News for hackers. Stuff that matters.
Re:MDS: Microarchitectural Data Sampling side-channel vulner... by jandrewrogers on Tuesday May 14, 2019 @02:41PM (#19912519)
Disabling hyper-threading is highly unlikely to produce a 30% performance hit. Most highly optimized software disables or avoids hyper-threading because doing so increases performance.

Hyper-threading tends to benefit the performance of applications that have not been optimized, and therefore presumably are also not particularly performance sensitive in any case.

Re:MDS: Microarchitectural Data Sampling side-channel vulner... by berkut on Tuesday May 14, 2019 @03:56PM (#19913270)
In highly-parallel workloads like rendering (ray tracing) where pipeline stalls due to loads happen quite regularly, it's fairly easy to get 20-35% speedups with HT.
Re:MDS: Microarchitectural Data Sampling side-channel vulner... by jcelerier on Tuesday May 14, 2019 @02:55PM (#19912682)
In music production and C++ code compilation I get a pretty reliable +25% perf boost with HT on (this was not the case a few gens ago though).