Jump to content

Review Request with Hyperthreading OFF

Hi everyone ,

 

Hello ,

we all know that games dont use more than 8 threads today ...

so to take advantage of an 8 cores or 10 cores CPU in Gaming you should Disable HT (Hyperthreading) and run the gaming test again to compare it against the 4 cores i7 6700K .

and tes it with SLI as well to reach the i7 6700k bottleneck !

let me put it more simple ,

The i7 6700K has 4 cores and can oc to 4.4 ghz easy . this CPU will give us 8 Virtual cores comparable to  2.2 GHZ clock for each virtual core .

However the 8 Coresi7 6900K , With the HT Turned OFF , will give us 8 cores @ 4.4 ghz EACH !

Thats double the speed of the 4 cores i7 ! if the game uses 8 threads .

EVEN if we dont OC the 8 cores , it would be 3.2GHZ VS 2.2 GHZ !!!

if you ask why Disable HT ? simple because the game will never use 16 Virtual cores !!! and the advantage is LOST .

Please run the test again for games with HT turned off .

and to stress the CPU more , TEST SLI as well , we want the i7 6700K to bottleneck !

THANKS

oh and Intel Should release i5 Broadwel-E CPU , 8 cores without HT , CHEAPER and BETTER for GAMERS 

Link to comment
Share on other sites

Link to post
Share on other sites

No.. not the way it works. please go read more about HT and what it does. it does not effect the speed at which the core runs.

 

Also, there have been tests like what your looking for in an "apples to apples" comparrison.

No real difference in anything that doesn't use the extra threads, difference in those that do use it.

I don'T PreSS caPs.. I juST Hit THe keYboARd so HarD iT CriTs :P

 

Quote or @dzzope to get my attention..

Link to comment
Share on other sites

Link to post
Share on other sites

sorry I disagree !

 

If the CPU is full 100% load and the game uses 8 threads it will make a huge difference !

 

I still demand benchmarks !

 

 

7 hours ago, DarkRuskov said:

^^^ everything is said.

 

wrong !!

 

Proof : i3 is slower in games than i5 !! at the same clock speed !

 

both have 4 threads !

 

but one with HT and another without !

 

and we need latest 8 threads games to test my idea !

Link to comment
Share on other sites

Link to post
Share on other sites

hyper threading does not simply divide a core by two, sorry to disapoint you.

Link to comment
Share on other sites

Link to post
Share on other sites

Typical desktop i3 is 2 cores 4 threads. In my testing, HT provides between 0 to 50% boost per physical core. That is, 2 core 4 threads with HT on, can have up to 50% more throughput than 2 cores 2 threads HT off. For sufficiently multi-threaded software that can really benefit from HT, you could say the i3 would perform like a 3 core 3 thread CPU of the same clock.

 

For software that doesn't benefit from HT at all, it is still 2 cores. If you run 4 threads on it, they would compete for time, and it would be roughly equivalent to having 4 cores at half the clock while they are all loaded. Note however it is the same throughput. You don't lose total performance, you don't gain any either.

 

I have discovered a case where disabling HT does provide a performance increase. Say I have a HT system, take the i3 again (applies similarly to i7). I have two physical cores, and I know the application has zero benefit from HT. So I run two threads. Each can run on a physical core, and I have full performance right? Not quite. I found about 10% loss in performance, compared to running two threads with HT off on exactly the same system. I believe the culprit is the OS scheduler. Windows will run those two app threads on all 4 CPU threads. I suspect some of the time, two threads will end up on the same physical core. As I've already stated the software has zero gain from HT, this means it is slowed down. Manually setting affinity brings the performance level up to HT off condition.

 

Maybe the last effect could kick in if you have a very high core count with not so threaded software, and you could gain a minor CPU performance boost from it. I wouldn't expect miracles though.

Main system: i9-7980XE, Asus X299 TUF mark 2, Noctua D15, Corsair Vengeance Pro 3200 3x 16GB 2R, RTX 3070, NZXT E850, GameMax Abyss, Samsung 980 Pro 2TB, Acer Predator XB241YU 24" 1440p 144Hz G-Sync + HP LP2475w 24" 1200p 60Hz wide gamut
Gaming laptop: Lenovo Legion 5, 5800H, RTX 3070, Kingston DDR4 3200C22 2x16GB 2Rx8, Kingston Fury Renegade 1TB + Crucial P1 1TB SSD, 165 Hz IPS 1080p G-Sync Compatible

Link to comment
Share on other sites

Link to post
Share on other sites

36 minutes ago, DarkRuskov said:

hyper threading does not simply divide a core by two, sorry to disapoint you.

I did not say divide core !  I said the total result in VIRTUAL. I said COMPARED TO! and I said this happens in full 100% load ! I know what I am talking about.

 

now some one PLEASE TEST THIS . the BENCHMARKS are the ANSWER !

 

make sure when you test to pick up games that use all 8 Threads . Thank you.

 

and try SLI as well to bottleneck the CPU more !

Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×