Since the first rumour of an Apple switch to Intel , everyone has been wondering about the possible speed of Intel - based Macs . Last hebdomad ’s announcement of the first shipping Intel - establish Macs brought with it the promise of a major speed cost increase : Apple’sWeb pagessuggest that the new iMac , power by the Intel Core Duo processor , is twice as degenerate as its G5 predecessor .
Macworld Lab ’s run do show that the newfangled Intel - ground iMac is faster than the iMac G5 when range aboriginal program . However , we found that those betterment are by and large much less than what Apple claims is a 2x betterment in speed .
alternatively , our tests found the new 2.0GHz Core Duo iMac takes rougly 10 to 25 pct less prison term than the G5 iMac to perform the same native coating task , albeit with some notable exceptions . ( If you ’d prefer , that makes the Core Duo iMac 1.1 to 1.3 times as tight . ) And we also found that coating that are n’t yet Intel - native — which must run using Apple’sRosetta code - transformation technology — tend to run half as fast as the same applications running natively on the iMac G5 .
All scores are in minutes:seconds. All systems were running Mac OS X 10.4.4 with 512MB of RAM, with G5’s processor performance set to Highest in the Energy Saver preference pane. Using iMovie, we applied 3 different video effects to a 1-minute movie, one at at a time. Next, we imported 100 JPEG photos into iPhoto and then exported them as a QuickTime movie, as a Web page, and as files, resized to be not more than 2,000-by-1,500 pixels. We created a Zip archive from a 1GB folder. We converted 45 minutes of AAC audio files to MP3 using iTunes’ High Quality setting. We saved an iDVD project containing a 6-minute, 46-second movie as a disk image. We used iSquint to compress the same movie for iPod video playback. We used BBEdit to run a Text Factory containing five editing, replacement, and sorting tasks on a 75.1 MB text file.—Macworld Lab testing by James Galbraith and Jerry Jung
Universal applications: Comparing apples to apples
Apple ’s much - publicise test scores for the unexampled iMac were made with programs designed specifically to generate test consequence . So they may give some indication of the overall execution potential of these systems . However , such test issue often do n’t match up to what even user see in their everyday work — i.e. , the speed of veridical - world applications .
iMac Core Duo
Several of the programs Macworld Lab practice to judge overall system performance are not yet usable in Universal variant . As a result , we added several fresh tests based on applications that are currently available in Universal shape . ( And we contrive on run even more test as more Universal applications arrive — we’ll be posting run updates as well as a complete review of the new iMac to Macworld.com in the do day . )
In tests with two iLife ’ 06 applications — iMovie and iPhoto — we found remarkably different performance depend on what feature of the programs we try on . For exemplar , the act of apply one iMovie effect to a video cartridge clip resulted in a remarkable speed improvement of 1.8 times . But a different effect show only half the improvement , and yet another showed no velocity melioration at all .
First Tests: Universal Applications
Best upshot inbold .
All scores are in hour : second . All systems were run Mac OS X 10.4.4 with 512 megabyte of Aries the Ram , with G5 ’s processor public presentation determine to Highest in the Energy Saver druthers pane . Using iMovie , we apply 3 unlike video effects to a 1 - instant flick , one at at a time . Next , we spell 100 JPEG pic into iPhoto and then exported them as a QuickTime movie , as a Web Sir Frederick Handley Page , and as files , resized to be not more than 2,000 - by-1,500 picture element . We make a Zip archive from a 1 GB folder . We converted 45 bit of AAC audio files to MP3 using iTunes ’ High Quality setting . We saved an iDVD labor containing a 6 - minute , 46 - second movie as a disc image . We used iSquint to compact the same moving picture for iPod video playback . We used BBEdit to function a Text Factory containing five redaction , replenishment , and assort tasks on a 75.1 MB text file.—Macworld Lab testing by James Galbraith and Jerry Jung
likewise , importing 100 photograph into iPhoto 6 took 35 percent less time on the Intel - base iMac , and exporting from iPhoto to a QuickTime movie take on 25 percent less time . But exporting iPhoto images to a vane page took only 8 percentage less sentence . And export those image to file actually take 9 percentmoretime on the Intel - found Macs .
Bare Bones Software ’s BBEditperformed well on the new scheme . In our BBEdit test battery , which performed five operations ( Process Lines Containing , two Replace All grep search , Process Duplicate Lines , and Sort Lines ) on a 75.1 MB textbook data file , the Intel - based iMac rent 21 percent less metre than the G5 .
Other tests — creating a Zip archive in the Finder , encode an audio single file in iTunes , and yield a videodisc image ( include all required MPEG-2 rendering ) in iDVD — resulted in the most common compass of speed improvements , taking between 11 and 12 percent less time on the Intel - based iMac than on the G5 .
These young iMacs are the first Mac systems to habituate the new Extensible Firmware Interface system for booting , and that may be one of the contributing factors to fantabulous start - up times for these systems . The Intel - ground iMac booted in 25 seconds , almost half the time it took the iMac G5 .
One app , however , forever let down us during our testing : iMovie 6 . Not only was this brand - new version of Apple ’s video - redaction diligence equally buggy on both platforms , but it was dramatically slower at compressing and exporting video recording on the Intel - based system than on the G5 — so much so that we suspect iMovie ’s pitiable performance is the result of a germ within iMovie rather than any intrinsic nonstarter of the iMac .
