Wednesday, May 15th 2019

Intel Puts Out Benchmarks Showing Minimal Performance Impact of MDS Mitigation

Intel Tuesday once again shook the IT world by disclosing severe microarchitecture-level security vulnerabilities affecting its processors. The Microarchitectural Data Sampling (MDS) class of vulnerabilities affect Intel CPU architectures older than "Coffee Lake" to a greater extent. Among other forms of mitigation software patches, Intel is recommending that users disable HyperThreading technology (HTT), Intel's simultaneous multithreading (SMT) implementation. This would significantly deplete multi-threaded performance on older processors with lower core-counts, particularly Core i3 2-core/4-thread chips.

On "safer" microarchitectures such as "Coffee Lake," though, Intel is expecting a minimal impact of software patches, and doesn't see any negative impact of disabling HTT. This may have something to do with the 50-100 percent increased core-counts with the 8th and 9th generations. The company put out a selection of benchmarks relevant to client and enterprise (data-center) use-cases. On the client use-case that's we're more interested in, a Core i9-9900K machine with software mitigation and HTT disabled is negligibly slower (within 2 percent) of a machine without mitigation and HTT enabled. Intel's selection of benchmarks include SYSMark 2014 SE, WebXprt 3, SPECInt rate base (1 copy and n copies), and 3DMark "Skydiver" with the chip's integrated UHD 630 graphics. Comparing machines with mitigations applied but toggling HTT presents a slightly different story.
In the second graph (above), you'll see a comparison between two machines, both of which have the MDS mitigations, but one machine has HTT enabled, and the other has HTT disabled. The selection of tests is the same as the first graph. Here, you'll see performance either drop by 8 percent on SYSmark 2014 SE, and by 9 percent on SPECInt rate base (n copy), to practically no difference in 3DMark "Skydiver." and a negligible 2 percent gain with WebXprt 3 (less parallelized tests tend to benefit from HTT being disabled). Intel put out a similarly extensive selection of Data Center-relevant tests showing negligible performance impact with its MDS mitigation and recommended HTT setting on Xeon enterprise processors released after 2017. Source: Intel
Add your own comment

31 Comments on Intel Puts Out Benchmarks Showing Minimal Performance Impact of MDS Mitigation

#1
Vya Domus
Aren't all these "minimal" performance impacts addding up to something not that minimal?
Posted on Reply
#2
HTC
Vya Domus, post: 4047664, member: 169281"
Aren't all these "minimal" performance impacts addding up to something not that minimal?
My thoughts exactly.

By themselves, each security issue fix isn't that impactful but once all of them are added up, they make quite a dent.
Posted on Reply
#3
LAN_deRf_HA
Why are they showing us just HT on/off? Should be HT on pre-patch then HT off+patch to see the full effect on 9900k.
Posted on Reply
#4
Abaidor
This is getting way out of line.....bravo Intel! At the end of the day you managed to keep IPC performance stable for the last 10 years after all these "patches"..
Makes me wonder if one of the reasons AMD was behind was because they are more cautious with security.
Posted on Reply
#5
Manu_PT
Glad I have a 9700k. Any form of smt is cancer. Physical cores ftw
Posted on Reply
#6
B-Real
Manu_PT, post: 4047679, member: 168799"
Glad I have a 9700k. Any form of smt is cancer. Physical cores ftw
And you will crave for a Zen2.
Posted on Reply
#7
erixx
Today's winupdate installed right now
Posted on Reply
#8
theoneandonlymrk
Vya Domus, post: 4047664, member: 169281"
Aren't all these "minimal" performance impacts addding up to something not that minimal?
Indeed, where did the prior 27% performance uplift of HT go, and when.
What's the point of HT if it only gains 2% yet costs so much in security term's.
Posted on Reply
#9
3rold
erixx, post: 4047701, member: 82798"
Today's winupdate installed right now
did smth come up that soft patches this issue?
Posted on Reply
#10
Imsochobo
HTC, post: 4047665, member: 51238"
My thoughts exactly.

By themselves, each security issue fix isn't that impactful but once all of them are added up, they make quite a dent.
Phoronix have done extensive testing!
It may be less on Windows, sometimes it's the same.
Linux usually is a good representation of potential theoretical performance for cpu and drives.
Gpu not so much yet but we're getting there

But yes! It absolutely does add up, gaming performance is adding up to 4% only at this point but usually 2-3..
Stil I think its all noteworthy.
Posted on Reply
#11
PanicLake
I would say that almost 20% less performance in certain scenarios is not "minimal".
Posted on Reply
#12
FeelinFroggy
GinoLatino, post: 4047717, member: 180136"
I would say that almost 20% less performance in certain scenarios is not "minimal".
Key word here is "certain". If it is a process that you rarely, if ever use, then yes it is certainly minimal.

I am not defending Intel as it does look like they have cut some corners with their security. But gamers wont notice a 1% difference in fps. That only shows up in a benchmark. m
Posted on Reply
#14
chaosmassive
Intel Puts Out Benchmarks Showing Minimal Performance Impact of MDS Mitigation
FTFY
Intel Puts Out Damage Control Slides to Minimize Impact of MDS Bugs on CPU sales.
Posted on Reply
#15
Manu_PT
B-Real, post: 4047684, member: 170068"
And you will crave for a Zen2.
Highly doubt it. Unless it can reach 5,1ghz with 4000mhz CL18 ram and without any added latencies.
Posted on Reply
#16
yakk
My poor swiss cheese servers... :cry:
Posted on Reply
#17
ExV6k
What a lame joke..
Posted on Reply
#19
lynx29
Vya Domus, post: 4047664, member: 169281"
Aren't all these "minimal" performance impacts addding up to something not that minimal?
well said. I hope @W1zzard does a 3700x or 3850x on x570 mobo review versus a 9700k/9900k with all these firmware updates including the latest ones for this issue whenever it comes out for mobo BIOS anyway.

I won't be surprised if we see a double whammy, aka, 3700x was going to win and beat out 9900k even at 1080p, but now we can slap on an extra 7% on top of that because of all these firmware updates.
Posted on Reply
#20
Patriot
Anyone else note that v4 took less of a hit than scaleable?
Posted on Reply
#21
InVasMani
So basically Intel's solution recommends that I can no longer play games that require 4 threads on my 2c/4t i3 CPU. I won't be buying another Intel CPU in a hurry.
Posted on Reply
#22
spnidel
minimal performance impact!
just disable hyperthreading guys, the selling point of our upper-end processors, no big deal!

lmao, classic intel
Posted on Reply
#23
John Naylor
Well the reality is Intel and AMD sold us a phony bill of goods as outside benchmarks, productivity is rarely enhanced by the extra cores / threads. Mostly affects bragging rights. Of course there are systems that CAN use more cores such as video editing, animation and rendering but the reality is, there's more folks complaining about problems than there are folks actually affected.
Posted on Reply
#24
raptori
So if someone want to avoid any performance loss what he should avoid updating ? Both Intel microcode updates and OS updates ? Does updating the OS alone will still cause performance loss?
Posted on Reply
#25
HisDivineOrder
So, are they trying to say that HT isn't worth enabling anyways? Then why charge a premium for it? Haha, silly Intel. Tricks are for kids.
Posted on Reply
Add your own comment