Patience is a virtue ;)

Generally I'm not very keen on advising people to spend their money on something which is a hobby for us, after all. BOINC is meant to use spare computation time, not to make people invest a fortune into new hardware ;)
However, if someone wants to buy I'll gladly try to tell them what makes sense from my point of view. Which occasionally is "don't buy".

MrS

---

Scanning for our furry friends since Jan 2002

Leaked specs and pricing from Toms hardware

GeForce GTX 480 : 480 SP, 700/1401/1848MHz core/shader/mem, 384-bit, 1536MB, 295W TDP, US$499

GeForce GTX 470 : 448 SP, 607/1215/1674MHz core/shader/mem, 320-bit, 1280MB, 225W TDP, US$349

Looks to me that the GTX470 is the better bang for the buck. Presumably the Tesla's got the fully functional chips (ie the full 512 SP), but no idea on pricing for them.

There is some mention of a GF104 chip to come out Q2 or Q3 2010 that is meant to be a lower-cost version (and presumably lower spec'ed) of the GF100 chip. It may be worthwhile waiting for these.

---

BOINC blog

ExtraTerrestrial Apes,

Patience is a virtue ;)

Generally I'm not very keen on advising people to spend their money on something which is a hobby for us, after all. BOINC is meant to use spare computation time, not to make people invest a fortune into new hardware ;)
However, if someone wants to buy I'll gladly try to tell them what makes sense from my point of view. Which occasionally is "don't buy".

MrS

100% agree, man :-) The onl thing - I built my rigs for BOINC :-) Otherwise I do not need that powerful PCs :-)

MarkJ
agree about GTX470. It's just a little bit less powerful, but pricewise is OK for.

But me personally (if Fermi is really good) will wait for GTX495 to appear somewhere Q2 or early Q3 this year

---

Name p14-IBUCH_chall_pYEEI_100301-26-40-RND0782_0
Workunit 1302269
Created 29 Mar 2010 1:18:10 UTC
Sent 29 Mar 2010 1:18:53 UTC
Received 29 Mar 2010 7:17:30 UTC
Server state Over
Outcome Success
Client state Done
Exit status 0 (0x0)
Computer ID 67855
Report deadline 3 Apr 2010 1:18:53 UTC
Run time 19101.678711
CPU time 4336.531
stderr out

<core_client_version>6.10.18</core_client_version>
<![CDATA[
<stderr_txt>
# Using CUDA device 0
# There is 1 device supporting CUDA
# Device 0: "GeForce GTX 480"
# Clock rate: 0.81 GHz
# Total amount of global memory: 1576468480 bytes
# Number of multiprocessors: 15
# Number of cores: 120
MDIO ERROR: cannot open file "restart.coor"
# Using CUDA device 0
# There is 1 device supporting CUDA
# Device 0: "GeForce GTX 480"
# Clock rate: 0.81 GHz
# Total amount of global memory: 1576468480 bytes
# Number of multiprocessors: 15
# Number of cores: 120
MDIO ERROR: cannot open file "restart.coor"
# Using CUDA device 0
# There is 1 device supporting CUDA
# Device 0: "GeForce GTX 480"
# Clock rate: 0.81 GHz
# Total amount of global memory: 1576468480 bytes
# Number of multiprocessors: 15
# Number of cores: 120
# Time per step: 30.239 ms
# Approximate elapsed time for entire WU: 18899.089 s
called boinc_finish

</stderr_txt>
]]>

Validate state Valid
Claimed credit 3977.21064814815
Granted credit 5965.81597222223
application version Full-atom molecular dynamics v6.71 (cuda23)

Name p14-IBUCH_chall_pYEEI_100301-26-40-RND0782_0
Workunit 1302269
Created 29 Mar 2010 1:18:10 UTC
Sent 29 Mar 2010 1:18:53 UTC
Received 29 Mar 2010 7:17:30 UTC
Server state Over
Outcome Success
Client state Done
Exit status 0 (0x0)
Computer ID 67855
Report deadline 3 Apr 2010 1:18:53 UTC
Run time 19101.678711
CPU time 4336.531
stderr out

