|
INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
#268259 - 11/09/11 10:09 AM
|
|
|
I finished building a I7-3930K system for a trade show next week, I ran out of time to fully test it today, but I did have enought time to wack the clock speed up to 4.5Ghz and a quick set of MAME benchmarks.
System spec: Intel I7-3930K @ 4.5Ghz ,Corsair H100 water cooler, ASUS P9X79 Deluxe motherboard, 16GB Kingston Hyper-X DDR3-1866 RAM, 2x AMD HD6970 graphics cards in crossfire, Windows 7 64bit SP1,MAMEUI64 [rom name] -bench 90 .
For comparison I've included RB's 4.8Ghz i7 2600K & the FX-8150 @ 4.8GHz I posted earlier this week.
ROM FX-8150(4.8ghz) I7-2600K (4.8ghz) I7-3930K (4.5ghz)
*
BLITZ 143.30% 258.00% 283.31%
DOLPHIN 27.62% 38.00% 39.18%
GAUNTLEG 199.48% 370.00% 378.57%
GRADIUS4 147.71% 236.00% 217.45%
PROPCYCL 119.31% 259.00% 213.75%
RADIKALB 125.12% 210.00% 191.33%
SCUD 79.36% 149.00% 146.15%
STARSLDR 67.92% 85.00% 92.83%
To tell the truth I wasn't expecting there to be a hugh difference between the I7-2600K & the I7-3930K since they are effect the same CPU, the i7-3930K just having two more cores, Quad Channel memory controller and Larger Cache memory, but few if any changes to the CPU Cores. The Extra Cores really don't look to be getting much love from MAME, I think the extra Cache memory and maybe the insane memory bandwidth that the quad channel offers up is the only thing helping the i7-3930K scores.
I'll be doing some more testing on the system tomorrow, I should to be able to run benchmarks at 4.8Ghz, and hopefully 5.0Ghz too. 
Edited by taz-nz (11/09/11 12:39 PM)
|
If all else fails, Burn the manual.
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: taz-nz]
#268260 - 11/09/11 10:38 AM
|
|
|
> System spec: Intel I7-3930K @ 4.5Ghz ,Corsair H100 water cooler, ASUS P9X79 Deluxe
> motherboard, 16GB Kingston Hyper-X DDR3-1866 RAM, 2x AMD HD6970 graphics card in SLI,
in crossfire you mean
|
Daffy Duck
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: DaffyDuck]
#268264 - 11/09/11 12:47 PM
|
|
|
> > System spec: Intel I7-3930K @ 4.5Ghz ,Corsair H100 water cooler, ASUS P9X79 Deluxe
> > motherboard, 16GB Kingston Hyper-X DDR3-1866 RAM, 2x AMD HD6970 graphics card in
> SLI,
>
> in crossfire you mean
Yeah, long day, fixed now.
|
If all else fails, Burn the manual.
|
|
| B2K24 |
|
MAME @ 15 kHz Sony Trinitron CRT user
|
|
|
|
|
Reged: 10/25/10
|
|
Posts: 2663
|
|
|
|
|
|
Send PM
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: taz-nz]
#268268 - 11/09/11 04:40 PM
|
|
|
> I think the extra Cache memory and maybe the insane memory bandwidth
> that the quad channel offers up is the only thing helping the i7-3930K scores.
Nice build, it looks very good!
Honestly, I think it's just higher clockspeed That gives the higher benchmarks, but I could be wrong.
|
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: taz-nz]
#268274 - 11/09/11 06:09 PM
|
|
|
I didn't know that these were already released... where can I read the official specs?
|
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: taz-nz]
#268276 - 11/09/11 06:18 PM
|
|
|
If you want to compare against RB's setup, benchmark MAME 0.141 instead. This especially goes for sh4 cpu optimizations(dolphin), and namcos22 additional gfx emulation(propcycl)
|
|
|
| John IV |
|
IV/Play, MAME, MAMEUI
|
|
|
|
|
Reged: 09/22/03
|
|
Posts: 1970
|
|
Loc: Washington, USA
|
|
|
|
Send PM
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: hap]
#268279 - 11/09/11 06:31 PM
|
|
|
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: John IV]
#268281 - 11/09/11 06:37 PM
|
|
|
Sigh...still cant get over how shockingly bad the new AMD chips are.
