How Screwed is Intel without Hyper-Threading?

As we've come to learn recently, there are 4 new hardware vulnerabilities that touch on Intel processors. These new flaws allow attackers to leak confidential data by exploiting microarchitectural data sampling (MDS) side-channel vulnerabilities, of which the most serious is arguably 'ZombieLoad'.

Unlike previous speculative execution flaws that partially afflicted AMD and Arm-based processors, the MDS flaws are exclusive to Intel chips. In the short term the only way to mitigate or minimize these vulnerabilities is to disable simultaneous multithreading (SMT), or equally Intel brands it "Hyper-Threading."

As it stands Microsoft is pushing out OS-level updates to address the 4 MDS vulnerabilities and yous'll become those with this calendar month's Windows x 1903 update. Even so, this doesn't mitigate the trouble entirely, for that we demand motherboard BIOS updates and reportedly Intel has released the new microcode to motherboard partners. However equally of writing no new BIOS revisions accept been released to the public. We believe we can examination a worst example scenario by disabling Hyper-Threading and for older platforms that won't become updated this might stop up being the only solution.

With that, today we're exploring the touch disabling Hyper-Threading has on Intel processors that support the feature. We've washed this in the past and it's an interesting exam, however in that location is a new critical incentive to go over this data considering that Intel's latest hardware security vulnerability impacts SMT.

We've grabbed a Cadre i7-8700K and 7700K and tested them in a battery of games and applications with and without Hyper-Threading enabled. We didn't bother with the i9-9900K because it's an 8-cadre part, and so the missing threads won't exist an issue for gaming performance, though at that place'll still be a negative touch on application performance and that should be inline with what we see from the 8700K and 7700K.

With more ample fourth dimension (we're about to head out to Computex 2022, so watch out for our coverage) we would have liked to test some dual-core Hyper-Threading enabled Intel CPUs every bit the impact there volition no doubtfulness be barbarous. Though we practise have some older information we can autumn dorsum on.

Nosotros performed all tests using Windows 10 build 1903, nosotros equipped the rigs with 32GB DDR4-3200 memory and a GeForce RTX 2080 Ti to reduce GPU bottlenecks. Gaming benchmarks were ran at both 1080p and 1440p, though nosotros'll kickoff with application benchmarks first.

Application Benchmarks

Starting time off we accept Cinebench R20 results and looking at the Core i7-8700K we run across a 24% reduction in performance with Hyper-Threading disabled. Naturally that kind of performance drop won't go unnoticed. Furthermore in terms of performance we're essentially turning the 8700K into a 7700K, and so a off-white old downgrade that.

Meanwhile the 7700K becomes 26% slower with Hyper-Threading disabled and now we have a manifestly old quad-core, or a Core i5 of the Kaby Lake generation. For applications that heavily leverage all cores, disabling SMT/Hyper-Threading has a large bear upon on performance.

WinRAR sees a massive 36% reduction in throughput for the 8700K. Clearly Hyper-Threading works very well for this type of workload. Likewise we see a massive drop off for the 7700K, a 39% reduction in this instance.

Corona is a loftier functioning renderer and here the 8700K saw a 31% performance decrease with Hyper-Threading disabled, while the 7700K saw a similar 33% drop off. In both cases the performance subtract is significant, signaling we could come across considerable performance driblet offs in rendering and encoding tasks depending on how the updates to mitigate the flaws piece of work.

Blender sees a smaller 25% drop off for the 8700K with Hyper-Threading disabled, which is closer to what nosotros saw on Cinebench R20, though it'south withal significant. The 7700K with fewer cores does endure a trivial more and here we encounter a 29% performance reduction.

Power Consumption

Earlier nosotros move on to gaming we wanted to note total arrangement ability consumption. Granted we're not looking at private processor consumption, so it'south hard to comment on efficiency, but equally y'all can encounter disabling Hyper-Threading on the 8700K doesn't save us much power in this test with a ~5% reduction in full organisation usage. The 7700K was better leveraged with HT enabled and here we saw an 11% reduction which is probably more in line with the performance drop off nosotros saw.

Gaming Benchmarks

First upwards are 1080p results for Assassinator's Creed Odyssey. Hither the 8700K simply saw a xiii% reduction for the average frame rate and no modify to the 1% low. The 7700K on the other hand with its fewer cores saw a massive reduction for both the average frame rate and 1% low results. Here nosotros saw a 23% drop off for the average frame rate and 21% for the ane% depression. Those with quad-core processors will be impacted significantly more by a reduction in Hyper-Threading performance.

At present if you lot're primarily GPU jump the 8700K does fine with Hyper-Threading disabled as we see at 1440p, even with an RTX 2080 Ti. Those with quad-cores and god foreclose dual-cores, whatsoever reduction in Hyper-Threading efficiency is going to sting.

Battlefield V is a very CPU intensive title though for this content nosotros simply had time to examination the single player portion of the game and even and then we needed 2 Origin accounts thanks to the delightful hardware change lockout. Keeping on subject field, we don't see much of a performance decline hither. The biggest drib off was up to 12% when looking at the 1% low margins for the 7700K.

Increasing the resolution to 1440p didn't aid with the ane% depression performance and we run across in both instances disabling Hyper-Threading does reduce performance though the gap is not as large as with saw on productivity workloads.

The Division 2's results are brutal. Look at the performance drop on the 7700K with Hyper-Threading disabled. The average frame charge per unit is reduced by 37% and the 1% low result by 38%, shut to what we saw on WinRAR.

