NVIDIA GeForce RTX 3070 Ti GA102 vs AMD Radeon Pro Duo Polaris
GPU · Specs Compare
Graphics Card
Release Date
Oct 2022
Apr 2017
Generation
GeForce 30
Radeon Pro GCN
Type
Desktop
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1575 MHz
—
Boost Clock
1770 MHz
—
Memory Clock
1188 MHz
1750 MHz
Memory
Memory Size
8GB
16GB
Memory Type
GDDR6X
GDDR5
Memory Bus
256bit
256bit
Bandwidth
608.3GB/s
224.0GB/s
Render Config
SM Count
48
—
Shading Units
6144
2304
TMUs
192
144
ROPs
96
32
Tensor Cores
192
—
RT Cores
48
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
4 MB
2 MB
Compute Units
—
36
Theoretical Performance
Pixel Rate
169.9 GPixel/s
39.78 GPixel/s
Texture Rate
339.8 GTexel/s
179.0 GTexel/s
FP16 (half)
21.75 TFLOPS
5.728 TFLOPS
FP32 (float)
21.75 TFLOPS
5.728 TFLOPS
FP64 (double)
339.8 GFLOPS
358.0 GFLOPS
Graphics Processor
GPU Name
GA102
Ellesmere
GPU Variant
GA102-150-A1
Ellesmere Gemini GL
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
290W
250W
Suggested PSU
600 W
600 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
1x HDMI 2.0b3x DisplayPort 1.4a
Power Connectors
1x 12-pin
1x 6-pin + 1x 8-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.3
1.3
CUDA
8.6
—
Shader Model
6.6
6.7
▲ Specs Compare
Data sourced from official specifications and benchmark tests.