|
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: hap]
#268291 - 11/09/11 10:06 PM
|
|
|
> If you want to compare against RB's setup, benchmark MAME 0.141 instead. This
> especially goes for sh4 cpu optimizations(dolphin), and namcos22 additional gfx
> emulation(propcycl)
I used RB's scores because they the closest I could find on short notice, but if I have enough time today and I can find a suitably spec 2600K PC I'll see if I can get it to 4.8Ghz and run a 143u9 benchmark run on it, no promises on this but.
|
If all else fails, Burn the manual.
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: Ramirez]
#268292 - 11/09/11 10:10 PM
|
|
|
> I didn't know that these were already released... where can I read the official
> specs?
Not Officially release for a few more days, I figured MAME was an obscure enough benchmark that no one would care if I posted scores a few days early. The Screen shot of CPU-Z in my original post should give you most of what you want to know.
|
If all else fails, Burn the manual.
|
|
| R. Belmont |
|
Cuckoo for IGAvania
|
|
|
|
|
|
Reged: 09/21/03
|
|
Posts: 9716
|
|
Loc: ECV-197 The Orville
|
|
|
|
Send PM
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: taz-nz]
#268295 - 11/09/11 10:33 PM
|
|
|
> > If you want to compare against RB's setup, benchmark MAME 0.141 instead. This
> > especially goes for sh4 cpu optimizations(dolphin), and namcos22 additional gfx
> > emulation(propcycl)
>
> I used RB's scores because they the closest I could find on short notice, but if I
> have enough time today and I can find a suitably spec 2600K PC I'll see if I can get
> it to 4.8Ghz and run a 143u9 benchmark run on it, no promises on this but.
That's not what he's saying. He's saying MAME performance on the same hardware changed dramatically in several of those games between 0.141 and now due to optimizations (dolphin) and pessimizations (propcycl).
And for the record, memory bandwidth is the mother's milk of emulators, followed closely by instructions per clock.
|
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: Ziggy100]
#268315 - 11/10/11 04:39 AM
|
|
|
> Sigh...still cant get over how shockingly bad the new AMD chips are.
They are bad only in comparison to Intel's i7, which is definitely at the forefront of increasingly irrelevant x86 performance improvements. Bulldozer is currently no better than AMD's last generation either, so you could say they are bad relative to those also, but I tend to think that the Bulldozer architecture has already proven that it has alot more headroom than the previous generation of AMDs processors did based on the overclocking that has been already achieved.
All that we're getting with these faster processors is adding a few more 9s to the end of the percentage of users for whom the speed of x86 processors is fast enough for everything they do, i.e. last generation was 99.9%, now we're at 99.99%. Yawn.
People who like to play 3d arcade games from the 2000's emulated in MAME still find x86 performance relevant, but even for them, it's only a handful of games that don't already play at 100%.
|
|
|
|
Re: INTEL I7-3930K @ 4.8Ghz & 5.0Ghz, MAME 0.143u9 Benchmarks
[Re: taz-nz]
#268330 - 11/10/11 07:44 AM
|
|
|
As promised benchmarks of the I7-3930 @ 4.8Ghz & 5.0Ghz.
