I'm no fanboy of either company, in fact i have owned same number of intel cpus as amd, i have owned 2 northwoods, 1 celeron d and an old p4 1.7ghz, amd ones include k6 - 2, a64, X2. If u have seen my posts i have said more than on one occation that athlon Xp's as well as prescotts are crap.
What i'm saying is that its rediculous to get that performance increase in a gpu limited game as cpus are absolutely crap in graphics and games, also a lot of the things brought up question how valid those benchmarks, firstly the older mainboard with bios which does not actually support an fx60, as well as other things mentioned.
Another point about the drivers is which compiler was used to recompile them, if it was done by intel than its not a far shot to assume that it was optimised for intel cpus and crippled amd ones. As it already known that intel compilers do that.
I would not be supprised if conroe is faster than the athlon, and neither i would care if it is faster, all i want to know is how well it performs compared to x2 in an equal enviroment with out all the marketing crap and optimisations.
Remeber there are benchmarks done BY intel which show that the p-d is better that x2, which in fact is not true, whats stops intel from exadurating the results in this point also.
I buy cpus based on performance, NOT company or pretty slides showed by marketing, and its important for me to know how it performs without bias before i consider it as an upgrade.
Originally posted by: dug777
It's a bit worrying to see that you all think you know better than Anand, who was there & ran the benchmarks
I trust him, but time till tell if he's right in his conclusion & feelings on the matter...
He ran the benchmarks, but he did not set up the test platforms or software, so ur point is not really valid.
dug777
Lifer
- Oct 13, 2004
- 24,778
- 4
- 0
Originally posted by: Dark Cupcake
Originally posted by: dug777
It's a bit worrying to see that you all think you know better than Anand, who was there & ran the benchmarks
I trust him, but time till tell if he's right in his conclusion & feelings on the matter...
He ran the benchmarks, but he did not set up the test platforms or software, so ur point is not really valid.
He still provided his very positive opinion on conroe, and he will get a huge amount of negative flack if it all turns out to be intel cheating, so he has a lot to loose by posting that review. He did, he does not seem to think that there was anything particularly fishy about the setups, and he is in an infinitely better position to consider the matter than any of you
So no. my point is valid.
I think that i would still not trust benchmarks and setups done by the company which makes that particular product that they are benchmarking, cause u can expect that in NO WAY in the world they would ever show their product loosing in something. Actually i do think that conroe will be faster that the current tech (as expected), its that before proper benchmarks come out we will not know how well it performs without bias.
So where did u find that there were complains about intel beating amd?
Whats the problem questioning how valid benchmarks are, maybe i want to know how well it performs in a real life set up.
Maximilian
Lifer
- Feb 8, 2004
- 12,604
- 15
- 81
About time too, last three years have been boring as hell. "Get an athlon 64 its cooler" "Buy AMD! theyre better for games" "A venice will overclock better, pick up a 3200+" "presshots suck, you can fry eggs on them!" *stretch* *yawn*
What have we gotten in 3 years anyways? a jump from 2.0-2.6ghz whoopee. Dual core is the one thing that dosent apply here dual core has been interesting and a noticeable performance difference is there.
No no, Intel crushed AMD. Intel didn't even have leads this large with the P4C versus the Athlon XP, these are Athlon 64 versus Prescott kind of leads.
AMD may be able to bounce back a little, but I'd say (assuming these benchmarks are real and accurate) that AMD has lost the performance lead until AT LEAST sometime in 2007.
I hope AMD fixes the bandwidth issue with AM2. If Conroe really does perform this well (i.e. no special optimizations, etc...), we'za gonna see a hurtin'
Although they officially stated that AM2 is for DDR2-667, we all hear how it can easily support DDR2-800, but at this point, maybe AM2 needs DDR2-1000
I guess it all depends on how much of a difference the ram can make (fast speeds, but what about LL)
In any case, 1/2 a year is not too far off LET THE GAMES BEGIN!!
Although they officially stated that AM2 is for DDR2-667, we all hear how it can easily support DDR2-800, but at this point, maybe AM2 needs DDR2-1000
I guess it all depends on how much of a difference the ram can make (fast speeds, but what about LL)
In any case, 1/2 a year is not too far off
LET THE GAMES BEGIN!!yay io am glad amd finally got some competition.
hope it turns out like ati/nvidia then in 2 yearts we'll all be buying 10 GHz 16 core procs for $100 each.
hope it turns out like ati/nvidia then in 2 yearts we'll all be buying 10 GHz 16 core procs for $100 each.
- Aug 22, 2001
- 31,730
- 31,667
- 146
Conroe follow-up Anand borked the res on the AMD setup, they used the new bios, and, borked some testing, so they fixed them, ect. End result is what I predicted, still wins just not as brutally, 20% instead of 41% in F.E.A.R., much more realistic. Conroe had actully been running looser timings than stated too 5-5-5- instead of 4-4-4- didn't make any real difference though.
:thumbsup: for Anand. That's very good he chased it up - good for reputation.
Now as for the results a little more sensible and now that they're much more uniform much more believable. I'll take back my sentiments on the test being biased in any way.
I'll just say congratulations to the Intel teams who developed Conroe.
Clearly AM2 even if it offers a 10% boost (likely 5-10%) over S939 it will have a very tough time of it as even the low-medium end will still offer 10 likely 15% more clock for clock over AM2 while looking to be much more overclockable. At the high end it looks to be a slaughter. Now where's AMD's next generation?
Rock Hydra
Diamond Member
- Dec 13, 2004
- 6,466
- 1
- 0
AM2 remains awefully quiet. Has the MC bug been fixed or not? Eager to see some numbers out, although my expectation is not very high anyway.
