Shortcuts

AMD's Next Gen Steamroller CPU Could Deliver Where Bulldozer Fell Short

rated by 0 users
This post has 32 Replies | 3 Followers

Top 10 Contributor
Posts 24,877
Points 1,116,600
Joined: Sep 2007
ForumsAdministrator
News Posted: Tue, Aug 28 2012 1:39 PM
Today at the Hot Chips Symposium, AMD's CTO Mark Papermaster is taking the wraps off AMD's upcoming CPU core, codenamed Steamroller. Steamroller is the third iteration of Sunnyvale's Bulldozer architecture and an extremely important part. Bulldozer, launched just over a year ago, was a major disappointment. The company's second-generation Bulldozer implementation, codenamed Piledriver, made a number of important changes and was incorporated into the Trinity APU family that debuted last spring.

Steamroller is the first refresh of Bulldozer's underlying architecture and may finally deliver the sort of performance and efficiency AMD was aiming for when it built 'Dozer in the first place. In the slides below, all of the comparisons and percentage gains are based on Trinity.

With Steamroller, AMD is taking a baby step or two back towards the traditional dual-core model. Here's Bulldozer's Fetch/Decode/Dispatch hardware, as compared to Steamroller's.


Bulldozer and Steamroller Fetch and Decode Architecture

One of Bulldozer's limitations was that it could only decode four instructions per module for a maximum of 16 instructions per clock in a four module / eight core configuration.That put the chip at a theoretical disadvantage compared to Istanbul (3 instructions/core, 18 total in a six-core configuration) and Sandy Bridge (4 instructions/core, 32 total in an eight-core CPU).

It's not clear if Steamroller can actually dispatch more instructions per clock, but a pair of dual-issue dispatch units may be quicker than the single, unified logic block Bulldozer used. BD's unified approach reduced multithreading performance by ~20% compared to a traditional dual-core. Given how much logic the chip shared, a 20% performance penalty isn't bad -- but reducing this penalty is a great place for AMD to recover performance.



Johan DeGelas' excellent in-depth article on Interlagos performance revealed that the L1 instruction cache had taken a nasty efficiency hit compared to older Istanbul-based chips. With both cores per module enabled, L1 hitrate had fallen to 95% from 97% (the mispredict rate nearly doubled, in other words).  AMD is "increasing" L1 instruction cache size to compensate -- presumably to 96-128K per module, from 64K in Bulldozer. A 30% reduction in i-cache misses would put the L1 hit rate back in 96-97% territory.

Steamroller L1 Cache and Integer Scheduler Improvements
Steamroller L1 Cache and Integer Scheduler Improvements

Interlagos' branch predictor was better than Istanbul's, but still significantly worse than Intel's. A 20% improvement here won't put AMD and Intel on equal footing, but it will boost Bulldozer's overall performance.



It's not clear what AMD means by "streamlined execution hardware." Typically that's execu-speak for "We got rid of some stuff," but that may not be a problem here. Sunnyvale is pushing the idea that the GPU effectively becomes the floating-point heavy lifter at some point in the not-too-distant future, and strong FPU performance isn't really driving adoption in any segments where AMD can reasonably expect to compete.

Putting It All Together:

Based on what we know now, Steamroller looks a lot like the CPU Bulldozer should've been. AMD is claiming a 15% performance/watt improvement, and that figure makes sense given what we've seen today. The good news is that another 15% definitely moves things forward for AMD. Trinity's major achievement was its ability to deliver Llano-equivalent performance at moderately less power; Steamroller should finally pull ahead of the old K10 architecture in clock-to-clock efficiency. That's critical -- AMD needs to strengthen its single-thread performance if it wants to compete with Intel in mobile markets.

The downside is that another 15% won't really change competitive positioning. Steamroller's raw performance may match Sandy Bridge, but it's unlikely to compete well against IVB or Haswell. This suggests that AMD's ability to gain share in mobile will continue to be performance-constrained. With that said, Steamroller is still hugely important -- it's shaping up to be the first real example of what AMD wanted to accomplish when it opted for CMT (Chip Multi-Threading) architecture.



