The 12th Generation Alder Lake chips from Intel bring in a new generation of x86 CPUs.

After months of anticipation and rumors, Intel is now set to introduce its first “Alder Lake” 12th-generation Core desktop CPUs, and they’re giving us a performance peek based on in-house benchmark studies. In future, you’ll also get independent assessment of the CPUs as we begin delving into all things Alder Lake, such as DDR5 vs. DDR4 performance, which motherboards are worth buying, and so on. There will be a lot of good days ahead.

Intel has already provided us a slew of data Intel has already provided us a slew of data about the Alder Lake architecture, including the new hybrid design with P-cores and E-cores, but today it all comes together in the form of actual CPUs that will be available beginning November 4.

Intel had always debuted its mobile chips first, but this is poised to change with the 12th-generation range. The first CPUs to be introduced next week are enthusiast desktop K-series devices, with the rest to follow in early 2019. Given that Intel’s desktop components are finally transitioning to a new manufacturing node with a totally new architecture, it appears that the company wants to start with the fastest performance models before filling out the lineup.

To refresh your memory on Alder Lake, Intel is transitioning to a new hybrid architecture that includes both performance cores (P-cores) and efficiency cores (E-cores). The P-cores are an upgrade to Intel’s current high-performance cores, featuring a larger, broader, and deeper architecture, additional cache, and better functions. Intel claims that these P-cores provide a 19% IPC boost over the Cypress Cove cores seen in Rocket Lake.

Meanwhile, the E-cores represent a significant upgrade over Intel’s existing Atom cores, bringing speed up to Skylake levels while being considerably smaller in terms of chip area and more efficient in terms of power consumption. These cores, according to Intel, are mostly intended for background operations, although they are no slouch and should dramatically improve multi-thread performance in several programs.
Intel’s new cache design ties everything together. Each P-core has 1.25 MB of L2 cache, while each E-core group has 2 MB of L2 cache. Then, Intel provides up to 30 MB of shared L3 cache, which is available across both P and E cores. Rocket Lake has a maximum L3 cache of 16 MB.

The Thread Director, a hardware scheduling mechanism that supports Windows 11 in distributing tasks to the proper cores, is also included in Alder Lake. When using a hybrid design, it is critical that programs execute on the appropriate cores — front, high-performance apps on the P-cores, and background duties on the E-cores. Thread Director gives Windows 11 with input that aids in this process.

About Alder Lake 12th-Gen CPUs

Intel is releasing six 12th-generation Core processors, three in the K series and three in the KF series. So we’re getting a Core i9 design, a Core i7 design, and a Core i5 design, all with and without an integrated graph.

The i9-12900K Core i9 variant is the fully unlocked Alder Lake die. It has eight P-cores and eight E-cores, for a total of sixteen CPU cores and twenty-four threads. Why not have 32 threads? Because E-cores lack hyperthreading, the P-core cluster has 8 cores and 16 threads, whereas the E-core cluster has 8 cores and 8 threads. In addition, there is 30 MB of L3 cache.

Because this CPU has two types of cores, clock speeds are more complicated than previously. The P-cores have a base frequency of 3.2 GHz and a boost frequency of 5.2 GHz, while the E-cores have a frequency range of 2.4 to 3.9 GHz. While the peak frequency of the P-cores is identical to previous generations, the E-cores are clocked a little lower and have less IPC.

The Core i7-12700K features 8 P-cores and 4 E-cores for a total of 12 cores and 20 threads, as well as 25 MB of L3 cache. Boost clock rates are somewhat lower than those of the Core i9 model, but base frequency is higher: 3.6 to 5.0 GHz for the P-cores and 2.7 to 3.8 GHz for the E-cores.

Then there’s the Core i5-12600K, which features six P-cores and four E-cores for a total of ten cores and sixteen threads, as well as 20 MB of L3 cache. The P-cores run at 3.7 to 4.9 GHz, while the E-cores run at 2.8 to 3.6 GHz.

All versions allow overclocking, and the K-SKUs with integrated graphics include Xe-based UHD Graphics 770, though Intel hasn’t said much about what this entails. All models also support DDR5-4800 and DDR4-3200 memory, but you must pick which technology to use; you cannot use both at the same time.

Intel isn’t fooling around when it comes to price. Despite AMD’s rival Ryzen 9 5950X CPU’s MSRP of $800, Intel is aiming for the throat by offering the 16-core Core i9-12900K at $589. You’ll save roughly $25 if you go with the Core i9 KF model. This appears to be quite competitive, however we have yet to see how it performs.

The Core i7 and Core i5 processors are even more powerful. The tray price for the 12700KF is $384, which is nearly the same as the current pricing for AMD’s Ryzen 7 5800X. However, unlike the 5800X, Intel offers not just eight performance cores but also four efficiency cores, which might provide a significant improvement to multi-threaded performance.

But there’s a greater shift going on here as well.
Intel has finally updated their “default” power setup to match how motherboard manufacturers have been running these CPUs for years. For the optimal performance, the default power mode for all K-SKU processors will be to operate the CPU at its maximum turbo power indefinitely (the graph on the right). Previously, the default configuration was what you see in the left graph, but practically all motherboards overrode this by default to operate the CPU as seen in the right graph. Both configurations were always in-spec, but it was unclear which was “right” or “default” and which mode reviewers should test with.

Brain Tech Solution