- Google is moving thousands of internal workloads from x86 to Arm CPUs
- The company created an artificial intelligence tool called CogniPort to automate migration fixes.
- Google engineers spent months fixing test flaws related to x86 infrastructure
Google has embarked on a hugely ambitious project to migrate all of its internal workloads from x86 to Arm-based CPUs, a process that involves one of the largest hardware transitions ever attempted by a global technology company.
The effort aims to enable its systems to run efficiently on both x86 processors and its custom Axion silicon.
With approximately 30,000 apps already converted, Google continues to rely heavily on automation to handle the huge code base involved in the process.
Warehouse-scale workload transfer
In a blog post describing the project, Parthasarathy Ranganathan, a Google engineer, and Wolff Dobson, a developer relations engineer, noted that the migration began with some of the company’s most critical systems, including F1, Spanner, and Bigtable.
Initially, teams relied on conventional software development practices with dedicated engineers and weekly coordination meetings.
Although they expected major architectural hurdles, modern compilers and debugging tools helped reduce many of the anticipated problems.
However, a large amount of time was still spent fine-tuning thousands of tests that were closely tied to Google’s existing x86-based infrastructure.
Engineers also faced challenges updating legacy build and release systems, managing production deployments, and ensuring stability in mission-critical environments.
To speed up the transition, Google developed a new artificial intelligence tool known as “CogniPort.”
The system works by analyzing build and test errors and then attempting to automatically fix them, particularly in cases where a specific Arm library or binary fails to compile.
CogniPort has shown a success rate of around 30%, with better performance in handling test fixes, data handling inconsistencies, and conditional platform code.
While not perfect, the tool represents a key step in enabling warehouse-scale automation and reducing the human workload required for such conversions.
The long-term motivation behind Google’s decision lies in performance and efficiency: its Axion-powered Arm servers are said to offer up to 65% better price-performance and can be up to 60% more energy efficient than comparable x86 instances.
This change could result in fewer x86 processors in Google’s vast data infrastructure, potentially transforming the makeup of its internal computing clusters.
For now, major apps like YouTube, Gmail, and BigQuery already work on both x86 and Arm-based systems.
As Google migrates the remaining 70,000 packages, questions remain about whether AI tools can handle such scale without adding new maintenance challenges across its systems.
Through The Registry
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
