NVIDIA Tesla P40 vs NVIDIA Tesla K20X
We compared two Professional market GPUs: 24GB VRAM Tesla P40 and 6GB VRAM Tesla K20X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla P40 's Advantages
Released 3 years and 10 months late
Boost Clock1531MHz
More VRAM (24GB vs 6GB)
Larger VRAM bandwidth (347.1GB/s vs 249.6GB/s)
1152 additional rendering cores
NVIDIA Tesla K20X 's Advantages
Lower TDP (235W vs 250W)
Score
Benchmark
FP32 (float)
Tesla P40
+198%
11.76 TFLOPS
Tesla K20X
3.935 TFLOPS
Graphics Card
Sep 2016
Release Date
Nov 2012
Tesla Pascal
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1303 MHz
Base Clock
-
1531 MHz
Boost Clock
-
1808 MHz
Memory Clock
1300 MHz
Memory
24GB
Memory Size
6GB
GDDR5
Memory Type
GDDR5
384bit
Memory Bus
384bit
347.1GB/s
Bandwidth
249.6GB/s
Render Config
-
-
-
30
SM Count
-
3840
Shading Units
2688
240
TMUs
224
96
ROPs
48
-
-
-
-
-
-
48 KB (per SM)
L1 Cache
16 KB (per SMX)
3 MB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
147.0 GPixel/s
Pixel Rate
40.99 GPixel/s
367.4 GTexel/s
Texture Rate
164.0 GTexel/s
183.7 GFLOPS
FP16 (half)
-
11.76 TFLOPS
FP32 (float)
3.935 TFLOPS
367.4 GFLOPS
FP64 (double)
1312 GFLOPS
Board Design
250W
TDP
235W
600 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
GP102
GPU Name
GK110
-
-
-
Pascal
Architecture
Kepler
TSMC
Foundry
TSMC
16 nm
Process Size
28 nm
11.8 billion
Transistors
7.08 billion
471 mm²
Die Size
561 mm²
Graphics Features
12 (12_1)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.1
6.1
CUDA
3.5
6.7
Shader Model
5.1
