The recent Meltdown and Spectre attacks illustrate the problematic nature of modern computing systems. While the earlier Rowhammer attack could read or attack one process running in a virtual environment from another process running on the same processor, the Meltdown and Spectre attacks are of a completely different class, enabling a process to read large amounts of information from another process’ memory space. This is because inside each hosts, CPU makers have embraced a scale up approach. But what would happen with a more scale out approach to the architecture?
There will almost certainly be doctoral economic theses written over the next decade about the exact impact of the Meltdown and Spectre vulnerabilities. In the present, the most glaring impact is on the raw performance of systems after receiving patches to mitigate the architectural flaws.
But simply saying Meltdown mitigation impact performance by a certain percent abstracts the lived in reality of a post-Meltdown reality. In this response to our Tech Talk series with Liqid, CEO Jay Breakstone gives some context into how Meltdown is effecting business operations across virtually all verticals.
Russ White considers the challenges of using GPU clusters in high performance computing. Aside from possibly lacking software to take advantage of it, the other challenge lies in the connection network. Ethernet is the default standard for this, but requires additional overhead. Russ sees using PCI Express as a much more efficient solution. He considers a PCIe switch from Liqid to dynamically compose infrastructure.