Slashdot Mirror
Mac vs. PC Digital Photography Comparison Redux
Macmurph writes "Bibble Labs has released a lightning fast version of the RAW image convertor, MacBibble. According to MacBibble creator, Eric Hyman, "MacBibble 3.x is almost 10 times faster than the manufacturers software when converting RAW files under OSX.". Prelimenary tests indicate the Mac may be faster than PCs in RAW image conversion afterall. This calls into question the relevance of the the hotly debated article Rob Galbraith posted just 3 weeks ago and discussed here on Slashdot. Two thumbs up for the PowerPC G4's AltiVec vector processing engine, now being put to work in MacBibble."
I've always thought that exploiting parallelism would be the next step after we hit some kind of practical performance wall in desktop systems. However, I've been saying that for 7 years and the wall just keeps moving, although I kind of think its gotten a little closer.
It's probably a question of economics more than anything else. A 2 CPU system for most end-user applications probably delivers less percentage increase in performance than its percentage increase in cost right now. But up till now its been cheaper to replace a single CPU with a faster single CPU than to invest more upfront in a multi-CPU system -- you have to keep it longer, which means you fall farther behind the current performance curve.
If it became 'standard' to have them, OS and App vendors would be able to deliver a performance jump out of 2 CPUs through better parallelism that would outweigh the increased hardware costs associated.
In the PC world, there's also the historical problem of lack of mainstream OS support for multiple CPUs -- I can't remember if XP consumer even supports it, now that I think about it -- which creates that chicken-and-egg problem. NT4 was a highly marginal 'consumer' OS, Win2k had more reach but still not what the 9x series had and XP adoption has been slower due to people just keeping PCs longer.
I've had a dual CPU system at home for 3 years and I'm not entirely sure I'd replace it with another one once I looked at the economics of it. The biggest single benefit I can think of is that it doesn't bottleneck the way a single CPU can when a single process pigs out at 100%, I still have a nearly-idle CPU to work with -- which is the problem with 2 CPUs, one's nearly idle.
I think you should consider yourself lucky.
No offence, but I use a PC for programming, and my Mac for design work, I once tried to work solely on the PC for everything in between getting my new Mac, tried it for nine months, and did some traditional high end stuff. Speed aside, I found Win XP to be much less reliable to work with, I felt it was always trying to find a way to screw up behind my back - and I *do* think that your experience of XP is un-commonly good if you use the machines daily and hard.
But if it works, and you like it then good! (Although if you haven't used OS X (I'm guessing you switched from OS 9, or from no Macs at all) then I think you're missing out).
Oh, and search slashdot for 'Mac +Mouse' to read the 13'000 posts that describe how you can plug any 'normal' mouse into OS X and it'll work instantly...
-Nex
This sig has been deprecated.
If you've read this far you might be interested to note this plug-in from Adobe that "enhances the reliability of Adobe® Photoshop® 7.0.x software running on a Mac OS X system that uses the G4 processor" from a couple of days ago.
No word on whether this gives the PS on G4s any kind of speed boost, though.
When did the future switch from being a promise to a threat? -C. Palahniuk
The beachball is displayed if the current window is not responding. You can mouse over the window of any other program (or window in another thread) and it'll disapear and you can get to work with that one while the other window chugs away at whatever it was doing (or in some cases until you force quit the application).
So, it's not a Beachball of Death. Maybe it is a Beachball of Partial Death.
mbbac
if you're on the level, LowEndMac is a great resource for this, they've got bag-loads of content on running older systems and pointers/links for where to find good deals on used systems. happy hunting!
Not only is the hardware of decent quality, but it runs all the software I want. I get the commercial packages such as office and cubase vst, and I can also drop to a terminal and apt-get basic unix packages, courtesy of fink.
I'm posting this from a dual 1ghz g4 with 15K SCSI drives. It's a fast machine, but more importantly, it's a good machine.
Actually, this shows the results of system specific optimizations. For instance, molecular modeling code optimized for my old SGI Octane was rippin fast. Much faster than on any other platform I could find. However, code not optimized for the SGI platform was just as fast on Intel or PowerPC. Now, that said, the G4 does have something called Altivec, and code optimized for this can be unbelieveably fast. Optimized BLAST libraries are faster on my dual G4 than anything I have ever used including some big SGI iron.
The trick is getting programmers to take the time and effort to optimize for specific platforms. This takes time and money to write quality code, but in the era of Microsoft timeline driven products, quality software code is harder to come by.
Visit Jonesblog and say hello.
For those who didn't know, MacBibble was already like 3 times faster than Nikon's Mac software. Making it multi-threaded makes it twice as fast. The latest AltiVec improvements only increased the speed 50-70%.
If Rob Galbraith ran the same benchmarks with a dual-proc P4 and the new MacBibble on a dual-proc Mac, the PC would still win, just by a smaller margin.
yeah, but IIRC AltiVec is a much cleaner, better implementation of a VPU than the x86 flavors (do they still share the FP registers a la MMX?) - so its code is still probably going to be faster than SSE optimized code (on a specialized black hole simulation that one of my former professors uses, i've seen a >20x speedup with good AltiVec code).
Facts do not cease to exist because they are ignored. - Aldous Huxley
Let's start...
Uhh... I cannot even start to debunk this. Probably because I don't get what you mean, except that you were whoring for karma with the open-source crowd.
