PDA

View Full Version : XBench Results




MacBandit
Sep 24, 2002, 12:53 AM
Hey everyone download this xBench (http://xbench.com) and post your complete results here.program (http://xbench.com)

I'm especially interested in comparing the memory test results of my new Dual Ghz/DDR mac to the previous Dual Ghz.

Also before I get razed about this I know benchmarking isn't exactly and exact science and also this program is probably not 100% accurate. I'm just curious.



MacBandit
Sep 24, 2002, 12:54 AM
Results 128.34

System InfoXbench Version 1.0b2
System Version 10.2.1
Physical RAM 1024 MB
ProcessorPowerPC,G4 @ 0 [1000 MHz]
ProcessorPowerPC,G4 @ 1 [1000 MHz]

CPU Test 136.33
GCD Recursion 125.06 4.88 Mops/sec
Floating Point Basic 137.69 119.15 Mflop/sec
AltiVec Basic 160.57 828.86 Mflop/sec
Floating Point Library 121.99 5.48 Mops/sec

Thread Test 117.86
Computation 128.80 1.04 Mops/sec, 4 threads
Memory Contention 91.10 288.16 MB/sec, 2 threads
Lock Contention 133.68 1.68 Mlocks/sec, 4 threads

Memory Test 151.01
System 161.45
Allocate 128.08 67.38 Kalloc/sec
Fill 277.04 1588.67 MB/sec
Copy 79.22 475.30 MB/sec
Stream 140.57
Copy 137.35 549.40 MB/sec [altivec]
Scale 142.28 569.13 MB/sec [altivec]
Add 145.49 581.96 MB/sec [altivec]
Triad 137.15 548.59 MB/sec [altivec]

Quartz Graphics Test 128.96
Line 129.85 3.31 Klines/sec [50% alpha]
Rectangle 123.65 8.70 Krects/sec [50% alpha]
Circle 131.01 3.02 Kcircles/sec [50% alpha]
Bezier 128.71 1.40 Kbeziers/sec [50% alpha]
Text 131.56 2.22 Kchars/sec

User Interface Test 131.46
Elements 131.46 42.07 refresh/sec

Disk Test 104.45
Sequential 98.60
Uncached Write 96.35 42.69 MB/sec [256K blocks]
Uncached Read 100.85 43.57 MB/sec [256K blocks]
Random 110.29
Uncached Write 107.80 25.34 MB/sec [256K blocks]
Uncached Read 112.77 22.66 MB/sec [256K blocks]

8thDegreeSavage
Sep 24, 2002, 01:28 AM
Results 91.50
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 768 MB
Processor PowerPC,G4@0 [867 MHz]
CPU Test 99.39
GCD Recursion 96.53 3.77 Mops/sec
Floating Point Basic 101.31 87.66 Mflop/sec
AltiVec Basic 99.07 511.35 Mflop/sec
Floating Point Library 100.65 4.52 Mops/sec
Thread Test 80.65
Computation 54.47 438.85 Kops/sec, 4 threads
Memory Contention 129.04 408.14 MB/sec, 2 threads
Lock Contention 58.45 733.68 Klocks/sec, 4 threads
Memory Test 102.28
System 99.70
Allocate 103.98 54.69 Kalloc/sec
Fill 93.44 535.82 MB/sec
Copy 101.67 610.03 MB/sec
Stream 104.87
Copy 103.42 413.68 MB/sec [altivec]
Scale 103.18 412.70 MB/sec [altivec]
Add 108.67 434.70 MB/sec [altivec]
Triad 104.20 416.81 MB/sec [altivec]
Quartz Graphics Test 114.26
Line 118.72 3.02 Klines/sec [50% alpha]
Rectangle 113.08 7.96 Krects/sec [50% alpha]
Circle 119.08 2.74 Kcircles/sec [50% alpha]
Bezier 108.59 1.18 Kbeziers/sec [50% alpha]
Text 111.82 1.88 Kchars/sec
User Interface Test 92.48
Elements 92.48 29.59 refresh/sec
Disk Test 59.97
Sequential 56.07
Uncached Sequential Write 54.96 24.35 MB/sec [256K blocks]
Uncached Sequential Read 57.18 24.70 MB/sec [256K blocks]
Random 63.87
Uncached Random Write 63.61 14.95 MB/sec [256K blocks]
Uncached Random Read 64.13 12.89 MB/sec [256K blocks]

8thDegreeSavage
Sep 24, 2002, 01:29 AM
Is my score alright?...91.50 is my overall right?..is that bad or good...?:(

MacBandit
Sep 24, 2002, 01:32 AM
Originally posted by 8thDegreeSavage
Is my score alright?...91.50 is my overall right?..is that bad or good...?:(

Sounds good to me. 100 is suppose to be the approx. speed of the developers Dual 800.

8thDegreeSavage
Sep 24, 2002, 03:04 AM
Wow thats pretty kick ass then!:D

Tiauguinho
Sep 24, 2002, 06:10 AM
Here you have the Benchmarks:

PowerMac G4 DP 1Ghz Quicksilver 1024RAM and GeForce 4MX 64Mb:

Results 120.63
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 1024 MB
Processor PowerPC,G4@0 [1000 MHz]
Processor PowerPC,G4@1 [1000 MHz]
CPU Test 129.39
GCD Recursion 124.72 4.87 Mops/sec
Floating Point Basic 139.21 120.47 Mflop/sec
AltiVec Basic 132.11 681.92 Mflop/sec
Floating Point Library 121.53 5.46 Mops/sec
Thread Test 104.98
Computation 129.60 1.04 Mops/sec, 4 threads
Memory Contention 59.65 188.66 MB/sec, 2 threads
Lock Contention 125.68 1.58 Mlocks/sec, 4 threads
Memory Test 138.09
System 179.23
Allocate 126.00 66.28 Kalloc/sec
Fill 298.47 1711.55 MB/sec
Copy 113.23 679.39 MB/sec
Stream 96.95
Copy 95.41 381.63 MB/sec [altivec]
Scale 98.42 393.69 MB/sec [altivec]
Add 99.06 396.25 MB/sec [altivec]
Triad 94.91 379.64 MB/sec [altivec]
Quartz Graphics Test 126.97
Line 128.32 3.27 Klines/sec [50% alpha]
Rectangle 124.64 8.77 Krects/sec [50% alpha]
Circle 129.88 2.99 Kcircles/sec [50% alpha]
Bezier 127.91 1.39 Kbeziers/sec [50% alpha]
Text 124.08 2.09 Kchars/sec
User Interface Test 134.30
Elements 134.30 42.98 refresh/sec
Disk Test 90.06
Sequential 91.26
Uncached Sequential Write 89.57 39.69 MB/sec [256K blocks]
Uncached Sequential Read 92.95 40.15 MB/sec [256K blocks]
Random 88.86
Uncached Random Write 83.12 19.54 MB/sec [256K blocks]
Uncached Random Read 94.61 19.01 MB/sec [256K blocks]


PowerBook G4 550Mhz 768RAM:

Results 54.23
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 768 MB
Processor PowerPC,G4@0 [550 MHz]
CPU Test 66.07
GCD Recursion 57.21 2.23 Mops/sec
Floating Point Basic 70.79 61.26 Mflop/sec
AltiVec Basic 74.27 383.37 Mflop/sec
Floating Point Library 61.99 2.78 Mops/sec
Thread Test 50.58
Computation 34.28 276.13 Kops/sec, 4 threads
Memory Contention 81.26 257.03 MB/sec, 2 threads
Lock Contention 36.21 454.50 Klocks/sec, 4 threads
Memory Test 61.40
System 42.93
Allocate 67.82 35.67 Kalloc/sec
Fill 24.51 140.54 MB/sec
Copy 36.48 218.85 MB/sec
Stream 79.87
Copy 78.25 313.00 MB/sec [altivec]
Scale 79.41 317.63 MB/sec [altivec]
Add 80.97 323.89 MB/sec [altivec]
Triad 80.84 323.38 MB/sec [altivec]
Quartz Graphics Test 57.12
Line 62.12 1.58 Klines/sec [50% alpha]
Rectangle 59.68 4.20 Krects/sec [50% alpha]
Circle 55.20 1.27 Kcircles/sec [50% alpha]
Bezier 57.41 623.84 beziers/sec [50% alpha]
Text 51.19 862.01 chars/sec
User Interface Test 48.32
Elements 48.32 15.46 refresh/sec
Disk Test 41.86
Sequential 38.81
Uncached Sequential Write 39.09 17.32 MB/sec [256K blocks]
Uncached Sequential Read 38.54 16.65 MB/sec [256K blocks]
Random 44.91
Uncached Random Write 41.23 9.69 MB/sec [256K blocks]
Uncached Random Read 48.58 9.76 MB/sec [256K blocks]

Zenith
Sep 24, 2002, 06:13 AM
Results: 64.45

System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 640 MB
Processor PowerPC,G4@0 [734 MHz]
CPU Test 82.13
GCD Recursion 71.76 2.80 Mops/sec
Floating Point Basic 83.34 72.11 Mflop/sec
AltiVec Basic 93.20 481.04 Mflop/sec
Floating Point Library 80.20 3.60 Mops/sec
Thread Test 52.84
Computation 45.16 363.82 Kops/sec, 4 threads
Memory Contention 63.96 202.32 MB/sec, 2 threads
Lock Contention 49.40 620.12 Klocks/sec, 4 threads
Memory Test 70.16
System 52.36
Allocate 83.56 43.95 Kalloc/sec
Fill 29.57 169.59 MB/sec
Copy 43.94 263.64 MB/sec
Stream 87.97
Copy 87.00 347.99 MB/sec [altivec]
Scale 88.63 354.54 MB/sec [altivec]
Add 91.28 365.13 MB/sec [altivec]
Triad 84.95 339.80 MB/sec [altivec]
Quartz Graphics Test 75.80
Line 79.67 2.03 Klines/sec [50% alpha]
Rectangle 85.41 6.01 Krects/sec [50% alpha]
Circle 84.82 1.96 Kcircles/sec [50% alpha]
Bezier 73.16 795.00 beziers/sec [50% alpha]
Text 55.96 942.32 chars/sec
User Interface Test 60.55
Elements 60.55 19.37 refresh/sec
Disk Test 45.19
Sequential 41.71
Uncached Sequential Write 35.72 15.83 MB/sec [256K blocks]
Uncached Sequential Read 47.70 20.60 MB/sec [256K blocks]
Random 48.67
Uncached Random Write 36.89 8.67 MB/sec [256K blocks]
Uncached Random Read 60.46 12.15 MB/sec [256K blocks]

That's what I thought... A QS 733 without L3 cache. Take a look at the memory fill test; 29.57, 169.59 MBps. I want a 1 Ghz MP upgrade for my Mac..!

chibianh
Sep 24, 2002, 08:42 AM
Results for a Tibook 800 :)

Results 81.04
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 512 MB
Processor PowerPC,G4@0 [800 MHz]
CPU Test 106.42
GCD Recursion 84.95 3.32 Mops/sec
Floating Point Basic 119.71 103.59 Mflop/sec
AltiVec Basic 131.71 679.93 Mflop/sec
Floating Point Library 89.31 4.01 Mops/sec
Thread Test 59.92
Computation 51.49 414.78 Kops/sec, 4 threads
Memory Contention 72.74 230.06 MB/sec, 2 threads
Lock Contention 55.55 697.30 Klocks/sec, 4 threads
Memory Test 101.75
System 113.46
Allocate 94.09 49.49 Kalloc/sec
Fill 189.52 1086.78 MB/sec
Copy 56.78 340.70 MB/sec
Stream 90.03
Copy 89.15 356.61 MB/sec [altivec]
Scale 91.56 366.25 MB/sec [altivec]
Add 92.51 370.04 MB/sec [altivec]
Triad 86.89 347.56 MB/sec [altivec]
Quartz Graphics Test 89.04
Line 107.45 2.74 Klines/sec [50% alpha]
Rectangle 67.03 4.72 Krects/sec [50% alpha]
Circle 89.37 2.06 Kcircles/sec [50% alpha]
Bezier 95.55 1.04 Kbeziers/sec [50% alpha]
Text 85.77 1.44 Kchars/sec
User Interface Test 89.16
Elements 89.16 28.53 refresh/sec
Disk Test 39.94
Sequential 35.88
Uncached Sequential Write 34.99 15.50 MB/sec [256K blocks]
Uncached Sequential Read 36.78 15.89 MB/sec [256K blocks]
Random 44.00
Uncached Random Write 39.09 9.19 MB/sec [256K blocks]
Uncached Random Read 48.90 9.83 MB/sec [256K blocks]

MacBandit
Sep 24, 2002, 10:20 AM
I wish I new what was killing some of my memmory tests. For example my copy rate is down by at least 20points of what it should be.

It will be interesting to see another test with the same machine and compare to see if we have the same problem.

Gaz
Sep 24, 2002, 10:42 AM
Results 54.30
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 768 MB
Processor PowerPC,G4@0 [500 MHz]
CPU Test 75.66
GCD Recursion 43.24 1.69 Mops/sec
Floating Point Basic 64.75 56.03 Mflop/sec
AltiVec Basic 118.58 612.11 Mflop/sec
Floating Point Library 76.06 3.42 Mops/sec
Thread Test 42.75
Computation 27.69 223.10 Kops/sec, 4 threads
Memory Contention 59.15 187.09 MB/sec, 2 threads
Lock Contention 41.42 519.87 Klocks/sec, 4 threads
Memory Test 64.66
System 61.92
Allocate 76.85 40.43 Kalloc/sec
Fill 78.02 447.42 MB/sec
Copy 30.88 185.29 MB/sec
Stream 67.39
Copy 66.95 267.78 MB/sec [altivec]
Scale 66.11 264.45 MB/sec [altivec]
Add 69.08 276.31 MB/sec [altivec]
Triad 67.43 269.73 MB/sec [altivec]
Quartz Graphics Test 55.73
Line 48.20 1.23 Klines/sec [50% alpha]
Rectangle 56.08 3.95 Krects/sec [50% alpha]
Circle 59.47 1.37 Kcircles/sec [50% alpha]
Bezier 58.94 640.48 beziers/sec [50% alpha]
Text 55.98 942.76 chars/sec
User Interface Test 49.87
Elements 49.87 15.96 refresh/sec
Disk Test 37.13
Sequential 33.82
Uncached Sequential Write 33.53 14.86 MB/sec [256K blocks]
Uncached Sequential Read 34.11 14.73 MB/sec [256K blocks]
Random 40.43
Uncached Random Write 36.27 8.52 MB/sec [256K blocks]
Uncached Random Read 44.60 8.96 MB/sec [256K blocks]

Seems to be faster than the 550 TiBook I saw on here, especially in the processor stakes which is odd.

Zenith
Sep 24, 2002, 11:04 AM
Originally posted by MacBandit
I wish I new what was killing some of my memmory tests. For example my copy rate is down by at least 20points of what it should be.

It will be interesting to see another test with the same machine and compare to see if we have the same problem.

