AMD Radeon Pro W6900X vs NVIDIA Tesla K20X
GPU · Specs Compare
Graphics Card
Release Date
Aug 2021
Nov 2012
Generation
Radeon Pro Mac
Tesla
Type
Desktop
Professional
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1825 MHz
—
Boost Clock
2150 MHz
—
Memory Clock
2000 MHz
1300 MHz
Memory
Memory Size
32GB
6GB
Memory Type
GDDR6
GDDR5
Memory Bus
256bit
384bit
Bandwidth
512.0GB/s
249.6GB/s
Render Config
Compute Units
80
—
Shading Units
5120
2688
TMUs
320
224
ROPs
128
48
RT Cores
80
—
L1 Cache
128 KB per Array
16 KB (per SMX)
L2 Cache
4 MB
1536 KB
L3 Cache
128 MB
—
Theoretical Performance
Pixel Rate
275.2 GPixel/s
40.99 GPixel/s
Texture Rate
688.0 GTexel/s
164.0 GTexel/s
FP16 (half)
44.03 TFLOPS
—
FP32 (float)
22.02 TFLOPS
3.935 TFLOPS
FP64 (double)
1376 GFLOPS
1312 GFLOPS
Graphics Processor
GPU Name
Navi 21
GK110
GPU Variant
Navi 21 Pro-XTA
—
Architecture
RDNA 2.0
Kepler
Foundry
TSMC
TSMC
Process Size
7 nm
28 nm
Transistors
26.8 billion
7.08 billion
Die Size
520 mm²
561 mm²
Board Design
TDP
300W
235W
Suggested PSU
700 W
550 W
Outputs
1x HDMI 2.14x Thunderbolt
No outputs
Power Connectors
None
1x 6-pin + 1x 8-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 (11_0)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.3
1.1
Shader Model
6.5
5.1
CUDA
—
3.5
▲ Specs Compare
Data sourced from official specifications and benchmark tests.