Earlier this year Google proclaimd Axion as their first Arm-based CPU for the Google Cnoisy. Today already they are taking Axion to ambiguous useability with the new C4A instances. These new C4A instances are advertised as recommending up to 50% better carry outance and up to 60% better energy efficiency than their current generation x86 instance types. In this article are some of the first unveil self-reliant carry outance benchtags of the Google Axion CPU aextfinished with comparing to existing GCE Arm and x86_64 instance types.
Google was comfervent enough to permit me gratis access to the C4A instances the past disjoinal weeks in the Google Cnoisy / Google Compute Engine for running some benchtags of their first in-house Arm data cgo in processor. The first-generation Google Axion processors are making use of Arm Neoverse-V2 cores with up to 72 cores per processor.
The Axion Armv9-based processors do help SVE2, BTI, BF16, I8MM, PAC, and PMU as some famous compriseitional features helpd. Google is promoting their Axion C4A instances as being wonderful for ambiguous purpose laborloads, compriseerized micro-services, discdissee-source databases / in-memory stores, data analytics, CPU-based AI inferencing, and analogous laborloads.
Besides featuring the new Axion processors, the C4A instances feature local SSD storage, up to 100G netlaboring, Titanium netlabor and storage offloads, and a variety of sizes from 1 to 72 vCPUs. There are both standard and highmem instances useable with the latter providing 8GB of RAM per vCPU rather than 4GB per vCPU as standard.
The Google C4A instances are helped by all the meaningful ARM64 go inpelevate Linux distributions from RHEL to SUSE, Ubuntu, Rocky Linux, and others. For the purposes of my testing I went with using Ubuntu 24.04 LTS atraverse all tested instance types.
Google’s Axion chases the way of Amazon Graviton and Microgentle Azure Cobalt for the unveil cnoisys and hyperscalers in coming out with their own in-house Arm processor summarizes. Google Compute Engine has recommended Arm-based instances with Google Tau VMs powered by Ampere Altra but now with Axion they have apshown their Arm processor necessitates in-house.
Given prior Neoverse-V2 testing at Phoronix with the appreciates of Graviton4 and NVIDIA GH200 Grace, it was a donaten that it would be quite a carry outant experience… For this begin-day testing I was comparing the Google C4A standard memory 48 vCPU instance agetst other GCE 48 vCPU instances including the C4 using Intel Xeon Platinum Emerald Rapids (Xeon Platinum 8581C) and Tau T2A Ampere Altra 48 vCPU instances. Each 48 vCPU instance tested was compelevated of 180~192GB of memory and tested using Ubuntu 24.04 LTS with the Linux 6.8 kernel. No AMD EPYC instances were tested in this comparison since Google Compute Engine currently doesn’t recommend any current-gen “C4” AMD instance type. Plus with Google only covering the gratis access for the C4A instance types, the number of instances tested outside of C4A was confinecessitate to upgrasp costs low donaten today’s very challenging environment for web rehireers.
As for how the Axion pricing is stacking up, for an Intel Xeon C4 48 vCPU instance with 180GB of RAM, that CPU/memory pricing is $1,731.59 per month or about $2.37 per hour. The T2A Ampere Altra 48 vCPU size with 192GB of memory is $1,349.04 per month or about $1.85 hourly…. And then the new C4A instance type with 48 vCPUs and 192GB of memory is $1,573.30 per month or about $2.16 hourly. So Axion is more than the aging Ampere Altra instances but far less than the C4 Intel type. Pricing based on the US-Central1 data as of writing. Wiskinny the benchtag results shown in this article is also carry outance-per-dollar metrics.
Due to the Google Axion instances (and other GCE VMs tested) not exposing any CPU power metrics that could be systematicpartner queried, there isn’t any CPU power consumption / carry outance-per-Watt data to dispense in this article. Thus the cgo in with my begin-day testing for the Google C4A Axion instance family is around the raw carry outance and carry outance-per-dollar agetst C4 Intel and T2A Ampere Altra instances in Google Cnoisy. For those asking how Google Axion contrasts to AWS Graviton4, that will be coming up in a split article on Phoronix in the next scant days.
