Episodi

  • Ep 26: Second Arizona fab volume production begins third-quarter twenty twenty-seven, advancing US…

    Ep 26: Second Arizona fab volume production begins third-quarter twenty twenty-seven, advancing US…
    Oct 17 2026
    AI Chips & Data Centres Daily Second Arizona fab volume production begins third-quarter twenty twenty-seven, advancing US three-nanometer supply. What You Need to Know: TSMC's second Arizona fab is slated for volume production in the third quarter of 2027, slightly ahead of the previous schedule, which moves US three-nanometer supply forward. Chairman and CEO C.C. Wei said on the October 15 call that the shell is built and tools are moving in. ... Sources: azbigmedia.com · hpcwire.com · sammyguru.com · techpowerup.com AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production. If this episode was useful, a rating or a short review on Apple Podcasts or Spotify is how the next listener finds the show — and following it in your app means the next episode is there when you are. 📝 Full show notes, transcript & sources: read the episode page 🌐 Part of the Nerra Network — explore every show at nerranetwork.com.
    Mostra di più Mostra meno
    10 min
  • Ep 25: Taiwan plans a Texas supplier park worth up to four billion dollars while tightening AI…

    Ep 25: Taiwan plans a Texas supplier park worth up to four billion dollars while tightening AI…
    Oct 16 2026
    AI Chips & Data Centres Daily Taiwan plans a Texas supplier park worth up to four billion dollars while tightening AI-chip export rules. What You Need to Know: Taiwan’s economics minister says the government plans a Texas industrial park worth up to four billion dollars for chip suppliers, in the same interview that sets criminal penalties for restricted AI-chip exports to China. On the show floor, an open AMD Helios switch tray shows why 224G in-rack copper still needs retimers. ... Sources: asiae.co.kr · techpowerup.com · nvidianews.nvidia.com · datacenterknowledge.com · datacenterdynamics.com · executivegov.com · datacenters.economictimes.indiatimes.com AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production. If this episode was useful, a rating or a short review on Apple Podcasts or Spotify is how the next listener finds the show — and following it in your app means the next episode is there when you are. 📝 Full show notes, transcript & sources: read the episode page 🌐 Part of the Nerra Network — explore every show at nerranetwork.com.
    Mostra di più Mostra meno
    8 min
  • Ep 24: Twenty-four hours after install, a photonics quantum computer was already running customer…

    Ep 24: Twenty-four hours after install, a photonics quantum computer was already running customer…
    Oct 15 2026
    AI Chips & Data Centres Daily Twenty-four hours after install, a photonics quantum computer was already running customer work in London. What You Need to Know: Orca Computing's PT-3 photonics system was installed and operational within twenty-four hours at Digital Realty's LHR19 in London and is already powering two projects. TSMC followed a sixth record quarter with a fourth-quarter revenue guide of $52.3 billion to $54.3 billion. ... Sources: datacenterdynamics.com · semiengineering.com · tikr.com · startupfortune.com · finance.yahoo.com · theinformation.com AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production. If this episode was useful, a rating or a short review on Apple Podcasts or Spotify is how the next listener finds the show — and following it in your app means the next episode is there when you are. 📝 Full show notes, transcript & sources: read the episode page 🌐 Part of the Nerra Network — explore every show at nerranetwork.com.
    Mostra di più Mostra meno
    7 min
  • Ep 23: Twenty times more AI compute by 2030 still stalls if memory cannot feed it.

    Ep 23: Twenty times more AI compute by 2030 still stalls if memory cannot feed it.
    Oct 14 2026
    AI Chips & Data Centres Daily Twenty times more AI compute by 2030 still stalls if memory cannot feed it. What You Need to Know: SK hynix told SEDEX 2026 that AI-infrastructure compute demand could reach about 20 times this year’s level by 2030, and that HBM alone will not hold the inference working set. The company is pushing High Bandwidth Flash and 3D-stacked DRAM as new tiers between today’s HBM and SSD. ... Sources: mk.co.kr · semiengineering.com · hpcwire.com · nvidianews.nvidia.com · blogs.nvidia.com · eetimes.com · tradingkey.com · finance.yahoo.com AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production. If this episode was useful, a rating or a short review on Apple Podcasts or Spotify is how the next listener finds the show — and following it in your app means the next episode is there when you are. 📝 Full show notes, transcript & sources: read the episode page 🌐 Part of the Nerra Network — explore every show at nerranetwork.com.
    Mostra di più Mostra meno
    10 min
  • Ep 22: Maia 300's memory bandwidth rises two and a half times, so inference stops waiting on…

