NVIDIA CMP 70HX vs NVIDIA Tesla V100 FHHL

Comparison of NVIDIA CMP 70HX with 8 GB GDDR6X and 3,840 cores vs NVIDIA Tesla V100 FHHL with 16 GB HBM2 and 5,120 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA CMP 70HX

NVIDIA CMP 70HX

MI250 MI250
Instinct MI300X Instinct MI300X
RX 7900 XTX RX 7900 XTX

NVIDIA Tesla V100 FHHL

13.4

NVIDIA Tesla V100 FHHL

13.4

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Additional

Memory

Memory Size

8 GB 16 ГБ

Memory Type

GDDR6X HBM2

Memory Bandwidth

608.3 GB/s 827.4 GB/s

Memory Bus Width

256 бит 4,096 бит

ML Performance

FP16 (Half Precision)

10.71 TFLOPS 26.42 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

10.71 TFLOPS 13.21 TFLOPS

FP64 (Double Precision)

0.1674 TFLOPS 6.605 TFLOPS

CUDA Cores

3,840 5,120

RT Cores

30 No

Architecture & Compatibility

GPU Architecture

Ampere Volta

SM (Streaming Multiprocessor)

30 80

PCIe Version

PCIe 1.0 x4 PCIe 3.0 x16

ML Software Support

CUDA Version

🔥 8.6
7.0

Clocks & Performance

Base Clock

1,365 937

Boost Clock

1,395 1,290

Memory Clock

1,188 808

Power Consumption

TDP/TGP

unknown 250 W

Recommended PSU

🔥 -67% 200 W
600 W

Power Connector

1x 12-pin 1x 8-pin

Rendering

Texture Units (TMU)

120 320

ROP

30 No

L2 Cache

4 MB 6 MB

Additional

Slots

Dual-slot Single-slot

Release Date

March 11, 2021 March 27, 2018

Display Outputs

No outputs
No outputs

Renting is cheaper than buying