FX giving bad FPS? Here's how to tune your old FX to give better in game performance... - Page 22 - Overclock.net - An Overclocking Community

Forum Jump: 

FX giving bad FPS? Here's how to tune your old FX to give better in game performance...

Reply
 
Thread Tools
post #211 of 609 (permalink) Old 11-26-2017, 02:46 PM
PC Evangelist
 
ZealotKi11er's Avatar
 
Join Date: May 2007
Location: Toronto, CA
Posts: 45,439
Rep: 1789 (Unique: 1170)
Quote:
Originally Posted by gapottberg View Post

Yes they do. It makes me irrationally angery when people say FX modules are basicly not true 8 core processors but 4 core ones with Hyperthreading. They have no clue what they are talking about and their statement could not be further from the truth.

Yeah cause 4C HT does not spank 4C i5 these days. The only thin about FX is that it needs to have at least 70%+ CPU usage to come close to i5 performance but because it still has performance left you will not encounter as much drops.

Ishimura
(13 items)
Yamato
(10 items)
CPU
Intel Core i7-3770K @ 4.8GHz
Motherboard
ASRock Z77E-ITX
GPU
AMD Radeon Vega Frontier Edition
RAM
AVEXIR Blitz 1.1 16GB DDR3-2400MHz CL10
Hard Drive
SanDisk Ultra II 960GB
Hard Drive
Toshiba X300 5TB
Power Supply
EVGA SuperNOVA 750 G3
Cooling
Corsair H100i GTX
Case
Fractal Design Define Nano S
Operating System
Microsoft Windows 10 Pro 64 Bit
Monitor
LG OLED55C7P
Keyboard
Cooler Master MasterKeys MK750
Mouse
Finalmouse Air58 Ninja
CPU
Intel Core i7-6700K @ 4.6GHz
Motherboard
ASUS Z170 Deluxe
GPU
EVGA GeForce GTX 1080 Ti Hybrid
RAM
Corsair Vengeance LPX 16GB DDR4-3000 CL15
Hard Drive
Samsung SM961 512GB
Hard Drive
HGST DeskStar NAS 6TB
Power Supply
EVGA SuperNOVA 750 P2
Cooling
Cooler Master Nepton 280L
Case
Fractal Design Meshify C TG
Operating System
Microsoft Windows 10 Pro 64 Bit
▲ hide details ▲


ZealotKi11er is offline  
Sponsored Links
Advertisement
 
post #212 of 609 (permalink) Old 11-26-2017, 03:17 PM
Oldtimer
 
gapottberg's Avatar
 
Join Date: Dec 2006
Posts: 794
Rep: 54 (Unique: 38)
Lol...my quote looks as if instead of agreeing with someone I am being confrentational.

Anyways...i recently came up with a good analogy of how to explain the difference between FX and Hyperthreading. Admitedly stolen in part from a LTT video on the topic, but expanded some.

Imagine a candy bowl full of a mix of various types of candy. Hard candy, soft candy, big candy, small candy. This bowl represents a task the CPU needs to complete.

Now imagine a person being told to eat the candy as fast as they can. This person represents a CPU. However not all CPUs are created equal. And niether are people.

Let's first look at an intel CPU with Hyperthreading. Looking at a single core we find it has one pipeline for completing tasks...but two for schedualing them. The hyperthreading acts like 2 hands keeping the cpu mouth fes. This is essentially what hyperthreading does. It keeps the CPU fed with tasks to complete. Thus an intel CPU is like a single person with 1 mouth and 2 hands stuffing their face with every type of candy they can eat.

Every core an intel processor has adds a potential person to the task of cleaning out the bowl as long as its a big enough bowl to accomadate them all. Size of the bowl represents how well threaded the task is. A bigger bowl can fit more workers around it.

Now lets look at an AMD FX module.

The FX module is a wierd siamese twin looking person. This person has 2 heads, two mouths, and two hands. One hand can feed each mouth...but there is one problem. One of the two twins hates chocolate. They will not eat any candy with chocolate in it. They will however use their hand to help feed the other head any chocolate candies they happen to pick up. Any other candy is fine for them to eat themself. Chocolate candy reptesents floating point operations in our analogy. Since the Module has a shared floating point unit...the CPU sort of acts like it only has one mouth even though there are two in some cases.

