Core i5 2500K and Core i7 2600K review

Posted by Hilbert Hagedoorn on: 01/02/2011 02:00 PM [ 0 comment(s) ]

Performance Mandel | ZLib | VP8

Updated and added benchmarks: On this page a couple of updated and new benchmarks. Very few results here as we have to start over from scratch with these benchmarks as their update required an AVX compatibility fix.

FPU Mandel, and in the near future we'll include CPU Hash benchmarks as well, they now also utilize Intel Advanced Vector Extensions (AVX) of Intel Sandy Bridge processors. System Stability Test module has also been enhanced to put even more stress on the system using AVX optimizations. Note: To unlock the AVX capabilities of the new Intel processors, Windows 7 Service Pack 1 is required.

Mandel FPU test

The Mandel FPU benchmark measures double precision (also known as 64-bit) floating-point performance through the computation of several frames of the popular "Mandelbrot" fractal. The code behind this benchmark method is written in Assembly, and it is extremely optimized for every popular AMD and Intel processor core variant by utilizing the appropriate x86 or SSE2 instruction set extension.

If you come from the Commodore 64 / Amiga era like me (Peek & Poke Commands FTW dude!), you can probably remember rendering Mandelbrot graphics, a mathematical formula that much like a paradox, never ends and thus is repetitive. Back in the 1990s it took me a full day to complete one Mandelbrot image. Amazing where we are right now as the same set of calculations can be done in a split second & even real-time.

The FPU Mandel test again is Hyper-Threaded, multi-processor (SMP) and multi-core aware. The Phenom II 970Be and X6 1100T are the fastest processors the competition has available, hence we included them. The updated Mandel test now embeds AVX support and that shows alright. Also, the test does not allow AVX to be disabled.

Again, over time these benchmark updates/new tests will get more and more comparative processors added.

ZLib Compression

This integer benchmark measures combined CPU and memory subsystem performance through the public ZLib compression library Version 1.2.2

The ZLIB compression test was recently overhauled as well, hence we had to start from scratch here again as well. This integer benchmark measures combined CPU and memory subsystem performance through the public ZLib compression library. CPU ZLib test uses basic x86 instructions thus no AVX, and it is Hyper-Threading, multi-processor (SMP) and multi-core (CMP) aware.

VP8 video compression

VP8 is an open video compression format released by Google, originally created by On2 Technologies.

This particular test is a 64-bit multi-threaded VP8 video encoding stress sequence, this is a brand new 64-bit multi-threaded HD video encoding benchmark, based on Googles VP8 (WebM) video codec. The VP8 test encodes 1280x720 pixel ("HD ready") resolution video frames in 1-pass mode at 8192 kbps bitrate with best quality settings and it is Hyper-Threading, multi-processor (SMP) and multi-core (CMP) aware.

If you look at the 1100T and the 2600K for a second, you'll spot nearly bang on similar performance, the difference is that the 2600 does the very same thing with only 4 CPU cores, while the Phenom II needs six of them.

23 pages « < 16 17 18 19 next »

Core i5 3570K processor review
We review the Core i5 3570K Ivy bridge processor. Will Ivy Bridge be the processor series everything you expected? Go find out in this extensive review here at Guru3D.

Core i5 2500K and Core i7 2600K review
Today we test and review Sandy Bridge, the Intel Core i7-2600K and Intel Core i5-2500K processors. We will pair the 2600K processor with the Intel Desktop Motherboard DP67BG and also run a test with the Intel Core i5-2500K processor on a Intel DH67BL motherboard

Core i5 655K and Core i7 875K processor review
Intel today releases two new processors targeted at a somewhat more enthusiast audience. Yes, processors for tweakers and overclockers. On socket LGA 1156 Intel now releases two K series processors. The 32nm Intel Core i5-655K processor has the very same specifications as the Core i5 650; it will operate at 3.2 GHz, will feature two cores with Hyper-Threading technology, sport 4MB of L3 cache and will be made using 32nm process technology. The difference between the 650 and 655K is the unlocked multiplier only. Then we have the enthusiast class Intel Core i7-875K processor, it has the very same specifications as the Core i7 870; it will operate at 2.93GHz, will feature four cores with Hyper-Threading technology, sport 8MB of L3 cache and will be made using 45nm process technology. The only difference between the two central processing units (CPUs) will be the unlocked multiplier on the 875K chip, which will allow overclockers and enthusiasts to easily boost clock-speed of the product without the necessity of overclocking other parts of their systems.

Core i5 650 - 660 and 661 processor review
The time has come for Intel to debut a new line of mainstream 32nm processors, which we have all learned to recognize under the codename 'Clarkdale', the new CPUs will be aimed at the mainstream desktop PC segment and will complement the chip maker's Core i3 and Core i5 line of products. The Intel processor lineup will include the Core i3 530 and 540 models, as well as the Core i5 650, 660, 661, and 670, which will be featured with Hyper-Threading, 4MB of L3 cache and support for dual-channel DDR3-1333 memory. Well, that and an integrated GPU as well of course. Guru3D will put the Core i5 650, 660 and 661 to the test.