NVIDIA Tesla K8 vs Intel Data Center GPU Flex 140
We compared two Professional market GPUs: 8GB VRAM Tesla K8 and 6GB VRAM Data Center GPU Flex 140 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla K8 's Advantages
More VRAM (8GB vs 6GB)
512 additional rendering cores
Intel Data Center GPU Flex 140 's Advantages
Released 7 years and 11 months late
Boost Clock has increased by 140% (1950MHz vs 811MHz)
Larger VRAM bandwidth (186.0GB/s vs 160.0GB/s)
Lower TDP (75W vs 100W)
Score
Benchmark
FP32 (float)
Tesla K8
2.491 TFLOPS
Data Center GPU Flex 140
+60%
3.994 TFLOPS
Graphics Card
Sep 2014
Release Date
Aug 2022
Tesla
Generation
Data Center GPU
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 4.0 x8
Clock Speeds
693 MHz
Base Clock
1600 MHz
811 MHz
Boost Clock
1950 MHz
1250 MHz
Memory Clock
1937 MHz
Memory
8GB
Memory Size
6GB
GDDR5
Memory Type
GDDR6
256bit
Memory Bus
96bit
160.0GB/s
Bandwidth
186.0GB/s
Render Config
-
-
-
-
-
-
1536
Shading Units
1024
128
TMUs
64
32
ROPs
32
-
-
-
-
RT Cores
8
16 KB (per SMX)
L1 Cache
-
512 KB
L2 Cache
4 MB
-
-
-
Theoretical Performance
25.95 GPixel/s
Pixel Rate
62.40 GPixel/s
103.8 GTexel/s
Texture Rate
124.8 GTexel/s
-
FP16 (half)
7.987 TFLOPS
2.491 TFLOPS
FP32 (float)
3.994 TFLOPS
103.8 GFLOPS
FP64 (double)
-
Board Design
100W
TDP
75W
300 W
Suggested PSU
250 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 2.0
1x 6-pin
Power Connectors
1x 8-pin
Graphics Processor
GK104
GPU Name
DG2-128
-
GPU Variant
ACM-G11
Kepler
Architecture
Generation 12.7
TSMC
Foundry
TSMC
28 nm
Process Size
6 nm
3.54 billion
Transistors
7.2 billion
294 mm²
Die Size
157 mm²
Graphics Features
12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.0
CUDA
-
5.1
Shader Model
6.6
