Sign in with
Sign up | Sign in
Your question
Closed

AES-NI Performance Analyzed; Limited To 32nm Core i5 CPUs

Tags:
  • Core
  • CPUs
  • Intel i5
  • Performance
Last response: in Reviews comments
Share
Anonymous
a b à CPUs
February 2, 2010 5:00:49 AM

Starting with its dual-core Clarkfield-based Core i5 processors, Intel is introducing AES New Instructions to its architecture. We've already seen great benefits from a number of synthetic benchmarks, but what are the real-life advantages of this tech?

AES-NI Performance Analyzed; Limited To 32nm Core i5 CPUs : Read more

More about : aes performance analyzed limited 32nm core cpus

a b à CPUs
February 2, 2010 5:33:31 AM

Great article, but still dont really have a idea about this AES stuff, encryption as far as i care, which i dont much really.
Would really love to see a article comparing hyperthreading to the real shiz, i3 530 vs i5 750, at 3ghz each, id love to see how they perform
Score
3
February 2, 2010 6:11:30 AM

I dont get this for a personal computer... They allready have plenty power to do this.

For a VPN server that would be great.... Hey wait most dont use x86 but hardware specialized for this purpose...

Nice little insignificant feature though
Score
5
Related resources
February 2, 2010 6:44:51 AM

P1n3apqlExpr3ssGreat article, but still dont really have a idea about this AES stuff, encryption as far as i care, which i dont much really.Would really love to see a article comparing hyperthreading to the real shiz, i3 530 vs i5 750, at 3ghz each, id love to see how they perform

Yeah, more interested in how useful hyperthreading is on these dual cors too.
All locked at, 3.0GHz, comparing i5-660 vs i5 750 vs any C2Q with a decent amount of cache. More than anything though, just comparing a dual core with HT LGA 1156 vs a C2Q.
Score
-1
February 2, 2010 8:10:03 AM

Well, I promised that we'd revisit AES-NI in the launch story, so we're keeping our word on that one =) I'll talk to the guys about some deeper insight on HT Ani!
Score
8
Anonymous
a b à CPUs
February 2, 2010 10:42:37 AM

For a user to say they will never have a need for encryption commands on the desktop processor is ridiculous. Life cycles on these processors will be several years, and AES finds its way into more and more software/hardware each day. If you use accounting software, I hope you use encryption. If you have sensitive data on your computer, putting it in an encrypted container is very easy and worthwhile.

Do you have plenty of horsepower with your old core 2 duo? sure. Do you read this site because you buy off the shelf and are satisfied with mediocre performance? I doubt it. What intel is doing is enabling you to have outstanding performance even in an AES encrypted environment.

I'd be interested in seeing benchmarks from cascaded encryption including AES - if you cascade AES and TwoFish, for example, I bet the performance hit is minimal with the on-chip AES support! I know without it, cascaded encryption gives a performance hit that makes you not want to use it...
Score
2
February 2, 2010 11:25:40 AM

You could have used the Via Nano also just for the fun of things...
Score
2
a b à CPUs
February 2, 2010 11:25:57 AM

Thanks.
Score
2
a b à CPUs
February 2, 2010 11:31:14 AM

It's a very useful NI for corporate mails/attachments... Once they teach people how to USE compression at all, rofl. I can see the use in it at least; could make it a default for some mail clients (cough cough Outlook/Windows Mail/Thunderbird, cough cough).

Hope this develops faster and AMD follows Intel on this one. I'd love to get (at least) close to "real time" encryption on my system for security matters. SSH communications also could get better/faster for servers (yeah sure, why not? XD!)

Great article, BTW!

Cheers!
Score
1
February 2, 2010 11:32:50 AM

You might mention that the application has to be compiled to use the AES-NI instructions or there will be absolutely no benefit from the instructions, as they won't get used.