Well the copy rate is down by almost 60 on my machine, and your machine has a fill rate ten times faster than mine.. :eek:

alex_ant
Sep 24, 2002, 12:22 PM
What's up with this 600, 700, 800 MFLOPS ****e? Isn't the dual GHz supposed to be capable of FIFTEEN GIGAFLOPPERS!?

alex_ant
Sep 24, 2002, 12:25 PM
Originally posted by Gaz
Seems to be faster than the 550 TiBook I saw on here, especially in the processor stakes which is odd.
The 550MHz is generally the slowest TiBook. Same slow bus speed as the 500, but less memory bandwidth than even the 400. The rev Bs used a different PPC series (7440?) than the As.

cyks
Sep 24, 2002, 12:52 PM
Results 136.39
System Info
Xbench Version 1.0b2
System Version 10.2
Physical RAM 1280 MB
Processor PowerPC,G4@0 [1000 MHz]
Processor PowerPC,G4@1 [1000 MHz]
CPU Test 134.21
GCD Recursion 124.64 4.87 Mops/sec
Floating Point Basic 132.73 114.88 Mflop/sec
AltiVec Basic 157.68 813.88 Mflop/sec
Floating Point Library 121.77 5.47 Mops/sec
Thread Test 126.45
Computation 115.22 928.23 Kops/sec, 4 threads
Memory Contention 146.07 462.01 MB/sec, 2 threads
Lock Contention 118.07 1.48 Mlocks/sec, 4 threads
Memory Test 148.51
System 136.45
Allocate 126.69 66.64 Kalloc/sec
Fill 199.03 1141.34 MB/sec
Copy 83.63 501.81 MB/sec
Stream 160.57
Copy 158.37 633.46 MB/sec [altivec]
Scale 161.35 645.40 MB/sec [altivec]
Add 168.47 673.88 MB/sec [altivec]
Triad 154.08 616.31 MB/sec [altivec]
Quartz Graphics Test 109.53
Line 121.70 3.10 Klines/sec [50% alpha]
Rectangle 83.89 5.90 Krects/sec [50% alpha]
Circle 111.99 2.58 Kcircles/sec [50% alpha]
Bezier 117.01 1.27 Kbeziers/sec [50% alpha]
Text 113.05 1.90 Kchars/sec
User Interface Test 115.58
Elements 115.58 36.99 refresh/sec
Disk Test 71.09
Sequential 66.22
Uncached Sequential Write 65.30 28.93 MB/sec [256K blocks]
Uncached Sequential Read 67.13 29.00 MB/sec [256K blocks]
Random 75.97
Uncached Random Write 69.91 16.43 MB/sec [256K blocks]
Uncached Random Read 82.03 16.48 MB/sec [256K blocks]

GeeYouEye
Sep 24, 2002, 02:26 PM
Results 37.13
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 192 MB
Processor PowerPC,750@0 [500 MHz]
CPU Test 57.15
GCD Recursion 41.85 1.63 Mops/sec
Floating Point Basic 58.49 50.64 Mflop/sec
Floating Point Library 71.10 3.19 Mops/sec
Thread Test 32.52
Computation 31.58 254.38 Kops/sec, 4 threads
Memory Contention 20.07 63.49 MB/sec, 2 threads
Lock Contention 45.91 576.35 Klocks/sec, 4 threads
Memory Test 33.15
System 37.91
Allocate 88.90 46.76 Kalloc/sec
Fill 16.41 94.11 MB/sec
Copy 8.41 50.44 MB/sec
Stream 28.39
Copy 28.13 112.51 MB/sec
Scale 28.16 112.63 MB/sec
Add 28.63 114.51 MB/sec
Triad 28.64 114.57 MB/sec
Quartz Graphics Test 41.25
Line 40.05 1.02 Klines/sec [50% alpha]
Rectangle 48.37 3.40 Krects/sec [50% alpha]
Circle 48.49 1.12 Kcircles/sec [50% alpha]
Bezier 44.49 483.38 beziers/sec [50% alpha]
Text 24.87 418.91 chars/sec
User Interface Test 31.50
Elements 31.50 10.08 refresh/sec
Disk Test 27.21
Sequential 23.35
Uncached Sequential Write 21.19 9.39 MB/sec [256K blocks]
Uncached Sequential Read 25.50 11.02 MB/sec [256K blocks]
Random 31.08
Uncached Random Write 28.51 6.70 MB/sec [256K blocks]
Uncached Random Read 33.65 6.76 MB/sec [256K blocks]

GeeYouEye
Sep 24, 2002, 02:30 PM
Results 43.05
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 320 MB
Processor PowerPC,750@0 [450 MHz]
CPU Test 58.46
GCD Recursion 42.13 1.65 Mops/sec
Floating Point Basic 61.91 53.57 Mflop/sec
Floating Point Library 71.34 3.20 Mops/sec
Thread Test 33.99
Computation 28.62 230.61 Kops/sec, 4 threads
Memory Contention 28.77 91.00 MB/sec, 2 threads
Lock Contention 44.59 559.72 Klocks/sec, 4 threads
Memory Test 35.70
System 37.03
Allocate 77.36 40.69 Kalloc/sec
Fill 23.05 132.16 MB/sec
Copy 10.69 64.14 MB/sec
Stream 34.36
Copy 34.09 136.37 MB/sec
Scale 34.10 136.41 MB/sec
Add 34.59 138.35 MB/sec
Triad 34.66 138.65 MB/sec
Quartz Graphics Test 49.39
Line 44.06 1.12 Klines/sec [50% alpha]
Rectangle 53.73 3.78 Krects/sec [50% alpha]
Circle 54.23 1.25 Kcircles/sec [50% alpha]
Bezier 50.83 552.31 beziers/sec [50% alpha]
Text 44.08 742.37 chars/sec
User Interface Test 44.66
Elements 44.66 14.29 refresh/sec
Disk Test 44.66
Sequential 41.11
Uncached Sequential Write 40.33 17.87 MB/sec [256K blocks]
Uncached Sequential Read 41.89 18.09 MB/sec [256K blocks]
Random 48.22
Uncached Random Write 44.40 10.44 MB/sec [256K blocks]
Uncached Random Read 52.04 10.46 MB/sec [256K blocks]

MacBandit
Sep 24, 2002, 09:14 PM
[QUOTE]Originally posted by cyks
Results 136.39
System Info
Xbench Version 1.0b2
System Version 10.2
Physical RAM 1280 MB
Processor PowerPC,G4@0 [1000 MHz]
Processor PowerPC,G4@1 [1000 MHz]


Memory Test 148.51
System 136.45
Allocate 126.69 66.64 Kalloc/sec
Fill 199.03 1141.34 MB/sec
Copy 83.63 501.81 MB/sec
Stream 160.57
Copy 158.37 633.46 MB/sec [altivec]
Scale 161.35 645.40 MB/sec [altivec]
Add 168.47 673.88 MB/sec [altivec]
Triad 154.08 616.31 MB/sec [altivec]



Your copy rate was very similar to mine but your fill rate was quite a bit lower. I was wondering did you do this on a fresh restart?

MacBandit
Sep 24, 2002, 09:19 PM
Originally posted by alex_ant
What's up with this 600, 700, 800 MFLOPS ****e? Isn't the dual GHz supposed to be capable of FIFTEEN GIGAFLOPPERS!?

It's theoretically capable of something like that if everything in this world was perfect. In actual like I have seen somewhere around a max of 9 GigaFlops. I don't think this program is very dual processor or altivec aware that's why it has the low ratings.

I did state at the begining of the thread that benchmarking is not exact. Basically all we're achieving here is an equally flawed and irrelevant score that we can compare to each other.:D


Also for those saying please don't laugh no one will this is an exercise in gathering of data. I want everyone to report.

MacBandit
Sep 24, 2002, 09:23 PM
Originally posted by cyks

I was comparing line for line and saw some rather large dissimilarities. Then I noticed you're still running 10.2. I wonder if that's the difference?

Stike
Sep 24, 2002, 09:53 PM
Results 102.48
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 512 MB
Processor PowerPC,G4@0 [934 MHz]
CPU Test 118.72
GCD Recursion 101.90 3.98 Mops/sec
Floating Point Basic 134.33 116.25 Mflop/sec
AltiVec Basic 131.52 678.86 Mflop/sec
Floating Point Library 107.13 4.81 Mops/sec
Thread Test 73.61
Computation 60.66 488.69 Kops/sec, 4 threads
Memory Contention 99.49 314.68 MB/sec, 2 threads
Lock Contention 60.68 761.70 Klocks/sec, 4 threads
Memory Test 134.76
System 154.31
Allocate 113.93 59.93 Kalloc/sec
Fill 239.93 1375.88 MB/sec
Copy 109.06 654.35 MB/sec
Stream 115.21
Copy 111.66 446.66 MB/sec [altivec]
Scale 112.55 450.22 MB/sec [altivec]
Add 121.93 487.72 MB/sec [altivec]
Triad 114.68 458.70 MB/sec [altivec]
Quartz Graphics Test 121.25
Line 122.27 3.11 Klines/sec [50% alpha]
Rectangle 121.36 8.54 Krects/sec [50% alpha]
Circle 127.02 2.93 Kcircles/sec [50% alpha]
Bezier 118.22 1.28 Kbeziers/sec [50% alpha]
Text 117.36 1.98 Kchars/sec
User Interface Test 121.21
Elements 121.21 38.79 refresh/sec
Disk Test 45.32
Sequential 40.25
Uncached Sequential Write 39.16 17.35 MB/sec [256K blocks]
Uncached Sequential Read 41.33 17.85 MB/sec [256K blocks]
Random 50.39
Uncached Random Write 51.51 12.11 MB/sec [256K blocks]
Uncached Random Read 49.26 9.90 MB/sec [256K blocks]


*The HD-Performance is somewhat low, because the test was performed on a 5400 Drive*

Rower_CPU
Sep 24, 2002, 10:48 PM
Results 69.00
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 640 MB
Processor PowerPC,G4@0 [400 MHz]
CPU Test 78.88
GCD Recursion 40.82 1.59 Mops/sec
Floating Point Basic 72.74 62.94 Mflop/sec
AltiVec Basic 132.10 681.95 Mflop/sec
Floating Point Library 69.87 3.14 Mops/sec
Thread Test 51.76
Computation 26.44 212.98 Kops/sec, 4 threads
Memory Contention 87.36 276.30 MB/sec, 2 threads
Lock Contention 41.49 520.78 Klocks/sec, 4 threads
Memory Test 76.37
System 66.71
Allocate 74.31 39.09 Kalloc/sec
Fill 87.79 503.44 MB/sec
Copy 38.02 228.13 MB/sec
Stream 86.03
Copy 83.64 334.55 MB/sec [altivec]
Scale 84.52 338.09 MB/sec [altivec]
Add 88.49 353.98 MB/sec [altivec]
Triad 87.46 349.84 MB/sec [altivec]
Quartz Graphics Test 56.46
Line 51.00 1.30 Klines/sec [50% alpha]
Rectangle 57.88 4.07 Krects/sec [50% alpha]
Circle 62.23 1.43 Kcircles/sec [50% alpha]
Bezier 59.22 643.52 beziers/sec [50% alpha]
Text 51.94 874.71 chars/sec
User Interface Test 55.44
Elements 55.44 17.74 refresh/sec
Disk Test 49.59
Sequential 41.71
Uncached Sequential Write 37.53 16.63 MB/sec [256K blocks]
Uncached Sequential Read 45.89 19.82 MB/sec [256K blocks]
Random 57.46
Uncached Random Write 56.59 13.30 MB/sec [256K blocks]
Uncached Random Read 58.33 11.72 MB/sec [256K blocks]

bidge
Sep 24, 2002, 11:51 PM
Results 64.77
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 384 MB
Processor PowerPC,G4@0 [700 MHz]
CPU Test 82.26
GCD Recursion 70.28 2.74 Mops/sec
Floating Point Basic 90.29 78.13 Mflop/sec
AltiVec Basic 89.56 462.33 Mflop/sec
Floating Point Library 78.90 3.54 Mops/sec
Thread Test 59.41
Computation 44.51 358.61 Kops/sec, 4 threads
Memory Contention 86.56 273.78 MB/sec, 2 threads
Lock Contention 47.16 591.96 Klocks/sec, 4 threads
Memory Test 65.62
System 51.55
Allocate 84.95 44.69 Kalloc/sec
Fill 34.87 199.96 MB/sec
Copy 34.82 208.91 MB/sec
Stream 79.70
Copy 78.72 314.88 MB/sec [altivec]
Scale 79.19 316.76 MB/sec [altivec]
Add 81.84 327.37 MB/sec [altivec]
Triad 79.04 316.18 MB/sec [altivec]
Quartz Graphics Test 71.62
Line 75.06 1.91 Klines/sec [50% alpha]
Rectangle 70.26 4.94 Krects/sec [50% alpha]
Circle 80.02 1.84 Kcircles/sec [50% alpha]
Bezier 72.05 782.92 beziers/sec [50% alpha]
Text 60.72 1.02 Kchars/sec
User Interface Test 57.20
Elements 57.20 18.30 refresh/sec
Disk Test 52.52
Sequential 49.85
Uncached Sequential Write 49.03 21.72 MB/sec [256K blocks]
Uncached Sequential Read 50.67 21.89 MB/sec [256K blocks]
Random 55.19
Uncached Random Write 51.14 12.02 MB/sec [256K blocks]
Uncached Random Read 59.23 11.90 MB/sec [256K blocks]

G5orbust
Sep 25, 2002, 12:37 AM
Results 48.15
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 512 MB
Processor PowerPC,G4@0 [934 MHz]
CPU Test 33.38
GCD Recursion 33.96 1.33 Mops/sec
Floating Point Basic 37.36 32.33 Mflop/sec
AltiVec Basic 31.89 164.59 Mflop/sec
Floating Point Library 30.31 1.36 Mops/sec
Thread Test 47.37
Computation 31.72 255.52 Kops/sec, 4 threads
Memory Contention 72.31 228.72 MB/sec, 2 threads
Lock Contention 38.08 478.04 Klocks/sec, 4 threads
Memory Test 48.68
System 43.48
Allocate 34.71 18.26 Kalloc/sec
Fill 62.42 357.92 MB/sec
Copy 33.32 199.93 MB/sec
Stream 53.88
Copy 58.25 233.00 MB/sec [altivec]
Scale 51.83 207.32 MB/sec [altivec]
Add 57.45 229.81 MB/sec [altivec]
Triad 47.99 191.96 MB/sec [altivec]
Quartz Graphics Test 59.21
Line 51.38 1.31 Klines/sec [50% alpha]
Rectangle 76.16 5.36 Krects/sec [50% alpha]
Circle 75.37 1.74 Kcircles/sec [50% alpha]
Bezier 42.81 465.18 beziers/sec [50% alpha]
Text 50.31 847.28 chars/sec
User Interface Test 40.28
Elements 40.28 12.89 refresh/sec
Disk Test 59.96
Sequential 50.33
Uncached Sequential Write 46.52 20.61 MB/sec [256K blocks]
Uncached Sequential Read 54.14 23.39 MB/sec [256K blocks]
Random 69.59
Uncached Random Write 57.18 13.44 MB/sec [256K blocks]
Uncached Random Read 82.00 16.48 MB/sec [256K blocks]


im gunna run this again with no programs running at all, so the second one will be the better one.

G5orbust
Sep 25, 2002, 12:42 AM
Ok here we go this is what i was looking for:

Results 94.09
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 512 MB
Processor PowerPC,G4@0 [934 MHz]
CPU Test 99.41
GCD Recursion 91.42 3.57 Mops/sec
Floating Point Basic 105.76 91.51 Mflop/sec
AltiVec Basic 105.42 544.16 Mflop/sec
Floating Point Library 95.04 4.27 Mops/sec
Thread Test 82.41
Computation 58.76 473.41 Kops/sec, 4 threads
Memory Contention 127.65 403.76 MB/sec, 2 threads
Lock Contention 60.81 763.27 Klocks/sec, 4 threads
Memory Test 119.36
System 142.96
Allocate 98.76 51.95 Kalloc/sec
Fill 219.09 1256.38 MB/sec
Copy 111.04 666.23 MB/sec
Stream 95.76
Copy 95.04 380.14 MB/sec [altivec]
Scale 95.90 383.60 MB/sec [altivec]
Add 98.22 392.87 MB/sec [altivec]
Triad 93.89 375.56 MB/sec [altivec]
Quartz Graphics Test 109.87
Line 105.76 2.69 Klines/sec [50% alpha]
Rectangle 116.62 8.20 Krects/sec [50% alpha]
Circle 128.10 2.95 Kcircles/sec [50% alpha]
Bezier 99.44 1.08 Kbeziers/sec [50% alpha]
Text 99.44 1.67 Kchars/sec
User Interface Test 93.88
Elements 93.88 30.04 refresh/sec
Disk Test 59.59
Sequential 53.94
Uncached Sequential Write 49.44 21.91 MB/sec [256K blocks]
Uncached Sequential Read 58.43 25.24 MB/sec [256K blocks]
Random 65.24
Uncached Random Write 52.44 12.33 MB/sec [256K blocks]
Uncached Random Read 78.05 15.68 MB/sec [256K blocks]

MacBandit
Sep 25, 2002, 01:03 AM
Originally posted by G5orbust
Ok here we go this is what i was looking for:



You could just blame your previous post on cell phone radiation. ;) :D

mc68k
Sep 25, 2002, 01:21 AM
9600/300
XLR8 g4/450
768MB RAM
u160 15k cheetah
radeon mac edition pci
--
QE over PCI:
Total score: 42.73

Quartz through CPU:
Total score: 43.62
--
It may be faster in the benchmarks for quartz to go through the CPU, but real-world for me says Quartz on the GPU. The circle, line, etc. tests don't seem to test the GL compositor much.

cyks
Sep 25, 2002, 02:48 AM
Just out of curiousity- and since I needed to update the system anyway- I re-ran the test... and overall it improved- however so slightly in most of them. Take a peak.

Results 119.62
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 1280 MB
Processor PowerPC,G4@0 [1000 MHz]
Processor PowerPC,G4@1 [1000 MHz]
Thread Test 120.69
Computation 125.13 1.01 Mops/sec, 4 threads
Memory Contention 106.98 338.37 MB/sec, 2 threads
Lock Contention 129.97 1.63 Mlocks/sec, 4 threads
Memory Test 150.32
System 159.91
Allocate 125.95 66.26 Kalloc/sec
Fill 274.05 1571.54 MB/sec
Copy 79.74 478.42 MB/sec
Stream 140.73
Copy 137.81 551.23 MB/sec [altivec]
Scale 142.02 568.06 MB/sec [altivec]
Add 145.77 583.06 MB/sec [altivec]
Triad 137.32 549.28 MB/sec [altivec]
Quartz Graphics Test 114.19
Line 123.70 3.15 Klines/sec [50% alpha]
Rectangle 85.32 6.00 Krects/sec [50% alpha]
Circle 113.99 2.63 Kcircles/sec [50% alpha]
Bezier 124.50 1.35 Kbeziers/sec [50% alpha]
Text 123.42 2.08 Kchars/sec
User Interface Test 126.15
Elements 126.15 40.37 refresh/sec
Disk Test 84.90
Sequential 80.57
Uncached Sequential Write 72.52 32.13 MB/sec [256K blocks]
Uncached Sequential Read 88.61 38.28 MB/sec [256K blocks]
Random 89.23
Uncached Random Write 81.92 19.26 MB/sec [256K blocks]
Uncached Random Read 96.54 19.40 MB/sec [256K blocks]

MacBandit
Sep 25, 2002, 10:09 AM
Originally posted by cyks
Just out of curiousity- and since I needed to update the system anyway- I re-ran the test... and overall it improved- however so slightly in most of them. Take a peak.



