Click for SMOKING FAST 6G SSDs!

A Click shows your site support to my Sponsors

---

The Source for Mac Performance News and Reviews

Review: MAChCarrierTM G3/500 CPU Card 10X G3 CPU Upgrade for PCI Macs Published: 11/02/99

MacBench 5.0 and ByteMark DR/3 Test Results

Intro | Benchmarks | Appl. Tests | Software Controls | Docs/Installation | Specs/Design | Summary

Benchmark Tests

Benchmark tests were run with MacBench 5.0 as it is the accepted Mac standard. I've also included BYTEMARK tests although that benchmark is not a good indicator of other important system performance areas like disk, memory and graphics card. Throughout this review I use the convention of showing CPU, Cache and Bus speeds (in MHz) in the format of (cpu speed)/(cachespeed)/(bus speed); so 500/250/50 would mean a CPU speed of 500 MHz, a backside cache speed of 250 MHz and a system bus speed of 50MHz. The default settings for the MAChCarrier G3/500 as shipped is 500/250/50. As noted on the front page of this review, the MAChCarrier G3/500 has an IBM 10X ratio (Bus to CPU multiplier), a more expensive version of the original G3 CPU. The 10X G3 CPU is required however to attain a 500MHz CPU speed. MacBench 5.0 was run on both systems used for the review - a loaded Genesis (based on a 9500 motherboard) and 9600/350. Remember that Macbench Graphics scores will vary depending on graphics mode and the installed video card. Since all these Macs have graphics cards of widely differing performance capability, this is not a reflection on the CPU card under review. In Macbench 5.0 a 1000 score is the baseline based on performance with an Apple Beige G3/300 running millions colors, 1152x870, so consider this when evaluating any scores at lower resolutions and color depths. See my notes below on disk scores and remember that disk performance will vary widely based on fragmentation, free space (outer tracks on the disk are fastest) and disk cache size set in the Memory Control Panel. Disk Cache settings boost MacBench scores up to a point (about 6MB or so) as noted in last year's Disk Cache Study. Be aware that each card and system has some tolerance variation, so these speeds may not be attainable with every card/system/hardware combination. Due to the risks involved I do not recommend overclocking but do test for maximum speeds (if the card is adjustable) during my reviews. The specific CPU chip on each card, your motherboard components, installed hardware and RAM mix can affect maximum reliable speeds. Never buy a CPU card assuming you will be able to overclock it or repeat anyone else's results (for instance reports in my Rate Your G3 Upgrade database). Consult the card vendor and your system dealer for warranty impacts from overclocking any product (required disclaimers apply). MacBench 5.0 Tests: The two graphs below compare performance of the MAChCarrier G3/500 in the Genesis system and in the 9600. Other systems and CPU upgrades are included for comparison. In the 9600, I ran tests at the maximum speed I found reliable with this particular card and system combo in both Copy-Back (noted CB) and Write-Through (noted WT) backside cache modes. All of the MacBench scores are higher than those from an early G4/400MHz CPU (2.2 stepping chip rev) upgrade in the Genesis as shown on my G4 Upgrade First Look test results. A red dot in the graph below indicates the upgrade was running beyond the rated speeds of the card. This speed was reliable in my particular systems with this particular sample but these results may not be repeatable in your Mac. MacBench 5.0 Performance Note: Publishing Graphics scores were from 1152x870, millions colors. Graphics test used 1024x768, thousands colors. The Rage128 in the Blue and White G3/400 was installed in the 66MHz PCI slot. The Genesis used a Formac Proformance 3 PCI graphics card in a 33MHz slot. The Genesis is also running at 1/2 the system bus speed as well as a less advanced PCI/memory controller. Both systems had disks appx. 80% full and not optimized. Genesis used UW SCSI Cheetah 4.5GB drive with 4MB disk cache. B&W G3/400 used stock Quantum IDE 6GB drive with OS 8.6 default disk cache setting of 6MB. The next graph shows the results of tests in the 9600/350 system. The 9600 uses an OEM (slower first revision) Rage128 card from a B&W G3 rev 1. Retail cards and later B&W G3s had the faster clock speed Rage128 (about 10% faster). Notes: Some explanation of the MacBench graph and test components. Disk Scores: The Genesis has a UW SCSI Cheetah drive (80% full) attached to an ATTO UW PCI SCSI Card. The 9600 used a Ultra2 SCSI Cheetah 4.5GB drive (10% full) attached to an ATTO Ultra2 PCI SCSI card. The B&W G3 used the onboard ATA/33 (UltraATA) IDE interface and 6GB Quantum IDE drive. Graphics Scores: Although a Rage128 was used in both the B&W G3 and the 9600, the Blue G3's 66MHz PCI slot, faster memory bus and improved PCI/memory controller as well as the faster clock speed version of the card results in better graphics card performance. This is especially true of applications that really stress the system (moving a lot of data over the bus) such as 3D Games. The Genesis used a Formac Proformance 3 card. See my video cards page for reviews of these cards and more. BYTEMARK Tests: I ran the BYTEMARK DR/3 test which is probably the most 'pure' CPU benchmark I know. I include it here for curiosity only, as I consider BYTEMARK the least indicative of all benchmarks as far as actual OS/Application performance. ByteMark is a small, synthetic benchmark and is highly affected by compiler optimizations (some tests on the PC with VisualC++ compiled versions show the PII scoring higher than the G3 for instance). I've included scores from a B&W G3/400 and some past CPU card reviews for comparison. All scores listed are from G3 CPUs with 1MB of backside cache. Scores are rounded off to two decimal places. Speculative Processing was disabled for all tests except the B&W G3 and sub-400MHz G3 upgrades. All tests used my normal extension set (the same as used for all other tests in this review). Note the very poor FPU scores for the G4/400 CPU, which I can only attribute to the very early CPU revision (2.2 stepping). I'll have more G4 CPU tests soon as I have a new G4 upgrade and G4/450 Apple system here for testing shortly. BYTEMARK DR/3 SCORES Card/Speed: Integer Score: FPU Score: XLR8 MAChCarrierG3/500 525.8/262.9/52.6 (Genesis/9500) 17.48 11.32 XLR8 MAChCarrier G3/500 500/250/50 (Genesis/9500) 16.62 10.76 XLR8 Prototype G4/400 400/200/50 (Genesis/9500) 12.81 9.98 XLR8 CarrierZIF G3/400 400/200/50 (Genesis/9500) 12.94 8.59 Blue &White G3/400 400/200/100 12.90 8.71 G3 322/214 8.92 6.70 G3 300/300 8.37 6.65 G3 266/177 7.36 5.75

Summary: Benchmark performance was the best I've seen from any Mac or upgrade so far. However I prefer to rely on real world application performance which is covered in the next page of this review. Or you may use the links below to jump to a specific page.

Index of XLR8 MAChCarrier G3/500 Review Pages Intro | Benchmarks | Appl. Tests | Software Controls | Docs/Installation | Specs/Design | Summary - or - Back to WWW.XLR8YOURMAC.COM

Copyright © Mike, 1999. All Rights Reserved. All brand or product names mentioned here are properties of their respective companies. Users of the web site must read and are bound by the terms and conditions of use.