Timing will be critical. Sunnyvale hasn't said when it expects Steamroller to ship beyond a broad "2013" target; an early launch window is infinitely preferable to allowing the core to slip into the back half of 2013. Right now, AMD has made no statements on the Kaveri SoC's launch timeframe (Kaveri is the first APU to integrate a Steamroller core). Sunnyvale's last public roadmap update, last February, indicates that Steamroller won't launch in an independent CPU flavor -- at least not in 2013. The Piledriver core at the heart of Trinity remains the top product in the company's lineup.

If it can launch ahead of Haswell, AMD has a chance to focus the conversation on its cycle of continuous, rapid improvements rather than being defined as an Intel also-ran. Hopefully we'll be able to glean more information from the company's presentations and whitepapers at Hot Chips, but Steamroller is a strong start.
  • | Post Points: 215
Top 500 Contributor
Posts 207
Points 1,845
Joined: Jan 2012
Location: Grand Rapids, MI
Erakith replied on Tue, Aug 28 2012 5:29 PM

Oooh I am interested. This is looking nice, good luck to AMD.. we need competition in the marketplace.

  • | Post Points: 5
Top 150 Contributor
Posts 619
Points 5,260
Joined: Dec 2011

I hope so. Competition would be awesome!

  • | Post Points: 5
Top 10 Contributor
Posts 4,796
Points 45,500
Joined: Feb 2008
Location: Kennesaw
rapid1 replied on Tue, Aug 28 2012 7:56 PM

Nice to see them still rolling along I had kind of given up on them after being a die hard for many many years (Since Athlon XP if anyone remembers those)!

 Machine name: rapid1
 Operating System: Windows 7 Ultimate 64-bit (6.1, Build 7600) 
 System Model: Gigabyte X58A-UD5
 Processor: Intel(R) Core(TM) i7 CPU         930  @ 2.80GHz (8 CPUs), ~3.6GHz
 Memory: Kingston 6144MB RAM
  • | Post Points: 35
Top 10 Contributor
Posts 8,437
Points 102,170
Joined: Apr 2009
Location: Shenandoah Valley, Virginia
MembershipAdministrator
Moderator
realneil replied on Tue, Aug 28 2012 8:11 PM

I remember my old Thunderbird CPUs and how quick they were.

Don't part with your illusions. When they are gone you may still exist, but you have ceased to live.

(Mark Twain)

  • | Post Points: 5
Top 500 Contributor
Posts 159
Points 1,365
Joined: Oct 2009
Schmich replied on Tue, Aug 28 2012 8:18 PM

Seems they really have given up on really competing seriously on enthusiast side of desktops. Considering that the desktop CPU-only chips will always be a generation behind :/

I don't know the details about chip-making. But when you think about all the AMD people out there who want the 8120-8150 of Piledriver and later Steamroller. It could make sense to at least just make one model of each generation and release asap. So lots of APUs and one high-end CPU so enthusiasts don't flee to Intel.

  • | Post Points: 5
Top 500 Contributor
Posts 207
Points 1,845
Joined: Jan 2012
Location: Grand Rapids, MI
Erakith replied on Tue, Aug 28 2012 8:23 PM

I had an Ath x64 3100.. nice little chip at the time.

  • | Post Points: 5
Top 500 Contributor
Posts 290
Points 2,255
Joined: Aug 2012

This would be a great comeback. If they can pull thru. Im still an amd fan because of their price performance ratio.

  • | Post Points: 20
Not Ranked
Posts 5
Points 40
Joined: Aug 2012
KBennett replied on Wed, Aug 29 2012 1:16 AM

The problem is gonna be Windows 8. For those that don't know the FP light "half core" design they used in Bulldozer and Steamroller has a serious performance issue in WinXP, Vista and 7 and MSFT has made it clear its a WILL NOT FIX except...in Windows 8.

So for all of you that don't want Metro? I'm afraid you should either avoid AMD or disable half of each module so it behaves like a "normal" chip because otherwise Windows treats it like hyperthreading which is bad. For those that don't know WHY its bad, imagine you buy a Steamroller 8 core. Now the best way for Windows to schedule 4 jobs would be ONE per module, that gives each of the 4 jobs its own FP unit. Instead thanks to the scheduler bug Windows will dump those 4 jobs on the first two modules, slowing them to a crawl, while the other two modules twiddle their thumbs...see the problem?

