AMD is sandbagging

Page 2 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Keysplayr

Elite Member
Jan 16, 2003
21,209
50
91
Originally posted by: Zstream
Originally posted by: UncivilizedAMD
Originally posted by: Zstream
Originally posted by: ShadowOfMyself
Originally posted by: Conky
Originally posted by: SickBeast
You guys need to read the blurb over at HardOCP. Kyle had a hands on with Barcelona and seemed thrilled with it.
Kyle was probably drunk again.

Lol, Kyle, the guy that said C2D wasnt any better than any Athlon X2 when he reviewed it

Well it really isnt, I mean maybe 5-6% performance difference, the reason why the C2D is doing so well is because it o/c's like crazy.

If C2D did not o/c so well I would still be on my 3800+x2. I believe many others would be also.

It's commonly accepted that C2D holds a ~20% advantage, clock for clock against X2 whether stock or overclocked. 5-6% is ludicrous.

Please show me one benchmark that proves this..... You can use price/price ratio if you like.

You're actually serious, aren't you?
 

dmens

Platinum Member
Mar 18, 2005
2,274
959
136
Originally posted by: Amaroque
AMD has a stronger FP unit. That is important to us AT DCers

The A64 line in general is ~17% faster than the C2D line in DPAD, but it is a bit slower in folding (clock for clock).

how'd you figure a64 is faster on fp? and what is DPAD? the only well-known benchmark workload i am aware of where the A64 is faster on the same price point is some crypto processing benchmark, and it isn't anywhere close to 17% faster.
 

Amaroque

Platinum Member
Jan 2, 2005
2,178
0
0
Originally posted by: dmens
Originally posted by: Amaroque
AMD has a stronger FP unit. That is important to us AT DCers

The A64 line in general is ~17% faster than the C2D line in DPAD, but it is a bit slower in folding (clock for clock).

how'd you figure a64 is faster on fp? and what is DPAD? the only well-known benchmark workload i am aware of where the A64 is faster on the same price point is some crypto processing benchmark, and it isn't anywhere close to 17% faster.

If you ever looked at our DC fourm, you'd have your answers...

 

Amaroque

Platinum Member
Jan 2, 2005
2,178
0
0
There is no fighting in the DC forum, and I recommended a fellow cruncher to buy a C2D because that is the best CPU for folding (he actually bought a C2 quad).
 

dmens

Platinum Member
Mar 18, 2005
2,274
959
136
Originally posted by: Amaroque
If you ever looked at our DC fourm, you'd have your answers...

i looked and the only answer i found was to "what is dpad". where's the comparison between c2d and a64
 

dmens

Platinum Member
Mar 18, 2005
2,274
959
136
Originally posted by: Amaroque
look harder, you're an intelligent man.

I post links for Newbies.

or you can just post the link and back up your claim of 17% faster, or is it 20% like you said in some other thread.
 

Zstream

Diamond Member
Oct 24, 2005
3,395
277
136
Originally posted by: keysplayr2003
Originally posted by: Zstream
Originally posted by: UncivilizedAMD
Originally posted by: Zstream
Originally posted by: ShadowOfMyself
Originally posted by: Conky
Originally posted by: SickBeast
You guys need to read the blurb over at HardOCP. Kyle had a hands on with Barcelona and seemed thrilled with it.
Kyle was probably drunk again.

Lol, Kyle, the guy that said C2D wasnt any better than any Athlon X2 when he reviewed it

Well it really isnt, I mean maybe 5-6% performance difference, the reason why the C2D is doing so well is because it o/c's like crazy.

If C2D did not o/c so well I would still be on my 3800+x2. I believe many others would be also.

It's commonly accepted that C2D holds a ~20% advantage, clock for clock against X2 whether stock or overclocked. 5-6% is ludicrous.

Please show me one benchmark that proves this..... You can use price/price ratio if you like.

You're actually serious, aren't you?


First off the links provided are not price/price ratio. I do not give a crap if you compare mhz/mhz.


 
Feb 20, 2005
181
0
0
Originally posted by: Zstream
Originally posted by: keysplayr2003
Originally posted by: Zstream
Originally posted by: UncivilizedAMD
Originally posted by: Zstream
Originally posted by: ShadowOfMyself
Originally posted by: Conky
Originally posted by: SickBeast
You guys need to read the blurb over at HardOCP. Kyle had a hands on with Barcelona and seemed thrilled with it.
Kyle was probably drunk again.

Lol, Kyle, the guy that said C2D wasnt any better than any Athlon X2 when he reviewed it

Well it really isnt, I mean maybe 5-6% performance difference, the reason why the C2D is doing so well is because it o/c's like crazy.

If C2D did not o/c so well I would still be on my 3800+x2. I believe many others would be also.