I noticed you didn't run your CPU test I wonder if this brought down your overall score.

Nipsy
Sep 25, 2002, 04:58 PM
2002 QS 733 1.5GB/240GB Raid 0:
Results 88.84
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 1536 MB
Processor PowerPC,G4@0 [734 MHz]
CPU Test 99.48
GCD Recursion 79.81 3.12 Mops/sec
Floating Point Basic 107.71 93.20 Mflop/sec
AltiVec Basic 124.56 642.91 Mflop/sec
Floating Point Library 85.84 3.86 Mops/sec
Thread Test 66.56
Computation 45.26 364.65 Kops/sec, 4 threads
Memory Contention 104.85 331.63 MB/sec, 2 threads
Lock Contention 49.56 622.05 Klocks/sec, 4 threads
Memory Test 85.58
System 59.06
Allocate 84.75 44.58 Kalloc/sec
Fill 44.34 254.24 MB/sec
Copy 48.10 288.62 MB/sec
Stream 112.10
Copy 109.71 438.83 MB/sec [altivec]
Scale 110.24 440.97 MB/sec [altivec]
Add 118.37 473.50 MB/sec [altivec]
Triad 110.07 440.26 MB/sec [altivec]
Quartz Graphics Test 74.93
Line 92.53 2.36 Klines/sec [50% alpha]
Rectangle 65.56 4.61 Krects/sec [50% alpha]
Circle 84.69 1.95 Kcircles/sec [50% alpha]
Bezier 74.87 813.51 beziers/sec [50% alpha]
Text 57.00 959.89 chars/sec
User Interface Test 61.75
Elements 61.75 19.76 refresh/sec
Disk Test 144.73
Sequential 162.88
Uncached Sequential Write 161.79 71.68 MB/sec [256K blocks]
Uncached Sequential Read 163.96 70.83 MB/sec [256K blocks]
Random 126.58
Uncached Random Write 136.48 32.08 MB/sec [256K blocks]
Uncached Random Read 116.67 23.45 MB/sec [256K blocks]

G5orbust
Sep 25, 2002, 05:47 PM
Originally posted by MacBandit



You could just blame your previous post on cell phone radiation. ;) :D

lol.... i wonder if i can sue?? :D ;) :p

MacBandit
Sep 25, 2002, 08:52 PM
I wrote a letter to Ladd Van Tol the creator of Xbench asking him about it here is the letter I sent him.

I have some basic questions about Xbench. First though here is a thread I started at MacRumors.com where we have been posting our results.

http://forums.macrumors.com/showthread.php?s=&threadid=11789&perpage=25&pagenumber=1

I have been wondering some basic things like what variables will effect xBench results. For example hard drive size, had drive free space, open applications, etc.. Also I've been wondering the basics behind some of the xBench benchmarks. Like what process it goes through to test memory etc..

I will really any information you provide me to the people on the thread or you can simply post it there yourself.

Thank you for your help.

Louis Stevenson

MacBandit
Sep 25, 2002, 08:53 PM
Here is the reply he sent me. It helps explain some of the odd results.


Louis,

I don't have a MacRumors account, so if you could pass this on:

Different tests will stress different areas of the System. Xbench is by no means even, or completely fair, but it does strive to measure some of the major performance bottlenecks that typical applications will experience.

I'll try to list the factors that effect each test:

First, and most importantly, ALL tests can be impacted by open applications, or having little memory available. You should be able to use top or ProcessViewer prior to running the benchmark to help you determine if any background processes/applications are using CPU time, or large amounts of memory. If you run the benchmark, and you hear the disk running during tests other than the disk test, you may be starting to page into VM, which will lower your scores considerably.

1. CPU Test (single processor only - a test of one application doing single-threaded work)
A) GCD Recursion - almost entirely limited by the processor's register speed, L1 cache, and integer math
B) Floating Point Basic - measures single precision floating point operations (+, -, *, /)
C) AltiVec Basic - measures single precision floating point operations implemented with AltiVec operations
D) Floating Point Library - measures double precision math library operations like sin, cos, sqrt, etc.

Unfortunately, in b2, Floating Point and AltiVec tests are somewhat flawed - they rely too heavily on memory bandwidth, and may make low memory machines VM page, producing extremely low results. This will be corrected soon. Their "FLOP" rating may never be directly comparable to theoretical FLOPs, or a real-world FLOPs produced by another benchmark.

2. Thread Test (tests multiple processors - a test of multiple applications, or a single app doing multithreading)
A) Computation - measures 4 worker threads performing integer operations, plus some memory bandwidth - always faster on MP machines
B) Memory Contention - measures 2 worker threads doing memory copies (same as Stream Copy) - usually faster on MP machines.
Notice that 2 threads won't achieve the same throughput as a single thread, which doesn't compete for memory bandwidth.
C) Lock Contention - measures 4 threads quickly acquiring and releasing thread locks - usually faster on MP machines
- locking performance may be important in certain types of multithreaded code.

The thread tests aren't representative of all types of threaded code, but they do measure some of the factors that effect threaded applications.

3. Memory Test (tests ability to perform memory operations)
A) System
a) Allocate - measures the system's ability to allocate many varying-sized blocks of data, using standard system calls
b) Fill - measures the system's ability to fill a large block with data, using standard system calls
c) Copy - measures the system's ability to copy data from one block to another, using standard system calls
B) Stream (derived from the standard STREAM benchmark - http://www.cs.virginia.edu/stream/)
These use 64-bit doubles and altivec cache prefetching when appropriate
a) Copy - measures copying speed between 2 large buffers,
b) Scale - measures load-float multiply-store operations between 2 large buffers
c) Add - measures load-load-add-store operations between 3 large buffers
d) Triad - measures load-load-multiply-add-store operations between 3 large buffers (scale and add in one step)

These tests will do better with more memory bandwidth. I expect DDR Macs to perform better, as their memory subsystem is optimized for big sequential reads/writes. On a system with very little memory, these may perform slowly.

I've seen Fill and Copy perform oddly on different machines - it appears that the OS or hardware is optimizing differently in some cases.

4. Quartz Graphics Test
A) Line - measures drawing lines of varying widths, colors and rotations at 50% alpha
B) Rectangle - measures drawing rects of varying widths, colors and rotations at 50% alpha
B) Circle - measures drawing circles of varying diameter, colors and rotations at 50% alpha
C) Bezier - measures drawing beziers of varying widths, colors and rotations at 50% alpha [same basic bezier curve repeated]
D) Text - measures drawing characters of varying font sizes and rotations at 100% alpha

This test does better with a better graphics card, more memory bandwidth, more CPU, altivec, etc. It's up to the system how to optimize the drawing.

5. Disk Test
A) Sequential
These tests measure typical throughput to the drive.
a) Uncached Write - measures writing in 256k blocks until a 100MB file is filled
b) Uncached Read - measures reading in a 100MB file in 256K blocks
B) Random
These tests will be slightly impacted by the disks's seek time
a) Uncached Write - measures writing 256k blocks in random locations into a 100MB file
b) Uncached Read - measures reading 256k blocks at random locations in a 100MB file

Most disks have slower throughput as they become more full and/or fragmented, so an extremely full disk may perform worse than expected.

Anyway, hope this helps out. Let me know if I can clarify any points.

I hope to continue to improve the accuracy, and provide comparison capabilities, so as to make Xbench more useful.

- Ladd

G5orbust
Sep 25, 2002, 10:23 PM
wow thats pretty cool. That also explains why i got like a 40 w/ like 2 apps open, but a 94 with none runing. Thanks for the effort.

zimv20
Sep 26, 2002, 12:00 AM
Results 30.66
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 192 MB
Processor PowerPC,750@0 [401 MHz]
CPU Test 36.06
GCD Recursion 39.18 1.53 Mops/sec
Floating Point Basic 8.82 7.63 Mflop/sec
Floating Point Library 60.17 2.70 Mops/sec
Thread Test 28.82
Computation 24.82 199.94 Kops/sec, 4 threads
Memory Contention 21.06 66.63 MB/sec, 2 threads
Lock Contention 40.57 509.25 Klocks/sec, 4 threads
Memory Test 33.38
System 34.36
Allocate 69.32 36.46 Kalloc/sec
Fill 23.60 135.35 MB/sec
Copy 10.17 61.04 MB/sec
Stream 32.40
Copy 31.68 126.70 MB/sec
Scale 31.64 126.57 MB/sec
Add 33.13 132.52 MB/sec
Triad 33.15 132.62 MB/sec
Quartz Graphics Test 28.07
Line 24.88 633.34 lines/sec [50% alpha]
Rectangle 23.75 1.67 Krects/sec [50% alpha]
Circle 25.66 591.35 circles/sec [50% alpha]
Bezier 38.33 416.47 beziers/sec [50% alpha]
Text 27.73 466.95 chars/sec
User Interface Test 34.94
Elements 34.94 11.18 refresh/sec
Disk Test 22.67
Sequential 19.17
Uncached Sequential Write 18.91 8.38 MB/sec [256K blocks]
Uncached Sequential Read 19.44 8.40 MB/sec [256K blocks]
Random 26.16
Uncached Random Write 23.79 5.59 MB/sec [256K blocks]
Uncached Random Read 28.54 5.74 MB/sec [256K blocks]

---------------------

it'd be great to see results from a 700 MHz iBook, as i'm thinking about getting one but fear it will be only a modest improvement from my pbook.

anyone? bueller?

MacBandit
Sep 26, 2002, 12:05 AM
Originally posted by zimv20

it'd be great to see results from a 700 MHz iBook, as i'm thinking about getting one but fear it will be only a modest improvement from my pbook.

anyone? bueller?


I think you will be pleasantly surprised at the speed of the new G3s. Also the iBook sports a faster hard drive among other things.

G5orbust
Sep 26, 2002, 12:06 AM
Originally posted by MacBandit



I think you will be pleasantly surprised at the speed of the new G3s. Also the iBook sports a faster hard drive among other things.


Also higher L2 cache and betetr performance all around

zimv20
Sep 26, 2002, 12:13 AM
Originally posted by MacBandit



I think you will be pleasantly surprised at the speed of the new G3s. Also the iBook sports a faster hard drive among other things.

awesome. let's see some numbers, someone.

this makes me wanna put osx on my dual 500 g4 just to do the benchmark.

MacBandit
Sep 26, 2002, 12:18 AM
I'm really glad I started this thread it's been a lot of fun. I've learned a little bit from some of the results.

To all of you take these results with a grain of salt. If you read the creators reply to my email carefully you will see that on some of the tests like the memory copy test he says there are strange results that vary from computer to computer.

G5orbust
Sep 26, 2002, 12:21 AM
Originally posted by MacBandit
I'm really glad I started this thread it's been a lot of fun. I've learned a little bit from some of the results.

To all of you take these results with a grain of salt. If you read the creators reply to my email carefully you will see that on some of the tests like the memory copy test he says there are strange results that vary from computer to computer.

yeah im happy u did too! i never knew about this benchmarking program before now. now i dont think my computer is crappy wehn it start sto slow down cuz it got a 94!

G5orbust
Sep 28, 2002, 01:13 PM
this is the results on a dual 867 in the san diego apple store:

Results 102.78
System Info
Xbench Version 1.0b2
System Version 10.2
Physical RAM 256 MB
Processor PowerPC,G4@0 [867 MHz]
Processor PowerPC,G4@1 [867 MHz]
CPU Test 83.93
GCD Recursion 108.08 4.22 Mops/sec
Floating Point Basic 114.72 99.27 Mflop/sec
AltiVec Basic 7.89 40.74 Mflop/sec
Floating Point Library 105.02 4.72 Mops/sec
Thread Test 96.31
Computation 110.08 886.85 Kops/sec, 4 threads
Memory Contention 63.93 202.23 MB/sec, 2 threads
Lock Contention 114.92 1.44 Mlocks/sec, 4 threads
Memory Test 115.37
System 120.28
Allocate 111.18 58.48 Kalloc/sec
Fill 185.80 1065.47 MB/sec
Copy 63.87 383.24 MB/sec
Stream 110.46
Copy 109.36 437.45 MB/sec [altivec]
Scale 111.51 446.04 MB/sec [altivec]
Add 115.17 460.70 MB/sec [altivec]
Triad 105.79 423.15 MB/sec [altivec]
Quartz Graphics Test 110.57
Line 106.53 2.71 Klines/sec [50% alpha]
Rectangle 107.79 7.58 Krects/sec [50% alpha]
Circle 113.98 2.63 Kcircles/sec [50% alpha]
Bezier 111.29 1.21 Kbeziers/sec [50% alpha]
Text 113.24 1.91 Kchars/sec
User Interface Test 112.48
Elements 112.48 35.99 refresh/sec
Disk Test 98.00
Sequential 93.01
Uncached Sequential Write 90.95 40.30 MB/sec [256K blocks]
Uncached Sequential Read 95.06 41.06 MB/sec [256K blocks]
Random 103.00
Uncached Random Write 103.43 24.31 MB/sec [256K blocks]
Uncached Random Read 102.57 20.61 MB/sec [256K blocks]

stromie952
Sep 28, 2002, 01:48 PM
Results 34.06
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 320 MB
Processor PowerPC,750@0 [500 MHz]
CPU Test 48.12
GCD Recursion 35.76 1.40 Mops/sec
Floating Point Basic 48.98 42.38 Mflop/sec
Floating Point Library 59.62 2.68 Mops/sec
Thread Test 27.65
Computation 25.04 201.74 Kops/sec, 4 threads
Memory Contention 20.41 64.54 MB/sec, 2 threads
Lock Contention 37.50 470.72 Klocks/sec, 4 threads
Memory Test 29.23
System 32.73
Allocate 74.55 39.22 Kalloc/sec
Fill 15.65 89.75 MB/sec
Copy 8.00 47.98 MB/sec
Stream 25.72
Copy 25.56 102.24 MB/sec
Scale 25.58 102.31 MB/sec
Add 25.88 103.50 MB/sec
Triad 25.87 103.47 MB/sec
Quartz Graphics Test 36.72
Line 31.63 805.25 lines/sec [50% alpha]
Rectangle 47.58 3.35 Krects/sec [50% alpha]
Circle 44.27 1.02 Kcircles/sec [50% alpha]
Bezier 30.89 335.67 beziers/sec [50% alpha]
Text 29.23 492.29 chars/sec
User Interface Test 34.95
Elements 34.95 11.18 refresh/sec
Disk Test 27.70
Sequential 24.06
Uncached Sequential Write 23.34 10.34 MB/sec [256K blocks]
Uncached Sequential Read 24.78 10.71 MB/sec [256K blocks]
Random 31.35
Uncached Random Write 28.31 6.66 MB/sec [256K blocks]
Uncached Random Read 34.38 6.91 MB/sec [256K blocks]

MacBandit
Sep 28, 2002, 02:01 PM
Originally posted by G5orbust
this is the results on a dual 867 in the san diego apple store:


It's amazing how much slower it is as compared to the Dual/1Ghz/DDR at some tasks.

Megaquad
Sep 28, 2002, 02:09 PM
Somebody with PBG4 800 MHz,please post results of xbench while running itunes and few more apps. I would really like to get one of those nice machines but I hope that wont be a mistake..
BTW,i need some os x utility for defragmenting my HD, any ideas? I just hope it wont screw up my data..
----------------------------------
Results 34.70
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 320 MB
Processor PowerPC,750@0 [350 MHz]
CPU Test 42.89
GCD Recursion 30.17 1.18 Mops/sec
Floating Point Basic 45.59 39.45 Mflop/sec
Floating Point Library 52.93 2.38 Mops/sec
Thread Test 26.04
Computation 21.06 169.68 Kops/sec, 4 threads
Memory Contention 23.29 73.66 MB/sec, 2 threads
Lock Contention 33.77 423.90 Klocks/sec, 4 threads
Memory Test 32.78
System 30.83
Allocate 59.61 31.36 Kalloc/sec
Fill 22.23 127.45 MB/sec
Copy 10.64 63.84 MB/sec
Stream 34.74
Copy 34.70 138.78 MB/sec
Scale 34.78 139.13 MB/sec
Add 34.76 139.05 MB/sec
Triad 34.71 138.85 MB/sec
Quartz Graphics Test 42.13
Line 37.08 943.88 lines/sec [50% alpha]
Rectangle 54.31 3.82 Krects/sec [50% alpha]
Circle 45.16 1.04 Kcircles/sec [50% alpha]
Bezier 40.27 437.56 beziers/sec [50% alpha]
Text 33.82 569.54 chars/sec
User Interface Test 38.34
Elements 38.34 12.27 refresh/sec
Disk Test 51.25
Sequential 43.58
Uncached Sequential Write 44.47 19.70 MB/sec [256K blocks]
Uncached Sequential Read 42.70 18.44 MB/sec [256K blocks]
Random 58.91
Uncached Random Write 61.07 14.35 MB/sec [256K blocks]
Uncached Random Read 56.75 11.41 MB/sec [256K blocks]

MacBandit
Sep 28, 2002, 02:22 PM
Originally posted by Megaquad
BTW,i need some os x utility for defragmenting my HD, any ideas? I just hope it wont screw up my data..


