So, basically AMD wants more GPGPU benchmarks. I find it a bit strange when AMD speaks about "relevance" while not a single one commercial OpenCL software is available. How is this relevant to users? I know that games also important for users but for that purpose there is a bunch of benchmarks (such as 3DVantage with more then 90% of GPU weight in a final score).
BTW, AMD didn't propose any benchmark instead of Sysmark2007
Your point being? Mine is: laugh at the marketing folks, it's all you can do with them.Originally Posted by tifosi
Just like that John Fruehe quoted post, where "pretty strong intel bias" (notice the lowercase i in Intel while not in the rest of names?) means "people who want the best performing compiler out there". Marketing at its best, and AMD marketing on top of that. These posts are food for laughs even before they're written
Friends shouldn't let friends use Windows 7 until Microsoft fixes Windows Explorer (link)
lol
Where have you get the infos AMD was asking about GPGPU parts in sysmark ?
you speak about AMD or Nvidia there ? ............. I ask me yet to who it will benefit more ..
Last edited by Lanek; 06-21-2011 at 02:07 PM.
CPU: - I7 4930K (EK Supremacy )
GPU: - 2x AMD HD7970 flashed GHZ bios ( EK Acetal Nickel Waterblock H2o)
Motherboard: Asus x79 Deluxe
RAM: G-skill Ares C9 2133mhz 16GB
Main Storage: Samsung 840EVO 500GB / 2x Crucial RealSSD C300 Raid0
Actually, from Nigel Dessau blog (posted above).
And here is BARCo's response:
June 21, 2011 06:20 PM Eastern Daylight Time
BAPCo® Reaffirms Open Development Process For SYSmark® 2012
SAN MATEO, Calif.--(BUSINESS WIRE)--Business Applications Performance Corporation (BAPCo®) is a non-profit consortium made up of many of the leaders in the high tech field, including Dell, Hewlett-Packard, Hitachi, Intel, Lenovo, Microsoft, Samsung, Seagate, Sony, Toshiba and ARCintuition. For nearly 20 years BAPCo has provided real world application based benchmarks which are used by organizations worldwide. SYSmark® 2012 is the latest release of the premiere application based performance benchmark. Applications used in SYSmark 2012 were selected based on market research and include Microsoft Office, Adobe Creative Suite, Adobe Acrobat, WinZip, Autodesk AutoCAD and 3ds Max, and others.
Advanced Micro Devices (AMD) was, until recently, a long standing member of BAPCo. We welcomed AMD’s full participation in the two year development cycle of SYSmark 2012, AMD’s leadership role in creating the development process that BAPCo uses today and in providing expert resources for developing the workload contents. Each member in BAPCo gets one vote on any proposals made by member companies. AMD voted in support of over 80% of the SYSmark 2012 development milestones, and were supported by BAPCo in 100% of the SYSmark 2012 proposals they put forward to the consortium.
BAPCo also notes for the record that, contrary to the false assertion by AMD, BAPCo never threatened AMD with expulsion from the consortium, despite previous violations of its obligations to BAPCo under the consortium member agreement.
BAPCo is disappointed that a former member of the consortium has chosen once more to violate the confidentiality agreement they signed, in an attempt to dissuade customers from using SYSmark to assess the performance of their systems. BAPCo believes the performance measured in each of the six scenarios in SYSmark 2012, which is based on the research of its membership, fairly reflects the performance that users will see when fully utilizing the included applications.
About BAPCo®
The Business Applications Performance Corporation (BAPCo) is a non-profit consortium of leading independent testing labs, PC hardware manufacturers, semiconductor manufacturers and software publishers. Current BAPCo membership includes: Dell, Hewlett-Packard, Hitachi Global Storage Technologies, Intel, Lenovo, Microsoft, Samsung, Seagate, Sony, Toshiba and ARCintuition.
So if you read carefully, you have may be 3 odd hdd manufacturers, a software vendor and 3-4 system integrators, but only 1 chip manufacturer, no graphic card manufacturer. All you have is one guy, who apparently has tried bribing the named system integrators (except Lenovo i guess) to sell its chips only/ primarily.
You don't wonder why VIA got up and left as well? Nvidia? So unless you're trolling without much real information to add, please waste somebody else's time with company issued statements like these. Oh, yes, did you notice that heading BAPCO is the guy from Intel who's in charge of performance management?
EDIT: Also, did you note that it wasn't just AMD who left, but they singled out AMD in their statement. That shows intent on BAPCO's part as to where their loyalties lie.
Last edited by tifosi; 06-22-2011 at 05:49 AM.
Instead of fighting about it you guys why don't you guys help me figure out how to spoof the cpu's completely?
I need msr info's, I got the cpu-id msr info already.
I need a few more id stuff's to complete the spoof.
Or do I need to doit all by myself lol :P???
Don't have a 990X which you're spoofing mate. Infact, have nothing more than a C2D at this moment, which is hilarious and yet quite shameful. :P
Also, i heard certain portions in an AMD chip are hard locked and just can't be spoofed thus. Kindly read Agner Fog's blog, and if you're doing something similar, it may give you some insight.
I found this a min ago:
www.intel.com/Assets/PDF/appnote/241618.pdf
It should be enough to gather what info I need to change, then I'll have to look up the particular id stuff up to see how i can re-program it with some msr's.
This is sorta of important so I'll get it done eventually some time or another, I mean, it's a mod that I would be interested in if it indeed does affect performance in several apps.
