NVIDIA Tesla S1075 vs SPARKLE Arc A310 OmniView

Comparison of NVIDIA Tesla S1075 with 4 GB GDDR3 and 240 cores vs SPARKLE Arc A310 OmniView with 4 GB GDDR6 and 768 cores.

Loading...

Performance Rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA Tesla S1075

NVIDIA Tesla S1075

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

4 GB ×4 (16 ГБ)
🔥 4 ГБ

Memory Type

GDDR3 GDDR6

Memory Bandwidth

102.4 GB/s ×4 (409.6 GB/s) 124.0 GB/s

Memory Bus Width

512 бит ×4 (2048 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)

0.6221 TFLOPS
🔥 +394% 3.072 TFLOPS

FP64 (Double Precision)

0.0778 TFLOPS
🔥 +887% 0.768 TFLOPS

CUDA Cores

240 ×4 (960)
🔥 +220% 768

RT Cores

No
🔥 6

Architecture & Compatibility

GPU Architecture

Tesla 2.0 Generation 12.7

SM (Streaming Multiprocessor)

30 No

PCIe Version

PCIe 2.0 x16 PCIe 4.0 x8

ML Software Support

CUDA Version

1.3 No

Clocks & Performance

Base Clock

No
🔥 2,000

Boost Clock

No
🔥 2,000

Memory Clock

800
🔥 +142% 1,937

Power Consumption

TDP/TGP

800 W
🔥 -91% 75 W

Recommended PSU

1200 W
🔥 -79% 250 W

Power Connector

No None

Rendering

Texture Units (TMU)

80 ×4 (320)
🔥 32

ROP

No
🔥 6

L2 Cache

256 KB
🔥 4 MB

Additional

Slots

Dual-slot Single-slot

Release Date

June 1, 2008 Nov. 18, 2024

Display Outputs

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

Renting is cheaper than buying