I also looked for a defrag program for a long while. I quit looking because I had it explained to me in detail that it was not needed in OSX because of the Unix under structure and HFS+.

Megaquad
Sep 28, 2002, 02:32 PM
I dont believe it.. I saw on spymac image gallery some beautiful osx defrag app which would show your hd fragmentation in aqua bubbles and status after fragmentation..

alex_ant
Sep 28, 2002, 03:04 PM
Originally posted by MacBandit



I also looked for a defrag program for a long while. I quit looking because I had it explained to me in detail that it was not needed in OSX because of the Unix under structure and HFS+.
I think someone was pulling your chain, because HFS+ is one of the worst, if not the worst, modern commonly-used filesystem there is when it comes to fragmentation.

G5orbust
Sep 28, 2002, 03:49 PM
The 800 Mhz PB at the SD apple store got a 66.35 in total. In comparison, the 867 got a 102 and my 933 got a 94. That rele good for a laptop, especially since it got 121 in the altivec test!

MacBandit
Sep 28, 2002, 04:01 PM
Originally posted by alex_ant

I think someone was pulling your chain, because HFS+ is one of the worst, if not the worst, modern commonly-used filesystem there is when it comes to fragmentation.

The difference is that the Unix structure isn't suppose to care about the fragmentation as it was explained to me. Unix was designed to be allowed to run for years without showing a slow down because of fragmentation. Again I say though that this is what was explained to me. If someone comes up with a good defrager let me know though because I would like to use it.

I have SystemWorks 2.0 but I hate the way it installs on the system and basically takes over and I don't exactly trust the defrager because it's not OSX native and I think it would do more harm then good to use it.

MacBandit
Sep 28, 2002, 04:12 PM
The new Drive 10 is suppose to have a very nice defragmenter. Having wasted my money on SystemWorks 2.0 I don't feel like laying out more cash for it.

Omad0n
Sep 28, 2002, 06:19 PM
this is a dual 867 with sadly only 384 Mgs of ram, I guess one of my 128 sticks has gone bad. Also I have a radeon 8500 in it.

Results 111.04
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 384 MB
Processor PowerPC,G4@0 [867 MHz]
Processor PowerPC,G4@1 [867 MHz]
CPU Test 112.12
GCD Recursion 108.31 4.23 Mops/sec
Floating Point Basic 103.92 89.92 Mflop/sec
AltiVec Basic 130.67 674.48 Mflop/sec
Floating Point Library 105.59 4.74 Mops/sec
Thread Test 94.58
Computation 109.19 879.62 Kops/sec, 4 threads
Memory Contention 62.80 198.65 MB/sec, 2 threads
Lock Contention 111.76 1.40 Mlocks/sec, 4 threads
Memory Test 126.43
System 138.75
Allocate 109.88 57.80 Kalloc/sec
Fill 241.68 1385.92 MB/sec
Copy 64.69 388.14 MB/sec
Stream 114.10
Copy 113.40 453.59 MB/sec [altivec]
Scale 115.57 462.26 MB/sec [altivec]
Add 117.91 471.65 MB/sec [altivec]
Triad 109.54 438.17 MB/sec [altivec]
Quartz Graphics Test 101.43
Line 99.82 2.54 Klines/sec [50% alpha]
Rectangle 81.78 5.75 Krects/sec [50% alpha]
Circle 107.66 2.48 Kcircles/sec [50% alpha]
Bezier 108.51 1.18 Kbeziers/sec [50% alpha]
Text 109.37 1.84 Kchars/sec
User Interface Test 112.49
Elements 112.49 36.00 refresh/sec
Disk Test 104.19
Sequential 99.81
Uncached Sequential Write 100.53 44.54 MB/sec [256K blocks]
Uncached Sequential Read 99.09 42.80 MB/sec [256K blocks]
Random 108.57
Uncached Random Write 107.64 25.30 MB/sec [256K blocks]
Uncached Random Read 109.51 22.01 MB/sec [256K blocks]

Dr. Distortion
Sep 28, 2002, 06:57 PM
Results 74.40
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 448 MB
Processor PowerPC,G4@0 [500 MHz]
Processor PowerPC,G4@1 [500 MHz]
CPU Test 91.50
GCD Recursion 54.55 2.13 Mops/sec
Floating Point Basic 76.55 66.24 Mflop/sec
AltiVec Basic 140.08 723.14 Mflop/sec
Floating Point Library 94.83 4.26 Mops/sec
Thread Test 65.82
Computation 66.55 536.16 Kops/sec, 4 threads
Memory Contention 46.40 146.76 MB/sec, 2 threads
Lock Contention 84.50 1.06 Mlocks/sec, 4 threads
Memory Test 78.72
System 84.34
Allocate 99.32 52.25 Kalloc/sec
Fill 114.03 653.88 MB/sec
Copy 39.67 238.00 MB/sec
Stream 73.10
Copy 71.83 287.33 MB/sec [altivec]
Scale 71.04 284.17 MB/sec [altivec]
Add 75.34 301.37 MB/sec [altivec]
Triad 74.17 296.69 MB/sec [altivec]
Quartz Graphics Test 67.92
Line 57.48 1.46 Klines/sec [50% alpha]
Rectangle 78.77 5.54 Krects/sec [50% alpha]
Circle 76.17 1.76 Kcircles/sec [50% alpha]
Bezier 53.32 579.38 beziers/sec [50% alpha]
Text 73.85 1.24 Kchars/sec
User Interface Test 75.66
Elements 75.66 24.21 refresh/sec
Disk Test 66.77
Sequential 59.48
Uncached Sequential Write 58.76 26.04 MB/sec [256K blocks]
Uncached Sequential Read 60.19 26.00 MB/sec [256K blocks]
Random 74.07
Uncached Random Write 73.56 17.29 MB/sec [256K blocks]
Uncached Random Read 74.57 14.99 MB/sec [256K blocks]

It's nice to see that it's at about 75% of their standard tested machine :)

Chaszmyr
Sep 28, 2002, 07:41 PM
Results 125.76
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 512 MB
Processor PowerPC,G4@0 [1000 MHz]
Processor PowerPC,G4@1 [1000 MHz]
CPU Test 136.29
GCD Recursion 125.32 4.89 Mops/sec
Floating Point Basic 137.29 118.80 Mflop/sec
AltiVec Basic 160.54 828.67 Mflop/sec
Floating Point Library 122.01 5.48 Mops/sec
Thread Test 120.84
Computation 129.26 1.04 Mops/sec, 4 threads
Memory Contention 99.96 316.16 MB/sec, 2 threads
Lock Contention 133.31 1.67 Mlocks/sec, 4 threads
Memory Test 150.48
System 145.52
Allocate 127.71 67.18 Kalloc/sec
Fill 224.40 1286.81 MB/sec
Copy 84.45 506.68 MB/sec
Stream 155.45
Copy 151.62 606.49 MB/sec [altivec]
Scale 154.67 618.68 MB/sec [altivec]
Add 164.27 657.08 MB/sec [altivec]
Triad 151.22 604.89 MB/sec [altivec]
Quartz Graphics Test 123.47
Line 127.76 3.25 Klines/sec [50% alpha]
Rectangle 120.69 8.49 Krects/sec [50% alpha]
Circle 129.19 2.98 Kcircles/sec [50% alpha]
Bezier 127.39 1.38 Kbeziers/sec [50% alpha]
Text 112.30 1.89 Kchars/sec
User Interface Test 127.42
Elements 127.42 40.78 refresh/sec
Disk Test 96.05
Sequential 88.14
Uncached Sequential Write 83.82 37.14 MB/sec [256K blocks]
Uncached Sequential Read 92.45 39.94 MB/sec [256K blocks]
Random 103.96
Uncached Random Write 101.44 23.85 MB/sec [256K blocks]
Uncached Random Read 106.48 21.40 MB/sec [256K blocks]

exbox
Sep 28, 2002, 08:38 PM
Here are the results for my Powerbook G3 Pismo 500, with 256 MB RAM

Results 44.16
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 256 MB
Processor PowerPC,750@0 [500 MHz]
CPU Test 63.20
GCD Recursion 43.26 1.69 Mops/sec
Floating Point Basic 68.36 59.24 Mflop/sec
Floating Point Library 78.00 3.50 Mops/sec
Thread Test 37.79
Computation 32.57 262.38 Kops/sec, 4 threads
Memory Contention 32.05 101.39 MB/sec, 2 threads
Lock Contention 48.75 611.95 Klocks/sec, 4 threads
Memory Test 42.35
System 45.53
Allocate 90.57 47.64 Kalloc/sec
Fill 32.77 187.92 MB/sec
Copy 13.25 79.48 MB/sec
Stream 39.17
Copy 38.88 155.53 MB/sec
Scale 38.99 155.94 MB/sec
Add 39.39 157.57 MB/sec
Triad 39.40 157.59 MB/sec
Quartz Graphics Test 40.03
Line 35.48 903.26 lines/sec [50% alpha]
Rectangle 35.29 2.48 Krects/sec [50% alpha]
Circle 40.15 925.50 circles/sec [50% alpha]
Bezier 52.06 565.67 beziers/sec [50% alpha]
Text 37.18 626.16 chars/sec
User Interface Test 53.05
Elements 53.05 16.98 refresh/sec
Disk Test 28.51
Sequential 25.31
Uncached Sequential Write 23.75 10.52 MB/sec [256K blocks]
Uncached Sequential Read 26.88 11.61 MB/sec [256K blocks]
Random 31.71
Uncached Random Write 26.93 6.33 MB/sec [256K blocks]
Uncached Random Read 36.49 7.33 MB/sec [256K blocks]

ecino1
Sep 28, 2002, 10:19 PM
Ok.. heres my results. I was just wondering why my hard drive read/write results (the last few tests) are worse than every hard drive result posted here? I know I am not running the fastest computer. But I do have the test running on a brand new 80GB Western Digital 7200RPM ATA drive. And i'm getting slower drive read/write speeds than a pismo (results for a pismo were posted here somewhere). Anyone have a clue whats goin on here? And of course I ran the test with nothign else using the disk at at the time.


Results 63.66
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 768 MB
Processor PowerPC,G4@0 [400 MHz]
CPU Test 78.51
GCD Recursion 37.87 1.48 Mops/sec
Floating Point Basic 73.98 64.02 Mflop/sec
AltiVec Basic 132.71 685.08 Mflop/sec
Floating Point Library 69.48 3.12 Mops/sec
Thread Test 50.29
Computation 26.69 215.02 Kops/sec, 4 threads
Memory Contention 84.81 268.25 MB/sec, 2 threads
Lock Contention 39.39 494.41 Klocks/sec, 4 threads
Memory Test 77.50
System 68.12
Allocate 76.14 40.05 Kalloc/sec
Fill 89.27 511.92 MB/sec
Copy 38.95 233.68 MB/sec
Stream 86.89
Copy 84.91 339.63 MB/sec [altivec]
Scale 84.41 337.65 MB/sec [altivec]
Add 89.61 358.43 MB/sec [altivec]
Triad 88.63 354.50 MB/sec [altivec]
Quartz Graphics Test 56.37
Line 50.75 1.29 Klines/sec [50% alpha]
Rectangle 62.19 4.37 Krects/sec [50% alpha]
Circle 61.78 1.42 Kcircles/sec [50% alpha]
Bezier 58.66 637.36 beziers/sec [50% alpha]
Text 48.48 816.47 chars/sec
User Interface Test 53.99
Elements 53.99 17.28 refresh/sec
Disk Test 65.32
Sequential 57.03
Uncached Sequential Write 65.97 29.23 MB/sec [256K blocks]
Uncached Sequential Read 48.08 20.77 MB/sec [256K blocks]
Random 73.60
Uncached Random Write 69.26 16.28 MB/sec [256K blocks]
Uncached Random Read 77.95 15.66 MB/sec [256K blocks]

Choppaface
Sep 29, 2002, 01:52 AM
Originally posted by MacBandit


The difference is that the Unix structure isn't suppose to care about the fragmentation as it was explained to me. Unix was designed to be allowed to run for years without showing a slow down because of fragmentation. Again I say though that this is what was explained to me. If someone comes up with a good defrager let me know though because I would like to use it.

I have SystemWorks 2.0 but I hate the way it installs on the system and basically takes over and I don't exactly trust the defrager because it's not OSX native and I think it would do more harm then good to use it.


try diskwarrior, it worked great when they repaired my comp. also i've used the norton utilities defragger w/ no probs on an OSX disk. I think that 'fragmentation doesn't matter' info was something somebody made up. I see noticeable speedups after I defrag my nearly-full 18 gig cheetah (nearly full as in about 3 gigs free and in excess of 120,000 files)

MacBandit
Sep 29, 2002, 12:20 PM
Originally posted by Choppaface



try diskwarrior, it worked great when they repaired my comp. also i've used the norton utilities defragger w/ no probs on an OSX disk. I think that 'fragmentation doesn't matter' info was something somebody made up. I see noticeable speedups after I defrag my nearly-full 18 gig cheetah (nearly full as in about 3 gigs free and in excess of 120,000 files)


Here's the link to the thread were they were trying to tell everyone that you didn't really need to defrag with OSX. On one hand I think it probably will help but I don't think it will help me or most of us all that much if we don't have our hard drives much over half full. I have an 80GB and I only have about 33GB on it. What I meant earlier about Norton is the problem as I see is that it wasn't originally created for OSX and does not run native in OSX so I doubt hightly that it knows the system structure that OSX should use. So when you optimize with it it starts moving system files and other data in places all over the drive where they shouldn't be. Yes all data is now optimized and in one neat path on the drive but the system still has to look all over the place to find those neatly ordered files. That's why at the moment I think the new Drive10 is the only program you can use. It was created from the ground up to optimize OSX drives. DiskWarrior hasn't been created for that yet. Though I hear they will be releasing a OSX only DiskWarrior here very soon.

conceptdev
Nov 19, 2002, 08:23 AM
Here are the results from a dying Lombard.
What I would really love to see is xserve data.

Results 34.31
System Info
Xbench Version 1.0b2
System Version 10.2.2
Physical RAM 384 MB
Processor PowerPC,750@0 [401 MHz]
CPU Test 49.77
GCD Recursion 37.09 1.45 Mops/sec
Floating Point Basic 50.96 44.10 Mflop/sec
Floating Point Library 61.26 2.75 Mops/sec
Thread Test 28.49
Computation 24.77 199.59 Kops/sec, 4 threads
Memory Contention 21.34 67.51 MB/sec, 2 threads
Lock Contention 39.36 494.03 Klocks/sec, 4 threads
Memory Test 34.35
System 36.67
Allocate 70.98 37.34 Kalloc/sec
Fill 29.10 166.89 MB/sec
Copy 9.94 59.66 MB/sec
Stream 32.04
Copy 31.47 125.87 MB/sec
Scale 31.23 124.92 MB/sec
Add 32.68 130.70 MB/sec
Triad 32.77 131.08 MB/sec
Quartz Graphics Test 29.70
Line 24.62 626.68 lines/sec [50% alpha]
Rectangle 23.56 1.66 Krects/sec [50% alpha]
Circle 25.44 586.44 circles/sec [50% alpha]
Bezier 38.63 419.76 beziers/sec [50% alpha]
Text 36.27 610.75 chars/sec
User Interface Test 33.19
Elements 33.19 10.62 refresh/sec
Disk Test 14.50
Sequential 11.02
Uncached Sequential Write 10.62 4.70 MB/sec [256K blocks]
Uncached Sequential Read 11.43 4.94 MB/sec [256K blocks]
Random 17.97
Uncached Random Write 15.95 3.75 MB/sec [256K blocks]
Uncached Random Read 19.99 4.02 MB/sec [256K blocks]

MacAficionado
Nov 19, 2002, 09:17 AM
Results 108.11
System Info
Xbench Version 1.0b2
System Version 10.2.1
Physical RAM 512 MB
Processor PowerPC,G4@0 [867 MHz]
Processor PowerPC,G4@1 [867 MHz]
CPU Test 112.63
GCD Recursion 107.68 4.21 Mops/sec
Floating Point Basic 106.42 92.08 Mflop/sec
AltiVec Basic 130.87 675.53 Mflop/sec
Floating Point Library 105.54 4.74 Mops/sec
Thread Test 100.28
Computation 110.41 889.51 Kops/sec, 4 threads
Memory Contention 83.79 265.02 MB/sec, 2 threads
Lock Contention 106.65 1.34 Mlocks/sec, 4 threads
Memory Test 121.05
System 118.91
Allocate 109.06 57.37 Kalloc/sec
Fill 178.96 1026.20 MB/sec
Copy 68.72 412.31 MB/sec
Stream 123.19
Copy 122.63 490.51 MB/sec [altivec]
Scale 125.01 500.04 MB/sec [altivec]
Add 128.56 514.24 MB/sec [altivec]
Triad 116.55 466.19 MB/sec [altivec]
Quartz Graphics Test 111.18
Line 111.65 2.84 Klines/sec [50% alpha]
Rectangle 111.32 7.83 Krects/sec [50% alpha]
Circle 115.09 2.65 Kcircles/sec [50% alpha]
Bezier 109.71 1.19 Kbeziers/sec [50% alpha]
Text 108.15 1.82 Kchars/sec
User Interface Test 108.56
Elements 108.56 34.74 refresh/sec
Disk Test 94.94
Sequential 90.52
Uncached Sequential Write 89.76 39.77 MB/sec [256K blocks]
Uncached Sequential Read 91.28 39.43 MB/sec [256K blocks]
Random 99.35
Uncached Random Write 99.09 23.29 MB/sec [256K blocks]
Uncached Random Read 99.62 20.02 MB/sec [256K blocks]


