IanCutress

Kabini ftw

It doesn't probe all bits of the CPU like Prime95/LinX, just normal arithmetic adds, divides, bitshifts et al. Almost memory agnostic too, just requires CPU speed

Here's a benchmark I wrote over a year ago, and I've been using it in my reviews ever since. Simply put, it is based on 3D Random Movement algorithms. There are a fair few when looking at the literature, and all use a variety of different mathematical formula to achieve the same result. Some are more trigonmetric heavy, some use random numbers generated using normal or variable distribution algorithms. When moving a single item a few spots, the speed of each algorithm is of no concern, but when you move into scientific computing and have to deal with billions, having the best algorithm for the job is on the table. So this is the 3D Particle Movement benchmark, 3DPM for short, which uses 6 of these algorithms so find the best speeds. The benchmark comes in two varieties: a) 3DPM-ST: Single Thread mode, where one thread is generated b) 3DPM-MT: MutliThread mode, where the CPU has to be able to cope with >10000 threads. If anyone is interested, I am in the process of organising integration of this benchmark into HWBot. Submissions to HWBot will be the usual CPU submission process - screenshot with CPU-Z of CPU and CPU-Z of Memory. The benchmark does produce an file, which I will be writing a website for shortly. But for now, here are the poignant links: Still in alpha phase on HWBot, for now Results page for 3DPM-ST: http://hwbot.org/benchmark/3dpm-st Results page for 3DPM-MT: http://hwbot.org/benchmark/3dpm-mt The download page: http://www.borandi.co.uk/3DPM Submission for 3DPM-ST: http://hwbot.org/submit/benchmark/3DPM-ST Submission for 3DPM-MT: http://hwbot.org/submit/benchmark/3DPM-MT Edit: For those wondering why AMD doesn't score so high... AMD architecture loves integer (whole number) operations, especially when parallel. This benchmark was written in floating point (FP) operations, which is the usual standard for scientific programming depending on the algorithm.

Running at half threads if anyone is interested

Ticket ID: 1761 Priority: High When you add a new benchmark to the database, and then change its name, the scores submitted for that benchmark all feature the old name.\r\n\r\nExample:\r\n\r\nI started a benchmark called \'3D Particle Movement-ST\'. I then changed the name to \'3DPM-ST\'. Here\'s submitted result for that benchmark:\r\n\r\nhttp://hwbot.org/submission/2407751\r\n\r\nIt states \' BORANDI`s 3D PARTICLE MOVEMENT - ST score \', and obviously the link that has in it goes to the wrong place.\r\n\r\nJust an FYI, looks like a string that is created on benchmark addition isn\'t changed when the owner updates it.

Andre may retire, but his results will live on for a long time. Nice going man, good luck in the new life

Yeah, something wrong there

It can take a while HWbot is slow sometimes

Force a recalculation on your whole profile if there are many scores mixed up. In your profile panel

Here's a suggestion. Say I search for a CPU or GPU in the search box, and I press enter too quickly before the quick search comes up. It then takes me to a page with the results for that search. If there's only one result, perhaps it should take me just to that result automatically instead of me clicking around? Newegg does this method when searching for kit

Pi worked fine today, Linpack did not; submitting direct from the PC that made the result. Is something wrong with the key generation? I had to download the latest version to get PI to work, but Linpack is a dodo atm for me

Lucky git with skulltrail!

Ticket ID: 1750 Priority: Low http://en.wikipedia.org/wiki/Haswell_(microarchitecture)#Server_processors\r\n\r\nIntel HD P4600 (GT2) on Xeon processors... overclocking optional

Ticket ID: 1746 Priority: Low These please \r\n\r\nhttp://www.cpu-world.com/CPUs/Xeon/TYPE-Xeon%20E3-1200%20v3.html\r\n\r\nIntel Xeon E3-1220 v3 - CM8064601467204 / BX80646E31220V3\r\nIntel Xeon E3-1225 v3 - CM8064601466507 / BX80646E31225V3\r\nIntel Xeon E3-1230 v3 - CM8064601467202 / BX80646E31230V3\r\nIntel Xeon E3-1230L v3 - CM8064601467601\r\nIntel Xeon E3-1240 v3 - CM8064601467102 / BX80646E31240V3\r\nIntel Xeon E3-1245 v3 - CM8064601466509 / BX80646E31245V3\r\nIntel Xeon E3-1265L v3 - CM8064601467406\r\nIntel Xeon E3-1268L v3 - CM8064601484200\r\nIntel Xeon E3-1270 v3 - CM8064601467101 / BX80646E31270V3\r\nIntel Xeon E3-1275 v3 - CM8064601466508 / BX80646E31275V3\r\nIntel Xeon E3-1280 v3 - CM8064601467001\r\nIntel Xeon E3-1285 v3 - CM8064601466703\r\nIntel Xeon E3-1285L v3 - CM8064601466804