ROM FX-8150(4.8ghz) I7-3930K (4.5ghz) I7-3930K (4.8ghz) I7-3930K (5.0ghz)
*
BLITZ 143.30% 283.31% 300.47% 312.75%
DOLPHIN 27.62% 39.18% 41.99% 43.74%
GAUNTLEG 199.48% 378.57% 400.84% 418.54%
GRADIUS4 147.71% 217.45% 235.88% 244.87%
PROPCYCL 119.31% 213.75% 227.50% 235.52%
RADIKALB 125.12% 191.33% 203.24% 211.85%
SCUD 79.36% 146.15% 154.47% 160.37%
STARSLDR 67.92% 92.83% 98.72% 103.00%
I dropped RB's I7-2600K scores as it wasn't a good comparison as people have pointed out, due to the changes in MAME from 0.141 to 0.143u9. I was hoping to do some updated benchmarks of a I7-2600K on 0.143u9 to see what the real preformance diffence was bewteen the two I7 CPUs at the same clock speed, but we didn't have any I7 2600K system laying around, only i5-2500Ks. With a little luck we'll get the I7-2700K instock soon and I can post some direct comparison benchmarks between the two difference series of I7 CPUs.
|
If all else fails, Burn the manual.
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: R. Belmont]
#268331 - 11/10/11 08:03 AM
|
|
|
> > > If you want to compare against RB's setup, benchmark MAME 0.141 instead. This
> > > especially goes for sh4 cpu optimizations(dolphin), and namcos22 additional gfx
> > > emulation(propcycl)
> >
> > I used RB's scores because they the closest I could find on short notice, but if I
> > have enough time today and I can find a suitably spec 2600K PC I'll see if I can
> get
> > it to 4.8Ghz and run a 143u9 benchmark run on it, no promises on this but.
>
> That's not what he's saying. He's saying MAME performance on the same hardware
> changed dramatically in several of those games between 0.141 and now due to
> optimizations (dolphin) and pessimizations (propcycl).
>
> And for the record, memory bandwidth is the mother's milk of emulators, followed
> closely by instructions per clock.
Yeah, I got what he was saying, I just figure in in lieu of you running new benchmark on you system with 0.143u9, I could run new benchmarks on another I7-2600K with MAME 143u9, to give a true comparison between the two CPUs.
It's interest what you say about the memory bandwidth, the I7-3930K has no shortage of that, but I might have a play and see what happen the benchmark results if I force it into dual channel or drop the memory clock, to see just how much the effect the drop in memory bandwidth has on MAME.
I'm not questioning what you say, I know how much memory bandwidth can effect some applications, I groan everything a see a single Dimm of memory in a quadcore system, I'm just interest to see the results.
|
If all else fails, Burn the manual.
|
|
| R. Belmont |
|
Cuckoo for IGAvania
|
|
|
|
|
|
Reged: 09/21/03
|
|
Posts: 9716
|
|
Loc: ECV-197 The Orville
|
|
|
|
Send PM
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: Bryan Ischo]
#268340 - 11/10/11 05:22 PM
|
|
|
> People who like to play 3d arcade games from the 2000's emulated in MAME still find
> x86 performance relevant, but even for them, it's only a handful of games that don't
> already play at 100%.
Not quite. Pure performance still matters for a lot of "workstation" type stuff, including programming, scientific work and 3D content creation.
And I think next year you'll start seeing new PC games that no longer support XP and hit CPUs a lot harder as a result (because machines with Vista or 7 on them are essentially guaranteed to be at least 2007 spec).
|
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: R. Belmont]
#268360 - 11/10/11 11:53 PM
|
|
|
> > People who like to play 3d arcade games from the 2000's emulated in MAME still find
> > x86 performance relevant, but even for them, it's only a handful of games that
> don't
> > already play at 100%.
>
> Not quite. Pure performance still matters for a lot of "workstation" type stuff,
> including programming, scientific work and 3D content creation.
I would expect the sum total of all programmers, scientists, and 3d content creators for whom PC performance is not adequate 99% of the time is less than 1 per 1000 PC users, which puts that squarely in the remaining 0.1% that I mentioned before.
I can't speak for scientists and content creators but as a programmer, PCs have already reached that point for me. MAME is one of the most demanding things I compile, and it takes 2.5 minutes on my now aging (1.5 years old) computer and I don't need to do it that often so I don't mind so much. Even at work, where compilation speed was a productivity problem for years, this issue has been reduced considerably to the point where for the first time in 10 years, I am not desperately wishing I had a newer workstation.
