Friday, October 24th 2008

AMD Responds to TechPowerUp Investigation, Issues Remedy

Earlier this week, when evaluating samples of the new Radeon HD 4830 GPU-based graphics card, W1zzard, who also authors the GPU-Z diagnostic utility, had found an anomaly with the stream processor (SP) counts on samples sent by AMD. The GPU could access only 560 out of its 640 SPs available. This affected the card's performance significantly, and TechPowerUp's findings were validated by several other reviewers with similar samples.

AMD on its part quickly followed up the issue with its engineering department, and released a video BIOS update that fixes the issue and makes available all the 640 SPs. AMD will be circulating this BIOS to all its press contacts and add-in-board (AIB) partners, to make sure the issue is isolated and fixed. The updated BIOS file can be downloaded from here. AMD also asserts that the issue isn't hardware related, and that updating the BIOS resolves the issue completely.
Add your own comment

45 Comments on AMD Responds to TechPowerUp Investigation, Issues Remedy

#1
theJesus
ulrik just gave me an idea. Would there be any way to "throttle" the amount of SP's enabled for extra power-saving during 2D mode?
Posted on Reply
#2
eidairaman1
how about you suggest that to wizzard for the next build of ATITool, if he will ever get around to deving that program anymore.
Posted on Reply
#3
theJesus
meh, I wouldn't suggest since I would never use it (not my house, i don't pay the electricity bill :laugh:)
Posted on Reply
#4
[I.R.A]_FBi
its teh idle clock of teh amd bios that cuases teh power savings, ask whizzinator
Posted on Reply
#5
Kreij
Senior Monkey Moderator
It's quite possible that AMD runs some additional tests to ensure that the review samples are working correctly (as opposed to doing partial batch testing for retail products).

It may be that they were using a variety of BIOS's to ensure that the shaders on the review cards were working correctly and accidentally sent the cards out in the final test configuration (minus one shader).

I really doubt it was any kind of deceipt on AMD's part as it simply does not make any logical sense for them to do that. Their quick response also points to a mistake, not a purposeful act.
Posted on Reply
#6
[I.R.A]_FBi
teh news post is a quote from AMD's press release
Posted on Reply
#7
iLLz
Awww man... You guys are defending AMD on this one, it makes me sick. If nVidia did this, you would be bashing the hell out of em. The point is they tried to get away with one and had a BIOS ready in case they got caught, that is why the "fix" came so quickly.:shadedshu
Posted on Reply
#8
flclisgreat
by: iLLz
Awww man... You guys are defending AMD on this one, it makes me sick. If nVidia did this, you would be bashing the hell out of em. The point is they tried to get away with one and had a BIOS ready in case they got caught, that is why the "fix" came so quickly.:shadedshu
it has been said and said again, the cards have the SP's on them already, it costs AMD/partners the same to produce the card with all of them working or not. so what possible benefit could it bring to BIOS disable some of them?
Posted on Reply
#9
Kreij
Senior Monkey Moderator
by: iLLz
Awww man... You guys are defending AMD on this one, it makes me sick. If nVidia did this, you would be bashing the hell out of em. The point is they tried to get away with one and had a BIOS ready in case they got caught, that is why the "fix" came so quickly.:shadedshu
Of course they had the correct BIOS availalbe. That is what the cards were supposed to be using. To mistakenly send out samples with the wrong (perhaps test) BIOS is an understandable mistake.

I've never bashed nVidia and have owned nVidia cards in the past and was pleased with them. It's true that at the moment I prefer ATI cards, but that is due to what I feel are more stable drivers and I also prefer their "once a month" driver releases (it's much less confusing than nVidia's method).

If nVidia release review samples with a similar issue, I would give them the benefit of the doubt until it was proved otherwise. I, personally, believe in "innocent until proven guilty".

Just my 2 cents.
Posted on Reply
#10
p_o_s_pc
F@H&WCG addict
kreij you are with ATI because you feel more stable drivers and i am with Nvidia because IMO i feel the drivers are more stable. I have seen so many threads about driver issues with ATI (as with Nvidia) that is what turned me away from ATI for now
Posted on Reply
#11
Kreij
Senior Monkey Moderator
by: p_o_s_pc
kreij you are with ATI because you feel more stable drivers and i am with Nvidia because IMO i feel the drivers are more stable. I have seen so many threads about driver issues with ATI (as with Nvidia) that is what turned me away from ATI for now
LOL ... that just goes to show you that we each perceive things differently.
I am thankful that there is an nVidia (and ATI) so that we as consumers have a choice, and the competition is good for us all.

