Bye Bye Super-Pi

Status
Not open for further replies.

superczar

Keymaster
All credit goes to Gophn @ NBR forums

:D Measure your Dual/Multi Core CPU Speed - Bye Bye to SuperPI :D
Last Updated: 2007-06-11

This is a thread that is a long time coming.

Note: It will be complimentary to the thread on:
- Measure your Notebook CPU Speed (mainly SuperPI related)
& Windows XP Multi Core config - Does your OEM do it for you?

:no: The Past CPU Benchmark(s): :no:
Super PI
superpidr1.jpg

- is single threaded, so its relevance as a measure of performance in the current era of multi-core processors is diminishing quickly. As the calculation times become faster and faster, Super PI is also becoming a rather poor stability test due to the need for a stability test to run long enough to stress the hardware. This program does not utilize all of the multi-cores/processors when running the test... strange that most people still use this as a benchmark... especially since the scores are geared towards high clock speed single-core CPUs.
_________________________________________

:wink: The New CPU Benchmark(s): :wink:
wPrime - (Download Site - choose hwbot GUI)
Compatibility:
- Virtually all CPUs (single-core, multi-core, multi-processors, multi-logical processors)
- Windows XP w/ SP2 and Vista (32-bit and 64-bit)
Note 1: (for all Windows versions w/ multiple user accounts) you need to have an account with Admin privileges to run this benchmark.
Note 2: (for Vista) you need to manually set 2 threads under the advanced settings. Otherwise the times will be doubled.
Note 3: (for XP w/ SP2 32-bit) if you have a dual-core [or multi-core] CPU, your scores can vary [be lower than expected] if you did not do the XP Multi-Core Hotfix
wprimepichz1.jpg

- is multi-threaded, which means that it will utilize the entire multi-core CPU within its test. It is very similar to SuperPI, but has a bit more features that is thanks to CPU-Z (install this missing library within wPrime) to retrieve most of the hardware information (CPU, Motherboard, etc..). Their site has many submissions on scores from a lot of CPUs (both in single and multi-core/processors).

Technicalities
wPrime uses a recursive call of Newton's method for estimating functions, with f(x)=x2-k, where k is the number we're sqrting, until Sgn(f(x)/f'(x)) does not equal that of the previous iteration, starting with an estimation of k/2. It then uses an iterative calling of the estimation method a set amount of times to increase the accuracy of the results. It then confirms that n(k)2=k to ensure the calculation was correct. It repeats this for all numbers from 1 to the requested maximum.

wprimeao7.jpg

Threading
The aim was to make a perfectly threaded benchmark, such that it would consistantly use 100% of the CPU while in use. This is achieved by using the WMI to detect the CPU count and use exactly that many processing threads to avoid any performance losses due to multiple threads running on any single physical thread. Each thread is designed to do 1/n of the work, where n is the number of threads. For example, if you're calculating 16 roots on 4 CPU's, each CPU will calculate 4 roots. Some might argue that this style of threading is unrealistic in real-time performance, but in fact is quite indicative of performance in several real world tasks such as F@H which allows you to run several instances of the work at any one time.

Multi-PI (still in beta testing)
multipiml8.jpg

- is a promising new CPU benchmarking program [Java-based] that is in beta testing. The most promising aspect of this benchmark is that it can also be used within Mac OS & Linux environments as well. When it gets a final release, this thread will be updated.

______________________________________________________

:notworthy: NBR wPrime Hall of Fame :notworthy:

