Tech News
Back to home
Technology

Tests show $30,000 AI GPUs are terrible password crackers — RTX 5090 gaming GPU outperforms Nvidia H200 and AMD MI300X

Source

Tom's Hardware

Published

TL;DR

AI Generated

Tests conducted by Specops revealed that expensive $30,000 AI GPUs like Nvidia's H200 and AMD's MI300X performed poorly compared to consumer graphics cards like Nvidia's RTX 5090 in password cracking. Despite the significant price difference, the RTX 5090 outperformed the other GPUs by 20% over the MI300X and 63.7% over the H200 on average. The RTX 5090 excelled due to its design with more INT32 cores, which are crucial for password cracking, while the AI GPUs prioritize different instructions for their machine learning tasks. This study underscores that consumer desktop GPUs remain the most efficient for password cracking tasks.

Read Full Article

Similar Articles

Pragmata PC performance tested: 18 GPUs take us to the Moon

Pragmata PC performance tested: 18 GPUs take us to the Moon

The article discusses the performance testing of the game Pragmata on PC across 18 GPUs. The game features a sci-fi shooter premise set in a lunar facility and incorporates strategic gunplay and puzzle-solving mechanics. Pragmata utilizes cutting-edge technologies like DLSS for realistic lighting effects, with Nvidia heavily promoting the game. However, the path tracing mode is exclusive to GeForce cards, disappointing Radeon users. The article also delves into image quality comparisons and notes, highlighting the benefits and shortcomings of different rendering modes like pure rasterization, RT, and path tracing.

Tom's Hardware•
Bain Capital's data center unit removes disgraced tenant suspected of smuggling Nvidia GPUs to China — Megaspeed previously alleged to have spent roughly $2 billion on AI processors for illicit distribution

Bain Capital's data center unit removes disgraced tenant suspected of smuggling Nvidia GPUs to China — Megaspeed previously alleged to have spent roughly $2 billion on AI processors for illicit distribution

Bain Capital's data center unit, Bridge Data Centers, has terminated its contract with Megaspeed International in Malaysia amid suspicions of smuggling Nvidia AI accelerators to China. The move reallocates power capacity to cloud provider Zenplayer, indicating a shift away from companies under investigation for illegal activities. This decision aligns with the heightened scrutiny of high-end computing hardware flows between the U.S. and China. As Bridge Data Centers seeks additional capital for expansion, maintaining compliant and stable tenants becomes crucial for securing funding in the competitive regional data center market.

Tom's Hardware•
Corsair's Strix Halo AI Workstation 300 gets even more expensive amid the RAMpocalypse — Ryzen AI Max 395+ flagship now sits at $3,399

Corsair's Strix Halo AI Workstation 300 gets even more expensive amid the RAMpocalypse — Ryzen AI Max 395+ flagship now sits at $3,399

Corsair's Strix Halo AI Workstation 300 prices have surged, with the Ryzen AI Max 395+ model now at $3,399 due to the ongoing RAMpocalypse. The top-end variant with 128 GB of RAM and 4 TB storage has seen a significant price increase. The escalating costs are attributed to the current component shortage exacerbated by geopolitical tensions. Despite the price hikes, these figures are in line with market rates for similar high-end systems. Other models like the Beelink GTR9 Pro and GMKtec Evo X2 offer comparable specs but at slightly lower prices.

Tom's Hardware•
SemiEngineering

State Of The Market For Edge Silicon

The rapid growth of data and AI is reshaping chip architecture, particularly at the edge where power, latency, and performance are crucial metrics that vary across applications and workloads. Steve Roddy from Quadric emphasizes the importance of balancing performance, efficiency, and flexibility in chip design for diverse applications. Understanding what distinguishes one chip from another and optimizing the mix of processing elements are key considerations in the evolving market for edge silicon.

SemiEngineering•

We use cookies

We use cookies to ensure you get the best experience on our website. For more information on how we use cookies, please see our cookie policy.