NVIDIA Tesla K80 vs NVIDIA CMP 100HX-210

GPU Specs Compare

G

NVIDIA Tesla K80

NVIDIA 2014-11
G

NVIDIA CMP 100HX-210

NVIDIA 2020-01

Graphics Card

Release Date
Nov 2014
Jan 2020
Generation
Tesla
Mining GPUs
Type
Professional
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 1.0 x1

Clock Speeds

Base Clock
562 MHz
555 MHz
Boost Clock
824 MHz
1147 MHz
Memory Clock
1253 MHz
810 MHz

Memory

Memory Size
12GB
16GB
Memory Type
GDDR5
HBM2
Memory Bus
384bit
4096bit
Bandwidth
240.6GB/s
829.4GB/s

Render Config

Shading Units
2496
5120
TMUs
208
320
ROPs
48
128
L1 Cache
16 KB (per SMX)
96 KB (per SM)
L2 Cache
1536 KB
6 MB
SM Count
-
80
Tensor Cores
-
640

Theoretical Performance

Pixel Rate
42.85 GPixel/s
146.8 GPixel/s
Texture Rate
171.4 GTexel/s
367.0 GTexel/s
FP32 (float)
4.113 TFLOPS
11.75 TFLOPS
FP64 (double)
1371 GFLOPS
5.873 TFLOPS
FP16 (half)
-
23.49 TFLOPS

Graphics Processor

GPU Name
GK210
GV100
GPU Variant
GK210-885-A1
-
Architecture
Kepler 2.0
Volta
Foundry
TSMC
TSMC
Process Size
28 nm
12 nm
Transistors
7.1 billion
21.1 billion
Die Size
561 mm²
815 mm²

Board Design

TDP
300W
250W
Suggested PSU
700 W
600 W
Outputs
No outputs
No outputs
Power Connectors
1x 8-pin
1x 6-pin + 1x 8-pin

Graphics Features

DirectX
12 (11_1)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.1
1.3
CUDA
3.7
7.0
Shader Model
5.1
6.8