The operation impact for the half dozen-core 8700K isn't nearly as farthermost, but nevertheless a thirteen% dip in 1% low functioning won't be appreciated past nigh gamers. Moving to 1440p and now the 8700K even with Hyper-Threading disabled isn't the performance limiting component, that would be the RTX 2080 Ti. However nosotros're even so seeing a 32% reduction for the 7700K when looking at 1% low performance.

A picayune side note. Far Cry New Dawn plays ameliorate on the 9700K than information technology does the 8700K. The 9700K allows for ~120 fps on average at 1080p. We bring this upwardly considering when we disable Hyper-Threading the 8700K matches the 9700K in this exam, so basically half dozen-cores/6-threads is more efficient in this title than 6-cadre with 12-threads and you see that quite a chip with games when testing SMT.

That said the 7700K with its fewer cores doesn't endure the same outcome with Hyper-Threading enabled, though it was notwithstanding a smidgen faster with it disabled. So at least for this game running without Hyper-Threading is a non-event and in fact is likely going to be beneficial, though non if you lot have a dual-core.

Moving to 1440p and we run into that core count isn't an issue here, information technology'south actually Hyper-Threading that's slowing downward the 7700K and 8700K.

Moving on we accept Hitman 2 and here we see that disabling Hyper-Threading has no real bear upon for the 8700K, however for the quad-core 7700K it is devastating. The average frame rate dropped by 18% but far worse, near a 30% reduction in ane% low performance. Granted we're still seeing over 60 fps at all times, simply for those chasing large frame rates this kind of functioning striking is harsh.

Even at 1440p the 7700K is hit hard with Hyper-Threading disabled as we still see over a 25% reduction in 1% low performance.

Side by side upwardly we have Rage 2 where the 8700K saw almost no decline in performance with Hyper-Threading disabled. On the 7700K the boilerplate frame rate is virtually unchanged, but the 1% depression drops by a significant 20% margin.

One time nosotros increment the resolution to 1440p in Rage ii that's enough to remove the CPU every bit the operation limiting component, at least when looking at the Hyper-Threading-less 7700K. So hither disabling Hyper-Threading has no touch on performance.

We've seen in the by just how demanding Shadow of the Tomb Raider tin can be and we're getting a reminder of that here. The 8700K saw a 10-12% performance drop off with Hyper-Threading disabled while the 7700K saw a 24% driblet off, though the 1% depression margins were like to what we witnessed with the 8700K. In either example disabling SMT does have a large bear on in this title.

Even at 1440p the effect is significant, at least for the 7700K. The 8700K still saw a small performance reject but it was nothing similar the xx% drop off the 7700K suffered.

Last upward we have some Globe War Z results using the low-level Vulkan API. Here the game runs but fine with 4 cores, so neither CPU suffers when Hyper-Threading is disabled. We come across something similar at 1440p as both CPUs are able to extract maximum operation from the RTX 2080 Ti.

Wrap Up

We now have a pretty skillful thought of how Intel'south iv and half dozen-core CPUs perform with Hyper-Threading enabled versus disabled. To quickly summarize the results, core heavy application performance was typically reduced anywhere from 25-35%.

The impact on gaming performance can vary significantly depending on the game and other factors such as the resolution, visual quality settings, and of course, the accompanying GPU. For the games we tested, with a 6-core Intel CPU y'all will see minimal impact on performance for the most function, though 1% operation does suffer at times and on high refresh rate gaming you'll discover the performance drib.

For those with an viii-core/16-thread part like the 9900K the impact on gaming will be nearly non-existent, though application performance will still run across a 25-35% drop without SMT. On the other manus, lower-cease CPUs that rely on Hyper-Threading more heavily will see the near substantial performance loss. Even the quad-core 7700K often suffered large performance dips in gaming tests and this means the loss of Hyper-Threading will be even more devastating for those with dual-core SMT enabled parts.

For at present nosotros tin can't exactly say how much of an impact the iv MDS mitigations will take on functioning (for Windows PCs), only nosotros tin can anticipate there will be some hit, and we know it'll exist felt most where Hyper-Threading has the biggest affect. Phoronix has tested the mitigations on Linux and the performance hit ranges from negligible to massive. Phoronix too found that Intel systems are at present ~16% slower out of the box than they were before the Spectre, Meltdown, Foreshadow and Zombieload mitigations. Meanwhile AMD has only seen a 3% performance drib. They also argue the mitigation touch on is enough to draw the Core i7-8700K much closer to the Ryzen 7 2700X and the Core i9-7980XE to the Threadripper 2990WX.

Unless Intel can pull a rabbit out of a hat and make mitigations so constructive that Hyper-Threading is left untouched, this could have disastrous consequences for those using dual and quad-core Intel CPUs that support Hyper-Threading. This includes Core i3 and Core i5 processors from Clarkdale to Kaby Lake, Core i7s upwardly to Kaby Lake, also as Kaby Lake and Coffee Lake Pentium processors.

For those using older hardware and non running any mission critical tasks, until attacks based on these exploits are conspicuously defined, perhaps the best functioning option volition be not to update. This is not our official recommendation simply color commentary on what could be an alternative route once the corresponding updates are released.

This commodity made for an interesting study of where Hyper-Threading makes the biggest divergence and while this shows a worst case scenario where SMT has to be thrown completely out of the motion-picture show, nosotros've seen some moves in that direction. Google turned off Hyper-Threading in Chrome Os, the OpenBSD customs recommends the aforementioned, while Apple has patched systems with partial mitigations and disclosed that full mitigation requires disabling Hyper-Threading. Other vendors like Microsoft have not taken a definitive stance yet.