Urgent.News

What's breaking now, across thousands of outlets.

Tech

IBM is building a dual-architecture mainframe chip that will run Arm and Z software on the same cores

The processor was showcased at Hot Chips 2026 and is expected to use 11 IBM Z cores built on a 2-nanometer process. IBM said the cores will operate above 5.7 GHz and support native execution of both z/Architecture and AArch64 instructions. Read Entire Article

IBM is building a dual-architecture mainframe chip that will run Arm and Z software on the same cores

IBM is developing a mainframe chip capable of running both Arm and Z software simultaneously on the same cores, as showcased at Hot Chips 2026. This dual-architecture chip is expected to utilize 11 IBM Z cores built on a 2-nanometer process, with each core able to execute both z/Architecture and AArch64 instructions concurrently.

The processor will include specialized accelerators for AI inference, data processing, compression, cryptography, and sorting. With a large cache system, including a 36 MB private L2 cache, 432 MB virtual L3 cache, and up to 3.5 GB of virtual L4 cache, the chip is designed to keep latency low for large databases and transaction-heavy workloads.

IBM's goal is to combine the reach of the Arm software ecosystem with the scalability, security, and high-availability features of its existing mainframe systems. The company expects the chip to arrive in 2028, potentially becoming a part of the future z18 mainframe family. This move could help IBM maintain its relevance in the mainframe market, which remains critical for many large organizations, particularly in financial services, while also catering to the growing demand for Linux and AI workloads.

Written by urgent.news from TechSpot's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at techspot.com →

More in Tech

Token Forensics: A Self-Hosted Observatory for Every Model Call

Free tokens vanish quietly. A retry loop. A long batch. A forgotten job. A budget gate stops the bleeding. It does not tell you where the blood went. You need a different tool.

  • Token-observatory records every model call
  • Stores metadata in SQLite database
  • Provides dashboard for token usage insights

Web Performance on a Budget: Bundle Size, API Limits, and Database Indexes

The three budgets every web app hits: bundle size, API rate limits, and database index selectivity. Learn the formulas, thresholds, and PR checklist.

  • Web applications have three performance budgets: bundle size, API limits, and database indexes.
  • Exceeding any budget leads to slower performance, errors, or timeouts due to averaging effects.

More from Tuesday 25 August →