Intel Data Center GPU Flex 140 vs NVIDIA Tesla K80
We compared two Professional market GPUs: 6GB VRAM Data Center GPU Flex 140 and 12GB VRAM Tesla K80 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Data Center GPU Flex 140 's Advantages
Released 7 years and 9 months late
Boost Clock has increased by 137% (1950MHz vs 824MHz)
Lower TDP (75W vs 300W)
NVIDIA Tesla K80 's Advantages
More VRAM (12GB vs 6GB)
Larger VRAM bandwidth (240.6GB/s vs 186.0GB/s)
1472 additional rendering cores
Score
Benchmark
FP32 (float)
Data Center GPU Flex 140
3.994 TFLOPS
Tesla K80
+2%
4.113 TFLOPS
Graphics Card
Aug 2022
Release Date
Nov 2014
Data Center GPU
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x8
Bus Interface
PCIe 3.0 x16
Clock Speeds
1600 MHz
Base Clock
562 MHz
1950 MHz
Boost Clock
824 MHz
1937 MHz
Memory Clock
1253 MHz
Memory
6GB
Memory Size
12GB
GDDR6
Memory Type
GDDR5
96bit
Memory Bus
384bit
186.0GB/s
Bandwidth
240.6GB/s
Render Config
-
-
-
-
-
-
1024
Shading Units
2496
64
TMUs
208
32
ROPs
48
-
-
-
8
RT Cores
-
-
L1 Cache
16 KB (per SMX)
4 MB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
62.40 GPixel/s
Pixel Rate
42.85 GPixel/s
124.8 GTexel/s
Texture Rate
171.4 GTexel/s
7.987 TFLOPS
FP16 (half)
-
3.994 TFLOPS
FP32 (float)
4.113 TFLOPS
-
FP64 (double)
1371 GFLOPS
Board Design
75W
TDP
300W
250 W
Suggested PSU
700 W
1x HDMI 2.1
3x DisplayPort 2.0
Outputs
No outputs
1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
DG2-128
GPU Name
GK210
ACM-G11
GPU Variant
GK210-885-A1
Generation 12.7
Architecture
Kepler 2.0
TSMC
Foundry
TSMC
6 nm
Process Size
28 nm
7.2 billion
Transistors
7.1 billion
157 mm²
Die Size
561 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.1
-
CUDA
3.7
6.6
Shader Model
5.1