So until AMD gets rid of the half core design, or gets MSFT to backport the fix, I'll be hanging onto my Thuban for another couple of years and then if it isn't fixed going to Intel. Because I don't kn ow about everyone else but I have NO desire to turn my desktop into a cell phone with Win 8's Metro UI.

  • | Post Points: 5
Top 150 Contributor
Posts 651
Points 5,915
Joined: May 2008
Location: Stockholm
mhenriday replied on Wed, Aug 29 2012 4:49 AM

Hold with those above who are hoping that Steamroller will perform sufficiently well to make it an alternative to Intel's Sandybridge and Ivybridge - and other chips in the pipleline - the x86 chip market desperately needs competition ! But even if AMD does well, two chip competitors are far too few ; while an oligopoly is preferable to a monopoly, what is needed are new players in the market, like ARM in the low-power segment. Still, the return of AMD as a serious competitor would be a most welcome event ; in my next build I look forward to being able to replace my current AMD Phenom II X4 955 processor with a hot (and reasonably priced) CPU from AMD, rather than having to pay an Intel tax due to that company's quasi-monopoly position....

Henri

Top 500 Contributor
Posts 309
Points 2,990
Joined: Mar 2011
JOMA replied on Wed, Aug 29 2012 7:24 AM

Last AMD processor I owned was the amd athlon 3200 socket 939. Fantastic chip but there hasnt been anything recently from AMD that has swayed me from Intel.

  • | Post Points: 20
Top 10 Contributor
Posts 8,437
Points 102,170
Joined: Apr 2009
Location: Shenandoah Valley, Virginia
MembershipAdministrator
Moderator
realneil replied on Wed, Aug 29 2012 7:42 AM

I never quit buying AMD CPUs. While I do have some Intel's here, my last two were AMD flavors.

My Phenom-II 980 Black does pretty well with the games I like, and the APU A8-3850 system that I put together for my wife is like a rock star in her office. She loves her new PC a lot.

If I was building a PC that had to have lots of performance characteristics, I would default to an Intel build, but AMD boxes are not as hopeless as some will make them out to be.

Don't part with your illusions. When they are gone you may still exist, but you have ceased to live.

(Mark Twain)

  • | Post Points: 20
Not Ranked
Posts 1
Points 35
Joined: Aug 2012
Itr0ll replied on Wed, Aug 29 2012 10:50 AM

15% performance increase 'claimed'...... LOL, AMD IS FINISHED DOT COM

What a failure. So happy with my i7 2600k @ 4.5ghz (ON AIR!) that I would never DREAM of going back to AMD

Current and future AMD owners pay too much for too little performance. You can STILL buy x4 955 BE (Which are unlocked and OC them to 4.5ghz on air) and get better value + better performance than existing Piledriver/Bulldozer. Install a sandy bridge and then tell me you want to use their shoddy APU or under-acheving 'Dozer architecture. THey have nothing to compare to but more of the same performance.

  • | Post Points: 35
Top 10 Contributor
Posts 8,437
Points 102,170
Joined: Apr 2009
Location: Shenandoah Valley, Virginia
MembershipAdministrator
Moderator
realneil replied on Wed, Aug 29 2012 11:05 AM

Itr0ll:
So happy with my i7 2600k @ 4.5ghz (ON AIR!) that I would never DREAM of going back to AMD

Itr0ll:
Install a sandy bridge and then tell me you want to use their shoddy APU or under-acheving 'Dozer architecture.

I have a 2600K too. And yeah, I still want, and use my (not shoddy) AMD APU and Phenom-II 980 Black Edition PCs. Not every system has to be earth shatteringly speedy to be worth using.

I'm glad that you're happy with your Intel rig. Mine is pretty nice too.

Don't part with your illusions. When they are gone you may still exist, but you have ceased to live.

