home.social

#neoverse — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #neoverse, aggregated by home.social.

  1. #Arm and #Nvidia are #partnering to integrate Arm-based #Neoverse #CPUs with Nvidia’s #GPUs using Nvidia’s #NVLink Fusion technology. This #collaboration will benefit customers, particularly #hyperscalers, who prefer custom infrastructure setups. The partnership highlights Nvidia’s strategy of collaborating with major tech companies to expand its influence in the #AIindustry. cnbc.com/2025/11/17/arm-nvidia #tech #media #news

  2. #Arm and #Nvidia are #partnering to integrate Arm-based #Neoverse #CPUs with Nvidia’s #GPUs using Nvidia’s #NVLink Fusion technology. This #collaboration will benefit customers, particularly #hyperscalers, who prefer custom infrastructure setups. The partnership highlights Nvidia’s strategy of collaborating with major tech companies to expand its influence in the #AIindustry. cnbc.com/2025/11/17/arm-nvidia #tech #media #news

  3. #Arm and #Nvidia are #partnering to integrate Arm-based #Neoverse #CPUs with Nvidia’s #GPUs using Nvidia’s #NVLink Fusion technology. This #collaboration will benefit customers, particularly #hyperscalers, who prefer custom infrastructure setups. The partnership highlights Nvidia’s strategy of collaborating with major tech companies to expand its influence in the #AIindustry. cnbc.com/2025/11/17/arm-nvidia #tech #media #news

  4. #Arm and #Nvidia are #partnering to integrate Arm-based #Neoverse #CPUs with Nvidia’s #GPUs using Nvidia’s #NVLink Fusion technology. This #collaboration will benefit customers, particularly #hyperscalers, who prefer custom infrastructure setups. The partnership highlights Nvidia’s strategy of collaborating with major tech companies to expand its influence in the #AIindustry. cnbc.com/2025/11/17/arm-nvidia #tech #media #news

  5. #Arm and #Nvidia are #partnering to integrate Arm-based #Neoverse #CPUs with Nvidia’s #GPUs using Nvidia’s #NVLink Fusion technology. This #collaboration will benefit customers, particularly #hyperscalers, who prefer custom infrastructure setups. The partnership highlights Nvidia’s strategy of collaborating with major tech companies to expand its influence in the #AIindustry. cnbc.com/2025/11/17/arm-nvidia #tech #media #news

  6. @zygoon @hrw are the #amazon #aws images expecting a particular machine configuration or are they generally #sbsa compliant? The #graviton chips are essentially #neoverse cores underneath and we model them in TCG.

  7. @zygoon @hrw are the #amazon #aws images expecting a particular machine configuration or are they generally #sbsa compliant? The #graviton chips are essentially #neoverse cores underneath and we model them in TCG.

  8. @zygoon @hrw are the #amazon #aws images expecting a particular machine configuration or are they generally #sbsa compliant? The #graviton chips are essentially #neoverse cores underneath and we model them in TCG.

  9. @zygoon @hrw are the #amazon #aws images expecting a particular machine configuration or are they generally #sbsa compliant? The #graviton chips are essentially #neoverse cores underneath and we model them in TCG.

  10. @zygoon @hrw are the #amazon #aws images expecting a particular machine configuration or are they generally #sbsa compliant? The #graviton chips are essentially #neoverse cores underneath and we model them in TCG.

  11. #Arm’s #Neoverse V2, in #AWS’s #Graviton4
    Arm has mastered the complexity of designing a modern out-of-order core over the past few years. #NeoverseV2 is yet another demonstration of that. It takes the solid foundation provided by prior Neoverse V and Cortex X cores, and makes improvements throughout the pipeline. Compared to #AMD and #Intel cores, Neoverse V2 might have a leg up because its design only caters to #servers and #smartphones.
    chipsandcheese.com/2024/07/22/

  12. #Arm’s #Neoverse V2, in #AWS’s #Graviton4
    Arm has mastered the complexity of designing a modern out-of-order core over the past few years. #NeoverseV2 is yet another demonstration of that. It takes the solid foundation provided by prior Neoverse V and Cortex X cores, and makes improvements throughout the pipeline. Compared to #AMD and #Intel cores, Neoverse V2 might have a leg up because its design only caters to #servers and #smartphones.
    chipsandcheese.com/2024/07/22/

  13. ’s V2, in ’s
    Arm has mastered the complexity of designing a modern out-of-order core over the past few years. is yet another demonstration of that. It takes the solid foundation provided by prior Neoverse V and Cortex X cores, and makes improvements throughout the pipeline. Compared to and cores, Neoverse V2 might have a leg up because its design only caters to and .
    chipsandcheese.com/2024/07/22/

  14. #Arm’s #Neoverse V2, in #AWS’s #Graviton4
    Arm has mastered the complexity of designing a modern out-of-order core over the past few years. #NeoverseV2 is yet another demonstration of that. It takes the solid foundation provided by prior Neoverse V and Cortex X cores, and makes improvements throughout the pipeline. Compared to #AMD and #Intel cores, Neoverse V2 might have a leg up because its design only caters to #servers and #smartphones.
    chipsandcheese.com/2024/07/22/

