Another improvement that Intel made with ICM is what they call Advanced Smart Cache. With dual-core NetBurst processors as in the current Pentium D line, each execution core had its own independent bank of L2 cache. The problem, well not really a problem but more of an underutilization, with this was that each execution core only had access to half of the processor’s total available L2 cache. As we have learned empirically, increased L2 cache pretty much always means greater performance. Advanced Smart Cache effectively doubles the utilization of L2 cache with ICM, allowing the processors to access and write information to the cache in larger amounts, decreasing cache misses and increasing performance. This technique is similar to what we already see in AMD’s Athlon 64 X2 offerings.

Intel’s Smart Memory Access is yet another way Intel has increased the overall performance of ICM. In Smart Memory Access, Intel implements something they call memory disambiguation. Memory Disambiguation is something that allows execution cores to speculate what data is needed from the memory before it actually executes. This allows the system to “pre-load” information while the previous instruction is being executed, drastically decreasing memory latency effects.

The final improvement we see in ICM is the Intel’s Advanced Digital Media Boost. This feature is basically the end result of the doubling of the speed at which SIMD instruction sets are executed. Previously to ICM, execution cores had to break down the 128-bit SSE,2,3 instructions into two 64-bit subsets in order to execute them, allowing one SIMD instruction set to be executed per every two clock cycles. With ICM, the entire 128-bit SIMD instruction set is executed in the same clock cycle, allowing one instruction set to be executed every clock cycle. As a result of Intel’s Advanced Digital Media Boost, the end-user experiences dramatically increased performance when processing multimedia instructions.

Specific to the Core 2 series of processors, and probably every processor hereafter, Intel has included several very interesting features. They are:

• Intel Virtualization (VT) Technology
• Intel Extended Memory 64 Technolgy (EM64T)
• Intel Execute Disable Bit

Virtualization Technology is something we’ve been hearing about for quite a while now. The main idea for VT technology is to allow multiple applications to be running simultaneously under different profiles. The way it does this it creates “Virtual” platforms, or environments, and allows processes to run in those environments when the computer is actively being used on a different platform. The application of this technology is likely far more promising and relevant in the enterprise/business world as opposed to the average home user, but the potential for overall productivity increases looks very attractive.

EM64T, while previously implemented on the 600 series of the Pentium 4 line and later processors, will again be used in Core 2 processors from Intel. EM64T is essentially the means by which Intel processors operate on x64 instructions. It also allows Intel processors to utilize greater amounts of virtual and physical memory. There is nothing ground-breaking to report here.

Intel’s Execute Disable Bit is basically a further enhanced attempt at hardware-based virus protection. The Execute Disable Bit marks memory banks as executable or non-executable, depending on whether or not it is infected by a virus or other malicious agent. If the operating system attempts to read data from a non-executable piece of memory, this will be recognized and avoided, disallowing the spread of the virus.

All these new features look very impressive on paper, but what about the realized performance? If the processor is theoretically capable of great things but cannot actually produce those results in the real world, what use is it? On to the interesting part of the review.