(Mark Twain)

  • | Post Points: 20
Top 150 Contributor
Posts 651
Points 5,915
Joined: May 2008
Location: Stockholm
mhenriday replied on Wed, Aug 29 2012 11:17 AM

What some users can't seem to understand is the simple fact that a healthy AMD is good for us all - both AMD and Intel users (and what I suspect is the majority of us who have chips from both makers in our various machines). As I mentioned above, the present x86 CPU situation is an oligopoly, which is hardly the ideal, but it is far better that a situation characterised by a monopoly, in which nothing other than (non-existant) good will on the part of the monopolist determines prices and quality. Those who boast that they wound «never» condescend to use an AMD chip are doing not only the rest of us, but also themselves a disservice....

Henri

Top 100 Contributor
Posts 1,038
Points 11,350
Joined: Jul 2009
Joel H replied on Wed, Aug 29 2012 12:28 PM

KBennett,

Microsoft released a patch for W7 earlier this year that fixed the scheduler issue. Performance improved by 1-3% in moderately threaded workloads. That's all you get, that's all you're going to get. Bulldozer's problems are directly tied to certain architectural decisions and cache performance.

  • | Post Points: 20
Not Ranked
Posts 1
Points 35
Joined: Aug 2012
Evilwake replied on Wed, Aug 29 2012 3:13 PM

Have to love those Intel fanboys first off u r right that amd does not preform as hi as some highly priced intel chips but i can do things with my amd 8 core that i cant do with my i2700 for one i can open 3 games at once on 3 monitors with no lag cant do that with my i 2700 lags like a ***,so my amd 8 cores loves me to feed it all the software i can and still runs great try that with your intel cpu.

  • | Post Points: 35
Top 100 Contributor
Posts 1,038
Points 11,350
Joined: Jul 2009
Joel H replied on Fri, Aug 31 2012 2:11 PM

Comparison video or it didn't happen. :)

  • | Post Points: 20
Top 10 Contributor
Posts 8,437
Points 102,170
Joined: Apr 2009
Location: Shenandoah Valley, Virginia
MembershipAdministrator
Moderator
realneil replied on Fri, Aug 31 2012 2:19 PM

Joel H:

Comparison video or it didn't happen. :)

 

LOL!

 

Don't part with your illusions. When they are gone you may still exist, but you have ceased to live.

(Mark Twain)

  • | Post Points: 20
Top 150 Contributor
Posts 651
Points 5,915
Joined: May 2008
Location: Stockholm
mhenriday replied on Fri, Aug 31 2012 2:36 PM

When comparing Intel and AMD CPUs, I suspect a lot of the gamers here will find this recent Tech Report article of great interest : http://techreport.com/articles.x/23246 ....

Henri

Top 10 Contributor
Posts 8,437
Points 102,170
Joined: Apr 2009
Location: Shenandoah Valley, Virginia
MembershipAdministrator
Moderator
realneil replied on Fri, Aug 31 2012 3:22 PM

Your link is a good read, but it only reinforces what most already know. AMD's FX CPUs have left them trailing Intel by a lot.

The good news is that the FX4170 and the 980 Black are a decent deal and I can say from personal experience that they do perform well.

You may not top the benchmarks with either of them, but they play games at decent frame-rates (with a good GPU installed in the system) without getting too hot.

Don't part with your illusions. When they are gone you may still exist, but you have ceased to live.

(Mark Twain)

  • | Post Points: 20
Top 150 Contributor
Posts 651
Points 5,915
Joined: May 2008
Location: Stockholm
mhenriday replied on Fri, Aug 31 2012 3:47 PM

I think, realneil, that the main point of the article was to show that frame rate is not an adequate measurement of the gaming experience and that frame latency is a superior metrological instrument for this purpose. Thus it has - if I understand it aright - a wider relevance than just the current situation obtaining between Intel and AMD CPUs (which I hope will at least in part be rectified by the Steamroller series) ; it teaches us - or at least should teach us - not to stare ourselves blind on frame rates. If more reviewers adopt these methods and the general public (or at least its enthusiast component) becomes aware of these facts, perhaps manufacturers will be forced to provide us with better processors (but they'd better not have rounded corners !)...

Henri

Top 10 Contributor
Posts 8,437
Points 102,170
Joined: Apr 2009
Location: Shenandoah Valley, Virginia
MembershipAdministrator
Moderator
realneil replied on Fri, Aug 31 2012 4:45 PM

mhenriday:
I think, realneil, that the main point of the article was to show that frame rate is not an adequate measurement of the gaming experience and that frame latency is a superior metrological instrument for this purpose.

