IBM and Nvidia move quantum processors into supercomputing workflows
New Slurm integration, a Fermilab co-design platform and GPU-accelerated error-correction tools aim to make quantum processors usable inside established HPC environments.
AI / NEWS BRIEF
TPU 8tx targets confidential AI workloads, while TPU 8i Max doubles compute and memory resources per package for long-context inference. Both are new systems built around existing eighth-generation silicon.
Google has expanded its eighth-generation TPU portfolio with TPU 8tx and TPU 8i Max. The company describes them as systems that reconfigure packaging, processors, networking and memory around its existing TPU 8t and 8i silicon. Independent coverage from Reuters and Data Center Dynamics confirmed the distinction. Google says 8tx is built for confidential inference and small-scale training, while 8i Max targets workloads with very long context windows.
TPU 8tx pairs TPU 8t silicon with fifth-generation AMD EPYC hosts and hardware-level confidential computing intended to protect data and model weights while they are processed. Google claims up to twice the latency performance of TPU 8t with a near-zero performance penalty. TPU 8i Max places two TPU 8i chips in one package, giving it twice the compute, SRAM and high-bandwidth-memory bandwidth of 8i within the same rack footprint. Those performance figures are Google-reported rather than independently benchmarked.
The launch shows accelerator competition moving beyond peak chip specifications toward systems tailored for regulated data and memory-heavy agent workloads. It also widens Google Cloud's alternative to Nvidia-based infrastructure without requiring an entirely new silicon design. The practical value will depend on availability, pricing, software compatibility and independently measured performance; Google did not provide those details in the launch post, so the announcement should not be read as proof of lower total cost or superior application performance.
New Slurm integration, a Fermilab co-design platform and GPU-accelerated error-correction tools aim to make quantum processors usable inside established HPC environments.
OpenAI has released healthcare-focused computer-use capabilities across its API and clinical products, with configurable approvals, audit logs and new performance results that remain provider-reported.