NASA Benchmarks the New G5 Powermac 751
sockit2me9000 writes "Well NASA's Langley Research Center recently benchmarked the new G5 dual 2ghz Powermac against a dual 1ghz Xserve, a dual 1.25 ghz Powermac, a Pentium4 2 ghz, and a Pentium4 2.66 ghz. To make things fair, the second processor in the G5 was switched off, as well as the other dual sysytems. Then, they all ran Jet3d. Even with un-optimized code and one processor, the G5 performance is impressive."
Single Processor Mode (Score:5, Informative)
For those of you who were wondering, you too can switch off one of your Mac's dual CPU's with the Apple CHUD Tools [apple.com]. Look near the bottom of the page. It'll make you appreciate your second processor
Personally though, I want to see how well it runs Seti@Home [berkeley.edu].
Re:Single Processor Mode (Score:5, Informative)
You can also do this simply with the cpus= boot argument; here's a reference [apple.com].
SETI (Score:5, Funny)
My bet is you still won't find any signs of Alien life. So it won't be any better than my old crappy ass P1 166.
But good luck to ya.
Re:SETI (Score:5, Funny)
Re:Single Processor Mode (Score:3, Insightful)
If you can think of a good reason to turn off 50% of your processing, why not save a lot of money and go for one of the two mid-range single cpu G5 configurations that Apple will happily sell you?
By testing in this ludicrous 'half a
Re:Single Processor Mode (Score:3, Insightful)
I also remember a few games having issues on dual processor computers, a while back. Though most of these issues have been resolved now, it'd be interesting to see if the problems cleared up if you disabled a cpu.
Re:Single Processor Mode (Score:5, Informative)
Re:Single Processor Mode (Score:5, Insightful)
Given that the 2 processors are (presumably) sharing 1 video card, one set of RAM chips, one I/O system, and one disk drive, surely there must be *some* kind of performance hit from sharing the rest of the machine with a second processor? Or some performance drain from putting all the housekeeping talks onto just one of the 2 processors?
I think this adds weight to my original point - that benchmarking a dual G5 against dual amd or intel systems is the only way we'll settle this 'fastest PC' question, and that arbitrarily shutting half the sysem off isn;t a sensible way to test things.
Re:Single Processor Mode (Score:4, Insightful)
My take.
Since everything inside the G5 is "point to point" then unless both CPUs need to talk to exactly the same thing at exactly the same time then the performance hit will be almost impossible to detect. (I wonder how RAIDing drives could make this overhead even more improbable?)
Since there is a lot of Mach-ness in the OS X kernel I would also think that there aren't too many critical regions there that force the use of only one CPU. In other words, I think the situation is better than that kernel (was it an early Solaris?) that had one mutex around the whole kernel.
As usual, anyone willing to pay me to benchmark one of these puppies for them? :-) The machine is suitable payment.
Re:Single Processor Mode (Score:4, Interesting)
I agree totally that we need to see benchmarks of one dual system against another. But bear in mind that the use of dual processors depends a lot upon the specific code being run and also the operating system. I think the general problem here is that the G5, while fast, is not like 10X faster than the competition and at this point it is difficult to tell what scores where.
Re:Single Processor Mode (Score:4, Insightful)
Re:Single Processor Mode (Score:3, Informative)
A benchmark will only show what is benchmarked. How many here care about how fast the cpu is in signle percentage points? Today's cpus are not as much as a bottleneck as they once were. Hardware has advanced beyond software for most apps.
What really matters is what you plan to do with it.
A disagree on the smp thing if your testing out chip performance. The reason being is that the OS and the particular benchmark have a huge influence on what the numbe
Re:Single Processor Mode (Score:3, Informative)
For this type of work the CPU usually runs flat out and the bottlenecks that apply to things like opening MSWord documents hardly come into play.
If it's properly written, then HDD access speed is irrelevant, and even main memory access is hardly ever the bottleneck.
This is one of those applications where the system speed is determined by the speed and efficiency of the
Re:Single Processor Mode (Score:5, Informative)
Also, they were getting baseline tests on performance, against the G4. They also broke it down to performance per MHz, which the G5 took a huge lead in.
I suspect a dual G5, with an optimized compiler, would prove more than a match for the dual Xeon setup (That would cost significantly more, similar spec dual-xeon dell's are in the $4000 range), at least for this application (which heavily benefits from Altivec, and Altivec is still king of the SIMD world, SSE2 isn't even close in performance)
Re:Single vs Double Precision (Score:4, Informative)
I agree that AltiVec is superior to SSE (ie. single precision), but you compared it to to SSE2, which is a bit apple-to-oranges (no pun intended, btw). If the G5 FPU is faster than current SSE2 at double precision, it just proves the well thought out design of the PowerPC architecture (and the unfortunate legacy of Intel's FPU instruction set, which is still a handicap even with SSE/SSE2, due to the need to mode switch).