Of course, if you have the source code, and a compiler that supports the AES-NI instructions it is easy to do it yourself. But few windows programs are open source, so you have to generally rely on the vendor.
Score
0
February 2, 2010 11:36:01 AM

Scores:

Intel I5 661 3.3Ghz - 2000 MB/s
Via Nano 1.3ghz - 0765 MB/s
Intel I7 870 2.9Ghz - 0710 MB/s
Intel QX9770 3.2Ghz - 0396 MB/s


lol a Via nano @ 1.3Ghz can beat a i7 870 in AES...
Score
2
February 2, 2010 12:57:31 PM

Quote:
The SHA-256 encryption test proves that the feature only accelerates AES.
SHA is just a hash function, it does not encrypt anything.
Score
1
February 2, 2010 1:55:51 PM

Just a quick question: what do you guys use to make a RAM drive that big? The biggest my RAM drive is allowed to be is 30 MB.
Score
0
a b à CPUs
February 2, 2010 1:57:19 PM

So what will this do for a little old lady whose idea of gaming is Windows Solitaire?
Score
0
February 2, 2010 4:23:09 PM

seems good but no one will buy it unless they add that to the core i7 series the casual user doesn't really benefit from this and even many servers wont benefit either, from my experience, one of the main problems faced with servers is CPU and hard drive performance. Most companies do not want SSD for really important tasks as they often show no signs of when they are ready to fail and the read/write cycles that the drives get put through 24/7 will kill a SSD

other than storage, there's a problem with CPU performance. Faster encryption is good but it wont be enough to make someone pick that CPU over a overall faster CPU as encryption isn't a large part of work that people need done, it is just a small and vital part of it.

people who want this kind of acceleration wont care about it much, what people want is a CPU that is as fast as possible and other additional accelerations such as the encryption, is just icing on the cake
Score
-1
February 2, 2010 5:40:57 PM

I have nearly 400,000 clients running a full disk encryption product. Benchmarks have shown that performance is easily CPU bound and not I/O as many might think. For an enterprise, this will have a huge impact and will be a 'must have' requirement for our next model transiton.
Score
3
February 2, 2010 6:28:05 PM

Remember that "time to encrypt " is only one possible benchmark. In a real-life situation, it's equally interesting to look at CPU load while en/decrypting. As an example, my X25-E delivers ~220MB/s read performance, while TrueCrypt benchmark shows it can do ~350MB/s AES-256 on my Q6600@2.4GHz.

In other words, I'm I/O limited and AES-NI wouldn't reduce the wall-clock time spent on en/decryption. However, that 350MB/s encryption bandwidth is at 100% CPU utilization (all 4 cores) - in other words, reading full-speed from my X-25E would be at approximately 63% CPU load.

Clearly, while AES-NI wouldn't get the job done faster, it would free up CPU cycles for other use.
Score
1
February 2, 2010 6:47:53 PM

First thing I thought when reading this is that Toms would use Truecrypt and it's built-in benchmarking tool to help use this as well, I was surprised they didn't.

Since Truecrypt also combines encryption techniques, this would be a good way to see how cascaded algorithms that contain AES are improved with the new instructions.
Score
0
February 2, 2010 9:25:45 PM

P1n3apqlExpr3ssGreat article, but still dont really have a idea about this AES stuff, encryption as far as i care, which i dont much really.Would really love to see a article comparing hyperthreading to the real shiz, i3 530 vs i5 750, at 3ghz each, id love to see how they perform


Anand did pit the processors against each other HERE. They were simulated i3s (underclocked i5-661 with Turbo turned off). No one's done it with the clock speeds locked to X though. However, a Lynnfield at stock turbos to 3.2 GHz for 1/2 threads, which is close enough to a i3 at 3.06.

The basic conclusion is this: the i3s are pretty good. However, when you hit 4 heavy threads, the real quads kick them to the curb.

Fortunately for i3, most games don't have 4 heavy threads, so they work fine there. Unfortunately for them, transcoding does, and they get demolished there.

YukaHope this develops faster and AMD follows Intel on this one.


It's in Bulldozer (2011), but not Thuban/Zosma. Don't know about Bobcat.

To be honest though, i5-6xx is for the enterprise market. Unless you have a particular need for AES-NI, they're not compelling from a price perspective.
Score
-1
February 3, 2010 1:12:03 AM

What about PCLMULQDQ, the other new instruction?
Score
-1
a b à CPUs
February 3, 2010 2:06:57 AM

.
Score
-4
a b à CPUs
February 3, 2010 3:49:15 PM

omoronovoFirst thing I thought when reading this is that Toms would use Truecrypt and it's built-in benchmarking tool to help use this as well, I was surprised they didn't. Since Truecrypt also combines encryption techniques, this would be a good way to see how cascaded algorithms that contain AES are improved with the new instructions.