:D Single Core: :D
<table width="100%" border="2" cellspacing="1" cellpadding="1"> <tr> <th> </th> <th>Processor (CPU) </th> <th>System Type/Model</th> <th>Score (32M) - Default Test </th> <th>Score (1024M) - Stress Test </th> </tr> <tr> <th>1.) R4000 </th> <td>AMD Athlon 64 3800+ @ 2.40GHz</td> <td>NB: Compaq R4000 | Vista Ultimate </td> <td>64.891s</td> <td>2109.828s</td> </tr> <tr> <th>2.) Necss</th> <td>Intel Core Solo CPU T1400 @ 1.83ghz</td> <td>NB: NEC P8210 | XP Home SP2</td> <td>69.529s</td> <td>n/a</td> </tr> <tr> <th>3.) EgoZum</th> <td>AMD Turion 64 MK-38 @ 2.20GHz</td> <td> NB: Aspire 5102AWLMi | Vista Home Premium </td> <td>70.540s</td> <td>2450.000s</td> </tr> <tr> <th>4.) DragoonThug</th> <td>Intel Pentium-M 770 @ 2.13GHz </td> <td>NB: Asus W2V | XP MCE2005 </td> <td> 84.875s</td> <td>n/a</td> </tr> <tr> <th>5.) R4000</th> <td>AMD Sempron 3300+ @ 2.00GHz</td> <td>NB: Compaq V5201US | XP Home </td> <td>86.046s</td> <td>2736.093s</td> </tr> <tr> <th>6.) slumbermann</th> <td>Intel Pentium 4 CPU w/ HT @ 3.20GHz</td> <td>DT: Fujitsu Scaleo 600 | XP SP2 </td> <td>89.359s</td> <td>3160.187s</td> </tr> <tr> <th>7.) Evolution</th> <td>Intel Pentium 4 540 CPU w/ HT @ 3.20GHz</td> <td>DT: custom desktop | XP Pro</td> <td>90.140s</td> <td>n/a</td> </tr> <tr> <th>8.) Chaz</th> <td>Intel Pentium-M 750 @ 1.86GHz</td> <td>NB: Sager 5320 (Clevo M560A) | Vista Ultimate </td> <td>91.887s</td> <td>2948.458s</td> </tr> <tr> <th>9.) Vivek</th> <td>Intel Pentium-M 750 @ 1.86GHz</td> <td>NB: Sony VAIO FJ270 | XP Home </td> <td> 95.015s</td> <td>3026.937s</td> </tr> <tr> <th>10.) odin243</th> <td>Intel Pentium-M @ 1.60GHz</td> <td>NB: Dell D400 | XP SP2 </td> <td>107.453s</td> <td>n/a</td> </tr> <tr> <th>11.) Apollo13</th> <td>Intel Pentium 4 CPU @ 2.66GHz</td> <td>DT: HP Pavilion 764n | XP Home </td> <td>119.812s</td> <td>3854.39s</td> </tr> <tr> <th>12.) Mr._Kubelwagen</th> <td>Intel Pentium 4 CPU @ 2.60GHz</td> <td> DT: Dell Dimension 8300 | XP Home </td> <td>169.705s</td> <td>n/a</td> </tr> <tr> <th>13.) John Ratsey</th> <td>Transmeta Crusoe CPU TM5600 @ 633MHz </td> <td>NB: Fujitsu P2020 | Win ME </td> <td> 608.792s</td> <td>5.92 hours</td> </tr></table>

