Data Center GPU Flex 170 vs Tesla K40st
We compared two Professional market GPUs: 16GB VRAM Data Center GPU Flex 170 and 12GB VRAM Tesla K40st to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Data Center GPU Flex 170 's Advantages
Released 8 years and 9 months late
Boost Clock2050MHz
More VRAM (16GB vs 12GB)
Larger VRAM bandwidth (512.0GB/s vs 288.4GB/s)
1216 additional rendering cores
Lower TDP (150W vs 245W)
Score
Benchmark
FP32 (float)
Data Center GPU Flex 170
+406%
16790
Tesla K40st
3312
Graphics Card
Aug 2022
Release Date
Nov 2013
Data Center GPU
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1950 MHz
Base Clock
-
2050 MHz
Boost Clock
-
2000 MHz
Memory Clock
1502 MHz
Memory
16GB
Memory Size
12GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
384bit
512.0GB/s
Bandwidth
288.4GB/s
Render Config
4096
Shading Units
2880
256
TMUs
240
128
ROPs
48
32
RT Cores
-
-
L1 Cache
16 KB (per SMX)
16 MB
L2 Cache
1536 KB
Theoretical Performance
262.4 GPixel/s
Pixel Rate
34.50 GPixel/s
524.8 GTexel/s
Texture Rate
138.0 GTexel/s
33.59 TFLOPS
FP16 (half)
-
16.79 TFLOPS
FP32 (float)
3.312 TFLOPS
-
FP64 (double)
1104 GFLOPS
Board Design
150W
TDP
245W
450 W
Suggested PSU
550 W
1x HDMI 2.1
3x DisplayPort 2.0
Outputs
No outputs
1x 8-pin
Power Connectors
-
Graphics Processor
DG2-512
GPU Name
GK110B
ACM-G10
GPU Variant
-
Generation 12.7
Architecture
Kepler
TSMC
Foundry
TSMC
6 nm
Process Size
28 nm
21.7 billion
Transistors
7.08 billion
406 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
3.5
6.6
Shader Model
5.1