I have no idea what all this is, so maybe somebody can tell me how my machine is doing and if I can do anything to optimize it!
Thanx

Approx
Nov 19, 2002, 09:26 AM
Results 119.70
System Info
Xbench Version 1.0b2
System Version 10.2.2
Physical RAM 1024 MB
Processor PowerPC,G4@0 [1000 MHz]
Processor PowerPC,G4@1 [1000 MHz]
CPU Test 134.63
GCD Recursion 125.04 4.88 Mops/sec
Floating Point Basic 134.77 116.62 Mflop/sec
AltiVec Basic 156.99 810.35 Mflop/sec
Floating Point Library 121.71 5.47 Mops/sec
Thread Test 129.76
Computation 125.92 1.01 Mops/sec, 4 threads
Memory Contention 135.38 428.20 MB/sec, 2 threads
Lock Contention 127.97 1.61 Mlocks/sec, 4 threads
Memory Test 144.15
System 151.89
Allocate 125.06 65.78 Kalloc/sec
Fill 254.86 1461.47 MB/sec
Copy 75.75 454.50 MB/sec
Stream 136.41
Copy 134.00 535.99 MB/sec [altivec]
Scale 137.79 551.17 MB/sec [altivec]
Add 140.90 563.61 MB/sec [altivec]
Triad 132.94 531.76 MB/sec [altivec]
Quartz Graphics Test 108.27
Line 123.16 3.14 Klines/sec [50% alpha]
Rectangle 85.14 5.99 Krects/sec [50% alpha]
Circle 111.99 2.58 Kcircles/sec [50% alpha]
Bezier 118.44 1.29 Kbeziers/sec [50% alpha]
Text 102.61 1.73 Kchars/sec
User Interface Test 118.93
User Interface Test 118.93
Elements 118.93 38.06 refresh/sec
Disk Test 82.47
Sequential 85.66
Uncached Sequential Write 81.58 36.14 MB/sec [256K blocks]
Uncached Sequential Read 89.74 38.76 MB/sec [256K blocks]
Random 79.28
Uncached Random Write 72.38 17.01 MB/sec [256K blocks]
Uncached Random Read 86.18 17.32 MB/sec [256K blocks]


Some People have better. please give me a tip

MacBandit
Nov 19, 2002, 10:21 AM
Originally posted by Approx
Results 119.70



Some People have better. please give me a tip

Seems to me that the G4MX is faster at these tests.

As a tip. Always repair permissions first and do a fresh restart immediatly before running the test. Also how full your hard drive is can have an affect on the drive performance.

MacBandit
Nov 19, 2002, 10:24 AM
Originally posted by conceptdev
Here are the results from a dying Lombard.
What I would really love to see is xserve data.


The tests I've seen on the XServe show that it performs nearly exactly like the DDR PowerMacs.

Funkatation
Nov 19, 2002, 11:01 AM
Here are the results for my PowerBook Pismo (Upgraded to a G4 and to a 40GB 5400RPM 8MB Cache IBM HDD)

Results 60.29
System Info
Xbench Version 1.0b2
System Version 10.2.2
Physical RAM 640 MB
Processor PowerPC,G4@0 [500 MHz]
CPU Test 84.45
GCD Recursion 50.29 1.96 Mops/sec
Floating Point Basic 79.22 68.55 Mflop/sec
AltiVec Basic 120.55 622.29 Mflop/sec
Floating Point Library 87.75 3.94 Mops/sec
Thread Test 42.98
Computation 32.42 261.19 Kops/sec, 4 threads
Memory Contention 49.97 158.07 MB/sec, 2 threads
Lock Contention 46.53 584.10 Klocks/sec, 4 threads
Memory Test 65.73
System 65.82
Allocate 92.82 48.83 Kalloc/sec
Fill 67.60 387.63 MB/sec
Copy 37.05 222.32 MB/sec
Stream 65.64
Copy 64.06 256.26 MB/sec [altivec]
Scale 64.38 257.52 MB/sec [altivec]
Add 67.80 271.20 MB/sec [altivec]
Triad 66.31 265.25 MB/sec [altivec]
Quartz Graphics Test 54.73
Line 44.90 1.14 Klines/sec [50% alpha]
Rectangle 60.79 4.28 Krects/sec [50% alpha]
Circle 63.49 1.46 Kcircles/sec [50% alpha]
Bezier 45.17 490.83 beziers/sec [50% alpha]
Text 59.31 998.79 chars/sec
User Interface Test 59.41
Elements 59.41 19.01 refresh/sec
Disk Test 54.42
Sequential 49.85
Uncached Sequential Write 50.29 22.28 MB/sec [256K blocks]
Uncached Sequential Read 49.42 21.35 MB/sec [256K blocks]
Random 58.99
Uncached Random Write 56.46 13.27 MB/sec [256K blocks]
Uncached Random Read 61.52 12.36 MB/sec [256K blocks]

chibianh
Nov 26, 2002, 12:12 AM
Seems like the new version of xbench can do the CPU Altivec basic test correctly.. I'm clockin in at over 4Gflops/sec while everyone else here are only in the 100 megaflops..

Results 77.75
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 768 MB
Processor PowerPC,G4@0 [800 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 134 MHz
CPU Test 86.51
GCD Recursion 77.26 3.02 Mops/sec
Floating Point Basic 94.44 318.29 Mflop/sec
AltiVec Basic 82.93 4.50 Gflop/sec
Floating Point Library 91.42 4.11 Mops/sec
Thread Test 62.60
Computation 48.91 394.06 Kops/sec, 4 threads
Memory Contention 85.10 269.18 MB/sec, 2 threads
Lock Contention 53.78 675.05 Klocks/sec, 4 threads
Memory Test 101.53
System 111.76
Allocate 96.85 50.95 Kalloc/sec
Fill 186.43 1069.09 MB/sec
Copy 52.00 312.01 MB/sec
Stream 91.29
Copy 90.48 361.90 MB/sec [altivec]
Scale 92.43 369.72 MB/sec [altivec]
Add 93.51 374.05 MB/sec [altivec]
Triad 88.74 354.95 MB/sec [altivec]
Quartz Graphics Test 85.90
Line 103.75 2.64 Klines/sec [50% alpha]
Rectangle 66.11 4.65 Krects/sec [50% alpha]
Circle 86.81 2.00 Kcircles/sec [50% alpha]
Bezier 90.40 982.30 beziers/sec [50% alpha]
Text 82.40 1.39 Kchars/sec
OpenGL Graphics Test 86.56
Spinning Squares 86.56 60.58 frames/sec
User Interface Test 69.69
Elements 69.69 22.30 refresh/sec
Disk Test 51.48
Sequential 61.08
Uncached Write 46.83 17.44 MB/sec [4K blocks]
Uncached Write 49.41 17.31 MB/sec [256K blocks]
Uncached Read 100.90 14.91 MB/sec [4K blocks]
Uncached Read 47.17 17.69 MB/sec [256K blocks]
Random 41.87
Uncached Write 30.59 0.51 MB/sec [4K blocks]
Uncached Write 45.49 9.45 MB/sec [256K blocks]
Uncached Read 39.41 0.43 MB/sec [4K blocks]
Uncached Read 52.00 10.01 MB/sec [256K blocks]

MacBandit
Nov 26, 2002, 01:08 AM
There have been some very obvious changes with XBench 1.0B3. If you look at my tests this one the latest with OSX 10.2.2 and the old one the 2nd post using OSX 10.2.1 and XBench 1.0B2. You will see that my new score is higher while most of the actual tests scored lower. This is most likely due to weighting of different groups of tests. Due to a correction in the XBench program itself my machine now scores much higher(correctly) at the thread test. It was falsely low before. Also if you look at some other tests take Altivec Basic for example my machine now scores much higher due to repairs in the program but the actual score is lower.

There are some basic reasons for the differences.

A) XBench has had some serious underlying changes made from version 1.0B2 to 1.0B3.
B) I'm now running OS 10.2.2 which had some major changes.
C) My machine has had some use on it and the drive an 80GB has 33.14GB on it. This would slow down my drive report on top of the revisions done in drive testing with XBench 1.0B3.



Results 134.076279

System InfoXbench Version 1.0b3
System Version 10.2.2
Physical RAM 1024 MB
ProcessorPowerPC,G4 @ 0 [1000 MHz] L1 Cache 32K (instruction), 32K (data) Bus Frequency 167 MHz
ProcessorPowerPC,G4 @ 1 [1000 MHz] L1 Cache 32K (instruction), 32K (data)Bus Frequency 167 MHz

CPU Test 125.601578
GCD Recursion 125.945030 4.92 Mops/sec
Floating Point Basic 126.446327 426.18Mflop/sec
AltiVec Basic 128.196152 6.95 Gflop/sec
Floating Point Library 121.818771 5.47 Mops/sec

Thread Test 128.630554
Computation 129.734543 1.05 Mops/sec, 4 threads
Memory Contention 123.953995 392.07 MB/sec, 2 threads
Lock Contention 132.203140 1.66 Mlocks/sec, 4 threads

Memory Test 149.249557
System 157.217712
Allocate 127.372681 67.00 Kalloc/sec
Fill 269.924652 1547.86 MB/sec
Copy 74.355820 446.13 MB/sec
Stream 141.281403
Copy 138.775681 555.10 MB/sec [altivec]
Scale 142.445068 569.78 MB/sec [altivec]
Add 146.008606 584.03 MB/sec [altivec]
Triad 137.896255 551.58 MB/sec [altivec]

Quartz Graphics Test 128.528549
Line 129.151428 3.29 Klines/sec [50% alpha]
Rectangle 123.935669 8.72 Krects/sec [50% alpha]
Circle 130.819626 3.02 Kcircles/sec [50% alpha]
Bezier 126.222771 1.37 Kbeziers/sec [50% alpha]
Text 132.513260 2.23 Kchars/sec

OpenGL Graphics Test 131.135254
Spinning Squares 131.135254 91.77 frames/sec

User Interface Test 131.457596
Elements 131.457596 42.07 refresh/sec

Disk Test 99.047821
Sequential 96.028198
Uncached Write 78.016449 29.05 MB/sec [4K blocks]
Uncached Write 77.830658 27.26 MB/sec [256K blocks]
Uncached Read 144.596573 21.37 MB/sec [4K blocks]
Uncached Read 83.669128 31.37 MB/sec [256K blocks]
Random 102.067451
Uncached Write 125.69049 12.10 MB/sec [4K blocks]
Uncached Write 109.704056 22.80 MB/sec [256K blocks]
Uncached Read 70.532486 0.76 MB/sec [4K blocks]
Uncached Read 102.342766 19.70 MB/sec [256K blocks]

Switcher2001
Nov 26, 2002, 01:55 AM
I just downloaded XBench tonight. Here are my results (I have a 600 MHz iBook with 640 MB RAM).


Results 50.07
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 640 MB
Processor PowerPC,750@0 [600 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 100 MHz
CPU Test 64.65
GCD Recursion 49.19 1.92 Mops/sec
Floating Point Basic 49.68 167.46 Mflop/sec
Floating Point Library 95.09 4.27 Mops/sec
Thread Test 42.98
Computation 37.28 300.36 Kops/sec, 4 threads
Memory Contention 35.84 113.35 MB/sec, 2 threads
Lock Contention 55.82 700.71 Klocks/sec, 4 threads
Memory Test 41.88
System 46.42
Allocate 105.70 55.60 Kalloc/sec
Fill 22.34 128.08 MB/sec
Copy 11.21 67.29 MB/sec
Stream 37.35
Copy 37.28 149.13 MB/sec
Scale 37.28 149.13 MB/sec
Add 37.20 148.80 MB/sec
Triad 37.64 150.57 MB/sec
Quartz Graphics Test 50.64
Line 49.97 1.27 Klines/sec [50% alpha]
Rectangle 57.86 4.07 Krects/sec [50% alpha]
Circle 58.31 1.34 Kcircles/sec [50% alpha]
Bezier 56.00 608.49 beziers/sec [50% alpha]
Text 31.05 522.92 chars/sec
OpenGL Graphics Test 69.41
Spinning Squares 69.41 48.57 frames/sec
User Interface Test 40.71
Elements 40.71 13.03 refresh/sec
Disk Test 40.21
Sequential 45.77
Uncached Write 41.95 15.62 MB/sec [4K blocks]
Uncached Write 44.32 15.52 MB/sec [256K blocks]
Uncached Read 55.08 8.14 MB/sec [4K blocks]
Uncached Read 41.73 15.65 MB/sec [256K blocks]
Random 34.65
Uncached Write 21.63 0.36 MB/sec [4K blocks]
Uncached Write 34.41 7.15 MB/sec [256K blocks]
Uncached Read 34.97 0.38 MB/sec [4K blocks]
Uncached Read 47.60 9.16 MB/sec [256K blocks]

macsavvy
Nov 27, 2002, 06:00 PM
Here is mine... Feel the power...
4 Year Old Lombard and still kickin'... ofcourse that's running under Mac OS 9. OS X, well that's another story.. note the pathetic performance (or lack therof) of OpenGL.

Results 27.54
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 256 MB
Processor PowerPC,750@0 [335 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 67 MHz
CPU Test 37.65
GCD Recursion 29.64 1.16 Mops/sec
Floating Point Basic 31.68 106.76 Mflop/sec
Floating Point Library 51.63 2.32 Mops/sec
Thread Test 24.48
Computation 19.95 160.70 Kops/sec, 4 threads
Memory Contention 20.98 66.35 MB/sec, 2 threads
Lock Contention 32.52 408.15 Klocks/sec, 4 threads
Memory Test 29.67
System 27.73
Allocate 58.14 30.58 Kalloc/sec
Fill 16.01 91.83 MB/sec
Copy 9.04 54.23 MB/sec
Stream 31.61
Copy 30.85 123.39 MB/sec
Scale 30.94 123.77 MB/sec
Add 32.38 129.52 MB/sec
Triad 32.28 129.13 MB/sec
Quartz Graphics Test 30.08
Line 24.78 630.88 lines/sec [50% alpha]
Rectangle 34.80 2.45 Krects/sec [50% alpha]
Circle 33.98 783.29 circles/sec [50% alpha]
Bezier 25.58 277.94 beziers/sec [50% alpha]
Text 31.26 526.47 chars/sec
OpenGL Graphics Test 9.45
Spinning Squares 9.45 6.61 frames/sec
User Interface Test 28.40
Elements 28.40 9.09 refresh/sec
Disk Test 33.06
Sequential 32.94
Uncached Write 26.28 9.78 MB/sec [4K blocks]
Uncached Write 28.88 10.12 MB/sec [256K blocks]
Uncached Read 42.02 6.21 MB/sec [4K blocks]
Uncached Read 34.59 12.97 MB/sec [256K blocks]
Random 33.18
Uncached Write 22.16 0.37 MB/sec [4K blocks]
Uncached Write 33.26 6.91 MB/sec [256K blocks]
Uncached Read 34.88 0.38 MB/sec [4K blocks]
Uncached Read 42.43 8.17 MB/sec [256K blocks]

iJon
Nov 27, 2002, 06:44 PM
Results 116.56
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 256 MB
Processor PowerPC,G4@0 [1000 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 167 MHz
Processor PowerPC,G4@1 [1000 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 167 MHz
CPU Test 125.08
GCD Recursion 125.90 4.92 Mops/sec
Floating Point Basic 126.68 426.94 Mflop/sec
AltiVec Basic 125.81 6.83 Gflop/sec
Floating Point Library 121.93 5.48 Mops/sec
Thread Test 114.32
Computation 128.44 1.03 Mops/sec, 4 threads
Memory Contention 83.04 262.66 MB/sec, 2 threads
Lock Contention 131.49 1.65 Mlocks/sec, 4 threads
Memory Test 136.08
System 131.33
Allocate 124.17 65.32 Kalloc/sec
Fill 196.39 1126.17 MB/sec
Copy 73.43 440.59 MB/sec
Stream 140.83
Copy 137.24 548.97 MB/sec [altivec]
Scale 140.87 563.50 MB/sec [altivec]
Add 148.15 592.61 MB/sec [altivec]
Triad 137.06 548.22 MB/sec [altivec]
Quartz Graphics Test 114.57
Line 122.94 3.13 Klines/sec [50% alpha]
Rectangle 100.29 7.06 Krects/sec [50% alpha]
Circle 102.40 2.36 Kcircles/sec [50% alpha]
Bezier 124.14 1.35 Kbeziers/sec [50% alpha]
Text 123.08 2.07 Kchars/sec
OpenGL Graphics Test 101.25
Spinning Squares 101.25 70.86 frames/sec
User Interface Test 103.22
Elements 103.22 33.03 refresh/sec
Disk Test 121.43
Sequential 133.61
Uncached Write 109.77 40.87 MB/sec [4K blocks]
Uncached Write 125.16 43.84 MB/sec [256K blocks]
Uncached Read 184.51 27.27 MB/sec [4K blocks]
Uncached Read 115.01 43.12 MB/sec [256K blocks]
Random 109.25
Uncached Write 127.42 2.13 MB/sec [4K blocks]
Uncached Write 121.36 25.22 MB/sec [256K blocks]
Uncached Read 75.03 0.81 MB/sec [4K blocks]
Uncached Read 113.17 21.79 MB/sec [256K blocks]