You can see from this analogy that in many cases the twins will mow through a bowl of candy faster than a normal two handed person would because two mouths are better than one when it comes to eating quickly. The same is true for CPU tasks.

However this is only partially true, and for bowls with less chocolate candy in them specificly. Too much chocolate and we basicly behave like a hyperthreaded single core CPU. Two hands but only one mouth. That is still worst case scenario though, and is only completely true in very specific workloads. The fewer chocloate candies in the bowl, the more efficient the FX becomes when compared to a normal hyperthreaded core.

There is more too it than this, as the individual effeciency of the cores makes a difference too. If one of the people in our analogy has a wold record for eating the most buffalo wings in 5 min...then they might be better at getting through a bowl of candy too. IPC or instructions per clock are not really presnet in the analogy above but they do matter. In many cases an Intel has an edge here and is a more "effecient eater" so to speak.

It's still a good analogy that shows why the freaky siamese style FX module is indeed a true 4, 6, or 8 core processor...and how it differes from a hyperthreaded one in some curious ways that can given similar IPC... make it faster at some tasks.

#REDTEAM
Serenity
(11 items)
Dat_Ashe
(12 items)
CPU
AMD FX-8320E OCed @ 4.5Ghz
Motherboard
ASRock 970 Fatality
GPU
MSI 390X
RAM
Gskill Ripjaw 16GB @ 2133MHz
Hard Drive
Samsung EVO 250GB SSD
Optical Drive
ASUS Blue Ray
Power Supply
Thermaltake toughpower 650watt
Cooling
Thermaltake Water 3.0
Case
Thermaltake T81
Operating System
Windows 10
Monitor
Asus VX248
CPU
FX-6300
Motherboard
BIOSTAR TA970
GPU
SAPPHIRE Radeon R9 270 2GB
RAM
G.SKILL Ripjaws X Series 8GB DDR3 1866mhz
Hard Drive
Seagate Barracuda 1TB Hard Drive
Optical Drive
ASUS Blu-ray Drive
Power Supply
Corsair 750watt PSU
Cooling
ZALMAN CNPS9900MAX-B 135mm CPU Cooler
Case
Antec GX500
Operating System
Windows 10 Technical Preview
Monitor
ASUS VX248 24" 1080p LCD Moniter
Mouse
Logitech G602 wireless gaming mouse
▲ hide details ▲


gapottberg is offline  
post #213 of 609 (permalink) Old 11-26-2017, 04:08 PM
PC Evangelist
 
ZealotKi11er's Avatar
 
Join Date: May 2007
Location: Toronto, CA
Posts: 45,439
Rep: 1789 (Unique: 1170)
Quote:
Originally Posted by gapottberg View Post

Lol...my quote looks as if instead of agreeing with someone I am being confrentational.

Anyways...i recently came up with a good analogy of how to explain FX and Hyperthreading. Admitedly stolen in part from a LTT video in the topic but expanded.

Imagine a candy bowl full of a mix of various types of candy. Hard candy, soft candy, big candy, small candy. This bowl represnets a task the CPU needs to complete.

Now imagine a person being told to eat the candy as fast as they can. This person reptesnets a CPU. However not all CPUs are created equal. And nither are people.

Lets look at an intel CPU with Hyper threading. Looking at a single core we find it has one pipeline for completing tasks...but two for schedualing them. This is essentially what hyperthreading does. It keeps the CPU fed with tasks to complete.

Thus an intel CPU is like a single person with 1 mouth and 2 hands stuffing their face with every type of candy they can eat. Every core an intel processor has adds a potential person to the task of cleaning out the bowl as long as its a bug enogh bowl to accomadate them all. Size of the bowl represnts how well threaded the task is. A bigger bowl can fit more workers around it.

Now lets look at an AMD FX module.

The FX module is a wierd siamese twin looking person. This person has 2 head, two mouths, and two hands. One hand can feed each mouth...but there is one problem. One of the two twins hates chocolate. They will not eat any candy with chocolate in it. They will however use their hamd to help feed the other head any chocolate related tasks they happen to pick up. Any other candy is fine. Chocolate candy reptesents floating point operations in out analogy. Since the Modual has a shared floating point unit...it act like it only has one mouth even though there are two.

