NVIDIA Tesla K20m vs AMD Radeon PRO W7900
GPU · Specs Compare
Graphics Card
Release Date
Jan 2013
May 2023
Generation
Tesla
Radeon Pro Navi
Type
Professional
Professional
Bus Interface
PCIe 2.0 x16
PCIe 4.0 x16
Clock Speeds
Memory Clock
1300 MHz
2250 MHz
Base Clock
—
1760 MHz
Boost Clock
—
2495 MHz
Memory
Memory Size
5GB
48GB
Memory Type
GDDR5
GDDR6
Memory Bus
320bit
384bit
Bandwidth
208.0GB/s
864.0GB/s
Render Config
Shading Units
2496
6144
TMUs
208
384
ROPs
40
192
L1 Cache
16 KB (per SMX)
256 KB per Array
L2 Cache
1280 KB
6 MB
Compute Units
—
96
RT Cores
—
96
L3 Cache
—
96 MB
Theoretical Performance
Pixel Rate
36.71 GPixel/s
479.0 GPixel/s
Texture Rate
146.8 GTexel/s
958.1 GTexel/s
FP32 (float)
3.524 TFLOPS
61.32 TFLOPS
FP64 (double)
1175 GFLOPS
1.916 TFLOPS
FP16 (half)
—
122.6 TFLOPS
Graphics Processor
GPU Name
GK110
Navi 31
Architecture
Kepler
RDNA 3.0
Foundry
TSMC
TSMC
Process Size
28 nm
5 nm
Transistors
7.08 billion
57.7 billion
Die Size
561 mm²
529 mm²
GPU Variant
—
Navi 31 XTW
Board Design
TDP
225W
295W
Suggested PSU
550 W
600 W
Outputs
No outputs
3x DisplayPort 2.11x mini-DisplayPort 2.1
Power Connectors
1x 6-pin + 1x 8-pin
2x 8-pin
Graphics Features
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
2.0
Vulkan
1.1
1.4
CUDA
3.5
—
Shader Model
5.1
6.9
▲ Specs Compare
Data sourced from official specifications and benchmark tests.