Overclock.net › Forums › General Hardware › General Processor Discussions › Why doesn't AMD come up with?
New Posts  All Forums:Forum Nav:

Why doesn't AMD come up with? - Page 18

post #171 of 235
Quote:
Originally Posted by KBcobra View Post
seriously Geforce GTX grow up. People like you is why we cant have a serious debates with a can of trolls and bull **** being released.
Couldn't agree more. I almost gave up on this thread because of your needless trolling.
post #172 of 235
Quote:
Originally Posted by DuckieHo View Post
As already known.... HT performance gains heavily depends on the workload. HT benefits when there are large numbers of highly parallel threads that don't fill up the processor pipeline.


For example, Folding yields a significant PPD boost using HT.

http://vr-zone.com/articles/does-cor....html?doc=6160
thanks duckie, but really vantage?
its supposed to be a synthetic gaming benchmark, right?
and yet in the actual games listed HT yields a negative effect?

im having a hard time finding 30% massive improvement in the "many applications" referred to previously.
post #173 of 235
Quote:
Originally Posted by wuttz View Post
[ fahwiki ]

i thought it was going to be on average 30% increase in performance.

Did you check what CPUs are being reference there? Pentiums.
Also, the way the article is written.. I believe there are talking about running multiple instances of Folding. (i.e. 2 instance on a single core with HT)

Users today would uses a SMP Folding were 1 instance would run on multiple cores. Go check current PPD of SMP Folding. An i7@4GHz without HT provides about 7K PPD. With HT on, it provides 10K PPD.

Quote:
Originally Posted by Fear of Oneself View Post
I'll bump this again, this is why AMD doesn't have HT, you can also read this on the second page: http://www.overclock.net/9412202-post5.html
...and if you read the post directly after yours: http://www.overclock.net/9412210-post6.html

Your analogy fails because you forget that a processor is a pipeline of instruction units.
Edited by DuckieHo - 5/21/10 at 1:40pm
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
post #174 of 235
Quote:
In games - completely useless.
Well, generally, it's not all that gainful, but.....

I have a P4 on which my son games, Cobra 11 driving simulator. The GPU is a Quadra FX4400 (old card, does fine).....

On an X2 AMD with that card, the game runs great.

On the P4 it stalls, locks for 10 seconds, occasionally during play.

Turn HT on, and it runs JUST like it did on the X2.

Far from useless on the P4, in that one game.
DevBox
(14 items)
 
  
CPUMotherboardGraphicsRAM
955 BE @ 3.7 / 1.425v Typical 785G HD4200 / Radeon 4650 8 Gbytes 
Hard DriveOptical DriveOSMonitor
WD/Samsung/Seagate 3.5TBytes LG / HP Win7 64 Samsung 24" x 3 
KeyboardPowerCaseMouse
MS Split (15 Yr Old) PCP&C 750 Nice Trash Rescue Logitech Laser 
Mouse PadAudio
Wood panel Onboard thru Yamaha RX-V590 
  hide details  
Reply
DevBox
(14 items)
 
  
CPUMotherboardGraphicsRAM
955 BE @ 3.7 / 1.425v Typical 785G HD4200 / Radeon 4650 8 Gbytes 
Hard DriveOptical DriveOSMonitor
WD/Samsung/Seagate 3.5TBytes LG / HP Win7 64 Samsung 24" x 3 
KeyboardPowerCaseMouse
MS Split (15 Yr Old) PCP&C 750 Nice Trash Rescue Logitech Laser 
Mouse PadAudio
Wood panel Onboard thru Yamaha RX-V590 
  hide details  
Reply
post #175 of 235
Quote:
Originally Posted by Fear of Oneself View Post
No
No? so you don't get increased performance in folding and rendering so basically heavy apps?

says otherwise in the benchmarks.


Edited by ~Strawberry~ - 5/21/10 at 1:41pm
Choadasaurus-Rex
(13 items)
 
  
CPUMotherboardGraphicsRAM
i5 2500k Asus P8P67 Pro [on route] Gigabyte GTX 580 Mushkin Blackline 4GB 1600mhz 8-8-8-24 
Hard DriveOptical DriveOSMonitor
2X Samsung F3 HD502HJ 500GB .-.-.-.-.-.-.-.-.-.-.-. Windows 7 HP 64 bit Samsung Syncmaster Xl2370 
KeyboardPowerCaseMouse
Logitech G15 Corsair HX750w Corsair 800D Logitech G9 
  hide details  
Reply
Choadasaurus-Rex
(13 items)
 