You can see from this analogy that in many cases the twins will mow through a bowl of candy faster than a normal two handed person would because two mouths are better than one.

However this is only true for bowls with less chocolate candy in them. Too mucj chocolate and we basicly behave like a hyperthreaded single core. Two hands and one mouth. That is still worst case scenario though, and is only completely true in very specific workloads. The fewer chocloate candies the mire effeicient the FX becomes when compared to a normal hyperthreaded core.

It's a good analogy that shows why the freaky siamese style FX module is indeed a true 4, 6, or 8 core processor...and how it differes from a hyperthreaded one.

In the end of the day HT is way more optimized then FX modules where ever optimized. There are negative effects in some games that can cause lower then expected performance. All this has been fix with HT in general. We just do not know how the module system is suppose to work correctly because Intel is market leader. Just look at how much difference their ring bus makes hindering even their own mesh design in Skylake-X in games. There is also one more thing with cores and why HT "look" better. Not all cores are loaded equally even if the system makes it seem like all are 90%+. For example for a game the physics calculation could be happening in the real cores and HT will do sound effect and less tasking calculation. If you do the same thing with 8 equal cores you are bottleneck buy having 8 weaker cores.

Ishimura
(13 items)
Yamato
(10 items)
CPU
Intel Core i7-3770K @ 4.8GHz
Motherboard
ASRock Z77E-ITX
GPU
AMD Radeon Vega Frontier Edition
RAM
AVEXIR Blitz 1.1 16GB DDR3-2400MHz CL10
Hard Drive
SanDisk Ultra II 960GB
Hard Drive
Toshiba X300 5TB
Power Supply
EVGA SuperNOVA 750 G3
Cooling
Corsair H100i GTX
Case
Fractal Design Define Nano S
Operating System
Microsoft Windows 10 Pro 64 Bit
Monitor
LG OLED55C7P
Keyboard
Cooler Master MasterKeys MK750
Mouse
Finalmouse Air58 Ninja
CPU
Intel Core i7-6700K @ 4.6GHz
Motherboard
ASUS Z170 Deluxe
GPU
EVGA GeForce GTX 1080 Ti Hybrid
RAM
Corsair Vengeance LPX 16GB DDR4-3000 CL15
Hard Drive
Samsung SM961 512GB
Hard Drive
HGST DeskStar NAS 6TB
Power Supply
EVGA SuperNOVA 750 P2
Cooling
Cooler Master Nepton 280L
Case
Fractal Design Meshify C TG
Operating System
Microsoft Windows 10 Pro 64 Bit
▲ hide details ▲


ZealotKi11er is offline  
Sponsored Links
Advertisement
 
post #214 of 609 (permalink) Old 11-26-2017, 04:12 PM
Oldtimer
 
gapottberg's Avatar
 
Join Date: Dec 2006
Posts: 794
Rep: 54 (Unique: 38)
I edited the post while you were quoting it. Sorry for the typos. I also added a few points. But you are correct. Proper programing and software optimization does also matter.

I still think it was an interesting idea in theory. You get all the effeicncy of a duel core in many workloads and cut the cost of production by a fair margin due to saved space on die. Just wish it had worked out better. I still think it has aged better than the tech press seem to suggest.

#REDTEAM
Serenity
(11 items)
Dat_Ashe
(12 items)
CPU
AMD FX-8320E OCed @ 4.5Ghz
Motherboard
ASRock 970 Fatality
GPU
MSI 390X
RAM
Gskill Ripjaw 16GB @ 2133MHz
Hard Drive
Samsung EVO 250GB SSD
Optical Drive
ASUS Blue Ray
Power Supply
Thermaltake toughpower 650watt
Cooling
Thermaltake Water 3.0
Case
Thermaltake T81
Operating System
Windows 10
Monitor
Asus VX248
CPU
FX-6300
Motherboard
BIOSTAR TA970
GPU
SAPPHIRE Radeon R9 270 2GB
RAM
G.SKILL Ripjaws X Series 8GB DDR3 1866mhz
Hard Drive
Seagate Barracuda 1TB Hard Drive
Optical Drive
ASUS Blu-ray Drive
Power Supply
Corsair 750watt PSU
Cooling
ZALMAN CNPS9900MAX-B 135mm CPU Cooler
Case
Antec GX500
Operating System
Windows 10 Technical Preview
Monitor
ASUS VX248 24" 1080p LCD Moniter
Mouse
Logitech G602 wireless gaming mouse
▲ hide details ▲