And the results of their testing was damn close to standard testing methodologies anyways. Intel still rules the roost and AMD CPUs don't.

My point was that (leaving benchmarks of any sort out of it) both of my AMD gaming CPUs, the 980 and the 4170 deliver a good 'real world' gaming experience if you have a decent GPU in the system. People keep pointing to benches and they ridicule AMD's efforts, but I say that they're OK with me.

Don't part with your illusions. When they are gone you may still exist, but you have ceased to live.

(Mark Twain)

  • | Post Points: 5
Not Ranked
Posts 3
Points 15
Joined: Sep 2012
RMadatyan replied on Wed, Sep 26 2012 11:05 PM

Spot on my friend, not everyone is aiming for the highest benchmark scores, some people need solutions that fit their need and are affordable. Intels prices though better then before do not compare to AMD, especially in regards to economy builds. AMD CPU's perform very well and are more then sufficient for most average users, Intels lead has captured the enthusiasts but the low to mid range belongs more to AMD. Piledriver looks very promising but steamroller will have a new architecture, that IMO will put AMD back into the minds of the benchmark obsessed. I have my x6 1055t @ 3.65 GHZ and it outperforms i5 2500k in every benchmark and is excellent for video rendering.

  • | Post Points: 5
Not Ranked
Posts 3
Points 15
Joined: Sep 2012
RMadatyan replied on Wed, Sep 26 2012 11:22 PM

Yes, but they also stated it is not the equivalent to Windows 8 core parking and module accessing, the hotfix is a meager attempt at rectifying the addressing issues by accessing modules as though they were SMT threads and not physical cores, the CMT design is flawed because it ignores the current standard for fetching and decoding found in most OS's. Linux is much better in this situation, the FX thrives in a Linux environment. Also, I have benched the FX on a Windows 8 machine, there were HUGE gains, Im talking 15-20% on most benchmarks, the BD architecture is fundamentally flawed several ways but if utilized properly is a real power house, the next step which will be addressed with Piledriver will be the TDP and IPC, but we will not see a true revision of the architecture until steamroller.

  • | Post Points: 5
Not Ranked
Posts 3
Points 15
Joined: Sep 2012
RMadatyan replied on Wed, Sep 26 2012 11:32 PM

Its hilarious when people get ecstatic by reaching an extra 20 frames in games while the competition performs at 100 frames, I guarantee those 20 frames will not be noticeable, as long as you get a steady FPS at 60 or better, you will have an equally satisfying experience. As for intel CPU's out performing AMD, sure the high end intel is light years ahead of AMD in most benchmarks, that however does not render all AMD CPU's useless, especially if you know how to properly overclock. My current x6 1055t which I bought for 70 dollars less then the i5 2500k completely blows it out of the water at 3.65 GHZ. Dont count out AMD just yet, intel has been here before too, veterans of tech know how the market trends can change instantly. Also even if AMD decides to drop out of the enthusiast segment, believe me they have plenty of other ventures to follow. When ARM shows up to the enthusiast desktop scene, things will get very interesting, and Nvidia has also made remarks about releasing a desktop CPU! The future looks very exciting, in any case I root for technology and competition, without a good competitor intels already inflated prices will only go up!

  • | Post Points: 5
Top 150 Contributor
Posts 651
Points 5,915
Joined: May 2008
Location: Stockholm
mhenriday replied on Thu, Sep 27 2012 5:00 AM

I think many (but, it would seem, not all) participants in this discussion share your hope, RMadatyan, that AMD gets back in the game with respect to high-end CPUs - not merely because of the effect that this would exert on prices, but also because it would stimulate innovation. Intel, for example, would hardly feel the same pressure to improve their products if AMD weren't around (and vice versa). For my part, I also hope that when testing CPU performance in a gaming context, the present somewhat excessive emphasis on frame rates (surely there's a limit above which an increase in frame rates provides no noticeable improvement in user experience, although just where that limit goes is open to debate) is toned down and that other considerations, like frame latency are taken into account. In any event, I'm greatly looking forward to Steamroller - if it does the job and the price is reasonable, I'll consider using one of the versions in a new build, even though I hardly need it - my trusty Phenom II X4 955 does everything I ask of it....

