# a64fx

Published articles for a64fx.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Three HPC Gurus Ask: Do We Still Need GPUs?

DevFeed: [Three HPC Gurus Ask: Do We Still Need GPUs?](<https://devfeed.tech/articles/three-hpc-gurus-ask-do-we-still-need-gpus-47979.md>)

Original publisher: [Read original article](<https://www.nextplatform.com/compute/2026/06/30/three-hpc-gurus-ask-do-we-still-need-gpus/5264552>)

Author: Timothy Prickett Morgan

Published: 2026-06-30T16:13:31Z

Content type: article

Language: en

Sources: [The Next Platform: In-depth coverage of high end computing](<https://devfeed.tech/sources/the-next-platform-in-depth-coverage-of-high-end-computing.md>)

Topics: [Computing](<https://devfeed.tech/topics/computing.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [a64fx](<https://devfeed.tech/tags/a64fx.md>), [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arm](<https://devfeed.tech/tags/arm.md>), [compute](<https://devfeed.tech/tags/compute.md>), [computing](<https://devfeed.tech/tags/computing.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [fugaku](<https://devfeed.tech/tags/fugaku.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hpc](<https://devfeed.tech/tags/hpc.md>), [lineshine](<https://devfeed.tech/tags/lineshine.md>), [lx2](<https://devfeed.tech/tags/lx2.md>), [ml](<https://devfeed.tech/tags/ml.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [processors](<https://devfeed.tech/tags/processors.md>), [supercomputer](<https://devfeed.tech/tags/supercomputer.md>)

### AI overview

The article examines whether GPUs are still necessary for AI training and high-performance computing as CPUs gain vector and matrix engines, mixed-precision support, high-bandwidth memory, and integrated interconnects. It discusses a forthcoming paper comparing all-CPU supercomputers including Fugaku and LineShine.

### Source excerpt

Yes, that simple question is, in the modern Nvidia world that has come to dominate AI training and t ...