According to Anandtech, Conroe beats FX-60
Moderators: NeilBlanchard, Ralf Hutter, sthayashi, Lawrence Lee
-
- Site Admin
- Posts: 12285
- Joined: Sun Aug 11, 2002 3:26 pm
- Location: Vancouver, BC, Canada
- Contact:
Yes, it was me, and it has nothing to do with political correctness or fanboyism. It has to do with wanting SPCR not to mislead anyone... not that this is really possible in a forum. "Conroe Destroys AMD" -- come on, talk about a flaming headline! It jumped at me on the front page everytime someone posted in the thread. The revised headline is simply more accurate.
-
- Posts: 220
- Joined: Wed Mar 15, 2006 10:16 am
- Location: U.S.A.
Anyway, this forum is a lot more civil regarding these types of discussions than say anandtech forums or xtremesystems forums. IMO, Anand published a very fair and very informative article yesterday regarding AM2 and the new F stepping. People should just chill and wait for both the AM2 and Conroe reviews and then make an educated decision.
Last edited by Goldmember on Wed Apr 12, 2006 7:47 am, edited 1 time in total.
I have to agree that the new topic is more accurate. And sure, the original topic was sensationalist, but personally, I didn't think it was so bad it had to be changed (imo there are topics with worse names on these forums). I don't even think it was misleading considering the results from the benchmarks. After all, results were amazing from a processor that wasn't even going to be released in the next few months and yet it had huge lead in media encoding benchmarks and even in gaming. To be perfectly accurate the topic should be. "According to Anandtech, early engineering sample of Conroe @2.66Ghz beats FX-60 @2.8Ghz", but that would have obviously been too long.MikeC wrote:Yes, it was me, and it has nothing to do with political correctness or fanboyism. It has to do with wanting SPCR not to mislead anyone... not that this is really possible in a forum. "Conroe Destroys AMD" -- come on, talk about a flaming headline! It jumped at me on the front page everytime someone posted in the thread. The revised headline is simply more accurate.
I really don't see why there have been so many posts like "In 6 months AMD too will release something new and faster." This of course is the banal truth. But even when AMD releases it's new processors, 2.66Ghz Conroe will still "destroy" the older FX-60s, nothing sensational in new processor beating an old one, but surely it's not misleading? I seriously doubt Intel or Anandtech cheated with the benchmarks and I seriously doubt that the manufacturing version of the Conroe will be any slower then those engineering samples.
-
- *Lifetime Patron*
- Posts: 618
- Joined: Mon May 23, 2005 7:05 am
- Location: State College, PA
-
- Moderator
- Posts: 7681
- Joined: Mon Dec 09, 2002 7:11 pm
- Location: Maynard, MA, Eaarth
- Contact:
Hello,
Ars Technica has a calm, even-handed take on the AM2/Conroe topic:
http://arstechnica.com/news.ars/post/20060411-6581.html
Ars Technica has a calm, even-handed take on the AM2/Conroe topic:
http://arstechnica.com/news.ars/post/20060411-6581.html
-
- Site Admin
- Posts: 12285
- Joined: Sun Aug 11, 2002 3:26 pm
- Location: Vancouver, BC, Canada
- Contact:
The Journal of Pervasive 64 bit Computing has a piece entitled Conroe Busted in which Conroe performance claims (made by Intel w/ Anand's help) are scrutinized and found wanting.
Now, for the very first time,someone actually got hold of a Conroe chip in their own lab and did some tests. It was a 2.4GHZ Conroe (Link: CPU-Z) against an Athlon 64 overclocked to 2.8GHZ. The overclocked Athlon 64 had a 2.8/2.4 -1 = 16.7% clockspeed advantage...
-
- Friend of SPCR
- Posts: 2887
- Joined: Mon Feb 28, 2005 4:21 pm
- Location: New York City zzzz
- Contact:
What a fantastic article and a great idea.
yes, of course any application that fits in 4 mb of space would go insanely fast.
lol. what fabrication.
If intel truly had a fast chip, think of it.... they would RELEASE THEM FOR TESTING.
they exist, obviously, even if only 10 were sent out to a few places, that would be way enough to get their stock flying high. And bios/mobo/chipset arguments really wouldnt matter as any manufacturer out there already would have a working mobo within 1-3% speed of the retail version.
hah. this would rule. and also would propel computing a bit more having intel being forced to yet again make a better chip as amd then would shoot up in sales again.
I really think the low voltage am2 chips are going to be the key things that make people drop intel. consider the overclockability of ddr2 and 1/2 the wattage chips?
yes, of course any application that fits in 4 mb of space would go insanely fast.
lol. what fabrication.
If intel truly had a fast chip, think of it.... they would RELEASE THEM FOR TESTING.
they exist, obviously, even if only 10 were sent out to a few places, that would be way enough to get their stock flying high. And bios/mobo/chipset arguments really wouldnt matter as any manufacturer out there already would have a working mobo within 1-3% speed of the retail version.
hah. this would rule. and also would propel computing a bit more having intel being forced to yet again make a better chip as amd then would shoot up in sales again.
I really think the low voltage am2 chips are going to be the key things that make people drop intel. consider the overclockability of ddr2 and 1/2 the wattage chips?
-
- Posts: 84
- Joined: Thu Dec 01, 2005 7:39 pm
Just because somebody has a blog, doesn't make them an expert.MikeC wrote:The Journal of Pervasive 64 bit Computing has a piece entitled Conroe Busted in which Conroe performance claims (made by Intel w/ Anand's help) are scrutinized and found wanting.Now, for the very first time,someone actually got hold of a Conroe chip in their own lab and did some tests. It was a 2.4GHZ Conroe (Link: CPU-Z) against an Athlon 64 overclocked to 2.8GHZ. The overclocked Athlon 64 had a 2.8/2.4 -1 = 16.7% clockspeed advantage...
