Deep Analysis
-
PremiumRapidus reportedly struggles to produce working SRAM on its 2nm node, putting 2027 mass production at riskJapan's semiconductor startup has demonstrated functioning GAA transistors, but integrating them into working memory cells appears to be a considerably greater challenge.
By Anton Shilov Published -
-
PremiumVAST says petabyte SSDs will outgrow today’s parallel file system RAIDVAST Data’s Glenn Lockwood told SC26 that petabyte SSDs need global declustering plus extra parity to avoid data loss.
By Shane Downing Published -
PremiumPhison details SSD with a built-in NPU and 64GB of memory that supports AI frameworks on the drivePhison showed a computational-storage SSD with an NPU and 64GB of memory, plus Mixed Media pSLC and QLC drives, at SC26.
By Shane Downing Published
-
-
-
PremiumPower and cooling limits force AI clusters with 100,000+ accelerators to use multiple data centersFaster GPUs are no longer enough as power constraints, network congestion, and communication overhead force the industry to rethink how massive AI systems are built.
By Anton Shilov Last updated -
PremiumSilicon Motion demos SM8466 PCIe 6.0 SSD controller, expected to ship by 2028 — controller boasts improved quality of service, samples imminentSilicon Motion's SM8466 has finally taped out and is set to enter the market in 2027-2028.
By Anton Shilov Published -
PremiumIntel Diamond Rapids shows signs of life in SC26 demo running live serverIntel’s next-gen Xeon Diamond Rapids CPUs appeared at two booths during SC26, one of which featured a running server, but neither were directly from Intel.
By Jake Roach Published -
PremiumNvidia says it’s ‘absurd’ to assume it predicted the agentic moment during Vera’s developmentIt turns out Nvidia doesn’t have a crystal ball, either.
By Jake Roach Published -
PremiumNvidia claims its Vera CPU can gain up to 39% performance boost via software optimization at SC26 — architectural fine-tuning is needed to fully unleash custom Olympus coresVera can speed up old code out of the box, but there's more performance to unlock
By Anton Shilov Published -
PremiumAMD attacks Nvidia's FP64 emulation at SC26, touts native double-precision on Instinct MI430XAMD says Ozaki FP64 emulation is no replacement for the real thing when it's needed.
By Jeffrey Kampman Published -
SemiconductorsSamsung, SK hynix, and Micron form unlikely alliance to standardize robot charging as chipmakers push toward unmanned fabsSamsung, SK hynix, and Micron are working to standardize charging infrastructure for mobile fab robot batteries to simplify automation and help fabs deploy larger mixed robotic fleets.
By Etiido Uko Published -
SupercomputersChina retains fastest supercomputer in the world crown as AI data centers soak up new hardwareThe Top 500 list records the fewest new entrants in its history amid a massive shift in compute infrastructure investments towards AI factories.
By Anton Shilov Published -
PremiumResearchers ‘recognize that AI will never replace HPC,’ says AMD executive — high-precision workloads will ‘exist for a very long time’ even as AI usage expandsThe emergence of AI has seemingly posed a threat to high-precision FP64 computation, but AMD doesn't think the HPC world is moving away from those complex calculations in the wake of AI.
By Jake Roach Published
-