:D Dual Core: :D
<table width="100%" border="2" cellspacing="1" cellpadding="1"> <tr> <th> </th> <th>Processor (CPU) </th> <th>System Type/Model</th> <th>Score (32M) - Default Test </th> <th>Score (1024M) - Stress Test </th> </tr> <tr> <th>1.) MrSneis</th> <td>AMD Athlon 64 FX-60 @ 2.60GHz </td> <td>PD: Sager 9750 (Clevo D900K) | Vista Ultimate x64 </td> <td>30.265s</td> <td>955.266s</td> </tr> <tr> <th>2.) hox</th> <td>Intel Core 2 Extreme CPU X6800 @ 2.93GHz</td> <td>PD: Sager 9260 (Clevo D900C) | XP Pro </td> <td>30.660s</td> <td>n/a</td> </tr><tr> <th>3.) Tenchi</th> <td>Intel Core 2 Duo CPU E6700 @ 2.66GHz</td> <td>PD: Sager 9260 (Clevo D900C) | XP Pro </td> <td>33.625s</td> <td>1069.656s</td> </tr> <tr> <th>4.) Chaz (NBR)</th> <td>Intel Core 2 Duo CPU E6700 @ 2.66GHz</td> <td>PD: Sager 9260 (Clevo D900C) | XP Pro </td> <td>33.718s</td> <td>1069.344s</td> </tr><tr> <th>5.) lmark84l</th> <td>Intel Core 2 Duo CPU E6600 @ 2.40GHz</td> <td>DT: custom desktop | XP SP2 </td> <td>35.000s</td> <td>1050.265s</td> </tr> <tr> <th>6.) VirtueTech</th> <td>Intel Core 2 Duo CPU T7600 @ 2.33GHz</td> <td>NB: Lenovo T60P | XP Pro </td> <td>38.200s</td> <td>n/a</td> </tr> <tr> <th>7.) nyst</th> <td>Intel Core 2 Duo CPU T7600 @ 2.33GHz</td> <td>NB: Sager 5760 (Clevo M570U) | XP SP2 </td> <td>38.406s</td> <td>1217.843s</td> </tr><tr> <th>8.) rb89</th> <td>AMD Turion 64 X2 TL-60 @ 2.00GHz</td> <td>NB: HP dv6000z | Vista Home Premium </td> <td>38.720s</td> <td>1233.63s</td> </tr> <tr> <th>9.) STEvil</th> <td>Intel Core 2 Duo CPU T7400 @ 2.16GHz</td> <td>NB: Alienware m5750 (Uniwill P72) | XP SP2 </td> <td><span id="user_5266">40.02</span>0s</td> <td><span id="user_5266">1273.53</span>s</td> </tr> <tr> <th>10.) McKillenstein</th> <td>Intel Core 2 Duo CPU T7400 @ 2.16GHz</td> <td>NB: LG S1 | XP SP2 </td> <td>40.843s</td> <td>n/a</td> </tr> <tr> <th>11.) dietcokefiend</th> <td>Intel Core 2 Duo CPU T7400 @ 2.16GHz</td> <td>NB: Lenovo T60 | XP Pro </td> <td>41.140s</td> <td>n/a</td> </tr> <tr> <th>12.) metalfandragula</th> <td>Intel Core 2 Duo CPU T7400 @ 2.16GHz</td> <td>NB: Dell e1705 | XP MCE2005 </td> <td>41.906s</td> <td>1331.437s</td> </tr> <tr> <th>13.) bob1182006</th> <td>Intel Core 2 Duo CPU T7200 @ 2.00GHz</td> <td>NB: Sager 5760 (Clevo M570U) | Vista Ultimate</td> <td>42.386s</td> <td>n/a</td> </tr><tr> <th>14.) jessi3k3 </th> <td>Intel Core 2 Duo CPU T7200 @ 2.00GHz</td> <td>NB: Toshiba P105 | Vista Home Premium </td> <td>42.428s</td> <td>1341.77s</td> </tr> <tr> <th>15.) rhino.software</th> <td>AMD Turion 64 X2 TL-56 @ 1.80GHz</td> <td>NB: Fujitsu XA 1526 | Vista</td> <td> 42.839s</td> <td>n/a</td> </tr> <tr> <th>16.) samuderaindia</th> <td>Intel Core Duo CPU T2500 @ 2.00GHz</td> <td> NB: Travelmate 8204WLMi | XP SP2 </td> <td>43.203s</td> <td> 1375.921s</td> </tr> <tr> <th>17.) heero_yuri</th> <td>Intel Core Duo CPU T2500 @ 2.00GHz</td> <td>NB: Sony Vaio FE28GP | XP Pro </td> <td> 43.406s</td> <td> 1388.078s</td> </tr><tr> <th>18.) theimmortal</th> <td>Intel Core Duo CPU T2500 @ 2.00GHz</td> <td>NB: HP NC8430 | XP SP2 </td> <td>43.640s</td> <td>n/a</td> </tr> <tr> <th>19.) Gator </th> <td>Intel Core 2 Duo CPU T7200 @ 2.00GHz</td> <td>NB: ASUS S96J | XP SP2 </td> <td>43.828s</td> <td>1384.375s</td> </tr> <tr> <th>20.) Surfer666</th> <td>Intel Core 2 Duo CPU T7300 @ 2.00GHz</td> <td>NB: Lenovo N200 | Vista </td> <td>44.171s</td> <td>n/a</td> </tr><tr> <th>21.) rahkunn</th> <td>Intel Core 2 Duo CPU T7200 @ 2.00GHz</td> <td>NB: Compal HEL-80 | XP SP2 </td> <td>44.827s</td> <td>n/a</td> </tr> <tr> <th>22.) John Ratsey</th> <td>Intel Core 2 Duo CPU T7200 @ 2.00GHz</td> <td>NB: Samsung X60plus | XP Pro </td> <td>44.922s</td> <td>1431.062s</td> </tr> <tr> <th>23.) Fusionburn</th> <td>Intel Core 2 Duo CPU T7200 @ 2.00GHz</td> <td>NB: Compal HGL-30 | XP Pro </td> <td>45.281s</td> <td>n/a</td> </tr><tr> <th>24.) plattnnum</th> <td>AMD Turion 64 X2 TL-60 @ 2.00GHz</td> <td>NB: HP dv6000z | XP SP2</td> <td>45.703s</td> <td>n/a</td> </tr><tr> <th>25.) John Ratsey</th> <td>Intel Core 2 Duo CPU T5600 @ 1.83GHz</td> <td> NB: Samsung Q35 | Vista Business & XP Pro </td> <td>45.850s (Vista) | 48.405s (XP)</td> <td>1445.62s (Vista) | 1527.156s (XP) </td> </tr> <tr> <th>26.) Vivek</th> <td>Intel Core Duo CPU T2400 @ 1.83GHz</td> <td>NB: Apple iMac | XP Pro </td> <td>47.046s</td> <td>1493.843s</td> </tr> <tr> <th>27.) John Ratsey</th> <td>Intel Core Duo CPU T2250 @ 1.73GHz</td> <td>NB: Samsung R20 | Vista Home Premium </td> <td>47.065s</td> <td>1496.119s</td> </tr> <tr> <th>28.) slumbermann</th> <td>Intel Core 2 Duo CPU T5500 @ 1.66GHz</td> <td>NB: Samsung Q35 | Vista Home Premium </td> <td>50.264s</td> <td>1597.687s</td> </tr> <tr> <th>29.) LFC</th> <td>Intel Core Duo CPU T2300 @ 1.66GHz</td> <td>NB: HP NC8430 | XP Home </td> <td>51.687s</td> <td>n/a</td> </tr><tr> <th>30.) mujtaba</th> <td>Intel Core Duo CPU T2300 @ 1.66GHz</td> <td>NB: ASUS W3J | XP Home</td> <td>52.380s</td> <td>n/a</td> </tr> <tr> <th>31.) AlexMcIver</th> <td>Intel Core Duo CPU T2300 @ 1.66GHz</td> <td>NB: Sony Vaio SZ2M/B | XP SP2 </td> <td>52.390s</td> <td>n/a</td> </tr> <tr> <th>32.) _radditz_</th> <td>Intel Core Duo CPU T2300 @ 1.66GHz</td> <td>NB: ASUS A6JC | XP SP2 </td> <td>52.750s</td> <td>1669.281s</td> </tr> <tr> <th>33.) j0hn00 </th> <td>Intel Core 2 Duo CPU T5500 @ 1.66GHz</td> <td>NB: ASUS W7J | XP SP2 </td> <td>52.969s</td> <td>1711.671s</td> </tr> <tr> <th>34.) jabba</th> <td>AMD Turion 64 X2 TL-50 @ 1.60GHz & OC 1.8GHz </td> <td>NB: unknown notebook | XP 32-bit & 64-bit </td> <td>53.000s & 52s (32-bit) | 57.00s (64-bit) </td> <td>n/a</td> </tr> <tr> <th>35.) miner</th> <td>AMD Turion 64 X2 TL-50 @ 1.60GHz</td> <td>NB: Compaq V3019US | XP Home </td> <td>53.015s</td> <td>1693.375s</td></tr><tr> <th>36.) Tinderbox (UK)</th> <td> Intel Core Duo CPU T2050 @ 1.60GHz</td> <td>NB: unknown notebook | XP Home </td> <td>53.812s</td> <td>n/a</td> </tr> <tr> <th>37.) AndyLH88</th> <td>Intel Core 2 Duo CPU T5500 @ 1.66GHz</td> <td>NB: Sony Vaio C140 | XP MCE2005</td> <td>54.047s</td> <td>n/a</td> </tr> <tr> <th>38.) adinu</th> <td>AMD Turion 64 X2 TL-50 @ 1.60GHz</td> <td>NB: Acer Aspire 5102WLMi | XP Pro</td> <td>54.214s</td> <td>n/a</td> </tr><tr> <th>39.) utprabh</th> <td>AMD Turion 64 X2 TL-50 @ 1.60GHz</td> <td>NB: Acer Aspire 5052 | XP SP2 </td> <td>57.920s</td> <td>1851.98s</td></tr></table>