Nelson79
Nov 27, 2002, 06:56 PM
New 800mhz iBook results
Results 64.19
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 384 MB
Processor PowerPC,750@0 [800 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 100 MHz
CPU Test 93.27
GCD Recursion 76.96 3.01 Mops/sec
Floating Point Basic 75.82 255.56 Mflop/sec
Floating Point Library 127.04 5.71 Mops/sec
Thread Test 57.25
Computation 51.17 412.28 Kops/sec, 4 threads
Memory Contention 44.51 140.80 MB/sec, 2 threads
Lock Contention 76.06 954.86 Klocks/sec, 4 threads
Memory Test 51.05
System 61.02
Allocate 145.56 76.57 Kalloc/sec
Fill 25.05 143.67 MB/sec
Copy 12.44 74.63 MB/sec
Stream 41.08
Copy 40.70 162.80 MB/sec
Scale 40.66 162.63 MB/sec
Add 41.50 166.02 MB/sec
Triad 41.47 165.89 MB/sec
Quartz Graphics Test 68.55
Line 64.68 1.65 Klines/sec [50% alpha]
Rectangle 65.91 4.64 Krects/sec [50% alpha]
Circle 77.61 1.79 Kcircles/sec [50% alpha]
Bezier 84.00 912.73 beziers/sec [50% alpha]
Text 50.55 851.31 chars/sec
OpenGL Graphics Test 61.00
Spinning Squares 61.00 42.69 frames/sec
User Interface Test 60.23
Elements 60.23 19.27 refresh/sec
Disk Test 57.99
Sequential 66.89
Uncached Write 54.80 20.40 MB/sec [4K blocks]
Uncached Write 60.56 21.21 MB/sec [256K blocks]
Uncached Read 94.86 14.02 MB/sec [4K blocks]
Uncached Read 57.33 21.50 MB/sec [256K blocks]
Random 49.10
Uncached Write 48.81 0.82 MB/sec [4K blocks]
Uncached Write 50.46 10.49 MB/sec [256K blocks]
Uncached Read 40.04 0.43 MB/sec [4K blocks]
Uncached Read 57.08 10.99 MB/sec [256K blocks]

bousozoku
Nov 27, 2002, 09:59 PM
Originally posted by alex_ant

I think someone was pulling your chain, because HFS+ is one of the worst, if not the worst, modern commonly-used filesystem there is when it comes to fragmentation.

Actually, only part of the time. HFS and HFS+ both use binary trees to store directory information. This allows consistent searching speeds and provides apparent faster speeds when accessing badly fragmented volumes in comparison to those (F.A.T.) which use less-sophisticated search methods. F.A.T. is faster on clean volumes but quickly slow because they're using modified linear search methods. HPFS/NTFS is much better but still handicapped a bit dealing with fragmentation.

Jimong5
Nov 27, 2002, 10:38 PM
My Dual 867 with Its piddily 256 MB RAM and radeon 9000... rather depressing....

Results 102.80
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 256 MB
Processor PowerPC,G4@0 [867 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 134 MHz
Processor PowerPC,G4@1 [867 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 134 MHz
CPU Test 108.32
GCD Recursion 109.02 4.26 Mops/sec
Floating Point Basic 109.41 368.73 Mflop/sec
AltiVec Basic 109.32 5.93 Gflop/sec
Floating Point Library 105.53 4.74 Mops/sec
Thread Test 107.90
Computation 110.09 886.91 Kops/sec, 4 threads
Memory Contention 107.34 339.53 MB/sec, 2 threads
Lock Contention 106.26 1.33 Mlocks/sec, 4 threads
Memory Test 114.55
System 113.14
Allocate 107.30 56.44 Kalloc/sec
Fill 172.30 988.03 MB/sec
Copy 59.80 358.83 MB/sec
Stream 115.96
Copy 113.71 454.84 MB/sec [altivec]
Scale 115.98 463.93 MB/sec [altivec]
Add 121.66 486.66 MB/sec [altivec]
Triad 112.49 449.98 MB/sec [altivec]
Quartz Graphics Test 96.16
Line 106.31 2.71 Klines/sec [50% alpha]
Rectangle 71.43 5.02 Krects/sec [50% alpha]
Circle 93.43 2.15 Kcircles/sec [50% alpha]
Bezier 105.56 1.15 Kbeziers/sec [50% alpha]
Text 104.10 1.75 Kchars/sec
OpenGL Graphics Test 86.93
Spinning Squares 86.93 60.84 frames/sec
User Interface Test 90.48
Elements 90.48 28.95 refresh/sec
Disk Test 115.25
Sequential 125.25
Uncached Write 108.58 40.42 MB/sec [4K blocks]
Uncached Write 117.88 41.29 MB/sec [256K blocks]
Uncached Read 164.40 24.30 MB/sec [4K blocks]
Uncached Read 110.13 41.29 MB/sec [256K blocks]
Random 105.26
Uncached Write 124.33 2.08 MB/sec [4K blocks]
Uncached Write 113.99 23.69 MB/sec [256K blocks]
Uncached Read 75.73 0.82 MB/sec [4K blocks]
Uncached Read 106.99 20.59 MB/sec [256K blocks]

zimv20
Nov 28, 2002, 12:14 AM
Originally posted by Nelson79
New 800mhz iBook results
Results 64.19
Disk Test 57.99


okay, your results are the highest for the 800 MHz ibooks. this is due to your disk score -- the others are in the mid-40s.

what kind of HD do you have? or have you done something wacky like defrag it before you ran the test?

also, what kind of memory? your memory score is towards the higher end -- i can't tell if it's due to the type or simply the amount. i've noticed that memory size roughly corresponds to a higher score.

thanks!

Nelson79
Nov 28, 2002, 09:58 AM
No everything is standard, haven't done anything to the HD. I got an extra 256 megs from crucial, and thats it.

Mr. Anderson
Nov 28, 2002, 10:57 AM
Ok, I hadn't realized that my machine was that slow - I'm really hoping Apple comes out with something sooner than later in the next gen processor.

Results 54.85
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 1024 MB
Processor PowerPC,G4@0 [450 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 100 MHz


Especially when a iBook beats me!

D

MacBandit
Nov 28, 2002, 12:30 PM
Originally posted by iJon
Results 116.56
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 256 MB
Processor PowerPC,G4@0 [1000 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 167 MHz
Processor PowerPC,G4@1 [1000 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 167 MHz


Whoaa!!! Major difference between my DDR Dual/1 GHz and yours.

It must be the difference in the amount of ram. You have 256 and I have 1gig.

Did you test this on a fresh restart? Where you running any other programs at the same time?

Review my test on this page just above.

vniow
Nov 30, 2002, 01:12 PM
One now and one when I get my new hard drive. Results 30.32
System Info
Xbench Version 1.0b3
System Version 10.2
Physical RAM 320 MB
Processor PowerPC,750@0 [300 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 67 MHz
CPU Test 35.07
GCD Recursion 28.20 1.10 Mops/sec
Floating Point Basic 29.17 98.31 Mflop/sec
Floating Point Library 47.86 2.15 Mops/sec
Thread Test 21.66
Computation 18.11 145.93 Kops/sec, 4 threads
Memory Contention 17.94 56.76 MB/sec, 2 threads
Lock Contention 28.92 363.07 Klocks/sec, 4 threads
Memory Test 25.82
System 26.06
Allocate 55.25 29.06 Kalloc/sec
Fill 15.31 87.81 MB/sec
Copy 7.61 45.64 MB/sec
Stream 25.58
Copy 25.55 102.20 MB/sec
Scale 25.51 102.05 MB/sec
Add 25.65 102.60 MB/sec
Triad 25.62 102.48 MB/sec
Quartz Graphics Test 33.92
Line 31.18 793.71 lines/sec [50% alpha]
Rectangle 40.24 2.83 Krects/sec [50% alpha]
Circle 38.75 893.19 circles/sec [50% alpha]
Bezier 35.65 387.34 beziers/sec [50% alpha]
Text 23.81 400.90 chars/sec
OpenGL Graphics Test 35.51
Spinning Squares 35.51 24.85 frames/sec
User Interface Test 32.16
Elements 32.16 10.29 refresh/sec
Disk Test 28.12
Sequential 29.93
Uncached Write 22.95 8.55 MB/sec [4K blocks]
Uncached Write 25.63 8.98 MB/sec [256K blocks]
Uncached Read 46.77 6.91 MB/sec [4K blocks]
Uncached Read 24.37 9.14 MB/sec [256K blocks]
Random 26.31
Uncached Write 18.75 0.31 MB/sec [4K blocks]
Uncached Write 25.89 5.38 MB/sec [256K blocks]
Uncached Read 32.16 0.35 MB/sec [4K blocks]
Uncached Read 28.42 5.47 MB/sec [256K blocks]

daPhil
Dec 2, 2002, 06:07 AM
I wonder why the hell i my IBM GXP 120 IDE disc gets better scores than my Cheetah 15000rpm U160SCSI disc... The Cheetah is supposed to be the fastest disc in the world according to www.storagereview.com who benchamarks all discs released.

MacBandit
Dec 2, 2002, 01:39 PM
Originally posted by daPhil
I wonder why the hell i my IBM GXP 120 IDE disc gets better scores than my Cheetah 15000rpm U160SCSI disc... The Cheetah is supposed to be the fastest disc in the world according to www.storagereview.com who benchamarks all discs released.

It has to do with the type of tests being performed. The tests that XBench does are pretty limited. If you were to see access times and random read and write it should destroy any ATA drive. Actually any modern SCSI drive should beat an ATA drive in access time I believe.

vniow
Dec 3, 2002, 07:28 PM
Just got my new hard drive today, 40GB 5400rpm IBM Travelstar with 8MB cache.
New benchmarks:

Results 36.43
System Info
Xbench Version 1.0b3
System Version 10.2
Physical RAM 320 MB
Processor PowerPC,750@0 [300 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 67 MHz
CPU Test 35.30
GCD Recursion 27.37 1.07 Mops/sec
Floating Point Basic 29.64 99.92 Mflop/sec
Floating Point Library 48.89 2.20 Mops/sec
Thread Test 22.36
Computation 18.60 149.83 Kops/sec, 4 threads
Memory Contention 18.86 59.67 MB/sec, 2 threads
Lock Contention 29.62 371.83 Klocks/sec, 4 threads
Memory Test 26.20
System 26.98
Allocate 55.59 29.24 Kalloc/sec
Fill 16.80 96.31 MB/sec
Copy 8.56 51.36 MB/sec
Stream 25.42
Copy 25.24 100.97 MB/sec
Scale 25.32 101.26 MB/sec
Add 25.59 102.36 MB/sec
Triad 25.54 102.17 MB/sec
Quartz Graphics Test 36.13
Line 31.50 801.87 lines/sec [50% alpha]
Rectangle 41.06 2.89 Krects/sec [50% alpha]
Circle 39.66 914.09 circles/sec [50% alpha]
Bezier 36.64 398.18 beziers/sec [50% alpha]
Text 31.80 535.60 chars/sec
OpenGL Graphics Test 37.24
Spinning Squares 37.24 26.06 frames/sec
User Interface Test 35.46
Elements 35.46 11.35 refresh/sec
Disk Test 62.29
Sequential 64.09
Uncached Write 58.22 21.67 MB/sec [4K blocks]
Uncached Write 71.90 25.19 MB/sec [256K blocks]
Uncached Read 60.48 8.94 MB/sec [4K blocks]
Uncached Read 65.77 24.66 MB/sec [256K blocks]
Random 60.50
Uncached Write 46.90 0.78 MB/sec [4K blocks]
Uncached Write 71.87 14.94 MB/sec [256K blocks]
Uncached Read 55.31 0.60 MB/sec [4K blocks]
Uncached Read 67.90 13.07 MB/sec [256K blocks]

MacBandit
Dec 3, 2002, 09:28 PM
[QUOTE]Originally posted by edvniow
[B]Just got my new hard drive today, 40GB 5400rpm IBM Travelstar with 8MB cache.
New benchmarks:

Wow that's quite the improvement.

vniow
Dec 3, 2002, 09:38 PM
No kidding. Wow.
Everything so much smoother on it and it wasn't all that hard to replace it.

For comparison:

Old drive: Fujitsu 6GB 4200rpm

Disk Test 28.12
Sequential 29.93
Uncached Write 22.95 8.55 MB/sec [4K blocks]
Uncached Write 25.63 8.98 MB/sec [256K blocks]
Uncached Read 46.77 6.91 MB/sec [4K blocks]
Uncached Read 24.37 9.14 MB/sec [256K blocks]
Random 26.31
Uncached Write 18.75 0.31 MB/sec [4K blocks]
Uncached Write 25.89 5.38 MB/sec [256K blocks]
Uncached Read 32.16 0.35 MB/sec [4K blocks]
Uncached Read 28.42 5.47 MB/sec [256K blocks]

New drive: 5400rpm IBM 40GB

Disk Test 62.29
Sequential 64.09
Uncached Write 58.22 21.67 MB/sec [4K blocks]
Uncached Write 71.90 25.19 MB/sec [256K blocks]
Uncached Read 60.48 8.94 MB/sec [4K blocks]
Uncached Read 65.77 24.66 MB/sec [256K blocks]
Random 60.50
Uncached Write 46.90 0.78 MB/sec [4K blocks]
Uncached Write 71.87 14.94 MB/sec [256K blocks]
Uncached Read 55.31 0.60 MB/sec [4K blocks]
Uncached Read 67.90 13.07 MB/sec [256K blocks]

buseman
Dec 8, 2002, 07:17 AM
on my old graphite:

Results 60.15
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 256 MB
Processor PowerPC,G4@0 [450 MHz]

rickvanr
Dec 11, 2002, 02:31 PM
Results 95.77
System Info
Xbench Version 1.0b3
System Version 10.2.1
Physical RAM 512 MB
Processor PowerPC,G4@0 [1000 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 134 MHz
CPU Test 117.01
GCD Recursion 111.36 4.35 Mops/sec
Floating Point Basic 118.18 398.34 Mflop/sec
AltiVec Basic 118.70 6.44 Gflop/sec
Floating Point Library 119.79 5.38 Mops/sec
Thread Test 76.96
Computation 64.07 516.14 Kops/sec, 4 threads
Memory Contention 99.09 313.42 MB/sec, 2 threads
Lock Contention 67.71 849.92 Klocks/sec, 4 threads
Memory Test 112.00
System 131.35
Allocate 122.27 64.32 Kalloc/sec
Fill 218.54 1253.21 MB/sec
Copy 53.24 319.45 MB/sec
Stream 92.66
Copy 93.28 373.11 MB/sec [altivec]
Scale 92.79 371.16 MB/sec [altivec]
Add 94.53 378.10 MB/sec [altivec]
Triad 90.04 360.16 MB/sec [altivec]
Quartz Graphics Test 101.34
Line 115.77 2.95 Klines/sec [50% alpha]
Rectangle 69.26 4.87 Krects/sec [50% alpha]
Circle 92.41 2.13 Kcircles/sec [50% alpha]
Bezier 116.01 1.26 Kbeziers/sec [50% alpha]
Text 113.23 1.91 Kchars/sec
OpenGL Graphics Test 105.45
Spinning Squares 105.45 73.79 frames/sec
User Interface Test 94.57
Elements 94.57 30.26 refresh/sec
Disk Test 63.05
Sequential 71.56
Uncached Write 64.84 24.14 MB/sec [4K blocks]
Uncached Write 62.66 21.95 MB/sec [256K blocks]
Uncached Read 98.95 14.62 MB/sec [4K blocks]
Uncached Read 59.77 22.41 MB/sec [256K blocks]
Random 54.54
Uncached Write 71.60 1.20 MB/sec [4K blocks]
Uncached Write 50.15 10.42 MB/sec [256K blocks]
Uncached Read 40.96 0.44 MB/sec [4K blocks]
Uncached Read 55.45 10.67 MB/sec [256K blocks]

MacBandit
Dec 12, 2002, 01:42 AM
[QUOTE]Originally posted by rickvanr
[B]Results 95.77
System Info
Xbench Version 1.0b3
System Version 10.2.1
Physical RAM 512 MB
Processor PowerPC,G4@0 [1000 MHz]


That's very impressive. Finally a laptop I could almost replace my desktop with. Almost.

buseman
Dec 12, 2002, 03:26 PM
quite satisfied with this
iTunes encode >30X
Quake 3 fps ~200fps
P7 launch 6 seconds
:cool:

Results 151.59
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 512 MB
Processor PowerPC,G4@0 [1250 MHz]

MacBandit
Dec 13, 2002, 01:57 AM
Originally posted by buseman
quite satisfied with this
iTunes encode >30X
Quake 3 fps ~200fps
P7 launch 6 seconds
:cool:

Results 151.59
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 512 MB
Processor PowerPC,G4@0 [1250 MHz]

What video card? Also what speed cd reader do you have. I have a 40x12x48 and it rips at >30x on my Dual/GHz/DDR.

buseman
Dec 13, 2002, 08:40 AM
Originally posted by MacBandit


What video card? Also what speed cd reader do you have. I have a 40x12x48 and it rips at >30x on my Dual/GHz/DDR.

