One of the major questions surrounding the Spectre and Meltdown security flaws has been just how much of a penalty Intel CPUs would take when patches for these fixes are fully applied. While Spectre affects CPUs from many vendors, including Apple, ARM, and AMD, Intel is the only company categorically exposed to Meltdown. Microsoft has previously issued guidance that suggested recent PCs should see single-digit performance drops, but that’s always the kind of claim that comes with a hefty asterisk attached. Performance drops might conform to a single-digit percentage average, but hit some programs much harder than others.
There’s a lot we still don’t know about the impact of these security patches on older PCs, but Tech Report recently put a Dell Alienware R13 with an Intel Kaby Lake Core i7-7700HQ through its paces, after making sure the only change to the system would be the application of a Spectre-specific patch after the system was otherwise completely updated. You’ll want to hit TR for the full report, but we’ll cover the highlights.
The average performance decline is in-line with the single-digit prediction, though there are exceptions, with some browser tests showing a ~10 percent drop. The largest drop is in PCMark 10’s app load times, which declined by 13.5 percent after a Spectre patch was applied. We’ve talked before about Meltdown possibly hitting I/O tests hard, but this is the first indication Spectre might whack them again.
Other applications saw smaller declines (spreadsheet handling, oddly enough, got faster with the patch) or didn’t change at all. As we expected, the performance shifts depend entirely on which applications you’re using and what workloads you run. We’ve yet to see any evidence game performance is impacted, for example, which is good news if you mostly use your PC for gaming. But that same variety in application usage models is going to make it harder to give an “average” report on what kind of performance hit consumers should expect. If the Spectre patch hits I/O workloads hard as a general rule (and this is strictly a hypothetical statement at this point in time) then two people who use the same content creation program for two different types of work might see two different performance impacts. It’s going to take time to map out these variations and longer still to cleanly map any variance in performance between AMD and Intel chips.
Could Meltdown, Spectre Help AMD?
Intel’s performance hit with this patch appears to conform to the mid-single-digit percentages Microsoft initially predicted. If AMD was still fielding Bulldozer-derived CPUs and APUs, the impact of either on the competitive market would essentially be nil. But AMD has much more powerful CPUs in market these days and a refresh waiting in the wings. Intel is potentially vulnerable as a result, but only potentially.
The largest competitive opportunity for AMD would be if Spectre and Meltdown patches hit older Intel desktops harder than newer ones and if AMD takes no hit or only a very small one. There are millions of Intel users still hanging on to CPUs from the Haswell, Ivy Bridge, or even Sandy Bridge eras. If those chips take heavier hits — say, in the 15 percent range instead of 6-8 percent — those enthusiasts may well feel burned. Some people will feel as if Intel has slowed their CPUs to push them towards upgrading, and while I don’t agree with that assessment, I don’t have to agree with it to see the argument.
The second risk for Intel, and TR touches on this point, is single-threaded performance increases have been few and far between these past seven years. It’s galling to eat even a 5-7 percent performance drop when that level of performance impact literally constitutes 18-24 months of single-threaded CPU performance improvement.
How you read this situation will depend on whether you think Intel has been deliberately holding CPU efficiency back (I don’t). If AMD delivers another potent improvement with its Ryzen+ 12nm CPUs at the same approximate time that Intel customers are losing 5-7 percent performance on current CPUs or worse, let’s call it 8-15 percent on older chips (keep in mind this is strictly hypothetical), it’s not hard to see how customers might look to AMD over Intel in such instances. And, of course, there’s the server market to consider. Sudden performance whacks server-side could, again, put Epyc on stronger footing for HPC, data center, or server customers.
To be clear, I don’t see the situation playing out this grimly and I suspect the competitive opportunity for AMD as a result of these patches, specifically, to be relatively small. But as far as whether or not Spectre and Meltdown could change perceived competitive standing between the two companies? I agree it could.
Should Spectre, Meltdown Be the Death Knell for the x86 Standard?
Spectre and Meltdown are serious CPU flaws, but do they warrant throwing out the entire closed-source CPU model?
Microsoft Pulls Spectre, Meltdown Patches for Older AMD Systems
Microsoft has halted the distribution of patches for Spectre, Meltdown on some AMD systems due to problems with BSODs and bricked systems.
AMD Releases Updated Risk Guidance on Meltdown, Spectre
AMD has clarified its own weaknesses against Spectre and Meltdown. One week later, things aren't quite as rosy as AMD hoped they'd be.