I've had this too. Also, I can submit a Pi result as a Linpack result and vice versa. Might want to have something in there to not do that

BOOM. There it is. Nice one

Crazy, was this chip ever sold to the public? Can't find it anywhere

Ticket ID: 1735 Priority: Low http://ark.intel.com/products/71073/\r\n\r\nDon\'t forget my Kabini APU GPUs (Ticket 1723 iirc)

It's on all the boards, and in the A-Tuning OS software on the disk http://anandtech.com/show/6989/11

Ticket ID: 1733 Priority: Low http://en.wikipedia.org/wiki/List_of_AMD_Accelerated_Processing_Unit_microprocessors#.22Kabini.22.2C_.22Temash.22_.282013.2C_28_nm.29\r\n\r\nA4-1200 2 Cores 1.0 GHz 1 MB 3.9 W AT1200IFJ23HM\r\nA4-1250 2 Cores 1.0 GHz 1 MB 8 W AT1250IDJ23HM\r\nA6-1450 4 Cores 1.4 GHz 2 MB 8 W May 2013 AT1450IDJ44HM\r\nE1-2100 2 Cores 1.0 GHz N/A 1 MB 9 W May 2013 EM2100ICJ23HM\r\nE1-2500 2 Cores 1.4 GHz 1MB 15 W May 2013 EM2500IBJ23HM\r\nE2-3000 2 Cores 1.65 GHz 1 MB 15 W May 2013 EM3000IBJ23HM\r\nA4-5000 4 Cores 1.5 GHz 2 MB 15 W May 2013 AM5000IBJ44HM\r\nA6-5200 4 Cores 2.0 GHz 2 MB 25 W May 2013 AM5200IAJ44HM\r\n\r\nAnd their corresponding IGPs:\r\n\r\nModel Config Freq. Turbo\r\nHD 8180 128:-:- 225 MHz\r\nHD 8210 128:-:- 300 MHz \r\nHD 8250 128:-:- 300 MHz \r\nHD 8240 128:-:- 400 MHz \r\nHD 8280 128:-:- 450 MHz \r\nHD 8330 128:-:- 500 MHz \r\nHD 8400 128:-:- 600 MHz\r\n\r\nEach of these has an E version as well (under on the wiki link)\r\n\r\nProof ! http://valid.canardpc.com/show_oc.php?id=2854398

I think you mean 80% of people are fine with it. This change has had over A YEAR from initial discussion to public discussion and people have always been free to state their opposition. If people are ONLY coming out of the woodwork now, then where the bunny have you all been? This is change that has been long overdue IMO.

^^ This There is always opportunity to get 'easy points' up to a certain extent - a pair of 4870x2s on air with a strong CPU for example can rack up a nice number of hardware points, just because those cards are mostly benched on air. Multi-CPU categories were another place, but the poignant issue here is global points. People have no qualms on 2 HW points on a multicore setup, but the 60 globals is the issue when you have zero competition (let alone the overclockability). As I noted, Dead Things drops out of the top 20 with this change, I lose some points too. If you spend money to 'exploit' easy points, then you do it for the moment. The minute you drive around the Nurburgring without insurance is the time you side-swipe into a tree The only guaranteed way to get points and move up the rankings is to prove your worth in difficult categories, where scores have longevity.

Interesting that Dead Things disappears from the EL top 20 completely, no?

Ticket ID: 1727 Priority: Low http://en.wikipedia.org/wiki/List_of_AMD_Accelerated_Processing_Unit_microprocessors#.22Kabini.22_.282013.2C_28_nm.29\r\n\r\nGX-420CA 4 Cores 2.0 GHz 25 W June 1, 2013 GE420CIAJ44HM\r\nGX-416RA 4 Cores 1.6 GHz 15 W June 1, 2013 GE416RIBJ44HM\r\nGX-415GA 4 Cores 1.5 GHz 15 W June 1, 2013 GE415GIBJ44HM\r\nGX-217GA 2 Cores 1.65 GHz 15 W June 1, 2013 GE217GIBJ23HM\r\nGX-210HA 2 Cores 1.0 GHz 9 W June 1, 2013

Ticket ID: 1726 Priority: Low ECS VX900-I:\r\nhttp://www.ecs.com.tw/ECSWebSite/Product/Product_Detail.aspx?DetailID=1374&MenuID=155&LanID=0\r\n\r\nECS NM70-I2:\r\nhttp://www.ecs.com.tw/ECSWebSite/Product/Product_Detail.aspx?DetailID=1445&CategoryID=1&MenuID=17&LanID=0\r\n\r\nASRock IMB-A180-H:\r\nhttp://www.asrock.com/ipc/overview.asp?Model=IMB-A180-H