'/%3e%3cpath%20d='M50.3943%2022.237V39.5876H43.5185V22.7481C43.5185%2019.2029%2042.0411%2017.3949%2039.036%2017.3949C35.7325%2017.3949%2034.0778%2019.5338%2034.0778%2023.7585V32.9759H27.2434V23.7585C27.2434%2019.5338%2025.5857%2017.3949%2022.2822%2017.3949C19.2949%2017.3949%2017.8027%2019.2029%2017.8027%2022.7481V39.5876H10.9298V22.237C10.9298%2018.6918%2011.835%2015.8754%2013.6453%2013.7877C15.5128%2011.7049%2017.9623%2010.6355%2021.0028%2010.6355C24.522%2010.6355%2027.1813%2011.9885%2028.9542%2014.6917L30.665%2017.5633L32.3788%2014.6917C34.1517%2011.9885%2036.811%2010.6355%2040.3243%2010.6355C43.3619%2010.6355%2045.8114%2011.7049%2047.6847%2013.7877C49.4931%2015.8734%2050.3963%2018.6899%2050.3943%2022.237Z'%20fill='white'/%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_89_8'%20x1='30.5'%20y1='0'%20x2='30.5'%20y2='65'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20stop-color='%236364FF'/%3e%3cstop%20offset='1'%20stop-color='%23563ACC'/%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e)
Asterfusion<p>🚀 RoCE vs. InfiniBand: Asterfusion 800G Switch in AI Networking<br>In the realm of AI data centers, the debate between RoCE and InfiniBand is intensifying. Recent evaluations of Asterfusion's 800G RoCE switches reveal:</p><p>Lower P90 Inference Latency: Enhanced performance in AI inference tasks.</p><p>Higher Token Generation Rate: Improved throughput for large-scale AI models.</p><p>Cost Efficiency: Comparable performance to InfiniBand at a reduced cost.</p><p>These findings suggest that RoCE, especially when implemented on Asterfusion's 800G switches, offers a compelling alternative for AI networking infrastructure.</p><p>📖 Dive deeper into the analysis:<br>🔗 RoCE Beats InfiniBand? Asterfusion 800G Switch for AI Networking</p><p><a href="https://techhub.social/tags/RoCE" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RoCE</span></a> <a href="https://techhub.social/tags/InfiniBand" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>InfiniBand</span></a> <a href="https://techhub.social/tags/AIInfrastructure" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIInfrastructure</span></a> <a href="https://techhub.social/tags/800GSwitch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>800GSwitch</span></a> <a href="https://techhub.social/tags/Asterfusion" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Asterfusion</span></a> <a href="https://techhub.social/tags/DataCenterNetworking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataCenterNetworking</span></a> <a href="https://techhub.social/tags/HighPerformanceComputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HighPerformanceComputing</span></a> <a href="https://techhub.social/tags/CloudSwith" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CloudSwith</span></a></p>
101010.pl is one of the many independent Mastodon servers you can use to participate in the fediverse.
101010.pl czyli najstarszy polski serwer Mastodon. Posiadamy wpisy do 2048 znaków.
Administered by:
Server stats:
506active users
101010.pl: About · Status · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.0-beta.1
#Datacenternetworking
1 post · 1 participant · 1 post today
Asterfusion<p>⚙️ Inside Asterfusion’s 800G AI Switch Architecture</p><p>AI workloads demand ultra-high bandwidth and low latency. Asterfusion’s 800G switch architecture delivers both—with a focus on open hardware, precision timing, and energy-efficient design.</p><p>In this post, we cover:<br>🔸 Why 800G switching is critical for next-gen AI clusters<br>🔸 How Asterfusion’s design balances speed, scale, and sustainability<br>🔸 The use of Broadcom Jericho3-AI & Tomahawk5 chips<br>🔸 Why their disaggregated model matters for AI networking</p><p>🔗 Explore the full breakdown: <a href="https://cloudswit.ch/blogs/asterfusions-800g-ai-switch-architecture" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">cloudswit.ch/blogs/asterfusion</span><span class="invisible">s-800g-ai-switch-architecture</span></a></p><p><a href="https://techhub.social/tags/800G" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>800G</span></a> <a href="https://techhub.social/tags/AISwitch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AISwitch</span></a> <a href="https://techhub.social/tags/DataCenterNetworking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataCenterNetworking</span></a> <a href="https://techhub.social/tags/Asterfusion" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Asterfusion</span></a> <a href="https://techhub.social/tags/Broadcom" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Broadcom</span></a> <a href="https://techhub.social/tags/OpenNetworking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenNetworking</span></a> <a href="https://techhub.social/tags/HyperscaleAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HyperscaleAI</span></a> <a href="https://techhub.social/tags/NetworkArchitecture" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NetworkArchitecture</span></a></p>
ExploreLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload