NVIDIA GeForce RTX 3080 Ti vs AMD Radeon RX 470D
GPU · Specs Compare
Graphics Card
Release Date
May 2021
Oct 2016
Generation
GeForce 30
Arctic Islands
Type
Desktop
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1365 MHz
926 MHz
Boost Clock
1665 MHz
1206 MHz
Memory Clock
1188 MHz
1650 MHz
Memory
Memory Size
12GB
4GB
Memory Type
GDDR6X
GDDR5
Memory Bus
384bit
256bit
Bandwidth
912.4GB/s
211.2GB/s
Render Config
SM Count
80
—
Shading Units
10240
1792
TMUs
320
112
ROPs
112
32
Tensor Cores
320
—
RT Cores
80
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
6 MB
2 MB
Compute Units
—
28
Theoretical Performance
Pixel Rate
186.5 GPixel/s
38.59 GPixel/s
Texture Rate
532.8 GTexel/s
135.1 GTexel/s
FP16 (half)
34.10 TFLOPS
4.322 TFLOPS
FP32 (float)
34.10 TFLOPS
4.322 TFLOPS
FP64 (double)
532.8 GFLOPS
270.1 GFLOPS
Graphics Processor
GPU Name
GA102
Ellesmere
GPU Variant
GA102-225-A1
Polaris 10 PROD
Architecture
Ampere
GCN 4.0
Foundry
Samsung
GlobalFoundries
Process Size
8 nm
14 nm
Transistors
28.3 billion
5.7 billion
Die Size
628 mm²
232 mm²
Board Design
TDP
350W
120W
Suggested PSU
750 W
300 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
1x HDMI 2.0b3x DisplayPort 1.4a
Power Connectors
1x 12-pin
1x 6-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.3
1.2
CUDA
8.6
—
Shader Model
6.6
6.4
Benchmark
3DMark Time Spy
19,629
—
3DMark Time Spy Extreme
10,032
—
3DMark Speed Way
5,330
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.