But SSE2 is still immature, and I expect compilers to improve, as well as chip implementations. Once they do, a more meaningful comparision can be made.
The Intel chips NEED stuff like SSE/SSE2 to achieve faster floating point speeds, whereas the PowerPC can get by without it, thanks to a much better FPU design, and thus, PowerPC makers will probably not spend the silicon to make a double precision SIMD instruction set anytime soon.
I stand by my claim that while most consumer and media software can get by with single precision, scientific computing (ie. large matrix calculations, to be blunt) quite often needs double precision (hell, you can get libraries that use 128 bit long doubles, these days), and will ultimately prefer SSE2. Scientists fuss with single precision SIMD simply because many of their applications can benefit so much from SIMD that it is worth the pain to use single precision (with proper conditioning and verification, etc.) Now that double precision SIMD is available, I can only predict they will want to jump to it, once tools for using it are there.
Granted, if Intel can't make a double precision SIMD unit that outperforms a double precision general FPU like the G5's, for matrix problems, then they don't deserve to design chips for scientific computing.
Bebox (Score:3, Funny)
-
Re:Single Processor Mode (Score:4, Informative)
No shit. You can also not be a total ramrod and realize that one needs CHUD installed for that particular System Pref. (fyi : CHUD = Computer Hardware Understanding Developement Tools)
You should check your facts before you flame.
(tig)
"We do not inherit the land from our ancestors"
"We borrow it from our children"
Re:Single Processor Mode (Score:5, Funny)
Re:Single Processor Mode (Score:5, Informative)
NASA Verifies Apple Benchmarks? (Score:5, Interesting)
By adding a second processor, the MFLOPS/Mhz output only dropped from 0.127 to 0.125 MFLOPS/Mhz. This chip can definitely perform in a multi-processor environment. The P4 scored 0.096 MFLOPS/MHz with a single processor.
Apple's benchmarks [apple.com] which were highly criticized by some, gave the Dual 2GHz Power Mac G5 a 194.5% performance advantage over a 3GHz P4 in SPECfp_rate_base2000. The G5 getting a score of 15.7, and the P4 getting an 8.07.
NASA's study found the Dual 2GHz Power Mac G5 to score 498 MFLOPS for their Jet3D performance. A P4 running at 2.66GHz scored 255 MFLOPS: a 195.3% performance advantage for the G5 in this test. If we assume a direct correlation between MHz and MFLOPS for the P4 (which would actually overstate the performance of the P4) and increase the P4's score by 12.782% this would give the 3GHz P4 a score of 287.594 MFLOPS. This is still a 173.16% performance advantage for the G5, and NASA states that a 20% increase in performance for the G5 would be reasonable "when G5-aware compiler tools become available."
So it would seem NASA's benchmarks go a long way in validating the benchmarks for the G5 that Apple released last month at the WWDC. In fact, NASA appears to be giving the G5 even better scores than Apple and Veritest did.
The vector tests that NASA performed to test the G5's AltiVec instruction set produce some even more impressive results, and would be a good indication for why the G5 outpaced the Xeon and P4 by such dramatic amounts on real world tests (at times more than 700% faster than a 3GHz P4). "The vector version of Jet3D runs an order of magnitude faster than the scalar version (speedups of 10X-13X are typical)." The dual 2GHz G5 was benchmarked at 5177 MFLOPS (a 1040% increase over the scalar test) and 1.29 MFLOPS/MHz. This also seems accurate considering Ars Technica's claim that the AltiVec engine wasn't as well integrated into the G5 as it was in the G4. The 2GHz G5 (single cpu) scored 2755 MFLOPS, or 1.378 MFLOPS/MHz, which shows a slightly larger performance hit for vector operations than floating point operations when moving to a dual G5.
Dak
Re:NASA Verifies Apple Benchmarks? (Score:4, Insightful)
First, 498 vs 255 is 95.3% (instead of 195.3%) advantage.
Second, why compare dual fastest G5 vs single mid-range P4? Singe 2GHz G5 scored 254 MFLOPS, it quite fast, but then again equally fast 2.66GHz P4 is available at $188.
It would be much more interesting to compare dual 2GHz G5 against dual Opterons and Xeons.
Re:NASA Verifies Apple Benchmarks? (Score:5, Informative)
More relevant, perhaps, are the figures in the raw MFLOPS graph:
Alas, difficulties in cross-platform benchmarking rear their ugly head:Scalar Code:
G4 using Absoft F90 v8: f90 -s -O -lU77 -N11
P4 using Portland Group F90 v4.0-3: pgf90 -byteswapio -tp p7 -O1
The author did apparently make an effort to use the compiler and flags best suited for each architecture if I read this correctly....
