NVIDIA GeForce GTX 580 Rev. 2 vs NVIDIA GeForce RTX 4070 Ti

GPU · Specs Compare

Products
GPU NVIDIA GeForce GTX 580 Rev. 2 NVIDIA · 2011-06
GPU NVIDIA GeForce RTX 4070 Ti NVIDIA · 2023-01
Graphics Card
Release Date
Jun 2011
Jan 2023
Generation
GeForce 500
GeForce 40
Type
Desktop
Desktop
Bus Interface
PCIe 2.0 x16
PCIe 4.0 x16
Clock Speeds
Memory Clock
1002 MHz
1313 MHz
Base Clock
—
2310 MHz
Boost Clock
—
2610 MHz
Memory
Memory Size
1536MB
12GB
Memory Type
GDDR5
GDDR6X
Memory Bus
384bit
192bit
Bandwidth
192.4GB/s
504.2GB/s
Render Config
SM Count
16
60
Shading Units
512
7680
TMUs
64
240
ROPs
48
80
L1 Cache
64 KB (per SM)
128 KB (per SM)
L2 Cache
768 KB
48 MB
Tensor Cores
—
240
RT Cores
—
60
Theoretical Performance
Pixel Rate
24.70 GPixel/s
208.8 GPixel/s
Texture Rate
49.41 GTexel/s
626.4 GTexel/s
FP32 (float)
1.581 TFLOPS
40.09 TFLOPS
FP64 (double)
197.6 GFLOPS
626.4 GFLOPS
FP16 (half)
—
40.09 TFLOPS
Graphics Processor
GPU Name
GF110
AD104
GPU Variant
GF110-380-A1
AD104-400-A1
Architecture
Fermi 2.0
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
40 nm
4 nm
Transistors
3 billion
35.8 billion
Die Size
520 mm²
295 mm²
Board Design
TDP
244W
285W
Suggested PSU
550 W
600 W
Outputs
2x DVI1x mini-HDMI 1.3a
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
1x 6-pin + 1x 8-pin
1x 16-pin
Graphics Features
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
1.1
3.0
Vulkan
N/A
1.3
CUDA
2.0
8.9
Shader Model
5.1
6.7
▲ Specs Compare Data sourced from official specifications and benchmark tests.