NotebookForums.com › Forums › General Notebook Discussions › Notebook Forums - General › AMD vs Intel in HL2: Winner = AMD
New Posts  All Forums:Forum Nav:

AMD vs Intel in HL2: Winner = AMD

post #1 of 17
Thread Starter 
Cool beans on Anandtech.

After our Doom 3 - CPU Battlegrounds article, we already knew what to expect from CPU performance under Half Life 2. At this point, Intel's Pentium 4 architecture does take a backseat to AMD's Athlon 64 when it comes to gaming. With performance advantages of around 15% at the same price point, the Athlon 64 does offer a noticeable increase in performance over the Pentium 4 in Half Life 2. The extensive physics engine in Half Life 2, especially as seen in Half Life 2 Deathmatch, is very CPU dependent and thus we see a real world performance advantage to the Athlon 64 over Intel's Pentium 4.

...
...

The impact of the CPU on gaming performance is in a transitional stage right now. As more games use Half Life 2 style physics we will see similar impacts with regards to CPU performance, but at this point there's a great deal of work being done on multithreading game engines for the next generation of games. So while the games coming in the immediate future may behave similarly to Doom 3 and Half Life 2, it's the games that follow that will truly be interesting.

http://www.anandtech.com/cpuchipsets...spx?i=2330&p=2
post #2 of 17
well i hope it won't start fight betwen Intel and AMD fan clubs, like it sometimes happen.
post #3 of 17
Quote:
Originally Posted by Rustican
first of all it's a notebook forum and who really cares about desktop performance. For a desktop I would probably get AMD because they are cheap, but for a laptop it will be always Intel.
post #4 of 17
Thread Starter 
Quote:
Originally Posted by klas
first of all it's a notebook forum and who really cares about desktop performance. For a desktop I would probably get AMD because they are cheap, but for a laptop it will be always Intel.

Because the same processors are used in both desktops and laptops. For example the P4EE which gets beaten by an AMD64 3000+ rating. For people who want a DTR it is more meaningful than those who want a mobile solution in the PM.
post #5 of 17
Just one of the reasons I'm waiting for AMD64 + PCI-e notebooks. This is such a sound beating of Intel it's not even funny.
post #6 of 17
15% is almost exactly the level of improvement gotten from the on-die memory controller of the AMD64 line. In fact, since almost zero consumer software is 64-bit these days, the memory controller is the source of almost all of the AMD64's prowess.
Don't get me wrong, its a much better chip than the P4 and has been even in the Athlon days, but the on-die memory controller is the reason for its performance at this time.

BUT....recent reviews and benchmarks show a 2Ghz Pentium M with an aging 855 chipset single channel DDR1 and AGP4x ATI x800 performing within 10% of a top of the line AMD 64 FX-55, 3.4Ghz P4EE, and 3.6Ghz P4 on most gaming benchmarks. Overclock the P-M to 2.5Ghz and it beats the best AMD and P4 chips on the market gaming.

That is a frightening display of just how much profit meaningless hype can create for AMD and Intel. Dual channel DDR, 64bit, Hypertransport, PCIe, on-chip memory controllers, onchip L3 caches, huge cooling systems, massive power consumption, and a piddly little modified Pentium III with aging, late-model memory and 1st generation AGP matches their performance.
post #7 of 17
what is katorga talking about..

on die memory controller is the key then maybe intel should put it in their chips..


no software is 64 bit...wait for it and see another 15% boost minimum


please show these recent reviews which show p-m beating the fx-55 . thank you
post #8 of 17
Quote:
Originally Posted by klas
first of all it's a notebook forum and who really cares about desktop performance. For a desktop I would probably get AMD because they are cheap, but for a laptop it will be always Intel.
Not when AMD64 Turion come out at 2nd half year of 2005
AMD.... I like ur price, and ur kick ass performance
post #9 of 17
Quote:
Originally Posted by katorga
15% is almost exactly the level of improvement gotten from the on-die memory controller of the AMD64 line. In fact, since almost zero consumer software is 64-bit these days, the memory controller is the source of almost all of the AMD64's prowess.
Don't get me wrong, its a much better chip than the P4 and has been even in the Athlon days, but the on-die memory controller is the reason for its performance at this time.

BUT....recent reviews and benchmarks show a 2Ghz Pentium M with an aging 855 chipset single channel DDR1 and AGP4x ATI x800 performing within 10% of a top of the line AMD 64 FX-55, 3.4Ghz P4EE, and 3.6Ghz P4 on most gaming benchmarks. Overclock the P-M to 2.5Ghz and it beats the best AMD and P4 chips on the market gaming.

That is a frightening display of just how much profit meaningless hype can create for AMD and Intel. Dual channel DDR, 64bit, Hypertransport, PCIe, on-chip memory controllers, onchip L3 caches, huge cooling systems, massive power consumption, and a piddly little modified Pentium III with aging, late-model memory and 1st generation AGP matches their performance.
Overclock to 2.5 ghz? Do you know how hot it will be for the cpu?
I think 10% overclock is safe (for max oc) but 2.5 ghz? thats like 25% oc.... hmm...don't sound so safe.
post #10 of 17
Quote:
Originally Posted by unholy
Overclock to 2.5 ghz? Do you know how hot it will be for the cpu?
I think 10% overclock is safe (for max oc) but 2.5 ghz? thats like 25% oc.... hmm...don't sound so safe.
I have an AMD 1700+ (1.4xx ghz) running at 2.4 ghz for two and a half years now . And an A64 3000+ (2.0 ghz) at 2.5 ghz for about half a year . Everything is fine. The whole "unsafe" overclock thing is a myth...
post #11 of 17
exactly, if you know what you are doing, using good cooling system 25% is possible on any platform
post #12 of 17
Quote:
Originally Posted by katorga
15% is almost exactly the level of improvement gotten from the on-die memory controller of the AMD64 line. In fact, since almost zero consumer software is 64-bit these days, the memory controller is the source of almost all of the AMD64's prowess.
Don't get me wrong, its a much better chip than the P4 and has been even in the Athlon days, but the on-die memory controller is the reason for its performance at this time.