    Ep 22: Maia 300's memory bandwidth rises two and a half times, so inference stops waiting on…
    Oct 13 2026
    AI Chips & Data Centres Daily Maia 300's memory bandwidth rises two and a half times, so inference stops waiting on compute. What You Need to Know: Maia 300's memory bandwidth rises two and a half times versus Maia 200, to 18 terabytes per second, while FP4 compute rises about 37 percent. Microsoft says production deployments begin in 2027 and that it will scale Maia to multi-gigawatt deployments as its primary inference system. ... Sources: blogs.microsoft.com · globaltimes.cn · semiengineering.com · blogs.nvidia.com · asia.nikkei.com · semiconductor-digest.com · x.com AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production. If this episode was useful, a rating or a short review on Apple Podcasts or Spotify is how the next listener finds the show — and following it in your app means the next episode is there when you are. 📝 Full show notes, transcript & sources: read the episode page 🌐 Part of the Nerra Network — explore every show at nerranetwork.com.
    Mostra di più Mostra meno
    8 min
  • Ep 21: Seven Virginia sites hold one thousand eighty-five megawatts, but Ohio's bigger map emits…

    Ep 21: Seven Virginia sites hold one thousand eighty-five megawatts, but Ohio's bigger map emits…
    Oct 12 2026
    AI Chips & Data Centres Daily Seven Virginia sites hold one thousand eighty-five megawatts, but Ohio's bigger map emits twice the carbon. What You Need to Know: TRG DataCenters' August 2026 ranking scores Virginia at 100 on seven mapped AI sites totaling 1,085 megawatts, while Ohio's larger mapped fleet is tied to roughly twice the annual CO2. Ohio, Tennessee, Georgia and Texas follow on the same 24-state score. ... Sources: datacenterknowledge.com · semiengineering.com · finance.yahoo.com · semiconductor-digest.com · tradingview.com · eetimes.com AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production. If this episode was useful, a rating or a short review on Apple Podcasts or Spotify is how the next listener finds the show — and following it in your app means the next episode is there when you are. 📝 Full show notes, transcript & sources: read the episode page 🌐 Part of the Nerra Network — explore every show at nerranetwork.com.
    Mostra di più Mostra meno
    8 min
  • Ep 20: A two-point-five-billion-dollar Nvidia-server diversion now has one guilty plea.

    Ep 20: A two-point-five-billion-dollar Nvidia-server diversion now has one guilty plea.
    Oct 11 2026
    AI Chips & Data Centres Daily A two-point-five-billion-dollar Nvidia-server diversion now has one guilty plea. What You Need to Know: A two-point-five-billion-dollar Nvidia-server diversion now has one guilty plea. Broker Ting-Wei Sun admitted the export case; Super Micro co-founder Wally Liaw still faces trial on November 2. ... Sources: tomshardware.com · ad-hoc-news.de · datacenterdynamics.com · servethehome.com AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production. If this episode was useful, a rating or a short review on Apple Podcasts or Spotify is how the next listener finds the show — and following it in your app means the next episode is there when you are. 📝 Full show notes, transcript & sources: read the episode page 🌐 Part of the Nerra Network — explore every show at nerranetwork.com.
    Mostra di più Mostra meno
    7 min
  • Ep 19: Black Hills will build 564 megawatts of gas in Cheyenne for Google's data centre.

    Ep 19: Black Hills will build 564 megawatts of gas in Cheyenne for Google's data centre.
    Oct 10 2026
    AI Chips & Data Centres Daily Black Hills will build 564 megawatts of gas in Cheyenne for Google's data centre. What You Need to Know: Black Hills will build 564 megawatts of gas-fired generation in Cheyenne, Wyoming, for Google's planned data centre, inside a resource mix it puts at about 2.7 gigawatts. ... Sources: power-eng.com · finance.biggo.com · eetimes.com · semiconductor-digest.com · datacenterdynamics.com · datacenterknowledge.com · hpcwire.com AI Disclosure: This podcast is curated by Patrick but uses AI-generated voice synthesis for audio production. If this episode was useful, a rating or a short review on Apple Podcasts or Spotify is how the next listener finds the show — and following it in your app means the next episode is there when you are. 📝 Full show notes, transcript & sources: read the episode page 🌐 Part of the Nerra Network — explore every show at nerranetwork.com.
    Mostra di più Mostra meno
    8 min