Three years ago Intel was on top of the world. They did, after all, have plenty reason to be. Their Pentium 4 processor was in every way superior to its competition in AMD’s Athlon XP series, their hold on the market share lead was more firm than ever, and they had some newfangled thing called “Prescott” on the horizon. Things were certainly looking good.

Then September of 2003 rolled around and things got a bit more interesting. AMD was launching a pair of brand new processors, the Athlon 64 3200+ (ClawHammer) and the Athlon FX-51 (SledgeHammer), one of which was going after the ultra-high-end market that Intel had laid claim to since… well, since forever. Not one to take such a move sitting down, Intel launched their first ever “Extreme Edition” processor in the same week as the FX-51. Toting higher clock speeds and an unlocked multiplier, the Pentium 4 EE chip had surely saved Intel from a possible threat. But what about that other chip? The seemingly innocent little Athlon 64, with its 2.0 GHz and on-chip memory controller only capable of single-channel operation, was starting to get a lot of attention. It took a little while, as things in the hardware world always do, but this Athlon 64 eventually became a really big deal. Hardware journalists and publications far and wide were hailing the 3200+ as the “fastest yet”, smoking the Pentium 4 in all sorts of benchmarks, including one really big one, games. But while the enthusiast community had seen the light, the rest of the world would end up being a bit more skeptical of these low clock speeds compared to the new 3.46 GHz Pentium 4 - How could it possibly be faster?

With the hype and press generated by Intel’s “Prescott”, you know, that one processor that turned out NOT to be the Pentium 5, AMD and their Athlon 64 remained mostly in the shadows of their larger rival. Then in June of 2004, AMD dropped what would cause an even more serious problem for Intel, a new socket 939 and a new 90nm core called Winchester. With this new socket came support for faster bus speeds and, more importantly, dual-channel memory configurations. Intel was in trouble. Not only did AMD have this new ace on the pitch, but their Prescott line was getting ripped left and right due to the lack of any significant performance increase resulting from the higher power consumption and heat levels. In a little under a year, things for Intel had taken a turn for the worse.

And while Intel may have retained most of the market-share for the last 3 years, their processor repertoire has been far from star-studded and almost unanimously considered inferior to that of AMDs. But Intel was not down for the count, and like any good competitor, they had a little something up their sleeve. In May of 2004, after realizing that the future of the Pentium 4’s "NetBurst" microarchitechture did not look very bright at all and that AMDs mid-range lineup was wiping the floor with the best they had to offer, Intel engineers started work on something new…

The term “Conroe” first hit the hardware scene sometime in 2005, tracking down the exact date would be like searching for a needle in a haystack when there wasn’t actually a needle in there in the first place. While we have certainly “known” about Conroe since around that time, we first wrote about it after details were released and confirmed at the Spring Intel Developer Forum (IDF) of this year.

In our previous article, we discussed the basic developmental aspects of the Intel Core Microarchitecture (ICM) including the history, the reasons, and the development itself. Now we would like to futher elaborate on ICM and its first face, Core 2 Duo.

---

Introduction
Features
Features (cont.)
Test System and Methods
Test Bed
Test Suite
3DMark05, PCMark05
Super PI 1.1
ScienceMark 2.0, Sandra 2007
Quake 4
F.E.A.R
Half-Life 2: Episode 1
Call of Duty 2
Oblivion
Multitasking
Overclocking
Conclusion