  15. #Arm’s #Neoverse V2, in #AWS’s #Graviton4
    Arm has mastered the complexity of designing a modern out-of-order core over the past few years. #NeoverseV2 is yet another demonstration of that. It takes the solid foundation provided by prior Neoverse V and Cortex X cores, and makes improvements throughout the pipeline. Compared to #AMD and #Intel cores, Neoverse V2 might have a leg up because its design only caters to #servers and #smartphones.
    chipsandcheese.com/2024/07/22/

  16. #GraceHopper, #Nvidia’s Halfway #APU
    Grace Hopper is an attempt to get Nvidia’s CPU efforts into high performance territory. #GH200 bundles a #CPU and #GPU together. The Grace CPU consists of 72 #Neoverse V2 cores running at up to 3.44 GHz, supported by 114 MB of L3 cache. Cores and L3 cache sit on top of Nvidia’s Scalable Coherency Fabric (SCF). SCF is a mesh interconnect, with cores and L3 cache slices attached to mesh stops.
    chipsandcheese.com/2024/07/31/ #HPC

  17. Axion — что нам известно о новом процессоре от Google?

    Создавать собственные процессоры в последнее время стало модным. Компания Apple со своими чипами серии «М» уже уверенно отвоевала заметный рыночный сегмент, Amazon активно использует в составе платформы AWS собственный процессор Graviton, а Microsoft недавно анонсировала Microsoft Cobalt. На протяжении вот уже нескольких лет в том же направлении двигается корпорация Google, в апреле этого года на конференции Next '24 представившая публике собственный процессор под названием Axion. Что это за микросхема, каковы ее возможности и в каких устройствах ее планируется применять? Давайте разбираться.

    habr.com/ru/companies/serversp

    #Axion #Cloud #ARM #VCU #Tensor #Neoverse

  18. Axion — что нам известно о новом процессоре от Google?

    Создавать собственные процессоры в последнее время стало модным. Компания Apple со своими чипами серии «М» уже уверенно отвоевала заметный рыночный сегмент, Amazon активно использует в составе платформы AWS собственный процессор Graviton, а Microsoft недавно анонсировала Microsoft Cobalt. На протяжении вот уже нескольких лет в том же направлении двигается корпорация Google, в апреле этого года на конференции Next '24 представившая публике собственный процессор под названием Axion. Что это за микросхема, каковы ее возможности и в каких устройствах ее планируется применять? Давайте разбираться.

    habr.com/ru/companies/serversp

    #Axion #Cloud #ARM #VCU #Tensor #Neoverse

  19. #Google Announces #Axion #ARM-Based #CPU For The Cloud
    Similar to Amazon AWS and Microsoft Azure spinning their own Arm-based processors for their data centers, #GoogleCloud announced the Google Axion Processors that will be available in the future. The initial Axion processors are built atop an Arm #Neoverse V2 design.
    phoronix.com/news/Google-Cloud

  20. #Google Announces #Axion #ARM-Based #CPU For The Cloud
    Similar to Amazon AWS and Microsoft Azure spinning their own Arm-based processors for their data centers, #GoogleCloud announced the Google Axion Processors that will be available in the future. The initial Axion processors are built atop an Arm #Neoverse V2 design.
    phoronix.com/news/Google-Cloud

  21. February 24, 2024 - Day 420 - NewPlay Review
    Total NewPlays: 456

    Game: Neoverse

    Platform: Steam
    Released: Feb 19, 2020
    Installed: Feb 1, 2024
    Unplayed: 23d
    Playtime: 34m

    Neoverse is a 3D-ish rogue-lite deckbuilder.

    It didn't get off to a good start. There are three main characters, all women. The opening cutscene seemed to be entirely about them engaging in various battles aimed at the male gaze.

    One of the main characters featuring in the game art is a character wearing a skintight silver bodysuit, viewed from behind and below the waistline, with her butt being the focal point.

    As for the game itself? Nowhere near that. It's set in a multiverse, where you and two other characters need to enter universes to fight a series of staged battles to unlock more cards and save the universe(s) through card battles.

    As rogue-lite card battlers go, Neoverse is (just barely):

    3: OK

    #Neoverse #3D #DeckBuilder #CardBattler #Strategy #Roguelite #Gaming #ProjectONG

  22. #ServeTheHome has published some more dazzling deets on the Microsoft Azure Cobalt 100 processor. The processor is using Neoverse N2 cores.

    It's not the highest performing cores, but it's not the weakest of the available server- or cloud-oriented cores either.

    servethehome.com/microsoft-azu

    #ARM #Neoverse #Microsoft #Azure

  23. #AmpereOne with 192 Cores 128x PCIe Gen5 Lanes and DDR5 in 2023
    AmpereOne no longer uses stock #Arm #Neoverse cores. Instead, a custom core designed by #Ampere. It still uses Arm ISA, but it is Ampere’s core. The core features 64KB 4-way L1 data cache per core, 16KB L1 instruction cache per core, and a 2MB L2 cache per core. AmpereOne will cover 136-192 cores, leaving #Altra/#AltraMax to core counts of 128 and below. The cache is doubled. PCIe Gen5 doubles the bandwidth.
    servethehome.com/ampereone-wit

  24. ARM won't be selling its Neoverse V2 chip designs to Chinese companies including Alibaba after determining that US and UK officials probably would probably block sales due to export restrictions imposed on China.

    ft.com/content/257b39c4-f146-4