Never heard of them. How about the industry-standard SPEC benchmarks? Oh, wait, Macs are twice as slow when compared to Pentium IIIs with the same clock speed, IIRC. Apple is so ashamed of the processors they use, you won't see a single SPEC benchmark published by Apple.
I have covered that extensively on the Slashnet forum with DCTI. To make a long story short, the rotate operations (not bit shifts) were made available on the Altivec instruction set, and MMX/SSE2 doesn't have them. Observe that these useless (for the most part) instructions are only provide on the x86 and PowerPC ISAs, all other major CPU architectures do not offer these instructions. The more I think about it, the more it seems Apple was going for ultimate RC5 performance by including these rotate operations on Altivec -- so they could have at least one benchmark they'd always be ahead of everyone else, as long as they can keep their clock speed within 33-50% of x86 processors (that's 2-3 times less, if you haven't realized).
Wrong, only 4 cycles.
This has to be the worse piece of BS I have ever read on my life.
This is where you have shown how you don't understand anything you're talking about. This cache-snooping protocol is a feature of the Athlon (I doubt the Macs have it), and it is valid for the whole range of memory and not only the PCI bus -- which probably is marked as uncacheable in the MTRR so reads and writes are not cached, you obviously don't want that for I/O data.
Quit the karma whoring, troll.
Join the NFSNET. Our prime goal is making little numbers out of big ones. http://www.nfsnet.org/
What the hell? What crack was the submitter smoking and the person who approved that posting. That article didn't even mention PCs or compare anything to the performance of PCs. MacBibble was ten times faster than the software THE CAMERA MANUFACTURER MADE! So what? This has NOTHING TO DO WITH PERFORMANCE RELATIVE TO THE PC!
NOTHING! This says NOTHING about performance in relation to x86. NOTHING! How could this -possibly- shed ANY light on the previous debate about performance between PCs and Macs? It's not like the previous article used any benchmarks involving software the camera people released.
*sighs* At least slashdot posts something meaningful every now and then.
Apple provides a very nice, extremely easy to use Altivec library. It requires writing no assembly code, and I believe it even resorts back to non-Altivec means of execution if a program written using the library is executed on a G3. So, for instance, in Altivec, you can write things like:
result = vec_add( aVector, someOtherVector );
and it works properly regardless of what sort of vector you've chosen to use for aVector.
I've yet to see anything similar for 3D Now or SSE/SSE2. Everything I've seen for them is either a library that is too application specific (like a premade image recognition library), or requires using assembly and a compiler newer than VC++ 6.0 (maybe only SSE2 really requires that).
Apple also provides a bunch of other libraries, like vDSP (I'm sure AMD and Intel provide an equivelent), and BLAS (this is a somewhat standardized library across platforms. My recall is that there is a SSE/SSE2 version, but Intel charges money for it, instead of giving it out for free), and in general, they make it easier for Apple developers to take advantage of Altivec than Intel does SSE2 or AMD does 3D Now. Unfortuntaly, a lot of developers want to maintain only one code base across all platforms, so they won't use the Apple provided tools (there are free unoptimized versions of BLAS for every platform though, so developers should at least use that so they can't get speed benefit on platforms that provide it), which sucks because GCC also sucks for speed, so people using vendor supplied compilers on other platforms (like Intel's on Windows or Linux, SGI's on Irix, Sun's on Solaris) get a nice speed boost that would require hand assembly optimization to get on a G4.
I'm a loser baby, so why don't you kill me.
Hang on a moment. The last Mac vs PC test was conducted fairly - Photoshop on a Mac vs Photoshop on a PC.
/. is pointing out that MacBibble has rewritten it's Mac version to take full advantage of the PowerPC's multithreading & Altivec processing and that it is much faster than it was before and therefore that one little task of interest only to professional photographers the Mac is back in the running as the fastest tool for that particular job.
/. (though not of Rob Galbraith) would be that they are trying to imply that these very narrow and specific benchmarks are indicative of general processor performance or general vector performance when that is not the case. In the first story the implication was that the PowerPC's one advantage had ceased to exist when that was not necessarily the case. In the second story the implication was that the PowerPC's one advantage was a general one and not tied to very specific computing tasks. In slashdots defense - RTA, the /. crowd should be assumed to be technically inclined and able to pay attention to such details and to care about them.
No, you didn't read the article - it conducted tests using several different pieces of software but not one of them was Photoshop, although one was a third party photoshop plug-in. The tests were very narrowly focussed for a specific set of tasks of vital interest to professional digital photographers but of very little interest to anybody else.
The complaint at the time was that all of the software used was originally written for the PC and ported to the Mac. To use your analogy: In the original article the pi calculator was written in assembly for the PC but in basic for the Mac and the Mac suffered from that. Despite the MHz gap this was counterintuitive to those who follow this kind of issue because it was exactly the kind of specialized task where the PowerPC's superior vector/SIMD performance should have (and was assumed to) MORE than compensated for it's slower clock speed. Still it's a perfectly fair test because if you're interested in doing that task and this is the only software to do it with it doesn't matter to you WHY one system is faster than the other, only that it IS.
NOW, however as a follow up on the original story & controversy
A fair criticism of
you can find them on JC's cross comparison, they're old though
JC's Home Page
Scroll down, on the right, under Benchmarking.
So, when's lunch?