-
- Posts: 84
- Joined: Thu Dec 01, 2005 7:39 pm
Check xtremesystems.org, they have a few samples there that are basically affirming Conroe's superiority.~El~Jefe~ wrote: they exist, obviously, even if only 10 were sent out to a few places, that would be way enough to get their stock flying high. And bios/mobo/chipset arguments really wouldnt matter as any manufacturer out there already would have a working mobo within 1-3% speed of the retail version.
Why? Intel already leads here, with Yonah beating the power consumption of low voltage Turions.I really think the low voltage am2 chips are going to be the key things that make people drop intel. consider the overclockability of ddr2 and 1/2 the wattage chips?
-
- Posts: 84
- Joined: Thu Dec 01, 2005 7:39 pm
http://www.silentpcreview.com/article313-page5.htmljaganath wrote:?with Yonah beating the power consumption of low voltage Turions.
LV Turions (MT-3X) have a TDP of 25W. Yonah (Core Duo/Solo) have TDP > 30W. Given that AMD's TDP is more reflective of actual max power dissipation than Intel, the gap is probably at least 10W.
1) You said low voltage Turions; I took this to mean the MT-XX processors, not the ML-XX tested in the Desktop Power Survey.
2) Yonah only beat the ML-XX in idle, and then only by less than 1W.
Now, given that the MT-XX Turions consume less power than ML-XX at all clock speeds, it is a relatively obvious conclusion that normal (non-LV) Yonah does not beat the power consumption of low voltage Turions.
2) Yonah only beat the ML-XX in idle, and then only by less than 1W.
Now, given that the MT-XX Turions consume less power than ML-XX at all clock speeds, it is a relatively obvious conclusion that normal (non-LV) Yonah does not beat the power consumption of low voltage Turions.
-
- Posts: 84
- Joined: Thu Dec 01, 2005 7:39 pm
The ML is volted at MT levels. MLs at normal voltage (1.35v) would be 35W.jaganath wrote:1) You said low voltage Turions; I took this to mean the MT-XX processors, not the ML-XX tested in the Desktop Power Survey.
http://www.silentpcreview.com/article300-page6.html
It beats it in load and idle.2) Yonah only beat the ML-XX in idle, and then only by less than 1W.
-
- Moderator
- Posts: 7681
- Joined: Mon Dec 09, 2002 7:11 pm
- Location: Maynard, MA, Eaarth
- Contact:
...back on topic:
Johan De Gelas has written an excellent piece comparing the architecture of the Intel "Core" CPU's to the AMD K8 (& K7) CPU's:
http://www.anandtech.com/cpuchipsets/sh ... spx?i=2748
It explains a lot -- there are some real improvements in the Conroe.
Johan De Gelas has written an excellent piece comparing the architecture of the Intel "Core" CPU's to the AMD K8 (& K7) CPU's:
http://www.anandtech.com/cpuchipsets/sh ... spx?i=2748
It explains a lot -- there are some real improvements in the Conroe.
you believe that blog? it's fanboy blog.MikeC wrote:The Journal of Pervasive 64 bit Computing has a piece entitled Conroe Busted in which Conroe performance claims (made by Intel w/ Anand's help) are scrutinized and found wanting.
the result is from victor wang sciencemark test, with two result being removed in order to show amd is much superior. http://www.xtremesystems.org/forums/sho ... hp?t=95021
in fact this is the comment from sciencemark author, redpriest
http://www.xtremesystems.org/forums/sho ... tcount=901
Conroe's score is amazing.
Keep in mind that he tested both the Pentium-M optimized binary and the Pentium 4 binary. Out of both binaries, the Pentium 4 was faster. This is compiled with Intel's latest *publicly* available compiler.
Conroe is more similar to the Pentium-M than to the Pentium 4, but the binary doesn't utilize Conroe's wider resources. In *scalar* code, x87 code is generated by the Pentium 4 optimized binary because the Pentium 4 can't execute pipelined scalar sse adds, but can in x87 mode. (I had thought this was not the case but Intel's optimization guide says this is the case, I'm not sure if I 100% believe that, but given that x87 code was generated with the most aggressive flags possible -- sse/sse2 code was used sparingly in with some of the x87 code).
I imagine that if you ran the 64-bit binary Conroe's lead would widen even more.
What I am perplexed about is why Conroe bombs on the encryption code -- the entire instruction mix consists of BSWAP, XOR, and various MOV instructions, none of which are micro-coded on other processors, and no jump instructions. With Conroe's wide integer resources, I don't see why this is the case. I'm guessing there is an address generation limitation, but since I don't have a Conroe I can't really test that theory. It's a blind guess.
In any case, I see this as a *strong* showing for Conroe, not a weak one as the blogger claims. In the benchmarks that matter (BLAS, MolDyn, Primordia) Conroe is at least equal to if not exceeding an Athlon at the same clock speed. The fact that in 32-bit mode, an Athlon64 clocked 400 mhz higher cannot exceed Conroe's performance gap is telling.
I can't wait for a 64-bit run....
-
- Moderator
- Posts: 7681
- Joined: Mon Dec 09, 2002 7:11 pm
- Location: Maynard, MA, Eaarth
- Contact:
some interesting speculation?
Hello,
Does AM2 have a "secret weapon"?
http://theinquirer.net/?article=32589
This may be speculation and/or a rumor, but it at least reminds us not to count our chickens before they hatch!
Does AM2 have a "secret weapon"?
http://theinquirer.net/?article=32589
This may be speculation and/or a rumor, but it at least reminds us not to count our chickens before they hatch!