Intel Data Center GPU Flex 140 vs NVIDIA Tesla P6
We compared two Professional market GPUs: 6GB VRAM Data Center GPU Flex 140 and 16GB VRAM Tesla P6 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 5 years and 5 months late
Boost Clock has increased by 29% (1950MHz vs 1506MHz)
Lower TDP (75W vs 90W)
NVIDIA Tesla P6 's Advantages
More VRAM (16GB vs 6GB)
Larger VRAM bandwidth (192.3GB/s vs 186.0GB/s)
1024 additional rendering cores
Score
Benchmark
FP32 (float)
Data Center GPU Flex 140
3.994 TFLOPS
Tesla P6
+54%
6.169 TFLOPS
Graphics Card
Aug 2022
Release Date
Mar 2017
Data Center GPU
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x8
Bus Interface
MXM-B (3.0)
Clock Speeds
1600 MHz
Base Clock
1012 MHz
1950 MHz
Boost Clock
1506 MHz
1937 MHz
Memory Clock
1502 MHz
Memory
6GB
Memory Size
16GB
GDDR6
Memory Type
GDDR5
96bit
Memory Bus
256bit
186.0GB/s
Bandwidth
192.3GB/s
Render Config
-
-
-
-
SM Count
16
1024
Shading Units
2048
64
TMUs
128
32
ROPs
64
-
-
-
8
RT Cores
-
-
L1 Cache
48 KB (per SM)
4 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
62.40 GPixel/s
Pixel Rate
96.38 GPixel/s
124.8 GTexel/s
Texture Rate
192.8 GTexel/s
7.987 TFLOPS
FP16 (half)
96.38 GFLOPS
3.994 TFLOPS
FP32 (float)
6.169 TFLOPS
-
FP64 (double)
192.8 GFLOPS
Board Design
75W
TDP
90W
250 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 2.0
Outputs
No outputs
1x 8-pin
Power Connectors
None
Graphics Processor
DG2-128
GPU Name
GP104
ACM-G11
GPU Variant
GP104-995-A1
Generation 12.7
Architecture
Pascal
TSMC
Foundry
TSMC
6 nm
Process Size
16 nm
7.2 billion
Transistors
7.2 billion
157 mm²
Die Size
314 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
6.1
6.6
Shader Model
6.4
