NVIDIA GRID K100 vs NVIDIA Tesla P6
We compared two Professional market GPUs: 256MB VRAM GRID K100 and 16GB VRAM Tesla P6 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla P6 's Advantages
Released 3 years and 9 months late
Boost Clock1506MHz
More VRAM (16GB vs 256GB)
Larger VRAM bandwidth (192.3GB/s vs 28.51GB/s)
1856 additional rendering cores
Lower TDP (90W vs 130W)
Score
Benchmark
FP32 (float)
GRID K100
0.326 TFLOPS
Tesla P6
+1792%
6.169 TFLOPS
Graphics Card
Jun 2013
Release Date
Mar 2017
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
MXM-B (3.0)
Clock Speeds
-
Base Clock
1012 MHz
-
Boost Clock
1506 MHz
891 MHz
Memory Clock
1502 MHz
Memory
256MB
Memory Size
16GB
DDR3
Memory Type
GDDR5
128bit
Memory Bus
256bit
28.51GB/s
Bandwidth
192.3GB/s
Render Config
-
-
-
-
SM Count
16
192
Shading Units
2048
16
TMUs
128
16
ROPs
64
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
48 KB (per SM)
256 KB
L2 Cache
2 MB
-
-
-
Theoretical Performance
3.400 GPixel/s
Pixel Rate
96.38 GPixel/s
13.60 GTexel/s
Texture Rate
192.8 GTexel/s
-
FP16 (half)
96.38 GFLOPS
326.4 GFLOPS
FP32 (float)
6.169 TFLOPS
13.60 GFLOPS
FP64 (double)
192.8 GFLOPS
Board Design
130W
TDP
90W
300 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
-
Power Connectors
None
Graphics Processor
GK107
GPU Name
GP104
-
GPU Variant
GP104-995-A1
Kepler
Architecture
Pascal
TSMC
Foundry
TSMC
28 nm
Process Size
16 nm
1.27 billion
Transistors
7.2 billion
118 mm²
Die Size
314 mm²
Graphics Features
12 (11_0)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.0
CUDA
6.1
5.1
Shader Model
6.4
