• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

AMD vs. Intel Stress test at Toms

There are about 3 threads dealing with this between here and the general hardware forum....

The P4 EE will do better with these 4 cpu task due to hyperthreading and the OS scheduler seeing the EE chips as having 4 cores.....The results are not surprising.....What would be interesting is if Toms would turn off the encoding and see how the INtel chip would use those cycles for the 3 remaining apps....There is possibly 20% being dedicated to the encoding that could help in the gaming and lame encoding...I doubt it would have helped in winrar where AMDs have the prowess....I would imagine that 20% would somehow be spread throughout all of the benches which would likely mean the X2 would still have the overall lead in 2 or 3 of the test....


One needs to ask themselves is this the type of multitasking one would do???

Also if they placed the encoding in the foreground perhaps and the lame encoding or winrar in the background the thread priorities would have perhaps been scheduled differently and the Divx test could have been closer, but likely that app that was thrown to the background will get the shaft and very little cpu cycles...either way that 4th test was always going to be Intels....

Also remember this is only the EE models and the 840, 830 and 820 normal line minus the HT will not see this and hit the same wall AMD is with 4 cpu intensive apps....
 
1) Duive, GK defaults setting priority to lower than normal (I think whatever level is directly below normal priority) hence the encoding getting hardly any time.
2) clarkey01, see above, it's an OS scheduler thing that's 100% THG fault for not bothering to set up the test properly.
3) Mods, can this be combined with the other thread, or locked?
 
people who mulitask. You could be encoding a new MP3 collection, rendering something, and surfing the web with about 15-20 panes/tabs open at once. A normal P.C. would be brought to its knees by such activity, yet a dual core would handle it pretty well.

Plus, there's always games + something else.
 
Is it me or is that review really hard to read?

Are all of those programs running at once? If so it's clear there's a problem with the AMD rig ignoring the DIVX encoding.

Edit: Oh my mistake, for some reason I thought it was a dual cpu dual core rig, not a single dual core rig. Probably the background of the monitor saying in large font, "2 cpu" It's almost as if they are intentionally making the review hard to read.
 
^^^ If you have the cash to have a dedicated encoding computer, Go Intel all the way. For poor 'ol me, on the other hand...
 
Just from the performance numbers, AMD seems to have the advantage, but remember what happens when you throw heat generation and power consumption back into the mix people? Heavy AMD advantage.

Of course, Intel has a significant price advantage, but when you factor in the cost of the required new motherboard, it's really not that much cheaper.
 
Originally posted by: zendari
Who the hell does 4 CPU intensive apps at a time?

Me, after I get my dual-core opterons, or 4-core opters (06 Q1) I haven;t found a way to kill it yet even with 4, but I can try !!
 
Well, the Intel box just re-booted again 13 minutes ago, but instead of going to 4 re-boots, it went down to 1 !!!!
 
Originally posted by: Markfw900
Well, the Intel box just re-booted again 13 minutes ago, but instead of going to 4 re-boots, it went down to 1 !!!!
88888888888888888888

I saw this note they ran the Intel with out the CPU fan for some time right off the bat. Would that wreck a CPU? I can not see that as the thing should not boot without the fan on the fan jumper. That is a weird note on the temperature chart for the Intel.
 
The number or reboots shown must be only for a specific amount of time not all time. Maybe it's # of reboots for a 24 hour period?
 
Actually I believe reboots is at 4 for the intel system now. Earlier in the day it showed 3 reboots, but it was reset to 1 during the last reboot.

 
"Swapping hardware right in the middle of a stability/stress test totally invalidates the test doesn't it?"

only at THG do they do stuff like that.... (note they don't even mention it)
 
That test is completely useless... 0 reboots, and both have been up and running for 9 hours and 12 minutes? Leave it to THG to fvck up something as simple as test of uptime.
 
Back
Top