NVIDIA CMP 30HX vs SPARKLE Arc A310 OmniView

Comparison of NVIDIA CMP 30HX with 6 GB GDDR6 and 1,408 cores vs SPARKLE Arc A310 OmniView with 4 GB GDDR6 and 768 cores.

Loading...

Performance Rating

NVIDIA CMP 30HX outperforms SPARKLE Arc A310 OmniView by 90.0% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA CMP 30HX

4.2

NVIDIA CMP 30HX

4.2
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

SPARKLE Arc A310 OmniView

2.2

SPARKLE Arc A310 OmniView

2.2

Contents:

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

Memory

Memory Size

🔥 +50% 6 ГБ
4 ГБ

Memory Type

GDDR6 GDDR6

Memory Bandwidth

336.0 GB/s 124.0 GB/s

Memory Bus Width

192 бит 64 бит

ML Performance

FP16 (Half Precision)

🔥 +64% 10.05 TFLOPS
6.144 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +64% 5.027 TFLOPS
3.072 TFLOPS

FP64 (Double Precision)

0.1571 TFLOPS
🔥 +389% 0.768 TFLOPS

CUDA Cores

🔥 +83% 1,408
768

RT Cores

No
🔥 6

Architecture & Compatibility

GPU Architecture

Turing Generation 12.7

SM (Streaming Multiprocessor)

🔥 22
No

PCIe Version

PCIe 1.0 x4 PCIe 4.0 x8

ML Software Support

CUDA Version

7.5 No

Clocks & Performance

Base Clock

1,530
🔥 +31% 2,000

Boost Clock

1,785
🔥 +12% 2,000

Memory Clock

1,750
🔥 +11% 1,937

Power Consumption

TDP/TGP

125 W
🔥 -40% 75 W

Recommended PSU

300 W
🔥 -17% 250 W

Power Connector

1x 8-pin None

Rendering

Texture Units (TMU)

🔥 +175% 88
32

ROP

No
🔥 6

L2 Cache

1536 KB
🔥 4 MB

Additional

Slots

Dual-slot Single-slot

Release Date

Feb. 25, 2021 Nov. 18, 2024

Display Outputs

No outputs
4x mini-DisplayPort 2.0
4x HDMI 2.1

Renting is cheaper than buying