AMD Radeon Pro 580 vs NVIDIA GeForce RTX 3070 Ti
GPU · Specs Compare
Graphics Card
Release Date
Jun 2017
May 2021
Generation
Radeon Pro Mac
GeForce 30
Type
Mobile
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1100 MHz
1575 MHz
Boost Clock
1200 MHz
1770 MHz
Memory Clock
1695 MHz
1188 MHz
Memory
Memory Size
8GB
8GB
Memory Type
GDDR5
GDDR6X
Memory Bus
256bit
256bit
Bandwidth
217.0GB/s
608.3GB/s
Render Config
Compute Units
36
—
Shading Units
2304
6144
TMUs
144
192
ROPs
32
96
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
2 MB
4 MB
SM Count
—
48
Tensor Cores
—
192
RT Cores
—
48
Theoretical Performance
Pixel Rate
38.40 GPixel/s
169.9 GPixel/s
Texture Rate
172.8 GTexel/s
339.8 GTexel/s
FP16 (half)
5.530 TFLOPS
21.75 TFLOPS
FP32 (float)
5.530 TFLOPS
21.75 TFLOPS
FP64 (double)
345.6 GFLOPS
339.8 GFLOPS
Graphics Processor
GPU Name
Ellesmere
GA104
GPU Variant
Ellesmere XTA(216-0886220)
GA104-400-A1
Architecture
GCN 4.0
Ampere
Foundry
GlobalFoundries
Samsung
Process Size
14 nm
8 nm
Transistors
5.7 billion
17.4 billion
Die Size
232 mm²
392 mm²
Board Design
TDP
185W
290W
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
None
1x 12-pin
Suggested PSU
—
600 W
Graphics Features
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.2
1.3
Shader Model
6.4
6.6
CUDA
—
8.6
Benchmark
3DMark Time Spy
3,791
14,872
3DMark Time Spy Extreme
1,684
7,416
3DMark Speed Way
—
3,761
▲ Specs Compare
Data sourced from official specifications and benchmark tests.