NVIDIA Tesla K20m vs AMD Radeon PRO W7700

GPU Specs Compare

G

NVIDIA Tesla K20m

NVIDIA 2013-01

Graphics Card

Release Date
Jan 2013
Nov 2023
Generation
Tesla
Radeon Pro Navi
Type
Professional
Desktop
Bus Interface
PCIe 2.0 x16
PCIe 4.0 x16

Clock Speeds

Memory Clock
1300 MHz
2250 MHz
Base Clock
-
1900 MHz
Boost Clock
-
2600 MHz

Memory

Memory Size
5GB
16GB
Memory Type
GDDR5
GDDR6
Memory Bus
320bit
256bit
Bandwidth
208.0GB/s
576.0GB/s

Render Config

Shading Units
2496
3072
TMUs
208
192
ROPs
40
96
L1 Cache
16 KB (per SMX)
128 KB per Array
L2 Cache
1280 KB
2 MB
Compute Units
-
48
RT Cores
-
48
L3 Cache
-
64 MB

Theoretical Performance

Pixel Rate
36.71 GPixel/s
249.6 GPixel/s
Texture Rate
146.8 GTexel/s
499.2 GTexel/s
FP32 (float)
3.524 TFLOPS
31.95 TFLOPS
FP64 (double)
1175 GFLOPS
998.4 GFLOPS
FP16 (half)
-
63.90 TFLOPS

Graphics Processor

GPU Name
GK110
Navi 32
Architecture
Kepler
RDNA 3.0
Foundry
TSMC
TSMC
Process Size
28 nm
5 nm
Transistors
7.08 billion
28.1 billion
Die Size
561 mm²
346 mm²
GPU Variant
-
Navi 32

Board Design

TDP
225W
190W
Suggested PSU
550 W
450 W
Outputs
No outputs
4x DisplayPort 2.1
Power Connectors
1x 6-pin + 1x 8-pin
1x 8-pin

Graphics Features

DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
2.2
Vulkan
1.1
1.3
CUDA
3.5
-
Shader Model
5.1
6.7

📊 Benchmark

3DMark Time Spy
-
15,693
3DMark Speed Way
-
3,224
Blender
-
1,910