NVIDIA A100 PCIe 80 GB vs NVIDIA CMP 90HX

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA CMP 90HX with 10 GB GDDR6X and 6,400 cores.

Loading...

Performance Rating

NVIDIA A100 PCIe 80 GB outperforms NVIDIA CMP 90HX by 103.9% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA A100 PCIe 80 GB

25.6

NVIDIA A100 PCIe 80 GB

25.6
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA CMP 90HX

12.6

NVIDIA CMP 90HX

12.6

Contents:

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

Memory

Memory Size

🔥 +700% 80 ГБ
10 ГБ

Memory Type

HBM2e GDDR6X

Memory Bandwidth

🔥 1.94 TB/s
760.3 GB/s

Memory Bus Width

5,120 бит 320 бит

ML Performance

FP16 (Half Precision)

🔥 +256% 77.97 TFLOPS
21.89 TFLOPS

BF16 (Brain Float)

🔥 311.84 TFLOPS
No

TF32 (TensorFloat)

🔥 155.92
No

Compute Power

FP32 (Single Precision)

19.49 TFLOPS
🔥 +12% 21.89 TFLOPS

FP64 (Double Precision)

🔥 +2,750% 9.746 TFLOPS
0.342 TFLOPS

CUDA Cores

🔥 +8% 6,912
6,400

RT Cores

No
🔥 50

Architecture & Compatibility

GPU Architecture

Ampere Ampere

SM (Streaming Multiprocessor)

🔥 +116% 108
50

PCIe Version

PCIe 4.0 x16 PCIe 1.0 x4

ML Software Support

CUDA Version

8.0
🔥 8.6

Clocks & Performance

Base Clock

1,065
🔥 +41% 1,500

Boost Clock

1,410
🔥 +21% 1,710

Memory Clock

🔥 +27% 1,512
1,188

Power Consumption

TDP/TGP

🔥 -6% 300 W
320 W

Recommended PSU

700 W 700 W

Power Connector

8-pin EPS 2x 8-pin

Rendering

Texture Units (TMU)

🔥 +116% 432
200

ROP

No
🔥 50

L2 Cache

🔥 +1,500% 80 MB
5 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

June 28, 2021 July 28, 2021

Display Outputs

No outputs
No outputs

Renting is cheaper than buying