The way most of the people are thinking is just the way Intel has planned. I am a AMD fan but I can realize competition is good for customers. I was shocked by Core performance but using a handicapped AMD system really annoyed me. First, reviewers have already proven RD580 or solutions with dual 16x can deliver up to 10-15% more performance when paired with high-end, bandwith hungry vga cards. Second, we have been hearing of dual core optimizations in display drivers for some time but were unable to see something significant until we saw Conroe performance; I am quite suspicious over some hefty optimizations in intel-cooked display driver. Time will reveal. Third, this might be the beginning of a new SSEx game with unfair optimizations for a new technoogy.
I am surprized how people are trashing the current as well as future AMD64 technology.But remember that Core is not out yet and all these might be some optimizations that has granted it this performance level. Moreover, the current AMD64 technology is almost 3 years old and the new AM2 will update its specs. AMD did not like DDR2 high latency; What they are looking for is its higher frequency that can be paired with the new AM2 FSB.For Athlon 64 and Sempron a 333mhz FSB that paires with DDR2 666 and for the Fx parts a 400 mhz FSB pairing with DDR2 800. If DDR1 could reach these frequencies you could now see the real potential of AMD64. This kind of bandwith will give Core a hard time. Also remember that AMD is increasing cache (L2 and maybe L3). Shared cache is also something that will be seen in the future products and will bring huge performance gains. Based on the preliminary data of 200/266 async single channel bandwith of 3500mb/s a memory bandwith of >10k is expected in the final product and if Intel was going to compare its future platform, it was not fare to compare it with an infrastructure of >2 years old. I am sure the new AM2 will regain AMD reputation once again. But we all must remember that this competition between major players is good for the end users.
I am surprized how people are trashing the current as well as future AMD64 technology.But remember that Core is not out yet and all these might be some optimizations that has granted it this performance level. Moreover, the current AMD64 technology is almost 3 years old and the new AM2 will update its specs. AMD did not like DDR2 high latency; What they are looking for is its higher frequency that can be paired with the new AM2 FSB.For Athlon 64 and Sempron a 333mhz FSB that paires with DDR2 666 and for the Fx parts a 400 mhz FSB pairing with DDR2 800. If DDR1 could reach these frequencies you could now see the real potential of AMD64. This kind of bandwith will give Core a hard time. Also remember that AMD is increasing cache (L2 and maybe L3). Shared cache is also something that will be seen in the future products and will bring huge performance gains. Based on the preliminary data of 200/266 async single channel bandwith of 3500mb/s a memory bandwith of >10k is expected in the final product and if Intel was going to compare its future platform, it was not fare to compare it with an infrastructure of >2 years old. I am sure the new AM2 will regain AMD reputation once again. But we all must remember that this competition between major players is good for the end users.
IntelUser2000
Elite Member
- Oct 14, 2003
- 8,686
- 3,787
- 136
Increasing HTT bus to 333MHz bus WON'T MATTER. Because AMD DOESN'T USE TRADITIONAL FRONT SIDE BUS OR PROCESSOR SIDE BUS. That's what the Integrated Memory Controller is for.
Traditional FSB: One/Two 64-bit memory is connected to Memory Controller. Whatever FSB speeds are is connected from Memory Controller to Processor. So FSB and memory bandwidth are almost directly related.
AMD Athlon 64's Integrated Memory Controller: One/Two 64-bit memory is connected to Memory Controller, which is INSIDE THE CPU, and don't need FSB.
Apart from that HTT is useful for servers and I/O communication(SATA, USB, and such).
Prove it. Chipset has NEVER seen to increase performance by 10-15%, at most its 5%.
Who cares?? AM2 is June 6th, and Core is July/August. Two months is gonna do a lot whoopee-do. AM2 doesn't have shared cache. AM2 doesn't have increased cache at least on the mainstream versions that Conroe will compete with. The 4MB L3 cache FX or whatever is gonna compete with much more capable Conroe than shown at the review. As shown with the first Extreme Edition, 4MB L3 isn't gonna help that much. Link: http://www.anandtech.com/showdoc.aspx?i=1965&p=4
All gaming benchmarks that demand GPU only benefited 4-5% with ADDITIONAL 2MB L3 on Pentium 4 EE, EVEN THOUGH IT DOESN'T HAVE A MEMORY CONTROLLER ON-DIE. AM2 with better memory and integrated controller is gonna benefit even less.
DDR2-800 point is moot. Even in Pentium 4's it has been shown that lower timing DDR2-667 is faster than DDR2-800. Also PRACTICALLY EVERYONE has been claiming its DDR2 memory that made Intel's LGA775 platform slower. And its gonna be different for AMD somehow??
Dear Intelligent user, Increasing HTT bus to 333MHz bus MATTERs when paired with appropriate memory. My budget sempron 2800 (1.6Ghz) is working @ 2.4(8x300) paired with a single 512MB module @ DDR600 (3,3,3,8,1T) which yields a mem bandwith of 4.6GB/s that is comparable with dual channel setups of you INTELligent users. So, do not resist to believe that AM2 and DDR2 will bring new performance era as Conroe and DDR2 will. Also please do not compare your extremely expensive edition parts with A64 architecture. A64 might use its valuable cache in a better way.
TRENDING THREADS
-
Discussion Zen 5 Speculation (EPYC Turin and Strix Point/Granite Ridge - Ryzen 9000)- Started by DisEnchantment
- Replies: 25K
-
Discussion Intel Meteor, Arrow, Lunar & Panther Lakes Discussion Threads
- Started by Tigerick
- Replies: 21K
-
Discussion Intel current and future Lakes & Rapids thread- Started by TheF34RChannel
- Replies: 23K
-
-
Facebook
Twitter