NVIDIA Tesla V100 FHHL vs NVIDIA CMP 50HX

GPU Specs Compare

G

NVIDIA Tesla V100 FHHL

NVIDIA 2018-03
G

NVIDIA CMP 50HX

NVIDIA 2021-06

Graphics Card

Release Date
Mar 2018
Jun 2021
Generation
Tesla
Mining GPUs
Type
Professional
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 1.0 x4

Clock Speeds

Base Clock
937 MHz
1350 MHz
Boost Clock
1290 MHz
1545 MHz
Memory Clock
810 MHz
1750 MHz

Memory

Memory Size
16GB
10GB
Memory Type
HBM2
GDDR6
Memory Bus
4096bit
320bit
Bandwidth
829.4GB/s
560.0GB/s

Render Config

SM Count
80
56
Shading Units
5120
3584
TMUs
320
192
ROPs
128
80
Tensor Cores
640
448
L1 Cache
128 KB (per SM)
64 KB (per SM)
L2 Cache
6 MB
5 MB
RT Cores
-
56

Theoretical Performance

Pixel Rate
165.1 GPixel/s
123.6 GPixel/s
Texture Rate
412.8 GTexel/s
296.6 GTexel/s
FP16 (half)
26.42 TFLOPS
22.15 TFLOPS
FP32 (float)
13.21 TFLOPS
11.07 TFLOPS
FP64 (double)
6.605 TFLOPS
346.1 GFLOPS

Graphics Processor

GPU Name
GV100
TU102
Architecture
Volta
Turing
Foundry
TSMC
TSMC
Process Size
12 nm
12 nm
Transistors
21.1 billion
18.6 billion
Die Size
815 mm²
754 mm²
GPU Variant
-
TU102-100-A1

Board Design

TDP
250W
250W
Suggested PSU
600 W
600 W
Outputs
No outputs
No outputs
Power Connectors
1x 8-pin
2x 8-pin

Graphics Features

DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.3
CUDA
7.0
7.5
Shader Model
6.6
6.8