I don't know how much I trust NASA tho. Afterall, they only do RealMedia and WindowsMedia streaming media. Perhaps there's some bias there in favor of Windows (yes, I realize that the testbed P4 system ran Red Hat. Lighten up)
Re:NASA Verifies Apple Benchmarks? (Score:5, Informative)
1) One of the Mac's processors was disabled
2) 195.3% advantage was on an MFLOP/MHz basis
That is how they are comparing the architechture of the chip and it's performance outside of a MHz pissing race. They are in the same ballpark now MHz wise so why shouldn't they take a look at how the actual chip performs. Not to mention how much more will likely come out of the chip with maturing compilers to take advantage of the arch.
Re:NASA Verifies Apple Benchmarks? (Score:4, Interesting)
Obviously a comparison against the Opteron or Itanium is not fair at this time, as they're not intended for the desktop but rather workstation audience. When the Athlon 64 comes out though, benchmarks of those vs. the G5 would be of interest as well.
Re:NASA Verifies Apple Benchmarks? (Score:3, Interesting)
1.) it is 95.3% greater than...
2.) it is 195.3% of...
Re:NASA Verifies Apple Benchmarks? (Score:5, Insightful)
Re:NASA Verifies Apple Benchmarks? The Future (Score:4, Insightful)
If, as widely reported, the PPC 970 goes from 2GHz to 3GHz in the next 12 months it will definitely be more than competative.
It has been along time since I've seen performance increase by near 50% in a year. Takes me back to the 486DX2-66 days.
Re:NASA Verifies Apple Benchmarks? (Score:5, Insightful)
You wanted to say year ago? Month ago Intel released 3 GHz, 800 MGh FSB P4 and new chipset for dual DDR 400 motherboards. Comparing G5 against older 533 MGh FSB processors on old chipset is hypocrisy.
Even 2.6 GHz 800 MGh FSU processor with i875 chipset-based motherboard and dual DDR 400 memory behaves much better than that 2.66 GHz processor.
Re:NASA Verifies Apple Benchmarks? (Score:3, Funny)
Me-Gaga-hertz?
Re:NASA Verifies Apple Benchmarks? (Score:3, Informative)
Damn Dude, RTFA (Score:4, Interesting)
With a single G5, the 2ghz got a 254, and the 2.66ghz P4 got 255 MFLOPs...
Please read the article more clearly, this DOES NOT IN ANY WAY validate apple's earlier claims... here's the quote that was misread
"Though dual processor benchmarks are not presented in detail here, it is worth noting that the G5 system benchmarked at 498 MFLOPS and 0.125 MFLOPS/MHz for scalar Jet3D performance when two processors were used."
Followed by a chart showing the P4 2.66ghz with 255MFLOPS at the top and a G5 2ghz with 254MFLOPS at the bottom...
So you could guess that a dual 2.66ghz would get about 499-500MFLOPS which would be a 0% performance advantage to the G5, and the P4 3.2ghz would be even faster...
Damn Dude, Read What I Wrote (Score:4, Informative)
Apple claims 15.7 for the Dual 2GHz G5, and the 3GHz P4 getting an 8.07. NASA gives the Dual 2GHz G5 498MFLOPS and the 2.66GHz P4 255MFLOPS.
If you use your math skills: 15.7 / 8.07 about equals 498 / 255. So therefore we can draw the conclusion that they have similar results.
Now, NASA only used a 2.66MHz P4 while Apple used a 3GHz P4. Although remember NASA's figure that the P4 had 0.096 MFLOPS/MHz? Give the P4 333 more MHz, and you find it has about 286.968 MFLOPS. NASA also suggests a 20% performance increase can be expected with compilers that take advantage of the G5.
Although, even without this increase Apple's benchmark and NASA's benchmarks are very close. Which would lead one to draw the conclusion that Apple's benchmarks were in fact valid.
I should also note that a P4 would not perform as well in a dual system as the G5 does. So your 500 MFLOPS number is a little rediculous. The G5 which is an amazing dual proc chip saw it's 254 MFLOPS for a single processor (508 when doubled) drop to 498 MFLOPS in a dual system. And the P4 isn't designed for a dual system, doesn't support HyperTransport, etc.
Dak
Re:Damn Dude, RTFA (Score:5, Insightful)
1. They weren't using a compiler optimized for the G5, and expect performance to increase when they have that opportunity.
2. Dual G5s appear to scale better than dual P4s. They're getting close to 2x performance with the dual G5s, much better than most folks are used to with SMP systems.
Re:Wha? (Score:4, Funny)
Though dual processor benchmarks are not presented in detail here, it is worth noting that the G5 system benchmarked at 498 MFLOPS and 0.125 MFLOPS/MHz for scalar Jet3D performance when two processors were used.
That was the above poster's point. Mkay?
</karma burn>
Summary (Score:3, Insightful)
"Benchmarks from the scalar version of Jet3D are shown in Figure 1 (MFLOPS) and Figure 2 (MFLOPS normalized by MHz). In terms of raw MFLOPS, the 2GHz G5 is about 32% faster than the 2GHz P4, 97% faster than the 1.25GHz G4, 142% faster than the 1GHz G4, and within 1 MFLOP of the 2.66GHz P4."