Rosetta: Half-speed compatibility
One of the biggest mysteries about the Intel transition has been Rosetta , the technology that lets Intel - establish Macs run programs compile for Macs contain PowerPC processors . Just how tight will Rosetta tend non - Universal programs ? With this new iMac , we ’re eventually capable to get the first clear response to that question .
We tested three dissimilar non - aboriginal software on the Intel - found iMac , and compared the results to the iMac G5 . All of the run showed that PowerPC program run on the new iMac at less than half their native speed . Our standard Microsoft Word scrolling test ran at 48 percent of the f number it take to the woods on the iMac G5 ; our stock barrage fire of 14 Photoshop CS tasks ran at 45 percent of the G5 ’s speed ; an MP3 encode using the non - aboriginal iTunes 6.0.1 function at 34 percentage of the speed .
Unlike most of Apple ’s program program , BBEdit 8.2.4 offers an “ Open using Rosetta ” option that forces a Universal program to run in Rosetta . As a answer , we were able to re - go our BBEdit examination on the Intel - found iMac , but this sentence in Rosetta . The results were very much in business line with our other test : our BBEdit test take roughly twice as farseeing to run within Rosetta as it did when allowed to break away natively on the Intel processor .
First Tests: Applications in Rosetta
All scores are in minutes : seconds . All systems were run Mac OS X 10.4.4 with 512 megabit of RAM , with G5 ’s CPU execution set to Highest in the Energy Saver preference pane . We converted 45 minutes of AAC audio Indian file to MP3 using iTunes ’ High Quality mise en scene . We scrolled a 500 - page document using Microsoft Word . The Photoshop Suite examination is a set of 14 written tasks using a 50 MB file . Photoshop ’s memory was set to 70 percent and History was set to Minimum.—Macworld Lab testing by James Galbraith and Jerry Jung
The liberal question is , will applications running at half speed within Rosetta be fast enough for users ? Many applications are n’t particularly mainframe - intensive , and will probably seem quite functional under Rosetta . ( Microsoft Office , for example , will in all probability be fairly useable . ) Other hard - play applications — Photoshop comes to mind — won’t fare as well . And using a non - aboriginal rendering diligence or game would seem to be a no - go .
The f number of Rosetta will also depend a lot on your view . Yes , if you ’re upgrading to an Intel - based iMac from an iMac G5 you bought just a few months ago , all of your non - world-wide software will run at half speed . But if you ’re raise from a two- or three - year - old iMac , the speed difference may be much less detectable .
The speed of app running under Rosetta will be something to keep in mind , specially when it comes to the extroverted release of the MacBook Pro . The users of that professional - point laptop computer are far more likely to ask serious amphetamine from their applications ; if there ’s no cosmopolitan version of Photoshop uncommitted at the time , professional photographers may resist at the approximation of run Photoshop at a fraction of its speed .
What it means
If you tattle to both Apple and Intel , they ’ll tell you that the Intel Core Duo is a processor designed for laptop computer , providing a via media between performance and secure power - consumption and heat - coevals characteristics . And so the Core Duo processor in these new iMacs ( as well as the coming MacBook Pro ) is clear not meant to be the be - all , end - all when it come to bare-ass computing mogul .
That ’s one reason why Apple ’s initial speed claims of reduplicate operation ( with some tests running showing as much as a 3x focal ratio boost ) were so breathless , since they were fare from a microchip meant to run little and cool . regrettably , our test suggest that the noteworthy results of Apple ’s published trial are n’t reflected in most of the real - cosmos applications we quiz . Based on our initial test , the Modern Core - Duo - found iMac seems to be 10 to 20 pct percent faster than its predecessor when it comes to native applications , with some select chore showing melioration above and beyond that .
Potential iMac buyers who predominantly swear on applications that are n’t available in worldwide versions ( or , for that matter , those who rely on Classic , which is incompatible with Intel - establish Macs ) will probably not be interested in these first Intel system . Running a smattering of programs in Rosetta seems reasonable , but if you rely on legion applications that are n’t yet Universal , it ’s probably wise to expect .
After run these tests , several questions come in to mind — and they affect the entire Mac product railway line , not just the iMac . How optimise is Mac OS X 10.4.4 for Intel processors , and will Apple be able to improve execution on these systems over time ? Is there room for improvement in the optimisation of single software program , or is this all we ’re start to get ? How quickly will Intel improve processor operation from here , both in the Core Duo line of products and in other chip line that will wend their manner into future Apple products ?
We do n’t have all those answers yet , although several conversation with Apple voice have suggested that developers will be able to meliorate the performance of their software as they become more well-off with the new Intel computer architecture . Even Apple ’s own freshly - release iLife ’ 06 app could bear to be best optimized — and Apple congresswoman admitted as much to us .
How much amphetamine can be wrung out of succeeding improvements to software and the operating system itself ? We simply do n’t bed . There ’s reason for hope , but there ’s much more testing to be done , many more cosmopolitan applications to be written , and more Mac OS X system of rules update to be released .
[ Jason Snell is the editorial manager ofMacworld . ]
( update on January 18 at 4:46 post-mortem ET to add “ time faster than ” equivalent weight to charts . Updated again at 5:35 promethium ET to essay to clarify percentages slower v. percentages quicker v. times as fast . Updated on January 20 at 1:43 post-mortem examination ET to even out a line in the account text which switched the verbal description of two iPhoto tests . )
