what does anandtech mean by this?

[CasioTech]

And the Pentium 4 does have a very exciting future ahead of it in these final months of 2001.

???

 

[VBboy]

I think many software manufacturers are beginning to take advantage of the P4's architecture, which means software will work faster. Game programmers will probably be taking advantage of it too.

 

[thorin]

Well the clock freq will be increased towards the end of the year. New chipsets will be coming out with support for DDR (and drop support for RDRAM). Also we will see the new packaging and form factor of the P4 shortly.

Thorin

 

[CasioTech]

uh huh, so then does that mean that games coming out to be optimized for the p4 actually mean that say, a 1.3ghz will then be able to be placed far ahead of the 1.2, 1.4ghz athlon?

 

[Adul]

Not likely, but it could mean a 1.5 would be faster then a 1.3 athlon.

 

[CasioTech]

I don't know about unlikely, I remember what people said about k6-2 with the 3dnow! and how much it wouldn't help, but it increased performance in games like quake 2 by 50%!

 

[mchammer187]

I think many software manufacturers are beginning to take advantage of the P4's architecture, which means software will work faster. Game programmers will probably be taking advantage of it too

i read something about that on aces hardware the optimized code on intel compilers helps the athlon out

i will find the link in a sec

 

[Adul]

but it was still below that of a p2 of the same speed at that time. I guess we will just have to wiat and see.

 

[CasioTech]

true, but p2 was like 3 times faster to begin with in some instances, this is not the case of the athlon 1.4ghz vs 1.3ghz p4. It is ahead by less than 20%, so I don't think it will be too hard to have p4's all come out on top after some new games are out, like unreal 2.

 

[mchammer187]

here is the link i promised it is a good read about the future of PIV optimizaions and the Athlon

 

[Sohcan]

Anand was likely referring to Northwood, the .13um P4...it is rumored to have 512KB of L2 cache, and as production ramps up, it will become more mainstream than Willamette has been.

As far as performance improvements from P4-aware compilers, don't expect miracles...a 10%, maybe up to 20%, improvement for general applications is likely, mostly from the re-ordering of code for the P4's pipeline. SIMD instructions (SSE2) can yield large performance increases when inside loops are hand-compiled, but no one has the time money to do so for commercial applications. SIMD-supported compilers aren't very good at extraction vector parallelism out of code, so most real-world apps gain 5-10% at best. The case of the K6-2 was a bit different...it's FP-unit wasn't pipelined, so it performed horribly in code that was optimized for the P3's pipelined FPU. The benchmarks that showed a huge boost from 3DNow were mostly hand-assembled, so they weren't a very fair indication of SIMD's usefullness for the K6-2.

But if you're really concerned about gaming performance, remember that the bottleneck is the video card, not the CPU. Benchmarks may show a big difference between the fastest available CPU and one that is 1+ years old, but those benchmarks are taken at 640x480x16bit color. Bump the resolution and color up past 1024x768x32bit color, and the video card fillrate and memory bandwidth becomes the bottleneck, and a 1GHz P3 might only be 10-15% slower than a 1.8GHz P4.