As a TruCrypt user (has my NAS and important stuff encrypted using it) I too would like to see these results.
Score
2
February 3, 2010 3:50:29 PM

on 7-zip, it says:

"The total processing time is now reduced to only one-fifth of the processing time with compression enabled, but the quad-core still wins here."

but the chart units are Kb/s, not time, so it looks like the i5 wins here.

by the way, what a great piece of software is 7-zip. His integrated benchmark is one of my over clocking tests. It raises the processor heat to the limit.
Score
0
February 3, 2010 5:30:40 PM

Razor512seems good but no one will buy it unless they add that to the core i7 series the casual user doesn't really benefit from this and even many servers wont benefit either, from my experience, one of the main problems faced with servers is CPU and hard drive performance. Most companies do not want SSD for really important tasks as they often show no signs of when they are ready to fail and the read/write cycles that the drives get put through 24/7 will kill a SSDother than storage, there's a problem with CPU performance. Faster encryption is good but it wont be enough to make someone pick that CPU over a overall faster CPU as encryption isn't a large part of work that people need done, it is just a small and vital part of it.people who want this kind of acceleration wont care about it much, what people want is a CPU that is as fast as possible and other additional accelerations such as the encryption, is just icing on the cake

SecureITFor a user to say they will never have a need for encryption commands on the desktop processor is ridiculous. Life cycles on these processors will be several years, and AES finds its way into more and more software/hardware each day. If you use accounting software, I hope you use encryption. If you have sensitive data on your computer, putting it in an encrypted container is very easy and worthwhile.Do you have plenty of horsepower with your old core 2 duo? sure. Do you read this site because you buy off the shelf and are satisfied with mediocre performance? I doubt it. What intel is doing is enabling you to have outstanding performance even in an AES encrypted environment.I'd be interested in seeing benchmarks from cascaded encryption including AES - if you cascade AES and TwoFish, for example, I bet the performance hit is minimal with the on-chip AES support! I know without it, cascaded encryption gives a performance hit that makes you not want to use it...


And many users/computers gain nothing from dual or quad graphics but for those situations where needed well??? Would you believe some corporations require all data on their employees portable computers to be encrypted. I think there is another side to where this can go that is not being seen...aside from the ability to increase security without penalty to the user. Definitely would be a waste to introduce it initially to a processor like the I7 though.

Totally not true about ssd drives. It is because of the mechanical/analog function of traditional drives that they can be monitored. Even for them the electronic failures cannot be predicted well and my experience has shown that more than half the time the metrics dont catch the actual failure. In many operations notification of failure comes after the drive fails so just slide another drive into the array and the server never skips a beat. Still the probability of failure is far superior. Put them in a raid 1, 5 or 0+1 then reliability speed and uptime blows away the traditional.

Anyway, the article
Score
0
February 4, 2010 3:44:59 AM

Just another publicity stunt to sell more CPU's... This time with hardware integrated encryption. And 'Limited To 32nm Core i5 CPUs ' LMFAO!
'
Quiet clear: new generation CPU's not get sold as much as they want because most Quad Core CPU's can do the same, just cheaper.
'
Suprised that TOMSHARDWARE bites on that....
Score
0
February 4, 2010 5:43:15 AM

Quote:
Quad Core CPU's can do the same, just cheaper.
Q6600@2.4GHz can do ~330MB/s AES-256 with TrueCrypt, while a 3.3GHz dualcore can do ~3.5GB/s. So sure, a quadcore can do the same... *cough*.
Score
0
February 4, 2010 11:35:28 AM

Mr_ManJust a quick question: what do you guys use to make a RAM drive that big? The biggest my RAM drive is allowed to be is 30 MB.