Geforce4 Ti 4600. i was actually surprised about the high q3 benchmarks, since i use 1280*1024 and everything set to max. It often peaks at over 300, but stays mostly around 200.

i got the superdrive which is only 24X of course, so the speeds are from aiff's on the disk.

MacBandit
Dec 13, 2002, 10:09 AM
Originally posted by buseman


Geforce4 Ti 4600. i was actually surprised about the high q3 benchmarks, since i use 1280*1024 and everything set to max. It often peaks at over 300, but stays mostly around 200.

i got the superdrive which is only 24X of course, so the speeds are from aiff's on the disk.

That's cool. It kind of gives me an idea of what kind of performance to expect from an ATI 9700 card in my computer. I currently have a G4MX in it. I got the computer with the G4MX because it cut $100 off the price and I was planning on getting an ATI9700 as soon as they become available any way. My frame rates are around 100FPS with Max everything at 1280x1024.

iJon
Dec 13, 2002, 04:54 PM
here is my new score with my dual ghz mmd r9000 .

Results 141.37
System Info
Xbench Version 1.0b3
System Version 10.2.3
Physical RAM 256 MB
Processor PowerPC,G4@0 [1000 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 167 MHz
Processor PowerPC,G4@1 [1000 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 167 MHz
CPU Test 124.69
GCD Recursion 124.77 4.87 Mops/sec
Floating Point Basic 123.62 416.67 Mflop/sec
AltiVec Basic 128.96 7.00 Gflop/sec
Floating Point Library 121.40 5.45 Mops/sec
Thread Test 131.74
Computation 118.14 951.74 Kops/sec, 4 threads
Memory Contention 157.08 496.85 MB/sec, 2 threads
Lock Contention 119.99 1.51 Mlocks/sec, 4 threads
Memory Test 132.23
System 134.89
Allocate 127.53 67.08 Kalloc/sec
Fill 205.52 1178.52 MB/sec
Copy 71.62 429.72 MB/sec
Stream 129.56
Copy 127.13 508.53 MB/sec [altivec]
Scale 130.65 522.61 MB/sec [altivec]
Add 137.07 548.28 MB/sec [altivec]
Triad 123.39 493.58 MB/sec [altivec]
Quartz Graphics Test 136.52
Line 130.32 3.32 Klines/sec [50% alpha]
Rectangle 144.76 10.18 Krects/sec [50% alpha]
Circle 148.95 3.43 Kcircles/sec [50% alpha]
Bezier 129.41 1.41 Kbeziers/sec [50% alpha]
Text 129.16 2.18 Kchars/sec
OpenGL Graphics Test 198.64
Spinning Squares 198.64 139.00 frames/sec
User Interface Test 152.31
Elements 152.31 48.74 refresh/sec
Disk Test 113.47
Sequential 119.45
Uncached Write 82.27 30.63 MB/sec [4K blocks]
Uncached Write 116.80 40.91 MB/sec [256K blocks]
Uncached Read 172.56 25.50 MB/sec [4K blocks]
Uncached Read 106.16 39.80 MB/sec [256K blocks]
Random 107.50
Uncached Write 129.48 2.16 MB/sec [4K blocks]
Uncached Write 115.54 24.01 MB/sec [256K blocks]
Uncached Read 75.42 0.81 MB/sec [4K blocks]
Uncached Read 109.56 21.09 MB/sec [256K blocks]

I installed my copy of 6g24 10.2.3. then i repaired permissions on my computer and it increased my score from 121 to 141. simply amazing. now i have to go check out 6g26.

iJon

iconrad
Dec 13, 2002, 08:08 PM
Results 50.26
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 256 MB
Processor PowerPC,750@0 [500 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 100 MHz
CPU Test 58.00
GCD Recursion 45.82 1.79 Mops/sec
Floating Point Basic 47.68 160.71 Mflop/sec
Floating Point Library 80.51 3.62 Mops/sec
Thread Test 38.82
Computation 31.44 253.30 Kops/sec, 4 threads
Memory Contention 35.63 112.68 MB/sec, 2 threads
Lock Contention 49.39 619.97 Klocks/sec, 4 threads
Memory Test 42.35
System 42.97
Allocate 92.76 48.79 Kalloc/sec
Fill 23.78 136.38 MB/sec
Copy 12.37 74.21 MB/sec
Stream 41.73
Copy 41.37 165.49 MB/sec
Scale 40.60 162.39 MB/sec
Add 42.46 169.83 MB/sec
Triad 42.48 169.93 MB/sec
Quartz Graphics Test 49.92
Line 44.70 1.14 Klines/sec [50% alpha]
Rectangle 59.98 4.22 Krects/sec [50% alpha]
Circle 57.12 1.32 Kcircles/sec [50% alpha]
Bezier 50.68 550.69 beziers/sec [50% alpha]
Text 37.15 625.58 chars/sec
OpenGL Graphics Test 66.54
Spinning Squares 66.54 46.57 frames/sec
User Interface Test 46.66
Elements 46.66 14.93 refresh/sec
Disk Test 49.55
Sequential 50.16
Uncached Write 58.74 21.87 MB/sec [4K blocks]
Uncached Write 54.33 19.03 MB/sec [256K blocks]
Uncached Read 42.81 6.33 MB/sec [4K blocks]
Uncached Read 44.78 16.79 MB/sec [256K blocks]
Random 48.94
Uncached Write 51.61 0.86 MB/sec [4K blocks]
Uncached Write 46.14 9.59 MB/sec [256K blocks]
Uncached Read 49.90 0.54 MB/sec [4K blocks]
Uncached Read 48.09 9.26 MB/sec [256K blocks]

Megaquad
Dec 14, 2002, 03:51 AM
I can encode mp3 at 4x speed on my iMac :D

G5orbust
Dec 14, 2002, 06:42 PM
aww man, all you guys have comps that blow mine out of the water. I remember when I had the best comp (933 G4) cuz no one could afford the fabled dual 1 GHz at the time.... Now everyone's xbench is jsut raping my measly 104. Oh well, atleast Im beating the 1 Ghz powerbook, but thats only because of HD tests... :rolleyes:

SilvorX
Dec 16, 2002, 10:01 AM
Originally posted by G5orbust
aww man, all you guys have comps that blow mine out of the water. I remember when I had the best comp (933 G4) cuz no one could afford the fabled dual 1 GHz at the time.... Now everyone's xbench is jsut raping my measly 104. Oh well, atleast Im beating the 1 Ghz powerbook, but thats only because of HD tests... :rolleyes:
my comp is getting half the results of yours :P, but then again, i love the portability, but i DO want louder speakers (theyre way too quiet for listening to music if theres a few people in the room), DVDs are even worse, but hopefully i'll get a set of 4.1 speakers and a splitter for xmas

D*I*S_Frontman
Dec 16, 2002, 05:00 PM
Did I read these results right? The guy with the upgraded Pismo (G4/500) scores comparably with a TiBook 800? Why is that, given the processor speed disparity? Maybe one of you hardware geniuses can explain it to me.

I have been intending to drop the $300 to send my Pismo G3/400 to Newertech or Powerlogix, and this test would seem to indicate that I would be an IDIOT not to.

Tarlach
Dec 16, 2002, 07:09 PM
G3 B & W 350 oc'd to 400 384 mb RAM and Maxtor 7200 30gb HD. Apache was running.
I ran this test without rebooting, it has been running apache, I am using it as a webserver.


Results 47.70
System Info
Xbench Version 1.0b3
System Version 10.2.2
Physical RAM 384 MB
Processor PowerPC,750@0 [399 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 100 MHz
CPU Test 47.49
GCD Recursion 38.60 1.51 Mops/sec
Floating Point Basic 39.36 132.64 Mflop/sec
Floating Point Library 64.51 2.90 Mops/sec
Thread Test 29.58
Computation 25.36 204.27 Kops/sec, 4 threads
Memory Contention 26.93 85.19 MB/sec, 2 threads
Lock Contention 36.47 457.73 Klocks/sec, 4 threads
Memory Test 37.93
System 36.93
Allocate 61.99 32.61 Kalloc/sec
Fill 36.39 208.68 MB/sec
Copy 12.40 74.41 MB/sec
Stream 38.94
Copy 38.25 153.01 MB/sec
Scale 38.24 152.97 MB/sec
Add 39.75 158.99 MB/sec
Triad 39.53 158.12 MB/sec
Quartz Graphics Test 47.99
Line 41.39 1.05 Klines/sec [50% alpha]
Rectangle 52.64 3.70 Krects/sec [50% alpha]
Circle 50.62 1.17 Kcircles/sec [50% alpha]
Bezier 47.77 519.07 beziers/sec [50% alpha]
Text 47.54 800.53 chars/sec
OpenGL Graphics Test 53.53
Spinning Squares 53.53 37.46 frames/sec
User Interface Test 49.48
Elements 49.48 15.83 refresh/sec
Disk Test 67.88
Sequential 68.22
Uncached Write 68.20 25.39 MB/sec [4K blocks]
Uncached Write 69.50 24.34 MB/sec [256K blocks]
Uncached Read 70.02 10.35 MB/sec [4K blocks]
Uncached Read 65.17 24.44 MB/sec [256K blocks]
Random 67.54
Uncached Write 73.26 1.22 MB/sec [4K blocks]
Uncached Write 70.94 14.74 MB/sec [256K blocks]
Uncached Read 57.20 0.62 MB/sec [4K blocks]
Uncached Read 68.78 13.24 MB/sec [256K blocks]

MacBandit
Dec 17, 2002, 01:52 AM
Originally posted by D*I*S_Frontman
Did I read these results right? The guy with the upgraded Pismo (G4/500) scores comparably with a TiBook 800? Why is that, given the processor speed disparity? Maybe one of you hardware geniuses can explain it to me.

I have been intending to drop the $300 to send my Pismo G3/400 to Newertech or Powerlogix, and this test would seem to indicate that I would be an IDIOT not to.

There is more then one thing going on. First off the test on the Pismo is with XBench 1.0B2 and the TiBook is with 1.0B3. These two versions can not be compared with any validity.

If you are going to compare them any way. Here's what I see. The TiBook is faster overall by nearly 17.5 points. This is huge amount. Much greater then you would think. Also based on some very irregular results I would say that not only are the systems being tested on two different versions of XBench but also probably on two different versions of OSX. Also I the TiBook could have been tested on a system with a full hard drive and hadn't had permissions or any other system maintenance done in a while.

Just a reminder to everyone. Please test on a fresh restart. Also to keep everything equal fix permissions immediatly prior to testing. On a final note if you don't leave your machine on over night at least once a week you should download MacJanitor (http://www.versiontracker.com/moreinfo.fcgi?id=10491&db=mac) and run it once and a while to allow the system to run it's cleanup routines.

Tarlach
Dec 19, 2002, 08:50 PM
[QUOTE]Originally posted by Tarlach
[B]G3 B & W 350 oc'd to 400 384 mb RAM and Maxtor 7200 30gb HD. Apache was running.
I ran this test without rebooting, it has been running apache, I am using it as a webserver.

I just installed OS X 10.2.3 and got around a 13% improvement on xbench scores. It seems as the main improvement is in the disk scores.
Interesting.

MacBandit
Dec 20, 2002, 12:48 AM
This is the test I did after installing 10.2.3 and repairing permissions. As you can see nearly everything tests slower with 10.2.3. The system overall doesn't feel any slower so it's either not significant or XBench is unable to test 10.2.3 comparably or correctly as compared to 10.2.2.

Tarlach
Dec 20, 2002, 10:30 AM
MacBandit, interesting. I noticed in a few things the scores were marginally lower but my overall score was higher.
My disk test scores were significantly higher.
When I get more time I'll test some more.
I'll halt apache, repair permissions and see what happens. I would be very much surprised if after doing that I got slower scores though.
What I can't do is go back and retest 10.2.2, but I do have the xbench scores from it saved all I can do is compare at this point.
Anyone else showing a slowdown?

Ben Sheehan
Dec 20, 2002, 09:00 PM
PB 667 DVI

Results 77.12
System Info
Xbench Version 1.0b3
System Version 10.2
Physical RAM 768 MB
Processor PowerPC,G4@0 [667 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 134 MHz
CPU Test 78.67
GCD Recursion 73.63 2.88 Mops/sec
Floating Point Basic 78.04 263.00 Mflop/sec
AltiVec Basic 83.45 4.53 Gflop/sec
Floating Point Library 79.56 3.57 Mops/sec
Thread Test 71.93
Computation 43.29 348.75 Kops/sec, 4 threads
Memory Contention 125.31 396.36 MB/sec, 2 threads
Lock Contention 47.19 592.32 Klocks/sec, 4 threads
Memory Test 100.83
System 101.20
Allocate 83.83 44.10 Kalloc/sec
Fill 167.42 960.05 MB/sec
Copy 52.35 314.07 MB/sec
Stream 100.47
Copy 99.30 397.19 MB/sec [altivec]
Scale 101.26 405.05 MB/sec [altivec]
Add 103.79 415.15 MB/sec [altivec]
Triad 97.52 390.06 MB/sec [altivec]
Quartz Graphics Test 78.05
Line 82.61 2.10 Klines/sec [50% alpha]
Rectangle 64.29 4.52 Krects/sec [50% alpha]
Circle 84.65 1.95 Kcircles/sec [50% alpha]
Bezier 83.57 908.06 beziers/sec [50% alpha]
Text 75.12 1.27 Kchars/sec
OpenGL Graphics Test 82.18
Spinning Squares 82.18 57.51 frames/sec
User Interface Test 74.29
Elements 74.29 23.77 refresh/sec
Disk Test 53.91
Sequential 64.01
Uncached Write 53.27 19.83 MB/sec [4K blocks]
Uncached Write 55.18 19.33 MB/sec [256K blocks]
Uncached Read 96.80 14.31 MB/sec [4K blocks]
Uncached Read 50.80 19.05 MB/sec [256K blocks]
Random 43.82
Uncached Write 30.87 0.52 MB/sec [4K blocks]
Uncached Write 47.56 9.88 MB/sec [256K blocks]
Uncached Read 41.85 0.45 MB/sec [4K blocks]
Uncached Read 54.98 10.58 MB/sec [256K blocks]

jefhatfield
Dec 21, 2002, 07:59 AM
with ghz tibooks near 100 in score/speed rating, what would my little old ibook at 300 mhz bench at?

i don't dare find out;)

MacBandit
Dec 21, 2002, 10:05 AM
Originally posted by jefhatfield
with ghz tibooks near 100 in score/speed rating, what would my little old ibook at 300 mhz bench at?

i don't dare find out;)

Around 30.

Rower_CPU
Dec 21, 2002, 06:25 PM
Results 103.53
System Info
Xbench Version 1.0b3
System Version 10.2.3
Physical RAM 1024 MB
Processor PowerPC,G4@0 [1000 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 134 MHz
CPU Test 113.56
GCD Recursion 105.85 4.13 Mops/sec
Floating Point Basic 118.01 397.73 Mflop/sec
AltiVec Basic 111.89 6.07 Gflop/sec
Floating Point Library 118.50 5.32 Mops/sec
Thread Test 87.92
Computation 63.89 514.68 Kops/sec, 4 threads
Memory Contention 132.38 418.72 MB/sec, 2 threads
Lock Contention 67.48 847.03 Klocks/sec, 4 threads
Memory Test 120.43
System 138.54
Allocate 122.25 64.31 Kalloc/sec
Fill 240.57 1379.52 MB/sec
Copy 52.81 316.83 MB/sec
Stream 102.31
Copy 101.96 407.83 MB/sec [altivec]
Scale 102.10 408.39 MB/sec [altivec]
Add 104.73 418.93 MB/sec [altivec]
Triad 100.47 401.88 MB/sec [altivec]
Quartz Graphics Test 121.81
Line 126.43 3.22 Klines/sec [50% alpha]
Rectangle 121.02 8.51 Krects/sec [50% alpha]
Circle 137.25 3.16 Kcircles/sec [50% alpha]
Bezier 121.83 1.32 Kbeziers/sec [50% alpha]
Text 102.53 1.73 Kchars/sec
OpenGL Graphics Test 97.61
Spinning Squares 97.61 68.31 frames/sec
User Interface Test 116.66
Elements 116.66 37.33 refresh/sec
Disk Test 66.70
Sequential 75.55
Uncached Write 65.90 24.53 MB/sec [4K blocks]
Uncached Write 68.68 24.06 MB/sec [256K blocks]
Uncached Read 103.41 15.28 MB/sec [4K blocks]
Uncached Read 64.20 24.07 MB/sec [256K blocks]
Random 57.86
Uncached Write 68.61 1.15 MB/sec [4K blocks]
Uncached Write 57.19 11.88 MB/sec [256K blocks]
Uncached Read 41.11 0.44 MB/sec [4K blocks]
Uncached Read 64.51 12.42 MB/sec [256K blocks]

jefhatfield
Dec 22, 2002, 07:37 AM
Originally posted by MacBandit


Around 30.

or below...because i only have 160 MB of RAM which is the max for a rev a model:p

Dr. Distortion
Dec 22, 2002, 08:30 AM
Hi fellow benchtesters,

has anyone tried this: in Terminal, type "sudo renice -20 [xbench thread #]" ?

it should give xbench maximum cpu power while benchtesting, because it gives the xbench process max. priority.

cheers,

-Dr.D.