Henri

Not Ranked
Posts 1
Points 20
Joined: Oct 2012
judzwho replied on Sat, Oct 27 2012 1:44 PM

as for me I have the I7 and I have a FX6100 and sorry to say but my amd fx6100 runs alot better than my i7. the I7 locks up all the time and my amd never slows down. I replaced my I7 thinking it was the processor being bad but my new one does the same thing

  • | Post Points: 20
Top 10 Contributor
Posts 8,437
Points 102,170
Joined: Apr 2009
Location: Shenandoah Valley, Virginia
MembershipAdministrator
Moderator
realneil replied on Sat, Oct 27 2012 3:07 PM

judzwho:
the I7 locks up all the time

Your i7 has configuration problems.

They usually work without any hiccups.

Mine seems to be bulletproof. (it's like the Energizer Bunny)

judzwho:
I replaced my I7 thinking it was the processor being bad but my new one does the same thing

It usually isn't the CPU that goes. The mainboard or the PSU are usually the culprits.

Don't part with your illusions. When they are gone you may still exist, but you have ceased to live.

(Mark Twain)

  • | Post Points: 5
Not Ranked
Posts 3
Points 15
Joined: Nov 2012
dwisen replied on Thu, Nov 15 2012 6:38 PM

The statement "You can STILL buy x4 955 BE (Which are unlocked and OC them to 4.5ghz on air)" is HIGHLY unlikely.
I have the 955 and an aftermarket air cooler and cant even get it stable @ 4Ghz.
Matter of fact the sweet spot for the majority of 955 users is at around 3.8Ghz..
Even with water cooling its harder than you think to get 4Ghz stable.

With that being said I still love my 955 and still love AMD and would not get an Intel ove an AMD product any day.
Intel charges WAY too much for their chips, and AMD can hold its own on a lot of different programs and games.

TLDR: I love AMD and Intel is way overpriced.

  • | Post Points: 5
Not Ranked
Posts 3
Points 15
Joined: Nov 2012
dwisen replied on Thu, Nov 15 2012 6:42 PM

Thank you for that.
I have said many times that AMD produces chips that can handle a much heavier work load than Intel could even imagine.
AMD also incorporates newer technology into it's chips that Intel just doesn't support.
In short you can do MORE with a "slower" AMD than you can do with a "faster" Intel.

  • | Post Points: 5
Not Ranked
Posts 1
Points 5
Joined: Feb 2013
umaxsto replied on Tue, Feb 5 2013 3:00 PM

I'm still using a phenom x4 9750, currently paired with a Radeon HD 6870 and up until the last year or so, I've been able to run pretty much every game at playable framerates and resolutions. In fact, I have more issues with the drivers for my GPU (mostly on Linux but I've had problems updating the Windows drivers) Before it stopped being able to run new games, my only gripes with my cpu are that the temp sensors don't work on Linux. And the linux driver for the sound part of the chipset doesn't play all that well with PulseAudio and Skype unless I add "tsched=0" into the config which screws up flash (the chrome version, the now unsupported version stretches in fullscreen mode if you have dual monitors.

Bottom line: I will be getting the Steamroller equivalent of the fx-8350 and when combined with a decent Nvidia GPU a little later down the line, my system will rock both in Linux and Windows.

  • | Post Points: 5
Not Ranked
Posts 1
Points 5
Joined: May 2013
fuzzout replied on Sat, May 4 2013 1:36 AM

Well,

I recently got myself an FX-8350... And I've heard outcries from people about crysis 3 putting a lot of weight onto i7's and making framerates drop...

You know why this is? i7 is quad; fx-8350 is 8-core.

Here's a video of me on Crysis 3; STREAMING (at high quality stream settings, so extra CPU load) on maxed out graphics: http://www.youtube.com/watch?v=KnQNY5BsMWM

Framerate drops are in this situation caused by my graphics card (it being GTX 550Ti)

I even captured my CPU activity at the time too (bottom right corner).

FX-8350 is my hero. :3

  • | Post Points: 5
Page 1 of 1 (33 items) | RSS