NVIDIA Tesla M2090 vs SPARKLE Arc A310 OmniView

Comparison of NVIDIA Tesla M2090 with 6 GB GDDR5 and 512 cores vs SPARKLE Arc A310 OmniView with 4 GB GDDR6 and 768 cores.

Loading...

Performance Rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA Tesla M2090

NVIDIA Tesla M2090

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

6 GB
🔥 4 ГБ

Memory Type

GDDR5 GDDR6

Memory Bandwidth

177.4 GB/s 124.0 GB/s

Memory Bus Width

384 бит 64 бит

ML Performance

FP16 (Half Precision)

No
🔥 6.144 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

1.3322 TFLOPS
🔥 +131% 3.072 TFLOPS

FP64 (Double Precision)

0.6661 TFLOPS
🔥 +15% 0.768 TFLOPS

CUDA Cores

512
🔥 +50% 768

RT Cores

No
🔥 6

Architecture & Compatibility

GPU Architecture

Fermi 2.0 Generation 12.7

SM (Streaming Multiprocessor)

16 No

PCIe Version

PCIe 2.0 x16 PCIe 4.0 x8

ML Software Support

CUDA Version

2.0 No

Clocks & Performance

Base Clock

No
🔥 2,000

Boost Clock

No
🔥 2,000

Memory Clock

924
🔥 +110% 1,937

Power Consumption

TDP/TGP

250 W
🔥 -70% 75 W

Recommended PSU

600 W
🔥 -58% 250 W

Power Connector

1x 6-pin + 1x 8-pin None

Rendering

Texture Units (TMU)

64
🔥 32

ROP

No
🔥 6

L2 Cache

768 KB
🔥 4 MB

Additional

Slots

Dual-slot Single-slot

Release Date

July 25, 2011 Nov. 18, 2024

Display Outputs

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

Renting is cheaper than buying