gapottberg is offline  
post #215 of 609 (permalink) Old 11-26-2017, 05:00 PM
New to Overclock.net
 
cssorkinman's Avatar
 
Join Date: Apr 2009
Posts: 9,287
Rep: 458 (Unique: 259)
Quote:
Originally Posted by ZealotKi11er View Post

Quote:
Originally Posted by gapottberg View Post

Lol...my quote looks as if instead of agreeing with someone I am being confrentational.

Anyways...i recently came up with a good analogy of how to explain FX and Hyperthreading. Admitedly stolen in part from a LTT video in the topic but expanded.

Imagine a candy bowl full of a mix of various types of candy. Hard candy, soft candy, big candy, small candy. This bowl represnets a task the CPU needs to complete.

Now imagine a person being told to eat the candy as fast as they can. This person reptesnets a CPU. However not all CPUs are created equal. And nither are people.

Lets look at an intel CPU with Hyper threading. Looking at a single core we find it has one pipeline for completing tasks...but two for schedualing them. This is essentially what hyperthreading does. It keeps the CPU fed with tasks to complete.

Thus an intel CPU is like a single person with 1 mouth and 2 hands stuffing their face with every type of candy they can eat. Every core an intel processor has adds a potential person to the task of cleaning out the bowl as long as its a bug enogh bowl to accomadate them all. Size of the bowl represnts how well threaded the task is. A bigger bowl can fit more workers around it.

Now lets look at an AMD FX module.

The FX module is a wierd siamese twin looking person. This person has 2 head, two mouths, and two hands. One hand can feed each mouth...but there is one problem. One of the two twins hates chocolate. They will not eat any candy with chocolate in it. They will however use their hamd to help feed the other head any chocolate related tasks they happen to pick up. Any other candy is fine. Chocolate candy reptesents floating point operations in out analogy. Since the Modual has a shared floating point unit...it act like it only has one mouth even though there are two.

You can see from this analogy that in many cases the twins will mow through a bowl of candy faster than a normal two handed person would because two mouths are better than one.

However this is only true for bowls with less chocolate candy in them. Too mucj chocolate and we basicly behave like a hyperthreaded single core. Two hands and one mouth. That is still worst case scenario though, and is only completely true in very specific workloads. The fewer chocloate candies the mire effeicient the FX becomes when compared to a normal hyperthreaded core.

It's a good analogy that shows why the freaky siamese style FX module is indeed a true 4, 6, or 8 core processor...and how it differes from a hyperthreaded one.

In the end of the day HT is way more optimized then FX modules where ever optimized. There are negative effects in some games that can cause lower then expected performance. All this has been fix with HT in general. We just do not know how the module system is suppose to work correctly because Intel is market leader. Just look at how much difference their ring bus makes hindering even their own mesh design in Skylake-X in games. There is also one more thing with cores and why HT "look" better. Not all cores are loaded equally even if the system makes it seem like all are 90%+. For example for a game the physics calculation could be happening in the real cores and HT will do sound effect and less tasking calculation. If you do the same thing with 8 equal cores you are bottleneck buy having 8 weaker cores.

Like most thing's it depends on what you are doing and what is actually limiting performance.

In some applications performance gains from H/T are non-existent , some cases it has been shown to actually hurt performance. Certain applications that make use of H/T scale at around 50% of what added cores on the FX do.

Makes for some interesting testing anyhow.

If anyone has any suggestions of what application would best cause the FX 8 cores to express performance hits from resource contention I'd be interested in hearing them.