We have seen what happens when there is no competition and a company justs sits back and does nothing new (no, I'm not naming any names ;) )
Posted on Reply
#12
roofsniper
by: iLLz
Awww man... You guys are defending AMD on this one, it makes me sick. If nVidia did this, you would be bashing the hell out of em. The point is they tried to get away with one and had a BIOS ready in case they got caught, that is why the "fix" came so quickly.:shadedshu
what? that doesn't even make any sense? why would amd release a card and pay money to have the sps on there but not use them? thats completely idiotic. thats like amd releasing a cpu that is supposed to clock at 3.0ghz but they clock it at 2.0ghz. because then people will get it and see that it sucks and go to intel. same with ati people might get it then return it and buy the nvidia offering. it would confuse me greatly as to why amd did this on purpose. especialy when they send the same exact versions to reviewers who should the performance of the card. and ontop of that what are the chances of every single person that reviews and buys the card to think that it has the correct number of sps? gpuz shows the sps right there and everyone knows what they are getting. i don't understand why anyone could possibly think that amd did this on purpose. to me it just seems like people wanting to start something to bash amd. :mad:
Posted on Reply
#13
Steevo
Nvidia has been called out on things, often. Such as the Crysis driver tweaks, and the 16bit vs 24bit. None of their cards untill the late 8800 series had the true precision ATI did.



ATI made a mistake, not overpromising hardware and underdelivering, but with a faulty BIOS, perhaps the man in charge of it placed a wrong character in the BIOS. What this does tell us is that a BIOS hack could be possible.
Posted on Reply
#14
roofsniper
by: Steevo
Nvidia has been called out on things, often. Such as the Crysis driver tweaks, and the 16bit vs 24bit. None of their cards untill the late 8800 series had the true precision ATI did.



ATI made a mistake, not overpromising hardware and underdelivering, but with a faulty BIOS, perhaps the man in charge of it placed a wrong character in the BIOS. What this does tell us is that a BIOS hack could be possible.
yea but nvidia was rigging things and this is a mistake that hurts the company. which just makes me so clueless as to how people can actualy think that amd is trying to pull a fast one when in no way at all it helps them.
Posted on Reply
#15
Steevo
read
comprehend
post
Posted on Reply
#16
btarunr
Editor & Senior Moderator
Just to add, AMD loses nothing by selling HD 4830 with its proper 640 SPs, just as they're not going to be upping profits/cutting mfg costs by cutting the SP count. This was an accident, it happened to be spotted on early, and AMD released a fix within 36 hours. Please don't make this a "if it were NVIDIA" discussion, don't play fortune-teller. Back to topic.
Posted on Reply
#17
krisna159
competition is good for market but cheating not included,thats illegal,i n this care indicated to "that",so let see who is right,who is wrong,lets wait n see
Posted on Reply
#18
erb
Some guy on newegg posted a review saying he unlocked the 800 shaders. I noticed it when I was purchasing the card last night. He doesn't say how he did it though of course, just says google to find out. I did that, but I didn't find anything. Anyone else better at googling things want to give it a shot?
Posted on Reply
#19
btarunr
Editor & Senior Moderator
He's lying. You can't bring 800 SPs for a HD 4830 by means of any softmod/bios. A HD 4830 is a RV770 with two ALU clusters (160 SPs) disabled by a physical method, not masked. After physically disabling the ALU clusters, they accordingly give out the BIOS. Some of the cards AMD sent out had 2 clusters disabled physically, but tables for three clusters were missing from the BIOS...hence the 560 SP HD 4830 anomaly. A simple BIOS fix solved, and enabled the extra ALU cluster that got disabled accidentally.
Posted on Reply
#20
thoughtdisorder
Nice job W1ZZ and nice job AMD! I'd say that upped the "stock" of TPU with AMD. :toast:
Posted on Reply
Add your own comment