> And I think next year you'll start seeing new PC games that no longer support XP and
> hit CPUs a lot harder as a result (because machines with Vista or 7 on them are
> essentially guaranteed to be at least 2007 spec).
The PC gaming market is shrinking and will continue to do so, and I think that gamers who play games with such high performance demands will also be in that 0.1% if not there already.
It's pretty clear that PC performance improvements are slowing, I remember the time when every 6 months performance was noticeably better than 6 months prior, this just isn't true anymore. I see so few video card reviews any more and I suspect it's because the number of new video card releases has slowed also. The whole thing is slowing down as we asymptotically reach "good enough for 99.9% of people 99.9% of the time", and we're pretty close to there now.
Of course, this probably just means that the world of software is ripe for some new ultra-demanding technology to come along and shake things up.
|
|
|
|
Re: INTEL I7-3930K @ 4.8Ghz & 5.0Ghz, MAME 0.143u9 Benchmarks
[Re: taz-nz]
#268361 - 11/11/11 12:01 AM
|
|
|
> As promised benchmarks of the I7-3930 @ 4.8Ghz & 5.0Ghz.
>
>
> ROM FX-8150(4.8ghz) I7-3930K (4.5ghz) I7-3930K (4.8ghz) I7-3930K (5.0ghz)
> *
> BLITZ 143.30% 283.31% 300.47% 312.75%
> DOLPHIN 27.62% 39.18% 41.99% 43.74%
> GAUNTLEG 199.48% 378.57% 400.84% 418.54%
> GRADIUS4 147.71% 217.45% 235.88% 244.87%
> PROPCYCL 119.31% 213.75% 227.50% 235.52%
> RADIKALB 125.12% 191.33% 203.24% 211.85%
> SCUD 79.36% 146.15% 154.47% 160.37%
> STARSLDR 67.92% 92.83% 98.72% 103.00%
>
> I dropped RB's I7-2600K scores as it wasn't a good comparison as people have pointed
> out, due to the changes in MAME from 0.141 to 0.143u9. I was hoping to do some
> updated benchmarks of a I7-2600K on 0.143u9 to see what the real preformance diffence
> was bewteen the two I7 CPUs at the same clock speed, but we didn't have any I7 2600K
> system laying around, only i5-2500Ks. With a little luck we'll get the I7-2700K
> instock soon and I can post some direct comparison benchmarks between the two
> difference series of I7 CPUs.
Cool numbers. From the searching I did it looks like, at equal clock speeds, the i7 is about 2x the performance of the Bulldozer. Assuming that it's just as easy to get both of these processors to 4.8 Ghz, and that the costs of doing so is the same, then the Bullldozer's price of approximately 1/2 that of the i7 (FX-8150: $240 @ Amazon, i7-3930K: announced at $570-ish) seems about right, making them about equal from a price:performance (i.e. value) perspective.
One thing that is not clear to me is how much more power efficient (and the more important derivative of this, quiet) the i7 is.
|
|
|
|
Re: INTEL I7-3930K @ 4.8Ghz & 5.0Ghz, MAME 0.143u9 Benchmarks
[Re: taz-nz]
#268367 - 11/11/11 02:02 AM
|
|
|
43% for dolphin blue.... ahhh !! almost half speed 
|
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: Bryan Ischo]
#268395 - 11/11/11 11:33 AM
|
|
|
> Even at work, where
> compilation speed was a productivity problem for years, this issue has been reduced
> considerably to the point where for the first time in 10 years, I am not desperately
> wishing I had a newer workstation.
Compilation performance is not generally a problem, although anything that takes longer than 10 seconds to build when trying to fix a bug is annoying. If the software takes ages to get to the point of the problem then you'll be tearing your hair out.
