Some media have reported that a new hardware bug in Intel processors, allowing user mode processes to access kernel mode memory, has been discovered:
It is understood the bug is present in modern Intel processors produced in the past decade. It allows normal user programs – from database applications to JavaScript in web browsers – to discern to some extent the layout or contents of protected kernel memory areas.
The effects [of fixes] are still being benchmarked, however we're looking at a ballpark figure of five to 30 per cent slow down, depending on the task and the processor model.
After the bug is fixed, which slowdown am I to expect for multicore floating point computations?
To my understanding, only the performance of switches between kernel and user mode are affected. For example, handling a lot of I/O is a workload where this is frequent, but CPU-intensive processes should not be affected as much.
To quote from one article that analyzes performance of the Linux KPTI patch:
Most workloads that we have run show single-digit regressions. 5% is a good round number for what is typical. The worst we have seen is a roughly 30% regression on a loopback networking test that did a ton of syscalls and context switches.
...
So PostgreSQL SELECT command is about ~20% slower with KPTI workaround, and I/Os in general seem to be impacted negatively according to Phoronix benchmarks especially with fast storage, but not gaming performance, Linux kernel compilation, H.264 encoding, etc…
So, if your FP computations rely mostly on in-memory data shifting and not I/O, they should be mostly unaffected.