Translation: Slower than the P4 for anyone who didn't look at the grid. And M stands for million. Not one.
Re:Summary (Score:3, Informative)
Real Translation: 0.4% slower, at 75% of the clock speed.
If I remember right... (Score:4, Informative)
So, based on what was said at the keynote (and my interpretation), the G5s are 10dB quieter. Twice as quiet sounds more impressive. Note that saying "half as loud" still implies "loud" so psychologically it's not as impressive.
If I'm wrong, I'm sure someone will jump on me soon enough. I'm holding on tight.
Re:If I remember right... (Score:5, Informative)
+3db Doubles Power, +10dB Doubles Loudness (Score:3, Informative)
Re:If I remember right... (Score:3, Interesting)
Re:No (Score:3, Insightful)
Re:Summary (Score:3, Interesting)
Curious... (Score:3, Funny)
(It's ok, you can mod me -1 Troll now. I'm just bitter about an edict on a project I'm working on.)
MFLOPS/MHz? No AMD, Old P4, Old Redhat. (Score:3, Interesting)
Why a Pentium 4 2.66mhz?
Why no Athlon?
Why no Opteron?
Why an old old version of RedHat 7.1?
and so on....
Re:MFLOPS/MHz? No AMD, Old P4, Old Redhat. (Score:3, Insightful)
Why no Athlon? They probably didn't have one and with the P4 at 3ghz and climbing, the old althon is becomming less and less significant for these pure number crunching apps. Plus maybe they've done previous tests that said that P4 they uesd was faster than an equivelent a
Re:MFLOPS/MHz? No AMD, Old P4, Old Redhat. (Score:3, Insightful)
Puh-lease... The gripe with the SPEC benchmarks was that Apples numbers for the competition were WAY below the OFFICIAL numbers, ot that Apples numbers for their own equipment was crap.
Jeeze...let's at least wait till these things are SHIPPING.
Bow wow wow yippie yo yippie yay... (Score:3, Informative)
Why No Cray? (Score:5, Insightful)
Re:MFLOPS/MHz? No AMD, Old P4, Old Redhat. (Score:4, Informative)
And surely the version of RH Linux hardly matters. Maybe they benchmarked using this OS because (shock, horror) it is what they use daily.
Re:MFLOPS/MHz? No AMD, Old P4, Old Redhat. (Score:3, Informative)
/ MFLOP \
| ----- |
\ S
-----------
/ MCYCLE \
| ------ |
\ S
Multiply by the reciprocal...
MFLOP S
----- * ------
S MCYCLE
Millions cancel, seconds cancel...
FLOP
-----
CYCLE
So it seems that this unit is equal to 1 floating point operation per CPU cycle. That makes a little bit more sense as a unit.
Re:I'll wait for a real comparison. (Score:5, Informative)
Re:I'll wait for a real comparison. (Score:3, Informative)
Hyper threading does not give you the performance of a multi-processor setup. Hyper threading speeds things up when you have lots of independent threads. Lets say You get into a situation where you have, say, a cache miss and the CPU
Portland compiler (Score:3, Interesting)
fortran compiler (Score:5, Informative)
Re:fortran compiler (Score:5, Insightful)
Interesting choice of processors (Score:5, Interesting)
Re:Interesting choice of processors (Score:4, Informative)
Budget had nothing to do with it; the PowerMac G5 isn't shipping yet. NASA had to have obtained theirs through a special arrangement with Apple.
G5 is really a full-blown workstation (Score:4, Interesting)
Apple has just created a new market for itself among the hardcore engineers who use workstations for numerical simulations like HSPICE, etc. Steve Jobs lucked out -- again.
By the way, the bell tolls. It tolls ominously for Sun Microsystems.
Re:G5 is really a full-blown workstation (Score:5, Interesting)
Um, yeah, sure is lucky Apple found the G5. I'm sure they had nothing to do with its development. It's not like Apple has been involved with development of the whole PowerPC architecture since the early 90s.
Re:Apple had little say in the Power4 CPU (Score:3, Informative)
Ah, but Power4 != G5. The G5 was called the GigaProcessor UltraLite (i know) in development and is quite a different beast from a full-blown Power4; it is scaled down to 'desktop tolerances', has not as many cores, and an AltiVec unit. Apple probably had a hand in what is now known as the 'G5' since the very beginning.
Re:G5 is really a full-blown workstation (Score:3, Informative)
Whats the difference? Distinction died long ago (Score:3, Interesting)
G5 has much slower SpecFP than Power4 (same clock) (Score:3, Informative)
Wrong Conclusion!
According to this pdf (page 13) [ibm.com] G5 @ 1.8GHz has 1051 SpecFP.
At the same time Power4 @ 1.7GHz has 1598 SpecFP !!! [spec.org]
It is very clear that Power 970 (G5) is much-much slower in floating point than it's Power4.