FX8370E 5839mhz MSI 990FXA GD80 - custom water http://valid.x86.fr/3jk1vz
FX - 9370 @ 5740mhz MSI 990FXA GD-80 with an H-100 proof.gifhttp://valid.canardpc.com/s04jcj
I like MSI motherboards and this is why smile.gif
8350 @ 5.2 ghz on a stock cooler proof.gif PM me! smile.gif
cssorkinman is offline  
post #216 of 609 (permalink) Old 11-26-2017, 05:08 PM
Oldtimer
 
gapottberg's Avatar
 
Join Date: Dec 2006
Posts: 794
Rep: 54 (Unique: 38)
I am not super familiar with code, but i have heard that you can show the floating point bottle neck really well in tasks that are almost 100% floating point in nature. The only one I can think of off the top of my head was one of those Pi calculators you sometimes see in benchmarking videos. When you comparing the single core performance of an FX in those tasks vs multi core performance, i believe it scales very poorly compared to more integer based and balanced workloads.

#REDTEAM
Serenity
(11 items)
Dat_Ashe
(12 items)
CPU
AMD FX-8320E OCed @ 4.5Ghz
Motherboard
ASRock 970 Fatality
GPU
MSI 390X
RAM
Gskill Ripjaw 16GB @ 2133MHz
Hard Drive
Samsung EVO 250GB SSD
Optical Drive
ASUS Blue Ray
Power Supply
Thermaltake toughpower 650watt
Cooling
Thermaltake Water 3.0
Case
Thermaltake T81
Operating System
Windows 10
Monitor
Asus VX248
CPU
FX-6300
Motherboard
BIOSTAR TA970
GPU
SAPPHIRE Radeon R9 270 2GB
RAM
G.SKILL Ripjaws X Series 8GB DDR3 1866mhz
Hard Drive
Seagate Barracuda 1TB Hard Drive
Optical Drive
ASUS Blu-ray Drive
Power Supply
Corsair 750watt PSU
Cooling
ZALMAN CNPS9900MAX-B 135mm CPU Cooler
Case
Antec GX500
Operating System
Windows 10 Technical Preview
Monitor
ASUS VX248 24" 1080p LCD Moniter
Mouse
Logitech G602 wireless gaming mouse
▲ hide details ▲


gapottberg is offline  
post #217 of 609 (permalink) Old 11-26-2017, 05:58 PM
New to Overclock.net
 
cssorkinman's Avatar
 
Join Date: Apr 2009
Posts: 9,287
Rep: 458 (Unique: 259)
Quote:
Originally Posted by gapottberg View Post

I am not super familiar with code, but i have heard that you can show the floating point bottle neck really well in tasks that are almost 100% floating point in nature. The only one I can think of off the top of my head was one of those Pi calculators you sometimes see in benchmarking videos. When you comparing the single core performance of an FX in those tasks vs multi core performance, i believe it scales very poorly compared to more integer based and balanced workloads.

Just looking at CB 15 scores from my 3770K Same single core scores for both tests locked at same freq. 4 c multi was 561 = 140 per thread 8 core was 729 = 91 per thread if you take the 729 and subtract 561 those HT threads only produced 42 per thread - less than 1/3 of what the physical cores produce.

Looking at that, it amazes me that people even see resource contention in FX to be a big deal

FX8370E 5839mhz MSI 990FXA GD80 - custom water http://valid.x86.fr/3jk1vz
FX - 9370 @ 5740mhz MSI 990FXA GD-80 with an H-100 proof.gifhttp://valid.canardpc.com/s04jcj
I like MSI motherboards and this is why smile.gif
8350 @ 5.2 ghz on a stock cooler proof.gif PM me! smile.gif
cssorkinman is offline  
post #218 of 609 (permalink) Old 11-26-2017, 06:05 PM - Thread Starter
Useful idiot
 
Minotaurtoo's Avatar
 
Join Date: Jun 2013
Location: Florence, AL
Posts: 2,342
Rep: 80 (Unique: 46)
Quote:
Originally Posted by gapottberg View Post

Lol...my quote looks as if instead of agreeing with someone I am being confrentational.

Anyways...i recently came up with a good analogy of how to explain the difference between FX and Hyperthreading. Admitedly stolen in part from a LTT video on the topic but expanded, but expanded some.

Imagine a candy bowl full of a mix of various types of candy. Hard candy, soft candy, big candy, small candy. This bowl represents a task the CPU needs to complete.

Now imagine a person being told to eat the candy as fast as they can. This person represents a CPU. However not all CPUs are created equal. And niether are people.

