Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
XBench Results
- Thread starter MacBandit
- Start date
- Sort by reaction score
My old mac
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.
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.
re-tested my mirror door... after updating to 10.2.1
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]
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]
Re: re-tested my mirror door... after updating to 10.2.1
I noticed you didn't run your CPU test I wonder if this brought down your overall score.
I noticed you didn't run your CPU test I wonder if this brought down your overall score.
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]
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]
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.
https://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
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.
https://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
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
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
400 MHz g3 pbook, 192 meg RAM
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?
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?
Re: 400 MHz g3 pbook, 192 meg RAM
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.
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.
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.
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.
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]
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]
Original iBook 500 320MB/10GB 4200RPM
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]
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]
poor imac-350 results
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]
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]
Re: poor imac-350 results
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 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+.
Re: Re: poor imac-350 results
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.
Re: Re: Re: poor imac-350 results
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.
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.
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.