Get RAMDISK 10 Plus from superspeed.com, you can have giant sized ramdrives. even placing your pagefile on the ramdrive, as it saves the contents of the ramdisk ay system shut down and reloads it at boot up.
Score
-1
February 4, 2010 4:44:05 PM

This will help speed up HTTPS, Disc/File/Database encryption, and VPN.

And for anyone who says this is pointless, so is 192GB of ram and a $200,000 SAN on a desktop computer, but I'm sure there's a server out there that would like this.
Score
0
February 4, 2010 9:44:05 PM

climberGet RAMDISK 10 Plus from superspeed.com, you can have giant sized ramdrives. even placing your pagefile on the ramdrive, as it saves the contents of the ramdisk ay system shut down and reloads it at boot up.
pagefile on ramdisk is one of the silliest ideas ever! - you end up using more ram, and thus higher chance of the pagefile being necessary. If you have enough RAM to consider doing this, you have enough RAM to turn off the pagefile entirely.
Score
0
February 4, 2010 11:13:54 PM

VIA introduced on die AES back in 2004. Why no mention of them? Can we see how the Intel AES engine stacks up against VIA's please?
Score
1
Anonymous
a b à CPUs
February 8, 2010 5:19:24 PM

truecrypt still doesn't use the special Intel AES instructions.
Score
0
February 10, 2010 10:26:35 AM

big question to Toms...

AES-NI I guess it provides a SET OF INSTRUCTIONS. Are there other instructions that can be used not to do AES but to accelerate other encription/hashing algorithms?
Score
0
February 10, 2010 11:08:06 AM

juancbig question to Toms...AES-NI I guess it provides a SET OF INSTRUCTIONS. Are there other instructions that can be used not to do AES but to accelerate other encription/hashing algorithms?
Nope - the only instructions that are directly dedicated to crypto stuff is the AES-NI on intel and VIA's AES Padlock. Nehalem also has CRC32 acceleration, but that isn't exactly cryptographic hashing, and it's a pretty specific CRC32 with a hardcoded polynomial.

Nitpickers corner: "generic" instruction sets like MMX and SSE2 can be used to accelerate some cryptographic functions, but nowhere near what dedicated instructions can achieve.
Score
0
February 13, 2010 3:03:07 AM

Wouldn't this be well implemented in defense of virus/trojan/zombie attacks? Although virus definition tables, etc. would no longer recognize the attacking code, both encryption and decryption processes could use a "look-up table", scanning for suspect software, digital signatures, etc. as they do their job. Use several chips, offloading duties, in parrall. You would get two chances of catching the offending code and halting any execution. I'm also guessing that encrypted viruses can't do much damage.

I don't use AES yet but, if in time, another security layer between me and prying eyes is developed from this technology I might use it IF (
Score
0
Anonymous
a b à CPUs
February 14, 2010 10:13:13 AM

And what about 3rd party? Since a business cannot be sure if a competitor is not watching through the backdoor with the aid of a security service, these proprietary solutions cannot really protect the most valuable data. See e.g. small companies on energetics. Think also outside US.

It was not accidental, that open pgp was _really_ not welcome by security services. And finally, after commercialization the code became closed, i.e. untrusted.
Score
0
February 14, 2010 10:38:05 AM

acsaAnd what about 3rd party? Since a business cannot be sure if a competitor is not watching through the backdoor with the aid of a security service, these proprietary solutions cannot really protect the most valuable data.
AES-NI isn't proprietary - it's a hardware implementation of an open standard. It's such a low-level set of routines that you can't really sneak backdoors in, and it's easy to verify against a software implementation.

You can't compare it to a complex piece of closed-source software that has a lot of opportunities for hiding backdoors.
Score
0
Anonymous
a b à CPUs
July 21, 2010 11:35:23 PM

Truecrypt 7.0 now supports AES-NI. PGP WDE is supposedly close to supporting it as well. I am in an environment with over 6,000 clients, all of which must run full disk encryption. AES-NI is clearly targeted at the enterprise, and we do not buy any i7 machines, only i5, so it is clearly in our sweet spot, H/W-wise. Unfortunately, our company is on Sophos SGE, which STILL does not support this instruction set.

Thanks for this article... I found it extremely enlightening and I hope you continue coverage on topics we in the enterprise care about.

A
Score
0
!