Let's first look at an intel CPU with Hyperthreading. Looking at a single core we find it has one pipeline for completing tasks...but two for schedualing them. The hyperthreading acts like 2 hands keeping the cpu mouth fes. This is essentially what hyperthreading does. It keeps the CPU fed with tasks to complete. Thus an intel CPU is like a single person with 1 mouth and 2 hands stuffing their face with every type of candy they can eat.

Every core an intel processor has adds a potential person to the task of cleaning out the bowl as long as its a big enough bowl to accomadate them all. Size of the bowl represents how well threaded the task is. A bigger bowl can fit more workers around it.

Now lets look at an AMD FX module.

The FX module is a wierd siamese twin looking person. This person has 2 heads, two mouths, and two hands. One hand can feed each mouth...but there is one problem. One of the two twins hates chocolate. They will not eat any candy with chocolate in it. They will however use their hand to help feed the other head any chocolate candies they happen to pick up. Any other candy is fine for them to eat themself. Chocolate candy reptesents floating point operations in our analogy. Since the Module has a shared floating point unit...the CPU sort of acts like it only has one mouth even though there are two in some cases.

You can see from this analogy that in many cases the twins will mow through a bowl of candy faster than a normal two handed person would because two mouths are better than one when it comes to eating quickly. The same is true for CPU tasks.

However this is only partially true, and for bowls with less chocolate candy in them specificly. Too much chocolate and we basicly behave like a hyperthreaded single core CPU. Two hands but only one mouth. That is still worst case scenario though, and is only completely true in very specific workloads. The fewer chocloate candies in the bowl, the more efficient the FX becomes when compared to a normal hyperthreaded core.

There is more too it than this, as the individual effeciency of the cores makes a difference too. If one of the people in our analogy has a wold record for eating the most buffalo wings in 5 min...then they might be better at getting through a bowl of candy too. IPC or instructions per clock are not really presnet in the analogy above but they do matter. In many cases an Intel has an edge here and is a more "effecient eater" so to speak.

It's still a good analogy that shows why the freaky siamese style FX module is indeed a true 4, 6, or 8 core processor...and how it differes from a hyperthreaded one in some curious ways that can given similar IPC... make it faster at some tasks.

I put a link to this in the OP... very interesting comparison... oh... I haven't decided if I should include it in the OP.. but I have a Cinebench score at 4.5ghz that beats the 4.7 ghz stock score... no turbo on either... only difference besides core clocks is the cpu/nb being bumped from 2400mhz to 2600 mhz.... strange how that little bit makes such a difference on my system... but 2600 to 2700 doesn't seem to add near as much and for some reason I can't get it fully stable at less than 1.4v on the cpu/nb while 2600 takes only 1.25... thinking 2600 is sweet spot for me... maybe the 2700 isn't fully stable at 1.4v and it's that FX will find a way to run thing that was mentioned earlier lol....

Intel who?


Minotaurtoo is offline  
post #219 of 609 (permalink) Old 11-26-2017, 06:11 PM
New to Overclock.net
 
cssorkinman's Avatar
 
Join Date: Apr 2009
Posts: 9,287
Rep: 458 (Unique: 259)
Quote:
Originally Posted by Minotaurtoo View Post

Quote:
Originally Posted by gapottberg View Post

Lol...my quote looks as if instead of agreeing with someone I am being confrentational.

Anyways...i recently came up with a good analogy of how to explain the difference between FX and Hyperthreading. Admitedly stolen in part from a LTT video on the topic but expanded, but expanded some.

Imagine a candy bowl full of a mix of various types of candy. Hard candy, soft candy, big candy, small candy. This bowl represents a task the CPU needs to complete.

Now imagine a person being told to eat the candy as fast as they can. This person represents a CPU. However not all CPUs are created equal. And niether are people.

Let's first look at an intel CPU with Hyperthreading. Looking at a single core we find it has one pipeline for completing tasks...but two for schedualing them. The hyperthreading acts like 2 hands keeping the cpu mouth fes. This is essentially what hyperthreading does. It keeps the CPU fed with tasks to complete. Thus an intel CPU is like a single person with 1 mouth and 2 hands stuffing their face with every type of candy they can eat.

