HP lets some Athlon64 specs out of the bag

Spitfire_x86

Splendid
Jun 26, 2002
7,220
0
25,780
<A HREF="http://news.com.com/2100-1006_3-1018579.html?tag=lh" target="_new">http://news.com.com/2100-1006_3-1018579.html?tag=lh</A>

Athlon XP 3100+ @ 1.8 GHz, 1 MB L2 cache.

If this one performs worse than AXP 3200+ (which performs like P4 2.8 GHz), then how AXP 3100+ is going to perform?

----------------
<b><A HREF="http://geocities.com/spitfire_x86" target="_new"> My Website</A></b>

<b><A HREF="http://geocities.com/spitfire_x86/myrig.html" target="_new"> My Rig</A></b>
 
Somebody correct me if I'm wrong, but isn't the A64 based off the current K7 core. In a sense, AMD took the K7 core, added 2 (???) extra pipes, made it 64 bit and added some cache. We are currently seeing the current core reach the end of it's run, so, if I'm right in my above statement (I have been wrong before) the A64 might run into some trouble in scaling later down the road. Indeed, as cool as 64bit computing is, will a, say, ~2.5/2.6 be able to compete with a 4ghz pentium?
I suppose this is more of a question than anything. Perhaps someone can clear it up.
 
I understand that the 64 will be coming out in SOI format, which should give a bit of a breather, but they will be switching to 90 nano chips next year.
As to wether an 1800mhz could compete, it depends on SSE2. The opteron fell down there, but if the athlon can get intel like numbers from it, along with its other features it could be very competative with the 800 fsb intels.
 
>>>but they will be switching to 90 nano chips next year

Unfortunately for them, their primary competitor will be switching to 90nm <b>this</b> year. 😉
 
IMO, this is the right section to post this news :smile:

The only good thing in this news is that A64 is definately going to be released at September 2003

----------------
<b><A HREF="http://geocities.com/spitfire_x86" target="_new"> My Website</A></b>

<b><A HREF="http://geocities.com/spitfire_x86/myrig.html" target="_new"> My Rig</A></b>
 
I'm almost certain that Athlon64 1.8 GHz will beat 3.0 GHz P4 in all gamaing benchmarks. But success in encoding/rendering apps. are very questionable with such low clockspeed.

----------------
<b><A HREF="http://geocities.com/spitfire_x86" target="_new"> My Website</A></b>

<b><A HREF="http://geocities.com/spitfire_x86/myrig.html" target="_new"> My Rig</A></b>
 
im fairly sure that 1.8ghz wont be the top speed grade at launch. why would amd launch an xp3100 when intel will be ready with a 3.4ghz? i think they will launch a 3300 at 1.9-2.0ghz and maybe a 3400 at 2.1-2.2ghz a month or so later..
just guessing tho
 
I hear a lot of guessing going on. It is so sad that a really good idea like a 32/64-bit proc is being handled so badly by such a stupid company. To clarify: Engineering, very bright. Every one else, dumb as rocks. I will never say AMD makes bad procs. I will say, the way they do business, horrible.

Zpyrd makes a good point; the only reason I hope AMD gets is act together is that I’ll only buy Intel, but I’d hate to see what would happen, price wise, if they ever become the only show in town and found out about it.

Just a question for the fan boys; What is the point if no one starts writing 64-bit apps? For instance, an OS? Yes yes……”It will do 32-bit just fine!!!” you say…..at 1.8GHZ? “It has a meg of cache” So when we see Prescott with it’s own meg, running at 3.4GHz or better, where are you going to take the argument?

As a end user, I hope this dose drive the industry toward a 64-bit PC standard. I think 64-bit power is going to make gamming just amazing. But you’ll have to get the major software writers to go 64-bit as well. Just hope that AMD dosen’t flub this up so bad that stops the 64-bit trend. And yes I do think that is possible

*Side note* I hear it said that some one rewrote UT2K03 to 64-bit in under a week (that seems a bit fast to me). However what would you run it on? Win 2003 server? Dose that even support Direct X 9?
 
there may be a lot of guessing going on but for the most part they are educated guesses. its very unlikely that the xp3100 1.8ghz part will be the highest grade at launch. it just doesnt make sense. why release a processor which by their own pr is slower than their current flagship. definitely doesnt make sense to release one that is a lot slower than their competitors by a long way. (intel will be at 3.4ghz by launch). and i have it from an amd techie that release speeds will be over 2ghz (probably2.1ghz) which kinda backs up my guesses and makes sense from a performance standpoint.
 
definitely doesnt make sense to release one that is a lot slower than their competitors by a long way. (intel will be at 3.4ghz by launch).
Indeed. If the 3100+ is outperformed by the 3200+ as suggested by its rating, then how can it possibly compete with a 3.4Ghz P4 <i>Northwood</i>, let alone a <i>Prescott</i>?
 
I don't think that it is meant to. I would imagine that AMD is going to play the '64-bit' card for all that it's worth and try to convince everyone that performance doesn't matter.

That and/or the rating of 3100+ could be the rating when running non-optimized code. (In other words, today's standard 32-bit code.) So AMD might push benchmarks based on optimized code to claim that it's faster than rated.

Then again, the 3100+ might be based on optimized code and it'll totally suck compared to an AXP running 32-bit code. (Not to mention a P4.) We will just have to wait and see.

"<i>Yeah, if you treat them like equals, it'll only encourage them to think they <b>ARE</b> your equals.</i>" - Thief from <A HREF="http://www.nuklearpower.com/daily.php?date=030603" target="_new">8-Bit Theater</A>
 
I believe it might be its own rating. Think of how the 2800+ Tbred is better than the 2800+ Barton. Now think of perhaps a reverse situation where the Athlon 64 is worth more per PR than the Barton.
But I still fail to see a 1.8GHZ acting at 3100+. I just don't believe it.

--
If I could see the Matrix, I'd tell you I am only seeing 0s inside your head! :tongue:
 
Well to throw some light on the subject (or perhaps just layer on another blanket of confusion) a letter sent to the inquirer from HP says that the sheet we've all been looking at was for when they thought amd64 was getting the earlier release date and that the system in question was actually released with the 2500. Akiba also has some new? info but my japanese is limited to like 20 words so I had to settle for the summary at aceshardware. I must admit that i'm a little iffy on a 2.4Ghz processor getting a rating of 4000 but we'll just have to wait and see.
 
so whats next...AMD Athlon64 4000+ @ 1.0GHz.

following right from the jump from the T-breds to the Barton and now to the 64, in terms of clock speed, i wudnt be surprised to see that.

<b><font color=red>The statement below is true.</font color=red></b>
<b><font color=blue> The statement above is false.</font color=blue></b>