NVIDIA Tesla K20X vs Intel Data Center GPU Flex 170
GPU Specs Compare
Graphics Card
Release Date
Nov 2012
Aug 2022
Generation
Tesla
Data Center GPU
Type
Professional
Professional
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Clock Speeds
Memory Clock
1300 MHz
2000 MHz
Base Clock
-
1950 MHz
Boost Clock
-
2050 MHz
Memory
Memory Size
6GB
16GB
Memory Type
GDDR5
GDDR6
Memory Bus
384bit
256bit
Bandwidth
249.6GB/s
512.0GB/s
Render Config
Shading Units
2688
4096
TMUs
224
256
ROPs
48
128
L1 Cache
16 KB (per SMX)
-
L2 Cache
1536 KB
16 MB
RT Cores
-
32
Theoretical Performance
Pixel Rate
40.99 GPixel/s
262.4 GPixel/s
Texture Rate
164.0 GTexel/s
524.8 GTexel/s
FP32 (float)
3.935 TFLOPS
16.79 TFLOPS
FP64 (double)
1312 GFLOPS
-
FP16 (half)
-
33.59 TFLOPS
Graphics Processor
GPU Name
GK110
DG2-512
Architecture
Kepler
Generation 12.7
Foundry
TSMC
TSMC
Process Size
28 nm
6 nm
Transistors
7.08 billion
21.7 billion
Die Size
561 mm²
406 mm²
GPU Variant
-
ACM-G10
Board Design
TDP
235W
150W
Suggested PSU
550 W
450 W
Outputs
No outputs
1x HDMI 2.13x DisplayPort 2.0
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
3.0
Vulkan
1.1
1.3
CUDA
3.5
-
Shader Model
5.1
6.6