX 2080
650 W
Power connectors
GeForce GTX 1080 Ti
1x PCIe 6-pin + 1x PCIe 8-pin
GeForce RTX 2080
1x PCIe 6-pin + 1x PCIe 8-pin
Slot width
GeForce GTX 1080 Ti
Dual-slot, 267 mm length, 40 mm width
GeForce RTX 2080
Dual-slot, 267 mm length, 35 mm width
Display / Media
Display outputs
GeForce GTX 1080 Ti
1x HDMI 2.0, 3x DisplayPort 1.4a
GeForce RTX 2080
1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C
Features
DirectX support
GeForce GTX 1080 Ti
DirectX 12.1
GeForce RTX 2080
DirectX 12.2
OpenGL support
GeForce GTX 1080 Ti
OpenGL 4.6
GeForce RTX 2080
OpenGL 4.6
Vulkan support
GeForce GTX 1080 Ti
Vulkan 1.4
GeForce RTX 2080
Vulkan 1.4
CUDA support
GeForce GTX 1080 Ti
6.1
GeForce RTX 2080
7.5
Shader Model
GeForce GTX 1080 Ti
6.8
GeForce RTX 2080
6.8
Ray tracing support
GeForce GTX 1080 Ti
Unknown
GeForce RTX 2080
Hardware RT units present
Performance / Benchmarks
FP32 throughput
FP16 throughput
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
Frame rates compare runs of the same game at the same quality preset on one test system. DLAA counts as native resolution, because it applies anti-aliasing at full render resolution rather than upscaling; DLSS and FSR upscaling are never counted as native. Where a capture named ray tracing without a readable on or off value, it is read as on.