Only benchmarks that matter are.... (Score:5, Insightful)
Costs (Score:3, Insightful)
I'd read some thread a while back on another board saying that "Macs are cheaper than PCs". I still can't believe anyone would make that argument. Doesn't being really good in a few areas satisfy the mac people? Do they have to try to spin higher costs as 'lower' (craziest thing I'd ever heard...)
Re:Costs - correction (Score:5, Informative)
It's spelled A-M-D (Score:3, Interesting)
Re:Costs (Score:5, Insightful)
The difference in speed mHz, RAM etc. is irrelevant for a person just getting used to computers and the net. When she is having weekly problems with the Siemens / Windows machine, it will be lost money in time. While the Mac is cheaper in usage, because of less "frustration time" and less hassle.
This is an argument I would strongly disagree with, if you asked me two years ago. But since then, I have come to the conclusion that the Mac simply work better for the lay people. It does the work, and faster because there are less frustrations and less hassle.
Re:Costs (Score:5, Interesting)
I'll make that argument any day of the week if you want to consider TCO. My family got a Powermac G4 in 1999, and it is still the daily use computer for them. (I have my own Cube, which is basically the same for performance comparisons.) That thing still does everything that they can ask of it and then some. Hell, it can still play all the games that I want to play, save UT2k3. The great part is that it is still humming along perfectly, and I don't see any reason why it won't last two or three more years. Find me a PC that you will still be using daily 6 or 7 years later.
This doesn't even take into account all the time and headaches that have been saved from using a Mac. Taking out the "Did you accidentally kick the power cord out?" type phone calls I've gotten to help them, I can think of maybe twice that they have had to call me and troubleshoot. There is no pricetag on this peace of mind.
Re:Costs (Score:3, Insightful)
Are you honestly claming that 129 is a higher number then 255? (fastest g4 to the fastest p4) Yeah, the g4 had a slightly higher flop/cycle score (that would have been much lower using the intel fortran compiler) but the p4's over all score was much higher.
When comparing the price of a 32bit system to that of a 64bit, it's a bit pointless...as you'
Re:Costs (Score:3, Informative)
The G5 (Score:3, Insightful)
Their scheme for OS X is the equivalent of Microsoft charging $100+ for a service pack, I just don't understand it.
I've used OS X, and it blows everything else out of the water in elequency and it seems the perfect balance between productive and 'cool factor'
But until I win the lottery, I'll stick with my cheap x86 machines
Re:The G5 (Score:5, Insightful)
Microsoft Windows XP Pro Upgrapde: $199
http://shop.microsoft.com/Referral/Productinfo.as
MacOS X 10.3/2/1 Full price: $129
http://www.apple.com/macosx/
Microsoft Windows XP Pro (5 Users): $1315.60
MacOS X 10.3/2/1 (5 Users): $199
If you bought Windows XP ($299), and then can upgrapde to Longhorn for $199, you paid $498. If you bought MacOS X 10.1, 10.2, 10.3, and 10.4, you paid $516. Pretty similar, and that's assuming you only have to pay $199 for Longhorn. In the meantime, Apple users enjoy continued advance, while Windows stagnates for 4+ years.
Do the same with a family licence of 5. Buy Windows XP for $1315.60, then upgrade for $875.60: $2191.20 (over 4 years, for 5 people: $109.56/user/year).
Buy MacOS 10.1, 10.2, 10.3, 10.4 (5 User Licence): $796 (over 4 years, for 5 people: $39.80/user/year).
Using http://shopper.cnet.com I found a copy of Windows XP Pro for $207, and an upgrade for Windows XP Pro for $177. I found a copy of MacOS X 10.2 for $98.
If these prices hold over to the newer Operating Systems these companies release, then Windows would cost $384 (23% savings), and MacOS X would cost $196 (24% savings). If you bought every point upgrade Apple released it would cost $392.
Dak
Re:The G5 (Score:4, Interesting)
You might have been able to do it, but you also might have just fed into the MS myth of "everybody pirates our stuff".
Re:The G5 (Score:3, Informative)
Wrong. (Score:4, Insightful)
The major OS version updates are when new features are added, etc. That is the equivelant of upgrading 98 to XP. The cost of buying a Mac is high. The cost of maint. is probably less than a Windows box.
MFLOPS/Mhz. - Useless Metric (Score:4, Insightful)
One might be tempted to design a chip that does more in one cycle and then clock it as fast as a chip that does less in one cycle. Unfortunately, while reality is a little more complex than this, the basic reason is that the more a chip does per cycle, the more heat it generates per cycle. If you try to squeeze too many cycles through it in a second it will fry.
So showing that the G5 has better performance per clock cycles is no more useful than showing that an AMD chip has better performance per clock cycle than an Intel chip. All that matters is how much performance you can get from a chip before it cannot be clocked any faster without requiring unreasonable cooling methods.