  
CPUMotherboardGraphicsRAM
i5 2500k Asus P8P67 Pro [on route] Gigabyte GTX 580 Mushkin Blackline 4GB 1600mhz 8-8-8-24 
Hard DriveOptical DriveOSMonitor
2X Samsung F3 HD502HJ 500GB .-.-.-.-.-.-.-.-.-.-.-. Windows 7 HP 64 bit Samsung Syncmaster Xl2370 
KeyboardPowerCaseMouse
Logitech G15 Corsair HX750w Corsair 800D Logitech G9 
  hide details  
Reply
post #176 of 235
Quote:
Originally Posted by Geforce_GTX View Post
Maybe i would defend a i7 with its HT e-peen also sure a i7 is nice,but the i7 is just a overhyped revision of the Q series quad core with 2 extra fake ones,and costing $300+ for 1 actually better than a AMD,and $1,000 for the true hexa core.
first let me be clear,this is in no way me being an intel fanboy.
heres where i stand.AMD has got an awesome cpu with thuban
and ill state this one more time for you,i am getting one,because
i play with both brands,ok?so now thats out of the way...........

your above statement is so full of unintelligent speech i dont know
what to say.you have no idea about cpu architecture at all do you?
the i7 is in no way a revision of the Qseries cpu's.the i7 was the tock
meaning its a brand new architecture.
the Q series were MCM packages,where two dual core were stuck onto
the cpu package.
the i7 series are native quad cores.
    
CPUMotherboardGraphicsRAM
AMD A6-3650 8.32GHz so close Gigabyte A75M-UD2H sapphire HD3450 2x2GB DDR3-1600 
Hard DriveOptical DriveOSMonitor
western digital 320GB ASUS DRW-24B1ST DVD Microsoft Windows 7 Ultimate x64 ASUS LED 23.6" MS246H 
PowerCase
Corsair 400W cardboard box w/lots of holes for fans 
  hide details  
Reply
    
CPUMotherboardGraphicsRAM
AMD A6-3650 8.32GHz so close Gigabyte A75M-UD2H sapphire HD3450 2x2GB DDR3-1600 
Hard DriveOptical DriveOSMonitor
western digital 320GB ASUS DRW-24B1ST DVD Microsoft Windows 7 Ultimate x64 ASUS LED 23.6" MS246H 
PowerCase
Corsair 400W cardboard box w/lots of holes for fans 
  hide details  
Reply
post #177 of 235
Quote:
Originally Posted by radaja View Post
first let me be clear,this is in no way me being an intel fanboy.
heres where i stand.AMD has got an awesome cpu with thuban
and ill state this one more time for you,i am getting one,because
i play with both brands,ok?so now thats out of the way...........

your above statement is so full of unintelligent speech i dont know
what to say.you have no idea about cpu architecture at all do you?
the i7 is in no way a revision of the Qseries cpu's.the i7 was the tock
meaning its a brand new architecture.
the Q series were MCM packages,where two dual core were stuck onto
the cpu package.
the i7 series are native quad cores.
Thank god he's left the thread ... (this is the part where he comes back and trolls like he's never troll'd before)
Choadasaurus-Rex
(13 items)
 
  
CPUMotherboardGraphicsRAM
i5 2500k Asus P8P67 Pro [on route] Gigabyte GTX 580 Mushkin Blackline 4GB 1600mhz 8-8-8-24 
Hard DriveOptical DriveOSMonitor
2X Samsung F3 HD502HJ 500GB .-.-.-.-.-.-.-.-.-.-.-. Windows 7 HP 64 bit Samsung Syncmaster Xl2370 
KeyboardPowerCaseMouse
Logitech G15 Corsair HX750w Corsair 800D Logitech G9 
  hide details  
Reply
Choadasaurus-Rex
(13 items)
 