Every core an intel processor has adds a potential person to the task of cleaning out the bowl as long as its a big enough bowl to accomadate them all. Size of the bowl represents how well threaded the task is. A bigger bowl can fit more workers around it.

Now lets look at an AMD FX module.

The FX module is a wierd siamese twin looking person. This person has 2 heads, two mouths, and two hands. One hand can feed each mouth...but there is one problem. One of the two twins hates chocolate. They will not eat any candy with chocolate in it. They will however use their hand to help feed the other head any chocolate candies they happen to pick up. Any other candy is fine for them to eat themself. Chocolate candy reptesents floating point operations in our analogy. Since the Module has a shared floating point unit...the CPU sort of acts like it only has one mouth even though there are two in some cases.

You can see from this analogy that in many cases the twins will mow through a bowl of candy faster than a normal two handed person would because two mouths are better than one when it comes to eating quickly. The same is true for CPU tasks.

However this is only partially true, and for bowls with less chocolate candy in them specificly. Too much chocolate and we basicly behave like a hyperthreaded single core CPU. Two hands but only one mouth. That is still worst case scenario though, and is only completely true in very specific workloads. The fewer chocloate candies in the bowl, the more efficient the FX becomes when compared to a normal hyperthreaded core.

There is more too it than this, as the individual effeciency of the cores makes a difference too. If one of the people in our analogy has a wold record for eating the most buffalo wings in 5 min...then they might be better at getting through a bowl of candy too. IPC or instructions per clock are not really presnet in the analogy above but they do matter. In many cases an Intel has an edge here and is a more "effecient eater" so to speak.

It's still a good analogy that shows why the freaky siamese style FX module is indeed a true 4, 6, or 8 core processor...and how it differes from a hyperthreaded one in some curious ways that can given similar IPC... make it faster at some tasks.

I put a link to this in the OP... very interesting comparison... oh... I haven't decided if I should include it in the OP.. but I have a Cinebench score at 4.5ghz that beats the 4.7 ghz stock score... no turbo on either... only difference besides core clocks is the cpu/nb being bumped from 2400mhz to 2600 mhz.... strange how that little bit makes such a difference on my system... but 2600 to 2700 doesn't seem to add near as much and for some reason I can't get it fully stable at less than 1.4v on the cpu/nb while 2600 takes only 1.25... thinking 2600 is sweet spot for me... maybe the 2700 isn't fully stable at 1.4v and it's that FX will find a way to run thing that was mentioned earlier lol....

What is your mem freq when you are trying to run 2700mhz nb? It's pretty hard to get 2700 fully stable with ram running faster than 2133 on my ASUS boards.

FX8370E 5839mhz MSI 990FXA GD80 - custom water http://valid.x86.fr/3jk1vz
FX - 9370 @ 5740mhz MSI 990FXA GD-80 with an H-100 proof.gifhttp://valid.canardpc.com/s04jcj
I like MSI motherboards and this is why smile.gif
8350 @ 5.2 ghz on a stock cooler proof.gif PM me! smile.gif
cssorkinman is offline  
post #220 of 609 (permalink) Old 11-27-2017, 01:22 AM - Thread Starter
Useful idiot
 
Minotaurtoo's Avatar
 
Join Date: Jun 2013
Location: Florence, AL
Posts: 2,342
Rep: 80 (Unique: 46)
Quote:
Originally Posted by cssorkinman View Post

What is your mem freq when you are trying to run 2700mhz nb? It's pretty hard to get 2700 fully stable with ram running faster than 2133 on my ASUS boards.
2400mhz on the memory

Intel who?


Minotaurtoo is offline  
Reply

Quick Reply
Message:
Options

Register Now

In order to be able to post messages on the Overclock.net - An Overclocking Community forums, you must first register.
Please enter your desired user name, your email address and other required details in the form below.
User Name:
If you do not want to register, fill this field only and the name will be used as user name for your post.
Password
Please enter a password for your user account. Note that passwords are case-sensitive.
Password:
Confirm Password:
Email Address
Please enter a valid email address for yourself.
Email Address:

Log-in



Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)
 
Thread Tools
Show Printable Version Show Printable Version
Email this Page Email this Page


Forum Jump: 

Posting Rules  
You may post new threads
You may post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are Off
Refbacks are Off