:D Quad Core (or Multi core): :D
<table width="100%" border="2" cellspacing="1" cellpadding="1"> <tr> <th> </th> <th>Processor (CPU) </th> <th>System Type/Model</th> <th>Score (32M) - Default Test </th> <th>Score (1024M) - Stress Test </th> </tr> <tr> <td>1.) kkk60091</td> <td>Intel Core 2 Duo CPU Q6600 @ 2.40GHz & OC 3.00GHz</td> <td>DT: custom desktop | XP SP2 </td> <td>18.203s (stock) | 14.452s (OC) </td> <td>575.00s (stock) | 453.00s (OC)</td> </tr> <tr> <td>2.) STEvil</td> <td>(Dual) Intel Xeon 5120 @ 2.80GHz OC</td> <td>DT: custom desktop | XP SP2</td> <td>15.875s</td> <td>494.782</td> </tr> <tr> <td>3.)</td> <td> </td> <td> </td> <td> </td> <td> </td> </tr></table>

Key:
NB = Notebook
PD = Portable Desktop (powerful notebook with desktop features)
DT = Desktop

More scores here (from wPrime site)

Please post your results. :)

Free REP for anyone that participates. :)

To optimize your score:
- disable resource hogs (System Restore, Antivirus, etc..)
- switch Appearance/Theme to Classic Mode
 
Even SuperPrime is multi-thread.

A few of us are going to start using that.

That's Cool Adi..

Just that benchmarks should be easy to compare

Even though Super-Pi may not be the best benchmark ever, it is so widely used that it provides an easy way to compare two systems...

A standalone benchie doesn't mean anything unless there is a big enough user base to compare results

All the best tho'..May the force be with you ! :)
 
Status
Not open for further replies.