All this paper shows is that, while the G5 is designed to do more in a clock cycle than a P4 is, the chip tested is ultimately not any faster than the P4 they benchmarked it against. It remains to be seen how the G5 will do at higher clock speeds. With this in mind, it would be *far* more useful to see heat dissipation stats on the G5 since that might give us some idea how close to it's design limits. If it is cranking out high-end P4 performance and running cool *then* I will be impressed.
Re:MFLOPS/Mhz. - Useless Metric (Score:5, Informative)
Originally, the pipelining was segmented based on the I-Fetch, D-Fetch (register/etc), Exec, Reg-Write-Back, with expensive floating point doing with different timing considerations (externalized or delay-locking multi-stage execution). Then they started sub-dividing each of those stages (especially in CISC archetectures). Now its common to see 15 integer execution pipeline stages - either with shared resources, such that you can only have one divide occuring at any given time (early P-I, P-II, P-III), or with fully independent/concurrent resources (AMD's Athlon).
The addition of the pipelinable-stages between I-Fetch, D-Fetch, exec, and WB was somewhat trivial, because prior to pipelining, there were still seperate events on seperate clock-ticks with inter-stage latching. However, in CPU's with exec-stages that are pipelined, you are introducing additional latches that cause additional undesirable propagation delays.
So a 15 stage integer multiply unit (excluding fetch/WB) has 15 x [guestimating] 4 propagations of additional latency over a single-stage I-unit. If there are resource-based stage-interlocks, or worse data-dependencies, then the pipelining is useless and you're totally hit by the excess propagation delays.
Still, marketing being what it is these days, adding more stages means less propagations per stage, thus less worst-case propagation time, and thus higher clockability (all else being equal; temperature, etc).
The P4, however, compensated by double-clocking the core integer stages, so the number of advertised stages is somewhat misleading.
On a side note, due to the latching in pipelining, you're definately doing more total work for a given instruction. And more importantly, the designers have to think of totally different logic-algorithms to efficiently pipeline than to single-stage. My guess is that the pipelined versions will always be less efficient (especially considering that not all stages will fully utilize their allotted clock-time), and thus there's an additional loss.
Ok, so this supports your post, but here's the part about power/heat.
There are two types of transistors used in modern CPUs (everything past the Pentium). BiPolar and Field-Effect. The CMOS-FET refers to Complementary Metal-Oxide-Semiconductor Field-Effect-Transistor. This acts similarly to a capacitor in that there is a charge and discharge time with little waste current, and power dessipation is typical V=IR, Pwr = I^2 * R. The gate capacitor charge-time is the killer, and what limits switching speed (and thereby clock-speed). Shrinking the area of the capacitor (related to the micron-size stated,
There's another way of reducing switching speed.. Increasing the amount of current running through the wires that ultimately charge/discharge the gate-capacitors. FETs are poor amplifiers, but BiPolar (while more complex and harder to make small) are phenominal. In addition to their complexity, Bipolar also are power hogs. While a FET only consumes power while turning on or off, BiPolars are always on, consuming power (there is current bleeding from the switch). So what often happens is that designers sprinkle BJT's here and there to amplify the current (at the expense of cost/complexity and power-dessipation), and continue using FETs everywhere else.
The bigger and greater number of BJTs that are used, the faster some heavily loaded FET gates will charge and the quicker their switching time will be.
If you up the voltage on a CPU, you're enhancing the amplifier's ability to charge the capacitors and thus gives you more safety-room to up the external clock-speed.
Again, this deviates somewhat from my knowledge domain, but you can often merely co
Interesting Thought (Score:5, Interesting)
There's also one benchmark I'de love to see. Power Mac G5 vs Sun UltraSPARC III. It's fair: they're both 64-bit procs, and it would really make people look at it in businesses that only look at supercomputers as viable. Then maybe people would start giving Apple and IBM some credit.
My 2 cents (Canadian). Thanks.
Re:Wha? (Score:5, Insightful)
By a whopping 0.4%, and with one of the G5's processors disabled. You can spin it any way you want, but the clear fact is that with the G5 Macs are competitive in CPU performance again. I don't see why this disturbs you so; competition is good.
MFLOPS per $ (Score:5, Interesting)
This seems to confirm my belief that most mac people don't buy their own hardware, but get it through work or school.
Re:MFLOPS per $ (Score:3, Interesting)
Why not show a "just works"/$ chart?
Vector Performance (Score:5, Insightful)
This would seem to be one of the more interesting points made, actually. Prior to the announcement of the G5s, speculation on the PPC 970 suggested that it would be stellar with FP & so-so with integer; the real question surrounded how well IBM would implement SIMD. Many were pessimistic. Given that it seems like they've managed to add it efficiently a scaled-down POWER4 core, future refinements could make this series of chips (PPC 9X0s) real monsters.
But the future viability of that roadmap (given how ruthless the company as a whole tends to be when faced with departmental money losses) depends as much upon the success of IBM's Linux strategy as it does on its success in the PowerMac line.