  
CPUMotherboardGraphicsRAM
i5 2500k Asus P8P67 Pro [on route] Gigabyte GTX 580 Mushkin Blackline 4GB 1600mhz 8-8-8-24 
Hard DriveOptical DriveOSMonitor
2X Samsung F3 HD502HJ 500GB .-.-.-.-.-.-.-.-.-.-.-. Windows 7 HP 64 bit Samsung Syncmaster Xl2370 
KeyboardPowerCaseMouse
Logitech G15 Corsair HX750w Corsair 800D Logitech G9 
  hide details  
Reply
post #178 of 235
Red Mist
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7-930 @ 3.6GHz 1.13v Asus Rampage III Extreme 2x EVGA GTX 260 (192 & 216) SuperClocked 6GB (3x2GB) Corsair Dominator GT 1600mhz 
Hard DriveOSMonitorPower
2x Samsung F3's 1TB RAID 0 Windows 7 Professional x64 Samsung LED BX2450 Corsair TX 750 
CaseMouse
Cooler Master HAF X Logitech G500 
  hide details  
Reply
Red Mist
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7-930 @ 3.6GHz 1.13v Asus Rampage III Extreme 2x EVGA GTX 260 (192 & 216) SuperClocked 6GB (3x2GB) Corsair Dominator GT 1600mhz 
Hard DriveOSMonitorPower
2x Samsung F3's 1TB RAID 0 Windows 7 Professional x64 Samsung LED BX2450 Corsair TX 750 
CaseMouse
Cooler Master HAF X Logitech G500 
  hide details  
Reply
post #179 of 235
Quote:
Originally Posted by DuckieHo View Post
An i7@4GHz without HT provides about 7K PPD. With HT on, it provides 10K PPD.
okay i need to see this, if anyone has a link.
of course for a fair comparison it has to be the same type of work-unit.

i appreciate the input.
post #180 of 235
Quote:
Originally Posted by wuttz View Post
An isolated case.

Exchange servers perform best with all kinds of optimizations that are not beneficial to most people. Go through the rest of mstechnet's optimizations, at least half of them are bad ideas for most uses.

I don't run an Exchange server, and I highly doubt more than a handful of people on OCN do either.

Quote:
SQL Server & Peoplesoft recommend HT be turned OFF: [ MS ]
Same story.

There are certainly a few cases where HT provides no help, or even hurts. They are very rare in desktop computing.

General usage, games, content creation, multimedia, archiving, multi-tasking, virtualization, and so on, and so on, are virtually never harmed by hyperthreading, and many of them are helped. Some benefit very significantly.

Quote:
[ advanced clustering ]

free "30% performance boost?" not in spec_int. only 15%.
compare, system 1: http://www.spec.org/cpu2006/results/...317-06800.html
system 2: http://www.spec.org/cpu2006/results/...317-06801.html
Linpack and SPEC are 100% synthetic. They exist as benchmarks only, with few to no equivalents that do real work.

Benchmarks like these are highly optimizied to load CPUs as much and as efficiently as possible.

Hyperthreading uses the gaps in an execution pipeline caused by inefficiencies. Without any gaps there is no lost performance to recoup.

I've pointed out in the past that the heat difference between HT on and off in LinX is no where near as extreme as with other stress tests. I've also used things like Perfmon to show how many instructions were retired by both programs. Linpack is a very efficient program, one should not expect much of a benefit from HT. The vast majority of real programs are not as efficient as Linpack. If everyone goes back to hand tuning everything in assembly language, then things might be different. However, this is very unlikely to happen.

Images from a test I did 18 months ago on my X3350:





See the difference? IBT (a linpack test) has almost double the IPC of Prime95, on the exact same setup. It's simply written to do more work. It leaves very little unused. Prime95, more efficient than most programs out there (and one that is part of a real distributed computing project), is a very different story.

Quote:
Originally Posted by wuttz View Post
i'd like to see what apps have a 30% performance boost with HT on compared to HT off.

Link to perfmon: http://www.cpuid.com/perfmonitor.php

thanks.
For me, Avidemux using x264 to encode videos often takes 30% less time to complete the same task with HT enabled.

Archiving with 7-zip is often 40-50% faster with HT enabled, on my system. Putting 13,000 files into a 40GB archive on ultra compression takes hours on my 4.2GHz i7. Turning HT on can save me 90-120 minutes, easily.

Doing anything CPU intensive (for my CPU) along with anything else goes
much faster with HT enabled.

If you want screen shots and specific results, I'll do some later today. I am not at my desktop right now. My laptop has hyperthreading, but I can't disable it in Acer's BIOS.

Quote:
Originally Posted by wuttz View Post
It's true.

Your examples of why HT isn't useful are either specialized and purely synthetic benchmarks, or are certain types of server loads that apply to almost no one here.

My examples of where HT is a big help, are things I, and many other people on OCN, do every day, to one degree or another.
Edited by Blameless - 5/21/10 at 2:02pm
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: General Processor Discussions
Overclock.net › Forums › General Hardware › General Processor Discussions › Why doesn't AMD come up with?