When trying to debug a problem that only occurs when reading a gig of xml and inserting it into a database, I'll take all the CPU & disk performance that I can get.
|
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: ]
#268416 - 11/11/11 07:20 PM
|
|
|
> Compilation performance is not generally a problem, although anything that takes
> longer than 10 seconds to build when trying to fix a bug is annoying. If the software
> takes ages to get to the point of the problem then you'll be tearing your hair out.
Speak for yourself; our codebase takes 45+ minutes to build from scratch even on fast machines and a no-op build is 2 minutes (crappy recursive makefiles for the win!). However we have ways of mitigating this; developers don't usually have to build everything themselves.
> When trying to debug a problem that only occurs when reading a gig of xml and
> inserting it into a database, I'll take all the CPU & disk performance that I can
> get.
I would humbly suggest that whoever decided to represent a gigabyte of information in XML should be ... re-educated, to put it politely. I personally will never use XML for anything given any possible alternative, but that's just me. Well, I lie; if I'm going to MARK UP some TEXT I might use the eXtensible Markup Language, but for representation of structured data, never.
|
|
|
| R. Belmont |
|
Cuckoo for IGAvania
|
|
|
|
|
|
Reged: 09/21/03
|
|
Posts: 9716
|
|
Loc: ECV-197 The Orville
|
|
|
|
Send PM
|
|
|
Re: INTEL I7-3930K @ 4.8Ghz & 5.0Ghz, MAME 0.143u9 Benchmarks
[Re: Bryan Ischo]
#268425 - 11/11/11 08:47 PM
|
|
|
> One thing that is not clear to me is how much more power efficient (and the more
> important derivative of this, quiet) the i7 is.
The i7 drops to 1.6 GHz and starts turning off cores basically the instant you quit MAME, so it's by far the most livable overclocked processor I've ever used. It's a significant turnaround from the days of the Pentium 4, to put it mildly.
|
|
|
|
Re: INTEL I7-3930K @ 4.8Ghz & 5.0Ghz, MAME 0.143u9 Benchmarks
[Re: R. Belmont]
#268426 - 11/11/11 09:26 PM
|
|
|
> > One thing that is not clear to me is how much more power efficient (and the more
> > important derivative of this, quiet) the i7 is.
>
> The i7 drops to 1.6 GHz and starts turning off cores basically the instant you quit
> MAME, so it's by far the most livable overclocked processor I've ever used. It's a
> significant turnaround from the days of the Pentium 4, to put it mildly.
That's great, but I was wondering more about under load. I hate it when fans spin up.
|
|
|
| B2K24 |
|
MAME @ 15 kHz Sony Trinitron CRT user
|
|
|
|
|
|
Reged: 10/25/10
|
|
Posts: 2663
|
|
|
|
|
|
Send PM
|
|
|
Re: INTEL I7-3930K @ 4.8Ghz & 5.0Ghz, MAME 0.143u9 Benchmarks
[Re: Bryan Ischo]
#268429 - 11/11/11 11:04 PM
|
|
|
> That's great, but I was wondering more about under load. I hate it when fans spin up.
Pick a decent MOBO that allows control over said features or Go Watercooling then.
|
|
|
|
Re: INTEL I7-3930K @ 4.8Ghz & 5.0Ghz, MAME 0.143u9 Benchmarks
[Re: B2K24]
#268432 - 11/11/11 11:57 PM
|
|
|
> > That's great, but I was wondering more about under load. I hate it when fans spin
> up.
>
> Pick a decent MOBO that allows control over said features or Go Watercooling then.
False dilemma. Choosing more efficient processors does not preclude any of the above.
|
|
|
|
Re: INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
[Re: taz-nz]
#268470 - 11/12/11 11:20 PM
|
|
|
Wave Shark, without a doubt, will probably run at full speed on that. Surprised no one benchmarked that game, and Teraburst, too. Both of these are pretty demanding Konami games.
|
|
|
Previous 
Index 
Next 
Threaded 
INTEL I7-3930K @ 4.5Ghz MAME 0.143u9 Benchmarks
Reply
[Re: 