G5orbust
Dec 24, 2002, 12:49 AM
Originally posted by Rower_CPU
Results 103.53
System Info
Xbench Version 1.0b3
System Version 10.2.3
Physical RAM 1024 MB
Processor PowerPC,G4@0 [1000 MHz]
L1 Cache 32K (instruction), 32K (data)
Bus Frequency 134 MHz
CPU Test 113.56
GCD Recursion 105.85 4.13 Mops/sec
Floating Point Basic 118.01 397.73 Mflop/sec
AltiVec Basic 111.89 6.07 Gflop/sec
Floating Point Library 118.50 5.32 Mops/sec
Thread Test 87.92
Computation 63.89 514.68 Kops/sec, 4 threads
Memory Contention 132.38 418.72 MB/sec, 2 threads
Lock Contention 67.48 847.03 Klocks/sec, 4 threads
Memory Test 120.43
System 138.54
Allocate 122.25 64.31 Kalloc/sec
Fill 240.57 1379.52 MB/sec
Copy 52.81 316.83 MB/sec
Stream 102.31
Copy 101.96 407.83 MB/sec [altivec]
Scale 102.10 408.39 MB/sec [altivec]
Add 104.73 418.93 MB/sec [altivec]
Triad 100.47 401.88 MB/sec [altivec]
Quartz Graphics Test 121.81
Line 126.43 3.22 Klines/sec [50% alpha]
Rectangle 121.02 8.51 Krects/sec [50% alpha]
Circle 137.25 3.16 Kcircles/sec [50% alpha]
Bezier 121.83 1.32 Kbeziers/sec [50% alpha]
Text 102.53 1.73 Kchars/sec
OpenGL Graphics Test 97.61
Spinning Squares 97.61 68.31 frames/sec
User Interface Test 116.66
Elements 116.66 37.33 refresh/sec
Disk Test 66.70
Sequential 75.55
Uncached Write 65.90 24.53 MB/sec [4K blocks]
Uncached Write 68.68 24.06 MB/sec [256K blocks]
Uncached Read 103.41 15.28 MB/sec [4K blocks]
Uncached Read 64.20 24.07 MB/sec [256K blocks]
Random 57.86
Uncached Write 68.61 1.15 MB/sec [4K blocks]
Uncached Write 57.19 11.88 MB/sec [256K blocks]
Uncached Read 41.11 0.44 MB/sec [4K blocks]
Uncached Read 64.51 12.42 MB/sec [256K blocks]


how did you PB do that?

I have a 933 G4 w/ 1024 MB of RAM and a GF4ti! and i barely get close to 100 (normal score is about 98) can osmeone tell me why that happenes?

MacBandit
Dec 24, 2002, 01:20 AM
Originally posted by G5orbust



how did you PB do that?

I have a 933 G4 w/ 1024 MB of RAM and a GF4ti! and i barely get close to 100 (normal score is about 98) can osmeone tell me why that happenes?

Retest it using XBench 1.0b3. Also did you test it when the hard drive was clean? Anyone testing a new system is likely testing it with the hard drive nearly empty. A 1GHz G4 will test higher especially with everything that I mentioned above.

MacBandit
Jan 15, 2003, 01:22 AM
XBench 1.0B5 has been released. I will post new comparrisons showing the differences in test results from 1.0B3 to 1.0B5 as soon as I get a chance.

MacBandit
Jan 15, 2003, 02:30 AM
Okay here are my lastest results using XBench 1.0B5. My latest results using 1.0B3 are on the left. My new results using 1.0B5 are on the right. As you can see my scores have dropped lower this once again means that all previous results are useless in comparring results as produced by 1.0B5.

There are a few simple reasons for this. The thread test for memory was dropped due to errors in results also 4k disk testing was modified for more accurate results this has all added up to an overall change in results for the lower at least with my machine.

One nice thing is that the display of system info has been cleaned up and L2 and L3 information has been added. Overall this is still a decent program for comparring machines including yours before and after an upgrade. Remember though that the results are not the end all of performance comparrisons. For instance it does not tell you how a Dual processor machine will compare to a single proccessor machine when multitasking etc..

bousozoku
Jan 16, 2003, 10:23 PM
Forget about b5...it's buggy and hangs up. b6 is out now.

sparkleytone
Jan 23, 2003, 10:25 AM
Results 46.11
System Info
Xbench Version 1.0b7
System Version 10.2.3
Physical RAM 640 MB
Processor PowerPC 750 @ 600 MHz
L1 Cache 32K (instruction), 32K (data)
L2 Cache 256K @ 600.00 MHz
Bus Frequency 100 MHz
Video Card ATY,RageM3
Drive Type TOSHIBA MK3017GAS
CPU Test 63.19
GCD Recursion 53.21 2.08 Mops/sec
Floating Point Basic 55.75 187.90 Mflop/sec
Floating Point Library 93.05 4.18 Mops/sec
Thread Test 45.75
Computation 38.21 307.79 Kops/sec, 4 threads
Lock Contention 57.01 715.61 Klocks/sec, 4 threads
Memory Test 29.39
System 24.45
Allocate 104.73 55.09 Kalloc/sec
Fill 23.38 134.06 MB/sec
Copy 14.21 71.04 MB/sec
Stream 36.83
Copy 36.88 161.25 MB/sec
Scale 37.01 161.45 MB/sec
Add 36.09 164.21 MB/sec
Triad 37.38 164.25 MB/sec
Quartz Graphics Test 50.42
Line 46.98 1.20 Klines/sec [50% alpha]
Rectangle 62.28 4.38 Krects/sec [50% alpha]
Circle 63.65 1.47 Kcircles/sec [50% alpha]
Bezier 44.74 486.15 beziers/sec [50% alpha]
Text 42.07 685.75 chars/sec
OpenGL Graphics Test 80.78
Spinning Squares 80.78 56.53 frames/sec
User Interface Test 43.76
Elements 43.76 14.89 refresh/sec
Disk Test 39.93
Sequential 47.48
Uncached Write 43.28 18.88 MB/sec [4K blocks]
Uncached Write 45.17 18.38 MB/sec [256K blocks]
Uncached Read 63.56 10.01 MB/sec [4K blocks]
Uncached Read 42.98 18.54 MB/sec [256K blocks]
Random 34.45
Uncached Write 19.87 0.30 MB/sec [4K blocks]
Uncached Write 40.92 9.39 MB/sec [256K blocks]
Uncached Read 47.61 0.31 MB/sec [4K blocks]
Uncached Read 49.19 9.64 MB/sec [256K blocks]

blogo
Jan 23, 2003, 11:10 AM
Results 52.69
System Info
Xbench Version 1.0b7
System Version 10.2.3
Physical RAM 640 MB
Processor PowerPC G4 @ 467 MHz
L1 Cache 32K (instruction), 32K (data)
L2 Cache 1024K @ 234.00 MHz
Bus Frequency 134 MHz
Video Card ATY,Rage128Pro (ATI Rage 128 Pro)
Drive Type Maxtor 33073H3 M
CPU Test 39.01
GCD Recursion 41.82 1.63 Mops/sec
Floating Point Basic 47.38 159.68 Mflop/sec
AltiVec Basic 23.02 1.25 Gflop/sec
Floating Point Library 70.97 3.19 Mops/sec
Thread Test 35.31
Computation 29.96 241.35 Kops/sec, 4 threads
Lock Contention 43.00 539.70 Klocks/sec, 4 threads
Memory Test 77.24
System 63.87
Allocate 73.66 38.75 Kalloc/sec
Fill 81.07 464.87 MB/sec
Copy 47.48 237.42 MB/sec
Stream 97.69
Copy 97.00 424.19 MB/sec [altivec]
Scale 97.90 427.12 MB/sec [altivec]
Add 96.77 440.29 MB/sec [altivec]
Triad 99.12 435.51 MB/sec [altivec]
Quartz Graphics Test 69.98
Line 61.57 1.57 Klines/sec [50% alpha]
Rectangle 78.02 5.49 Krects/sec [50% alpha]
Circle 77.47 1.79 Kcircles/sec [50% alpha]
Bezier 69.69 757.23 beziers/sec [50% alpha]
Text 66.07 1.08 Kchars/sec
OpenGL Graphics Test 68.56
Spinning Squares 68.56 47.98 frames/sec
User Interface Test 63.49
Elements 63.49 21.60 refresh/sec
Disk Test 46.91
Sequential 55.26
Uncached Write 48.19 21.02 MB/sec [4K blocks]
Uncached Write 52.03 21.17 MB/sec [256K blocks]
Uncached Read 83.71 13.18 MB/sec [4K blocks]
Uncached Read 48.86 21.08 MB/sec [256K blocks]
Random 40.76
Uncached Write 38.65 0.58 MB/sec [4K blocks]
Uncached Write 38.60 8.85 MB/sec [256K blocks]
Uncached Read 39.28 0.26 MB/sec [4K blocks]
Uncached Read 47.85 9.38 MB/sec [256K blocks]

FlamDrag
Jan 23, 2003, 11:35 AM
Results 33.63
System Info
Xbench Version 1.0b7
System Version 10.2.3
Physical RAM 256 MB
Processor PowerPC 750 @ 500 MHz
L1 Cache 32K (instruction), 32K (data)
L2 Cache 1024K @ 200.00 MHz
Bus Frequency 100 MHz
Video Card ATY,RageM3
Drive Type TOSHIBA MK1214GAP
CPU Test 51.56
GCD Recursion 44.92 1.75 Mops/sec
Floating Point Basic 43.83 147.72 Mflop/sec
Floating Point Library 76.27 3.43 Mops/sec
Thread Test 38.80
Computation 31.86 256.65 Kops/sec, 4 threads
Lock Contention 49.61 622.68 Klocks/sec, 4 threads
Memory Test 29.84
System 27.95
Allocate 77.98 41.02 Kalloc/sec
Fill 39.57 226.93 MB/sec
Copy 14.45 72.23 MB/sec
Stream 31.99
Copy 32.00 139.94 MB/sec
Scale 32.08 139.97 MB/sec
Add 31.38 142.80 MB/sec
Triad 32.53 142.93 MB/sec
Quartz Graphics Test 38.64
Line 35.56 905.26 lines/sec [50% alpha]
Rectangle 35.22 2.48 Krects/sec [50% alpha]
Circle 38.21 880.76 circles/sec [50% alpha]
Bezier 50.07 544.01 beziers/sec [50% alpha]
Text 37.39 609.38 chars/sec
OpenGL Graphics Test 25.71
Spinning Squares 25.71 17.99 frames/sec
User Interface Test 44.12
Elements 44.12 15.01 refresh/sec
Disk Test 23.81
Sequential 24.93
Uncached Write 20.52 8.95 MB/sec [4K blocks]
Uncached Write 21.76 8.85 MB/sec [256K blocks]
Uncached Read 55.51 8.74 MB/sec [4K blocks]
Uncached Read 20.94 9.04 MB/sec [256K blocks]
Random 22.78
Uncached Write 14.90 0.22 MB/sec [4K blocks]
Uncached Write 23.80 5.46 MB/sec [256K blocks]
Uncached Read 32.03 0.21 MB/sec [4K blocks]
Uncached Read 28.38 5.56 MB/sec [256K blocks]


I can't wait for my new PB!

That was using b7 of xbench.

jefhatfield
Jan 23, 2003, 12:09 PM
i wonder if there is a database for older benchmarks for pismos, clamshell ibooks, beige tower macs, and the like

sparkleytone
Jan 23, 2003, 03:20 PM
if people submit the results, you can look at them...

http://ladd.dyndns.org/xbench/

edit: btw jef, now that the iBook G4 is out...you gonna upgrade??

jefhatfield
Jan 23, 2003, 08:23 PM
Originally posted by sparkleytone
if people submit the results, you can look at them...

http://ladd.dyndns.org/xbench/

edit: btw jef, now that the iBook G4 is out...you gonna upgrade??

you mean the G4 12" aluminum powerbook, which in many ways is kind of like a g4 ibook...with some extra professional pizzaz:D

i have my eye on that one

MacBandit
Feb 2, 2003, 05:05 PM
Here's my latest test of my Dual/GHz/DDR. This is running XBench 1.0 and after a fresh install of OSX with all the updates to 10.2.3. This is as good as it gets for tests with XBench 1.0.

Rower_CPU
Feb 2, 2003, 11:43 PM
Reran tests on the Gigabook w/ Xbench 1.0...

Good enough for the top rated 1GHz TiBook on the Xbench database. :D

pnz999
Feb 3, 2003, 03:30 PM
Originally posted by Rower_CPU
Reran tests on the Gigabook w/ Xbench 1.0...

Good enough for the top rated 1GHz TiBook on the Xbench database. :D


Where is the X-bench database.

diorio
Feb 3, 2003, 03:35 PM
Just a question, is benchmark anything like 3D mark for athalon?

-hh
Feb 3, 2003, 04:31 PM
Okay guys.

I've looked at a bunch of neat numbers and the like. Obviously, "bigger is better", but now let's get down to brass tacks: what's it really mean?

For example, consider what your advice should be for the following:


Q1: An old system still running OS 9, and doing "general duty" stuff (Web @ 56Kbps, email, etc). What's the lowest (MINIMUM) XBENCH score you'll tolerate sitting behind before you pull out your hair at using such a slow beast and replace it?


Q2: The guy who updated a few years ago. Same "General Purpose" application. The difference is that he's running OS 10.2.x What's the lowest (MIN) XBENCH before you replace it?

Q3: Similar to Q3 above, except our user is now modestly more demanding - he plays games, dabbles in Photoshop, etc. At what XBENCH does he need to start shopping?

Q4: The supreme power user, for who the answer's already obvious (whatever's the fastest current model). Included so as to clarify that the User in Q3 is not this guy.


An example of your opinion might look like this:

Q1: 35
Q2: 50
Q3: 100
Q4: 130&up

Is this not enough/okay/plenty of power for each of these applications?

...or are we simply going to admit that we buy to whatever our budget can afford? :D

-hh

Rower_CPU
Feb 3, 2003, 05:58 PM
pnz999:
You submit your scores to the database by clicking the "Submit" button in the Xbench toolbar. This connects you to the database automatically. Or you can go to this link:
http://ladd.dyndns.org/xbench/

diorio:
3D Mark only tests your graphics hardware, whereas Xbench tests your whole system. I'd say it's more similar to Sisoft's Sandra, but with an overall score feature, which Sandra lacks.

MacBandit
Feb 4, 2003, 12:52 AM
Originally posted by -hh
Okay guys.

I've looked at a bunch of neat numbers and the like. Obviously, "bigger is better", but now let's get down to brass tacks: what's it really mean?

For example, consider what your advice should be for the following:


Q1: An old system still running OS 9, and doing "general duty" stuff (Web @ 56Kbps, email, etc). What's the lowest (MINIMUM) XBENCH score you'll tolerate sitting behind before you pull out your hair at using such a slow beast and replace it?


Q2: The guy who updated a few years ago. Same "General Purpose" application. The difference is that he's running OS 10.2.x What's the lowest (MIN) XBENCH before you replace it?

Q3: Similar to Q3 above, except our user is now modestly more demanding - he plays games, dabbles in Photoshop, etc. At what XBENCH does he need to start shopping?

Q4: The supreme power user, for who the answer's already obvious (whatever's the fastest current model). Included so as to clarify that the User in Q3 is not this guy.


An example of your opinion might look like this:

Q1: 35
Q2: 50
Q3: 100
Q4: 130&up

Is this not enough/okay/plenty of power for each of these applications?

...or are we simply going to admit that we buy to whatever our budget can afford? :D

-hh

I started this thread and have been thoroughly involved in this for a while no.w I must say that your numbers are exactly what I was thinking when I was reading the questions. Even before I saw the numbers you listed below.

diorio
Feb 4, 2003, 06:39 PM
Originally posted by Rower_CPU


diorio:
3D Mark only tests your graphics hardware, whereas Xbench tests your whole system. I'd say it's more similar to Sisoft's Sandra, but with an overall score feature, which Sandra lacks.

Thanks for the info. switching from AGP to PCI makes the score on 3D mark go down about 3000!