It's commonly accepted that C2D holds a ~20% advantage, clock for clock against X2 whether stock or overclocked. 5-6% is ludicrous.

Please show me one benchmark that proves this..... You can use price/price ratio if you like.

You're actually serious, aren't you?


First off the links provided are not price/price ratio. I do not give a crap if you compare mhz/mhz.


You didn't say anything about price/performance in your original post. You originally claimed a 5-6% difference between c2d and x2. If it's price/performance you are looking for than AMD is competetive clock for clock at stock.
 

apoppin

Lifer
Mar 9, 2000
34,890
1
0
alienbabeltech.com
i doesn't appear intel is sandbagging ... courtesy theInq:

Intel responds to Barcelona numbers
Last week, at the Microprocessor Forum, Intel did just that in a response to AMD's Barcelona numbers.

If you recall, AMD scored just over 4000 on a POV benchmark with a 16 core 4S system (here and here).

These were 68W low power low clocked HE parts, down about a Ghz on the SE ones coming out in a few months. Expect a lot more from the release bits on a competitive platform.

If 4000+ sounds good, last week Intel trotted out a production Blackford/Clovertown system in V8 livery (We are not supposed to know Intel is seeding V8 test systems and plans production, so don't tell anyone) as a spoiler. Is was running at 3Ghz with a 1333FSB. These almost production parts are the bar AMD has to hurdle.

That said, the numbers speak for themselves, 4933, almost 5000, with only 8 cores. POV might be the worst case scenario for Barcelona, and there are a lot of mitigating factors at play, but AMD still has a lot of work to do. It got thumped on this one, even if you consider apples to oranges comparisons invalid.
 

Amaroque

Platinum Member
Jan 2, 2005
2,178
0
0
Please don't post inq links, commentaries. The inq is Internet tabloid...

You know that yourself.
 

Pwntcomputer

Senior member
Oct 6, 2005
273
0
0
Yeah and what does Intel know about processors anyway? That picture? Probably fake or made by aliens. I mean look at the case "CoolerMaster" Never heard of 'em. PovRay? Might as well test it using the Johnson Rod Curve Bell Score Technique.

 

Lord Banshee

Golden Member
Sep 8, 2004
1,495
0
0
Originally posted by: UncivilizedAMD

You didn't say anything about price/performance in your original post. You originally claimed a 5-6% difference between c2d and x2. If it's price/performance you are looking for than AMD is competitive clock for clock at stock.

Isn't that what he said? At stock they are competitive but not for clock for clock, price per price. Core2Duo has a better IPC such a case it is better clock for clock but not price.

Here is another link that proves it:
http://www.xbitlabs.com/articles/cpu/display/core2duo-e6420_6.html#sect1

Price/Price: X2 5000+ ~ E6300/E6320

That said if i had to buy a new system today it would be Intel due to 50+% overclock. But i do not plan on building a new system anytime sooner than next summer so we will see how has the best quad core setup next year as my system isn't too slow for me

 

golem

Senior member
Oct 6, 2000
838
3
76
Originally posted by: Lord Banshee
Originally posted by: UncivilizedAMD

You didn't say anything about price/performance in your original post. You originally claimed a 5-6% difference between c2d and x2. If it's price/performance you are looking for than AMD is competitive clock for clock at stock.

Isn't that what he said? At stock they are competitive but not for clock for clock, price per price. Core2Duo has a better IPC such a case it is better clock for clock but not price.

Here is another link that proves it:
http://www.xbitlabs.com/articles/cpu/display/core2duo-e6420_6.html#sect1

Price/Price: X2 5000+ ~ E6300/E6320

That said if i had to buy a new system today it would be Intel due to 50+% overclock. But i do not plan on building a new system anytime sooner than next summer so we will see how has the best quad core setup next year as my system isn't too slow for me

I don't he really specified. Anyway it's more natural to assume a performace/mhz ratio, it's pretty much a fixed ratio unless the chip itself is revised. Price/performance changes according to location, time, sales etc. It can swing wildly from day to day and generally, isn't really as relevant a number.

 

Lord Banshee

Golden Member
Sep 8, 2004
1,495
0
0
Golem,

True that price/performance does change every day but most of the time it changes on both sides of the part equally (or it should). Personally i think it is a very relevant number, at least to my bank account.

But when you factor in OC then you get a much better price/performance on the Intel side as i would if i was really buying a part today.
 

golem

Senior member
Oct 6, 2000
838
3
76
Originally posted by: Lord Banshee
Golem,

True that price/performance does change every day but most of the time it changes on both sides of the part equally (or it should). Personally i think it is a very relevant number, at least to my bank account.

