Hosted by site sponsor WebMate.
Silver Tower Mac Pro (Dual Optical) Q&A - Published February 9, 2008
All Mac Q&As >> Silver Tower Mac Pro Dual Optical Q&A (Home)
To be notified of new Q&As, sign up for EveryMac.com's bimonthly email list.
How much faster are the "Early 2008" (Harpertown/Penryn) Mac Pro models compared to the original Mac Pro?
Please note that all models mentioned in this Q&A have been discontinued. The "Early 2008" Mac Pro line was replaced by the "Early 2009" line on March 3, 2009.
In the press release announcing the "Early 2008" Mac Pro, Apple heralded that this model "delivers up to twice the performance of its predecessor".
To back up this claim, the company provided synthetic performance benchmarks that show the default Mac Pro "Eight Core" 2.8 (Early 2008) is 1.9 times faster in the SPECint_rate_base2006 test and 1.7 times faster in the SPECfp_rate_base2006 test than the original Mac Pro "Quad Core" 2.66 and 1.3 times faster in both tests than the previous build-to-order "Clovertown" Mac Pro "Eight Core" 3.0.
Apple released real-world test results as well with a variety of applications that show the default Mac Pro "Eight Core" 2.8 (Early 2008) system performing between 1.2 times and 2.3 times faster than the original Mac Pro "Quad Core" 2.66 and between 1.1 and 1.3 times faster than the "Clovertown" Mac Pro "Eight Core" 3.0.
With faster and more efficient processors, larger level 2 caches, a more advanced vector engine, faster frontside buses (1.6 MHz instead of 1.33 MHz), faster memory (800 MHz instead of 667 MHz), and faster PCIe 2.0 slots, it seems reasonable for the "Early 2008" Mac Pro models to perform substantially better than their predecessors in line with Apple's reported test results.
Nevertheless, as the marketing department at any company generally is compelled to present the most favorable set of test results, rather than objective ones, independent third-party analysis always is essential.
In an in-depth review that should be read in its entirety, the always reliable MacWorld found that:
The new 2.8 GHz Mac Pro scored 22 percent higher than the older 2.66 GHz Mac Pro. In certain tests -- Cinema 4D and Compressor -- the new 2.8 GHz showed an even more impressive performance advantage, with the new model completing those tests about 75 percent faster than the old model. Comparing the new eight-core 2.8 GHz Mac Pro results to the older eight-core 3 GHz Mac Pro, the new model is faster in half of the tests. Unsurprisingly, the older 3 GHz Mac Pro had a higher Speedmark score (317) than the new 2.8GHz model (314), but not by much. . .
As it stands, the new eight-core 3 GHz system’s Speedmark score was about four percent higher than the new eight-core 2.8 GHz model, clocking in at 13 percent faster in the Compressor test and 18 percent faster in the Photoshop test, and about 3 percent faster than the old 3 GHz model. Alternately, the new four-core 2.8GHz system [available as a "downgrade" to save US$500] was about 6 percent slower than the new eight-core 2.8 GHz machine in our Speedmark test, and though these two machines performed almost on par in certain tests, the results for Cinema 4D and Compressor were 63 percent slower and 33 percent slower respectively for the 4-core machine.
Comparing the Mac Pro "Eight Core" 3.2 (Early 2008) available via build-to-order, MacWorld found that it was "nearly 9 percent faster than the stock, 2.8 GHz 8-core Mac Pro, and 4.6 percent faster than the [Early 2008] build-to-order 3 GHz system" as well as "8 percent faster at Speedmark, 9 percent faster in our Photoshop test suite, and 13 percent faster at Cinema 4D" than the previous year's build-to-order "Clovertown" Mac Pro "Eight Core" 3.0.
The continually excellent BareFeats also released a series of benchmark and application tests comparing the stock Mac Pro "Eight Core" 2.8 (Early 2008) to a build-to-order 3.2 GHz configuration, the previous year's build-to-order "Clovertown" "Eight Core" 3.0 and "Woodcrest" "Quad Core" 3.0, as well as the Power Macintosh G5 "Quad Core" (2.5).
The complete test results should be reviewed in their entirety, but the author ultimately concluded that "the 3.2 GHz 'Harpertown' was from 7% to 11% faster than the 2.8 GHz model" and "though the core frequency gain of the 3.2 GHz 'Harpertown' is only 6.7% compared to the 3.0 GHz 'Clovertown,' the speed advantage in the tests ranged from 12% to 24%."
To purchase a used Mac Pro, high-quality storage or memory for the Mac Pro, visit site sponsor Other World Computing.
Permalink | Report an Error/Typo | Sign Up for Site Update Notices
<< Mac Pro Dual Optical Drives Q&A (Main) | All Mac Q&As
Established in 1996, EveryMac.com has been created by experts with decades of experience with Apple hardware. EveryMac.com includes, and always has included, original research incorporating detailed, hands-on inspection of packaging, computers, and devices as well as extensive real-world use. All information is provided in good faith, but no website or person is perfect. Accordingly, EveryMac.com is provided "as is" without warranty of any kind whatsoever. EveryMac.com, and the authors thereof, shall not be held responsible or liable, under any circumstances, for any damages resulting from the use or inability to use the information within. For complete disclaimer and copyright information please read and understand the Terms of Use and the Privacy Policy before using EveryMac.com. Copying, scraping, or use of any content without expressed permission is not allowed, although links to any page are welcomed and appreciated.