[With apologies to BadAndy of the Ars Technica boards; thanks for sharing your insights.]
In all fairness... (Score:5, Insightful)
Re:In all fairness... (Score:3, Funny)
Apple Rocked By "G5" Scandal.
Just one week after the "G5"'s introduction, Apple has been hit by shocking allegations that the name of the chip powering the computer is nothing more than a tawdry attempt at huckstering, worthy of the lowest flim-flam artist.
According to highly placed industry sources, the "G5" is actually the IBM PowerPC 970, and Apple has been using the "G5" name simply to sell more computers.
Through a systematic application of underhanded techniques known as "m
NASA never benchmarked the G5! (Score:5, Funny)
OS X 10.2.7 (Score:5, Interesting)
Additional Notes: The G5 system was running Mac OS X 10.2.7 and
I'm only running 10.2.6, and Software Update says nothing new is available. What's up with that?
Re:OS X 10.2.7 (Score:4, Informative)
MacOS X 10.2.7 - codename Smeagol [thinksecret.com] - is a stop-gap solution to provide JUST ANY working OS to the G5's until Panther is ready for prime time. Your Sofware Update is right not to install it on your machine, as most probably it is not a G5, sir.
5177 MFLOPS 288 MFLOPS (Score:5, Insightful)
"The vector version of Jet3D runs an order of magnitude faster than the scalar version (speedups of 10X-13X are typical)." The dual 2GHz G5 was benchmarked at 5177 MFLOPS (a 1040% increase over the scalar test) and 1.29 MFLOPS/MHz."
5177 MFLOPS when running a Velocity Engine optimized version of Jet3D.
Now, how much does an P4 extrapolated to 3.2 GHz get? Like 288 MFLOPS?
Someone please explain to me how 5177 MFLOPS and ~300 MFLOPS are even comparable.
As the Mathematica guy said, the competition is no longer high-end PCs, it's now $10,000 UNIX workstations...and the G5 is still faster than any of them.
No wonder the G5s smoke the dual Xeon in the Photoshop, Mathematica, Logic, and Luxology app bake-off. All these apps would have been optimized to use the Velocity Engine.
If I were a scientist doing lots of image processing and vector calculations, I'd need a cluster of about 18 or so 3.2 GHz P4 machines to keep up with the dual 2 GHz G5 PowerMac running a typical Velocity Engine optimized app.
That's a sweet 5177 MFLOPS for you - evidence the G5s rock as hard as Apple has been indicating.
Re:5177 MFLOPS 288 MFLOPS (Score:5, Interesting)
They're not, which is what makes this whole benchmark so entirely useless.
Look at it: The conclusion, basically, is that there's no point in running CFD code using scalar FP. So why didn't they port their code to SSE2? P4's, and particularly the new 800MHz FSB P4 get data through SSE2 code like there's no tomorrow.
Nah, I'll listen when someone compares SSE2 and AltiVec properly. Until then it's just more blah. Don't get me wrong, I'm rapidly turning into the biggest Mac fanboy you've ever seen (Cocoa, since you ask) but the G5's are not the quantum leap Apple are making them out to be. Back in contention? Sure, but I promise you a dual Opteron 2GHz will blow the doors off a dual G5.
Dave
Re:5177 MFLOPS 288 MFLOPS (Score:5, Informative)
Re:5177 MFLOPS 288 MFLOPS (Score:4, Interesting)
Another message from the Benchmark author (Score:5, Informative)
Date: Mon, 13 Jan 2003 23:29:38 -0500
From: Craig Hunter
Subject: G4 vs. P4 performance
I have been following the discussion of Rob Galbraith's benchmarks with much interest, as I have spent a good deal of time testing, optimizing, and benchmarking software for the G4 (OS X) and P4 (Linux).
The first thing to realize is that there are numerous benchmarks that show the P4 is faster, and there are numerous benchmarks that show the G4 is faster. What matters? Well, probably the benchmarks that apply to the kind of work you do. For people doing photo processing with the software Rob tested, his results are extremely relevant. But, someone working with a program optimized for AltiVec and dual processors might have a completely opposite experience.
Just to give an example of a benchmark that goes the other way, see this chart.
(You're welcome to mirror this benchmark image, since my web site may not handle a lot of traffic). These real-world results come from the Jet3D computational fluid dynamics noise prediction software, which I developed for my doctoral thesis and currently use in my work at NASA. Jet3D is written in a combination of FORTRAN 77, FORTRAN 90, and C, and is optimized for AltiVec and dual processors on G4 hardware. When compiled on Linux using Intel's ifc compiler tools, Jet3D also becomes optimized for the P4 (using the various SIMD extensions available on the P4).