Athlon vs P3 there wasn't a clear cut winner, Athlon XP vs Willamete was a bloodbath.
Northwood changed that picture a bit and with intruduction of HT intel left Athlon XP standing.
A64 was singlethread monster of the day, but in some cases P4 had its' way.
X2s were clear winners, but they showed one big thing for me - that AMD would price their CPUs as steep as they can, if they can get away with it. Even the cheapest X2 3800 was too pricey.
Just a piece of history from my standpoint.
And as for Intel cpu exclusive optimizing with Intel compiler - that's a completely true story. Intel defended with 'if its our CPU we know it can take the optimizations, if it isn't, then we do not know, and do not apply them'..
2x Dual E5 2670, 32 GB, Transcend SSD 256 GB, 2xSeagate Constellation ES 2TB, 1KW PSU
HP Envy 17" - i7 2630 QM, HD6850, 8 GB.
i7 3770, GF 650, 8 GB, Transcend SSD 256 GB, 6x3 TB. 850W PSU
Plenty of truth in this post, i concur with it.Athlon vs P3 there wasn't a clear cut winner, Athlon XP vs Willamete was a bloodbath.
Northwood changed that picture a bit and with intruduction of HT intel left Athlon XP standing.
A64 was singlethread monster of the day, but in some cases P4 had its' way.
X2s were clear winners, but they showed one big thing for me - that AMD would price their CPUs as steep as they can, if they can get away with it. Even the cheapest X2 3800 was too pricey.
Just a piece of history from my standpoint.
And as for Intel cpu exclusive optimizing with Intel compiler - that's a completely true story. Intel defended with 'if its our CPU we know it can take the optimizations, if it isn't, then we do not know, and do not apply them'..
Intel's own logo has a lower case i. You are ridiculous.Your point being? Mine is: laugh at the marketing folks, it's all you can do with them.
Just like that John Fruehe quoted post, where "pretty strong intel bias" (notice the lowercase i in Intel while not in the rest of names?
Considering how the biggest compilers have been stated to *not* be intel, I am having a hard time finding that you think people who want the best performing compiler ... use intel compilers and then run benchmarks on them.
This well documented effect has already been explained as a result of IMC. Keep laughing, it will only make you look sillier.Slower but smoother
Last edited by cegras; 06-23-2011 at 07:22 AM.
E7200 @ 3.4 ; 7870 GHz 2 GB
Intel's atom is a terrible chip.
Well X2 3800+ cost 350$ at the time of premiere, you had dual core opterons fairly cheaply too.Now , Intels cheapest six core was 700-900$ for quite some time.Now its still like 500$....
X2s were clear winners, but they showed one big thing for me - that AMD would price their CPUs as steep as they can, if they can get away with it. Even the cheapest X2 3800 was too pricey.
Since when do you or anybody with a bit of formation and not writing an SMS refer to a company with lowercase names?
Since when market share is related to perfomance only? I do not think, I just know, because I use them. Intel compilers being the fastest is a well known and documented fact, check the good ol' Agner Fog article AMDdroids always use as reference and Google if you don't believe it. I'm sure you can find a corner case, but Intel compilers on Intel CPUs almost always perform better than Microsoft for example. If this wasn't the case, you wouldn't see AMD & Co. complaining. In fact, Intel compiled binaries are faster on AMD too, once you tell the compiler to use all the optimizations it uses for Intel only
Yes, sorry, I just can't stop laughing. Specially when people use that serious tone
Friends shouldn't let friends use Windows 7 until Microsoft fixes Windows Explorer (link)
Athlon vs P3 there wasn't a clear cut winner, Athlon XP vs Willamete was a bloodbath.
Northwood changed that picture a bit and with intruduction of HT intel left Athlon XP standing.
A64 was singlethread monster of the day, but in some cases P4 had its' way.
X2s were clear winners, but they showed one big thing for me - that AMD would price their CPUs as steep as they can, if they can get away with it. Even the cheapest X2 3800 was too pricey.
Just a piece of history from my standpoint.
And as for Intel cpu exclusive optimizing with Intel compiler - that's a completely true story. Intel defended with 'if its our CPU we know it can take the optimizations, if it isn't, then we do not know, and do not apply them'..
Agree with most of your history except this part. At the time, IntEl's anti-competitive, illegal and market abusive tactics were in full affect (now they're just implimented in different ways). IntEl were selling their selling their hotter, slower and more power hungry chips for a significant amount more, and selling them well. The market balance would have stayed exactly the same whether AMD sold their top of the line for $300 and IntEl sold theirs for the same $1200. IntEl was controlling pricing, it wasn't open market competition.
As far as the 'smoothness' that many refer to, of course it is noticeable and quantifiable. People would notice it as 'lag' or 'latency' when opening applications, switching windows, switching tasks, etc.
If true, that is quite a conflict of interest, and OEM support of BAPCo (at $10k-$20k annually ??) kinda reeks of a pay-to-play scheme.AMD also points out that the president of BAPCo happens to be the head of performance benchmarking at Intel.
You cant. Change the CPUID in the CPU and your board will go nuts.Instead of fighting about it you guys why don't you guys help me figure out how to spoof the cpu's completely?
I need msr info's, I got the cpu-id msr info already.
I need a few more id stuff's to complete the spoof.
Or do I need to doit all by myself lol :P
Smile
This thread is going well and staying on topic...wait, no it's not.
Thread closed.
Posting Permissions
Bookmarks