Why not pay 1000 dollars for a CPU, yet we see TRI and QUAD SLI/XFIRE.

[NTMBK]

I suspect the answer here lies beyond the simple statistic that a singular metric like average FPS will capture and convey.

Take the techreport's methodology of capturing and reporting the average frame rate for just the 99th percentile, or the time spent rendering frames that exceed 33.3ms.

These are ways to analytically capture and analyze game response factors that matter to the end-user above and beyond a flat "what is my average framerate?" because average fps does not speak to stuttering and lag in ways that the experiential result does.

I have no doubt that a hexcore is unlikely to improve on the gameplay from a flat average framerate perspective over that of a quad, but I have every expectation that a user playing a game on a hexcore is more likely to find the gameplay more fluid with less noticable random minimums in the framerate and so forth.

In many ways this is no different than what Anand uncovered and highlighted years ago regarding SSDs and the lockups they would do with random read/write of small files and so forth. That was a very real issue that was not captured by benchmarks designed to measure sequential bandwidth with large files.

For all the reasons that mattered for SSD users, I expect the same to manifest with gamers and their video cards versus cpu core count (since core count reduces contention on the backend where system processes are transpiring simultaneously).

I'm amazed that other sites haven't started copying their methodology; it really uncovers some seriously interesting performance characteristics. Take a look at this page from their Trinity review: http://techreport.com/review/23662/amd-a10-5800k-and-a8-5600k-trinity-apus-reviewed/10 The important thing to note is the Pentium's performance. While on an average FPS the Pentium is only 1FPS behind Trinity, when looking at 99th percentile frame time it's pretty disastrous. This will translate into a real world worse experience, with choppy, stutter-filled bad performance.

 

[Lepton87]

I have no idea how you got any of that out of my post.

When did hyperthreading come into the discussion?

Puppies04 already explained why I made that connection. Also because 2c/4t CPUs are faster in games then 2c/2t but the same isn't true for quads. So games benefit from hyper-threaded cores, so why wouldn't they benefit from 4 extra threads but somehow benefit from 2 extra cores?

 

[BrightCandle]

A month ago on this very forum there was a discussion on whether HT made a difference to games. The bench marker was showing benefits in a some games for HT even on a 4 core machine. Since SB it seems the negative impact of HT has been all but eliminated and its now slightly positive.

If building a PC for games on a budget there is little return for more than 4 cores. HT is likely not worth paying for either. But on some games there is a performance benefit as they utilise more than 4 threads. But games continue to be mostly held back by graphics and not CPU performance so its certainly not the first thing to look at.

 

[Idontcare]

Puppies04 already explained why I made that connection. Also because 2c/4t CPUs are faster in games then 2c/2t but the same isn't true for quads. So games benefit from hyper-threaded cores, so why wouldn't they benefit from 4 extra threads but somehow benefit from 2 extra cores?

My comments were specifically relating to the context of actual cores, not virtual cores as concocted by means of SMT or CMP.

 

[Puppies04]

A month ago on this very forum there was a discussion on whether HT made a difference to games. The bench marker was showing benefits in a some games for HT even on a 4 core machine. Since SB it seems the negative impact of HT has been all but eliminated and its now slightly positive.

I would imagine the only reason quads with HT started to perform better was that newer games were being tested that could handle the extra threads, I doubt SB had anything to do with this it was just a coincidence or are you saying older hyper threaded quads were taking more of a performance hit compared to newer ones?

 

[Puppies04]

Puppies04 already explained why I made that connection. Also because 2c/4t CPUs are faster in games then 2c/2t but the same isn't true for quads. So games benefit from hyper-threaded cores, so why wouldn't they benefit from 4 extra threads but somehow benefit from 2 extra cores?

I also provided a possible answer to that, I wasn't necerssarily agreeing with you I just saw why you had brought HT into the conversation.

HT provides a performance boost in tasks that allow an extra thread to take up spare CPU cycles on a core. The last thing you want is for a game to require a greater % of a cores resources only to find that another program snuck in and started using them because it thought they were not needed.

As for 2c2t chips being slower than 2c4t ones this would generally be attributed to the fact that most games can use at least 2 cores of a chip now days and if you only have 2 cores available then anything running in the background is going to have to interrupt the game while the core switches tasks momentarily, HT would enable the background process to use some of the cores processing power without halting the games code being run which while not ideal is a lot better than the alternative described above.