- AWS Becomes First Cloud Provider to Offer Cost-Effective PCIe 6.0 Processors
- Graviton5 combines 192 Arm cores with 96 PCIe lanes
- Memory bandwidth exceeds 800 GB/s on latest AWS server platform
AWS has quietly achieved a milestone that neither AMD nor Intel first achieved in commercially available cloud infrastructure by deploying a PCIe 6.0 compatible processor.
The company’s Graviton5 CPU is now generally available through Amazon EC2 M9g and M9gd instances, allowing customers to rent PCIe 6.0 hardware by the hour.
While that advancement seems significant on paper, the practical benefits remain difficult for most users to identify at the current stage of implementation.
PCIe 6.0 arrives in the cloud before it reaches most hardware
Graviton5 was developed by Annapurna Labs and adopts a chiplet design based on TSMC’s 3nm manufacturing process technology.
The processor combines four compute dies containing 48 Arm v3 cores each, bringing the total core count to 192.
AWS says each core carries 1MB of dedicated cache, while the platform integrates 12 channels of DDR5 memory running at speeds up to DDR5-8800.
According to company figures, the memory subsystem can deliver more than 800 GB/s of aggregate bandwidth in demanding workloads.
The processor also includes 96 PCIe 6.0 lanes, making it the first cloud CPU that customers can actively access with PCIe 6.0 connectivity.
Communication between chiplets is based on a coherent interconnection capable of transferring data at 420 GB/s while maintaining unified operation.
AWS claims that Graviton5 can deliver performance improvements as high as 25% compared to previous generations deployed on its infrastructure.
Additional figures suggest that application workloads can run 35% faster, while database operations improve 30% under the right conditions.
Network bandwidth reportedly increases by up to 15%, while storage bandwidth increases by approximately 20% across all instance categories.
For larger deployments, AWS says network performance can double compared to previous offerings available through its cloud platform.
Why PCIe 6.0 may not matter much yet
The challenge is that PCIe 6.0 alone does not automatically transform application performance unless the surrounding hardware can take advantage of the added bandwidth.
This limitation becomes clearer when examining storage devices capable of taking advantage of today’s newest interface standard.
Micron’s 9650 NVMe SSD is among the first PCIe 6.0 drives to reach commercial availability, although its audience remains hyperscale operators.
The SSD can reportedly achieve sequential read speeds of 28GB/s, nearly double the performance commonly associated with PCIe 5.0 storage.
Still, these units are largely intended for AI inference environments rather than conventional cloud computing or enterprise workloads.
The same pattern appears in Teamgroup’s recently announced PCIe 6.0 SSD, which reaches 28 GB/s but is still far from widespread implementation.
For many AWS customers, processor architecture, memory bandwidth, cache capacity, and software optimization will likely be much more important.
M9gd instances also include local SSD storage that reaches a capacity of 11.4 TB and offers 30% higher IOPS than its predecessors.
Although PCIe 6.0 gives AWS early technological distinction, significant gains will largely depend on broader adoption of the ecosystem.
Today, the achievement seems more important as an infrastructure milestone rather than a feature that immediately changes everyday cloud workloads.
Via The 3D Guru / Wccftech
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds.