BUT....recent reviews and benchmarks show a 2Ghz Pentium M with an aging 855 chipset single channel DDR1 and AGP4x ATI x800 performing within 10% of a top of the line AMD 64 FX-55, 3.4Ghz P4EE, and 3.6Ghz P4 on most gaming benchmarks. Overclock the P-M to 2.5Ghz and it beats the best AMD and P4 chips on the market gaming.

That is a frightening display of just how much profit meaningless hype can create for AMD and Intel. Dual channel DDR, 64bit, Hypertransport, PCIe, on-chip memory controllers, onchip L3 caches, huge cooling systems, massive power consumption, and a piddly little modified Pentium III with aging, late-model memory and 1st generation AGP matches their performance.
Of course the on-die memory controller is the source of AMD's prowess, the hugely decreased memory latencies (as well as other improvements, but I wont get into them) are what is driving the performance of these chips. And yes, even though I am pro-amd, the pentium m is a better processor for gaming than the athlon 64 , but not to the extent you describe. In gaming, the dothan architecture beats tha athlon clock for clock (helped partly by the huge l2 cache), but the dothan architecture is linear as opposed to athlon64/P4's parallel (I know I worded that wrong, so feel free to correct me, but don't flame me on it, those of you who know what I'm talking about will know), so whereas the dothan is better for gaming and other linear type calculations clock for clock (which clockspeeds arent as high as the athlon64, which can also be overclocked even higher you a$$) it is horrible in parallel tasks. If you look at the benchmarks at something like compiling a kernel it takes almost 4-5 times as long. In short, the pentium-m has it's strong points, but it's price/performance is horrible and it doesn't scale as well as athlon/P4 cpus do. (i.e. the performance isn't consistent, whereas it shines in a few benchies, it horribly fails in others, whereas the athlon/p4 might not beat everything, but at least it is consistently performing comparatively)
post #13 of 17
We already knew that:

Half-Life 2 CPU Shootout: AMD versus Intel



Choosing the Best CPU for Half-Life 2



Quote:
Since physical modeling sets most of the workload on the central processor during Half-Life 2 gameplay, AMD’s solutions appear the fastest as they have always been known for their high performance in scientific mathematical and physical tasks. These processors appear a way ahead Intel CPUs: Intel’s top processors lose even to the mainstream AMD solutions.
Half Life 2: CPU Scaling and Performance Revealed



Quote:
Our results show that at 1GHz to about 1.7GHz there is no separation performance at each resolution. At 1.8GHz we start to sees some separation, and by the time we get up to 2.2GHz things really start to separate for the 1280X1024 resolution that more gamers are likely to play at.

CPU scaling is clear throughout as the grade at which performance increases is pretty even up until we start to hit the wall at 2.7GHz. We see at that speed performance begins to level out which could mean that the video card has reached its limit in performance.

So we see that Half Life 2 will scale very linearly with the Athlon 64 when the video card is not the limiting factor.
post #14 of 17
"1GB Corsair 3-3-3-8 533MHz DDR2 Memory (2x512MB)
1GB Corsair 2-2-2-5 400MHz DDR Memory (2x512MB)"

The DDR-II Ram definetly had a negative impact on the Intel Processors
post #15 of 17
Thread Starter 
Quote:
Originally Posted by snorre
We already knew that:

I must have been living under a rock then. Thank's Snorre
post #16 of 17
Quote:
Originally Posted by lithiumcharles
Of course the on-die memory controller is the source of AMD's prowess, the hugely decreased memory latencies (as well as other improvements, but I wont get into them) are what is driving the performance of these chips. And yes, even though I am pro-amd, the pentium m is a better processor for gaming than the athlon 64 , but not to the extent you describe. In gaming, the dothan architecture beats tha athlon clock for clock (helped partly by the huge l2 cache), but the dothan architecture is linear as opposed to athlon64/P4's parallel (I know I worded that wrong, so feel free to correct me, but don't flame me on it, those of you who know what I'm talking about will know), so whereas the dothan is better for gaming and other linear type calculations clock for clock (which clockspeeds arent as high as the athlon64, which can also be overclocked even higher you a$$) it is horrible in parallel tasks. If you look at the benchmarks at something like compiling a kernel it takes almost 4-5 times as long. In short, the pentium-m has it's strong points, but it's price/performance is horrible and it doesn't scale as well as athlon/P4 cpus do. (i.e. the performance isn't consistent, whereas it shines in a few benchies, it horribly fails in others, whereas the athlon/p4 might not beat everything, but at least it is consistently performing comparatively)
which area it fails? please mention some usual one, cux i am considering btw Sonoma and A64.
post #17 of 17
Quote:
Originally Posted by unholy
which area it fails? please mention some usual one, cux i am considering btw Sonoma and A64.
I assume you ask what the p-M shortcomings are, so here is what i know:
Any data intensive application (rendering, compiling large projects, database aplications, multimedia, encoding, CAD, etc). It is a great a gaming CPU because of the cache and it is the champ in cache friendly stuff (super pi, office apps).
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Notebook Forums - General
NotebookForums.com › Forums › General Notebook Discussions › Notebook Forums - General › AMD vs Intel in HL2: Winner = AMD