As you can see, the G4 does quite well here. A dual processor 1.25GHz G4 system is more than 3.5X faster than a single processor 2GHz P4 system. Though it's not shown on the chart, a single 1.25GHz G4 processor benchmarks at about 1589 MFLOPS, 1.9X faster than the P4. If you look at MFLOPS per MHz for a single processor, the G4 comes in at 1.27 MFLOPS/MHz, while the P4 comes in at 0.42 MFLOPS/MHz. If you want a good example of the MHz myth, look at the Cray, which comes in at 1.78 MFLOPS/MHz with only a 500MHz processor, beating both the G4 and P4.
Without AltiVec, the Jet3D benchmark would be about 794 MFLOPS on the dual-1.25GHz G4, which erases the performance lead over the P4. And then, using only a single processor, the 1.25GHz G4 benchmarks at about 418 MFLOPS, which is about half as fast as the P4. And all of a sudden, the G4 doesn't look very compelling. For the Jet3D benchmark, AltiVec and dual processors are key (AltiVec more so than dual procs). This is true for most benchmarks I have looked at; thus numerically intensive applications that can't use AltiVec and/or dual processors are likely to suffer on the G4.
In the case of Jet3D, it was easy to optimize for AltiVec. I was able to hand-vectorize about 10 lines of code within the guts of the FORTRAN algorithm and convert the computations to C for easy access to AltiVec hardware instructions. It had a huge effect for not a lot of work. For other more complicated cases, it may be possible to use the VAST compiler tools to automatically vectorize and tie in with AltiVec (VAST has parallel tools also). But in some cases, vectorization is not possible or feasible. In those instances, you're stuck with the processor's scalar performance, and the P4 generally has better scalar performance than the G4 in my experience. One final note: these are my personal views, and do not represent the views of NASA Langley Research Center, NASA, or the United States Government, nor do they constitute an endorsement by NASA Langley Research Center, NASA, or the United States Government
Re:Turn the optimizations on first. (Score:5, Informative)
It should be noted that Apple uses gcc to compile Mac OS X and most of their applications, so it would be appropriate to use gcc on the G5. Intel's compiler might be a more appropriate choice for the Xeon.
Re:Turn the optimizations on first. (Score:5, Interesting)
I think the thing that most people on /. seem to keep missing is this: MacOS X and Linux both use GCC as their primary compiler. The Linux kernel is compiled with GCC, as is Darwin. Most software for each platform is compiled with GCC.
Now, with all these Linux-heads around here insisting that Linux is faster than Windows on x86, you'd think GCC for x86 might be a good compiler. Certainly the SPEC tests Apple (and Veritest) did with GCC on the G5 with OS X and the dual Xeon Dell with Red Hat had to have been a valid comparison between those two situations.
I also keep seeing all these comparisons to Dell computers without full specs of the Dell. The base configurations for the PowerMac G5 is positively loaded. How many $500 Dells come with Gigabit Ethernet? How many have the same level of engineering into the thermal managment?
Only time will tell for sure. In the mean time, remember that IBM will be producing blade systems with the 970. We'll get a chance to compare those as well eventually.
Because ... (Score:4, Interesting)
Re:And before anyone asks... (Score:3, Informative)
Those systems aren't *exactly* what I would call comparable. A HD that is 4x bigger, a superdrive, and thats just the stats you posted (I'm sure I could draw it out with things like the Airport Antenna).
"I still haven't seen reliable benchmarks with the dual 2.0GHz facing a P4/3.2GHz with Hyperthreading on"
Veritest disabled HT for tests where the system would be slower, left it on where it was faster. They also enabled SSE2. You can check all of that in their report off of their website.
"if th
Re:And before anyone asks... (Score:4, Interesting)
Sorry, but it's worth $1000 to me to have a computer with a better ROI and no Windows.
Re:And before anyone asks... (Score:5, Informative)
How about a more fair comparison? Namely, between similarly configured high-end single-processor systems:
Apple PowerMac G5:
1.8GHz PowerPC G5
250GB Serial ATA - 7200rpm
SuperDrive (DVD-R/CD-RW)
512MB DDR400 SDRAM (PC3200)
Mac OS X
AppleWorks
ATI Radeon 9800 Pro
56k V.92 internal modem
No Monitor
$2874
Dell Dimension XPS:
3.2GHz Pentium 4
200GB Ultra ATA - 7200rpm
DVD+RW/DVD+R/CD-RW
512MB DDR400 SDRAM
Microsoft® Windows® XP Professional w/ Microsoft® Plus!
Microsoft® Works Suite 2003
ATI Radeon 9800 pro
No Monitor
$3062
And if you are to believe the benchmarks, it seems that Apple is selling the faster system for a lesser price than a similarly configured Dell.
Apple has never competed at the low end. It is not starting now.
-Mike
Re:Still not the same comparisons... (Score:3, Insightful)
He did not say the first 64-bit computer or 64-bit server but 64-bit personal computer.
Sheesh.
Alpha's and Sparcs are not cheap and are considered servers . You do not go to CompUSA and buy a digital Alpha server or Ultra 10x workstation. THey are certainly not designed for the average joe and the price reflects it.
Their is no software for them that is not s