Although Intel has been using the Xeon name since 1998 , the dual - center Xeon 5100 processors that power the Mac Pro and Xserve line are altogether new potato chip , based on Intel ’s 64 - bit Core architecture chopine . This platform was ab initio insert to the public late in 2005 , with chips continuing to swan out throughout this year ; it includes the Core Duo and Core Solo processor used in the Mac Mini and the iMac , as well as some other chips that have n’t shown up in Macs — at least not yet .

Code - discover “ Woodcrest , ” the Xeon 5100 debuted at the conclusion of June , and was designed to volunteer top - focal ratio computational throughput with better power efficiency than Intel ’s late high - ending mainframe . The troupe term it a “ server ” chip , although most computer hardware vendors , Apple admit , will practice it in professional systems like the Mac Pro . That ’s due to the fact that the check was designed to excel at the processing of vast amounts of datum , like those find in real - world applications like movie production with Final Cut Pro , or image editing in applications like Aperture or Adobe Photoshop ( once Photoshop is Intel - aboriginal on OS X ) .

The Xeon 5100 powering the Mac Pro comes in three speeds : 2.0GHz , 2.67GHz , and 3.0GHz . Like the Core Duo and IBM ’s PowerPC 970MP used in the current Power Mac G5 , the 5100 has two microprocessor cores built into each splintering . Both cores range at the same rated velocity , with a 1.33GHz frontside jalopy ( which connect the processor to the respite of the scheme ) and divvy up a 4 MB Level 2 cache , which helps keep the processors humming during compute - intensive tasks .

Unlike the cache in the Core Duo and PowerPC 970MP , either processor heart can apply the entire stash if necessary , which afford a performance cost increase in crucial data - processing tasks , especially with legacy , non - multithreaded diligence that are n’t design to take advantage of multiple processors .

One other understanding , away from carrying out , that the Xeon 5100 was the perfect chip to expend in Apple ’s flagship Mac was because it is the only Core chip that can currently be used in a treble - processor conformation similar to the Power Mac Quad G5 . The 5100 can only be used in single- or dual - processor configurations , so we wo n’t see any Xserves with four Xeons in it , although Intel is expected to herald a quadriceps - magnetic core successor to the 5100 series some clip in 2007 .

How much better than a G5 ?

In synthetical exam , Apple claims that the 3GHz Mac Pro , with its twin Xeon processors , offer more thantwice the integer performanceof the premature top of the line , the 2.5GHz Power Mac Quad G5 , and 1.6 times the float dot carrying out . Of course , actual - world bench mark will tell the true narration of the Mac Pro as it compares to its forerunner , but the Xeon 5100 should have a distinguishable performance edge over the older PowerPC Saratoga chip , as we would gestate in any more New chip design with a fast front - side charabanc and big and more conciliatory cache . ( Each centre in the PowerPC 970MP chip has 1 MB of dedicated Level 2 cache . )

But , with the Xeon 5100 , Intel claim that it has rule out one vast performance advantage held by the PowerPC computer architecture : transmitter processing . bonk to Mac users as AltiVec , or the Velocity Engine , this technology increase transmitter - based processing importantly on the PowerPC simple machine , and was one of the grounds that applications programme like Photoshop were able to manipulate such tumid image file cabinet with simpleness , even when other part of the Mac subsystem were n’t as fast as like Intel - based PCs .

In the Core architecture , Intel has a feature call Advanced Digital Media Boost , . That may not roll off the clapper as flawlessly as AltiVec , but Intel claim that it achieves the same goal . For Mac user , the important affair to notice about Advanced Digital Media Boost is that it executes 128 - bit transmitter - based teaching in one clock cycle , instead of the two clock hertz ingest by old Intel designs . This theoretically doubles the carrying out of vector operations , and brings Intel to parity with AltiVec . It also should provide enhanced carrying into action of aboriginal computer graphic applications , specially when ferment with enceinte sum of datum . ( If you would care a much more in - depth ( i.e. geekier ) account , check out ArsTechnica ’s excellentanalysis of the Core architecture , write by Jon Hannibal Stokes . )

Intel and IBM do n’t use the same metrics or language when talk over major power efficiency , so it ’s hard to compare the true business leader efficiency of the Xeon 5100 series with the Power Mac G5 ’s PowerPC 970MP processor . The fact that Apple has been able to reject so much of the Power Mac ’s cooling apparatus says quite a moment about the power demand of the 5100 , however . Apple evidence us that the Mac Pro system as a whole only pulls 980 W , versus 1,000 Watt for the Power Mac Quad G5 , and a lot of that powerfulness is spreadeagle to the PCI Express bus .

The 5100 is only the beginning

The last two class have seen chip manufacturers advertize away from the “ speeds and feeds ” learning ability of the premature decennium , largely a effect of the fact that , as chip have increased in velocity , their king consumption has increased as significantly . The result is that companies like Intel , Advanced Micro Devices , and IBM have moved to multi - core design that do n’t bid immense leap in peeled performance speed ( as measured in gigacycle ) , instead allow tangible increases in performance ( through multiple CPU core on a single chopper ) without linear increases in index economic consumption .

One of the great affair for Mac users is that the Xeon 5100 used in today ’s Mac Pro is only the get-go of a line of credit of high - performance chips that will be released in the next twelvemonth — as take note , we should see quad - core chips , as well as chip better tuned to run in portable systems , and bit that pop the question notable increases in functioning for low - final stage desktops .

[ Rick LePage isMacworld ’s editor - at - large . ]