But when you factor in OC then you get a much better price/performance on the Intel side as i would if i was really buying a part today.

Hmm.. maybe I phrased things wrong. The price/performance number is relevant on a personal level. It helps a person decide on which chip to buy and where. But it's not directly comparable between people unless they are shopping in the same place at the same time (same is not the right word, but I hope you get my meaning). It's not a number that you can post on a forum and automatically expect it to be useful to someone else. If the other person is on the other side of the world or reading the post after a one sided price drop, the number MAY still be good or may be useless.

Why would someone ask for a price/performance ratio on a forum? The numbers could be all over the place, that's why I said it's more natural to assume he was talking about performance/mhz. That number should be much more fixed and is comparable over time and location, unless you try and skew the number by choosing apps that favor one processor over another.
 

apoppin

Lifer
Mar 9, 2000
34,890
1
0
alienbabeltech.com
Originally posted by: Amaroque
Please don't post inq links, commentaries. The inq is Internet tabloid...

You know that yourself.

i'd like to post your opinion ... but you already did
--theInq has a BENCHMARK for all to see ... even if the AMD fans dare not look at it.
 

SickBeast

Lifer
Jul 21, 2000
14,377
19
81
Originally posted by: apoppin
Originally posted by: Amaroque
Please don't post inq links, commentaries. The inq is Internet tabloid...

You know that yourself.

i'd like to post your opinion ... but you already did
--theInq has a BENCHMARK for all to see ... even if the AMD fans dare not look at it.
Do you really think Barcelona scales linearly with the current A64s? Are you seriously going to have us believe that AMD engineered Barcelona to be the same speed per clock as current A64s? That benchmark made *no* sense and was *complete* nonsense.
 

Amaroque

Platinum Member
Jan 2, 2005
2,178
0
0
Tabloid crap is all it is really. I'm neither pro AMD, nor pro Intel... I'm pro competition. BTW, I own X2 and C2D systems...
 

BigDH01

Golden Member
Jul 8, 2005
1,630
82
91
Originally posted by: SickBeast
Originally posted by: apoppin
Originally posted by: Amaroque
Please don't post inq links, commentaries. The inq is Internet tabloid...

You know that yourself.

i'd like to post your opinion ... but you already did
--theInq has a BENCHMARK for all to see ... even if the AMD fans dare not look at it.
Do you really think Barcelona scales linearly with the current A64s? Are you seriously going to have us believe that AMD engineered Barcelona to be the same speed per clock as current A64s? That benchmark made *no* sense and was *complete* nonsense.

The benchmark wasn't crap it's just that Barcelona doesn't really improve on the IPC of the Opteron in the workload placed on it by said benchmark. The improvement of the 16 core system over the 8 core system is about what is expected in two systems that have cores that have identical IPC performance when considering Amdahl's Law. It just happens to be that AMD didn't pick a benchmark to showcase their improvements to the core. I'll leave it to you to decide why they did this.

Furthermore, we can't be absolutely positive that the IPC performance of the Barcelona will be better than the Core 2. Many of the improvements to the Barcelona make the Athlon architecture more "core-like." We expect that it will pull ahead because of the IMC and L3 cache. However, we know that Intel has been able to extract a great deal of performance out of awesome prefetchers and a fast northbridge memory controller. I would venture to guess that this is a wash in most desktop applications. I would venture to guess that the Barcelona has a 5-10% IPC advantage on average in most situations with some being more and some being like the current released benchmarks which show no real IPC improvement at all. This is speculation on my part but I believe we will see that this is accurate. I wouldn't expect a "core killer."
 

Amaroque

Platinum Member
Jan 2, 2005
2,178
0
0
I've never said it was a C2D killer. IMO IPC will be on par with each other. But C2D should OC much better, making it a better choice for us ATers and the like.

For the average "jo" though, I doubt the CPU will matter much, if at all.
 

Gikaseixas

Platinum Member
Jul 1, 2004
2,836
218
106
Guys i wouldn't read too much into theinq. article. It is shady imo. When i actually read the same on Anand or Tom's i'll believe it. After researching around i found very little info but i hope they can release some numbers at Computex next week...
 

allies

Platinum Member
Jun 18, 2002
2,572
0
71
I hope that AMD is sandbagging. I hope that they're really not having problems with frequencies. I hope that Barcelona will be a success. If they don't start turning things around, only intel will be left in the game. Not really something I want to see.
 

Conky

Lifer
May 9, 2001
10,709
0
0
My biggest gripe is that if AMD intended to roll over and play dead then why did they bother with ATI?

This is just like when 3DFX decided to buy STB and died shortly afterwards.

I really, really, hope this isn't the case with AMD. Without any real competition Intel will rape us almost as bad as AMD did when they were on top.
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |