AWS says it overcame those obstacles with two key innovations: software and custom hardware. The first is a custom routing protocol called Spraypoint, which distributes traffic across large numbers of available paths rather than relying primarily on the shortest path. The second is a passive optical device called ShuffleBox, designed to organize and standardize the immense amount of cabling required to build the network at scale.
According to Amazon, the resulting architecture not only moves data roughly one-third faster than conventional designs but also requires significantly fewer switches and routers. The company says those reductions lower both capital expenditures and operating costs while simultaneously reducing power consumption.
AI models are growing larger and more capable, and so are their user bases. To sustain this growth, hyperscalers have to continue optimizing the entire technology stack. Faster chips remain crucial, but so are advances in cooling, power delivery, storage systems, optical interconnects, and networking. AWS believes RNG is one such advantage. The company rightly considers the achievement of deploying random graph theory at scale, “a breakthrough that will deliver greater reliability and performance for AWS customers, save billions of dollars in hardware, and lower CO2 emissions.”
Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Etiido Uko is a news contributor for Tom's Hardware covering the latest updates in big tech and the PC industry. He is a mechanical engineer and senior technical writer with over nine years of experience in documentation and reporting. He is deeply passionate about all things engineering and technology, and is an expert in gadgets, manufacturing, robotics, automotive, and aerospace. ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-24/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Etiido Uko Social Links Navigation News Contributor Etiido Uko is a news contributor for Tom's Hardware covering the latest updates in big tech and the PC industry. He is a mechanical engineer and senior technical writer with over nine years of experience in documentation and reporting. He is deeply passionate about all things engineering and technology, and is an expert in gadgets, manufacturing, robotics, automotive, and aerospace.
rluker5 I hope somebody who was behind implementing that gets a lot of money for the wealth he helped create. Reply
Blastomonas Jeff will need the savings to replace his rockets 🤪 In all seriousness though, this seems like an impressive and much needed achievement. Considering the numbers of data centres popping up. Reply
Brakheart Blastomonas said: Jeff will need the savings to replace his rockets 🤪 In all seriousness though, this seems like an impressive and much needed achievement. Considering the numbers of data centres popping up. There aren't that many data centers "popping up". In the US at least, there are a few "under construction" (can be from literally just the land being cleared up all the way to actual infrastructure being built) and the rest are either stalled or abandoned (already built but off) because they don't have the necessary power infrastructure to become operational. Reply
cp0x Brakheart said: There aren't that many data centers "popping up". In the US at least, there are a few "under construction" (can be from literally just the land being cleared up all the way to actual infrastructure being built) and the rest are either stalled or abandoned (already built but off) because they don't have the necessary power infrastructure to become operational. There are more than 3000 data centers operating today in the US (and a data center tracking map reveals more than 4200). There are at between 900 and 3000+ additional data centers in various stages of planning and construction in the US. Of those scheduled to come online in 2026, a substantial portion may be facing delays and even cancellation, but the percentage impacted is below 50%. Power infrastructure and availability is one reason, but a larger reason may be that the capacity that already is available has not been used up yet, and the hardware that would be used in these data centers is currently too expensive and/or unavailable. Regardless, the "fat tree" network topology hasn't been in vogue in 20 years. And Amazon itself was experimenting with much more intelligent topologies back in 2011 (IIRC). Reply
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/big-tech/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/big-tech/amazon-unveils-resilient-network-graphs-data-center-network-that-cuts-hardware-by-69-percent-and-boosts-throughput-by-33-percent-now-the-default-for-most-aws-workloads#main
- https://www.tomshardware.com/subscription
- Save up to $1,000 on Dell's elite gaming gear before it's gone — prebuilt PCs to laptops that will change the way you game.
- California Assembly passes 3D printer bill that would criminalize bypassing mandated gun-blocking software
- Epic Games’ Tim Sweeney slams Valve over Steam Deck price hikes — mocks founder Gabe Newell over rising costs of megayachts
- [Daily Due Diligence] AMD AMD
- Kevin O'Leary claims Chinese propaganda is to blame for anti-datacenter backlash, 'hundreds of millions of dollars' being spent to kill US dominance in AI — ind
Informational only. No financial advice. Do your own research.