<core_client_version>6.10.18</core_client_version>
<![CDATA[
<stderr_txt>
# Using CUDA device 0
# There is 1 device supporting CUDA
# Device 0: "GeForce GTX 480"
# Clock rate: 0.81 GHz
# Total amount of global memory: 1576468480 bytes
# Number of multiprocessors: 15
# Number of cores: 120
MDIO ERROR: cannot open file "restart.coor"
# Using CUDA device 0
# There is 1 device supporting CUDA
# Device 0: "GeForce GTX 480"
# Clock rate: 0.81 GHz
# Total amount of global memory: 1576468480 bytes
# Number of multiprocessors: 15
# Number of cores: 120
MDIO ERROR: cannot open file "restart.coor"
# Using CUDA device 0
# There is 1 device supporting CUDA
# Device 0: "GeForce GTX 480"
# Clock rate: 0.81 GHz
# Total amount of global memory: 1576468480 bytes
# Number of multiprocessors: 15
# Number of cores: 120
# Time per step: 30.239 ms
# Approximate elapsed time for entire WU: 18899.089 s
called boinc_finish

</stderr_txt>
]]>

Validate state Valid
Claimed credit 3977.21064814815
Granted credit 5965.81597222223
application version Full-atom molecular dynamics v6.71 (cuda23)

Where's the 480 cuda-cores?

---

BOINC blog

OMG LOL

---

POLISH NATIONAL TEAM - Join! Crunch! Win!

OMG LOL

And it's the only task they've got to run at all: All tasks for host 67855.

It cannot run ACEMD V2 tasks because of the way that app was compiled – for G200 cards, not Fermi cards!

Either the app cant see all the cores or it is just not reporting them.

It cannot run ACEMD V2 tasks because of the way that app was compiled – for G200 cards, not Fermi cards!

Either the app cant see all the cores or it is just not reporting them.

You have 197.33 driver and what version DLL's did you use? Perhaps the developers need to compile a cuda 3.0 app for you to see all the 480 cuda cores. But still if it only used a quarter of them and managed 30ms/step thats good.

---

BOINC blog

Where's the 480 cuda-cores?

It's just a reporting artifact. The device query code assumes 8 cores/sm (15.8=120). Fermis actually have 32 (15.32=480).

MJH

It cannot run ACEMD V2 tasks because of the way that app was compiled – for G200 cards, not Fermi cards!

That's right. We need to rebuild the ACEMD V2 and beta apps to include kernel code compiled for Fermi. The older app will work because it's built in a different way.

MJH

After compairing the IBUCH task that ran on the GTX480 to a similar task that ran on a GTX275 (240shaders), it really looks like the GTX480 was only running on 120 shaders. This would mean the GTX480 is 9% faster when only using 120 shaders! (anyone)?

So, if it could use all 480 shaders it could be 4.36 times as fast as a GTX275. This makes more sense than just a reporting error, given the cards architecture and would tie in well with other CUDA findings, such as folding@home (non-Boinc).

http://www.gpugrid.net/workunit.php?wuid=1298681

p14-IBUCH_chall_pYEEI_100301-26-40-RND0782 completed in 19,101sec (5h18min) claimed credit was 3,977, granted credit was 5,965.

p20-IBUCH_5Ans_pYEEI_100216-35-40-RND4473 completed on a GTX275 in 20868sec (5h48min) claimed 3,977 credit and was granted 5,965 credit.

Boinc (6.10.18) is not reading the card correctly, so some problems are stemming from that.

By the way it is CC2.0

skgiven,
not bad result with GTX480. I wonder to see results for recompiled apps. If it will that fast on 480 cores, I'm ready to change my mind and take GTX470 :-)

---

I think the techs are building an app for Fermi.
Fermi won't hit the shops until 12th Apr apparently, so that gives them time to work on it. The drivers need work too, but it was known in advance that there would be compatibility issues with the applications, and the drivers will no doubt have many revisions by NVidia over the next couple of years. As it's the drivers that are reporting the card details, a driver update might allow the card to use the correct amount of shaders on an ACEMD task. Obviously NVidia would want the drivers to work before general release, so it would be reasonable to expect the main driver related problems to be gone within a couple of weeks and the techs to have working apps fairly soon.



Source

I think the techs are building an app for Fermi.
Fermi won't hit the shops until 12th Apr apparently, so that gives them time to work on it. The drivers need work too, but it was known in advance that there would be compatibility issues with the applications, and the drivers will no doubt have many revisions by NVidia over the next couple of years. As it's the drivers that are reporting the card details, a driver update might allow the card to use the correct amount of shaders on an ACEMD task. Obviously NVidia would want the drivers to work before general release, so it would be reasonable to expect the main driver related problems to be gone within a couple of weeks and the techs to have working apps fairly soon.



Source

Here's hoping they will be fixed soon. If you search on the nvidia web site it doesn't list any drivers for the GTX470 or 480. Their driver page only goes up to the Geforce 300 family.

Have you tried a later BOINC version? 6.10.43 isn't too bad. It would be interesting to see what it reports for the card. I suspect that it too may need to be tweaked to correctly report things.

I was hassling my computer shop for pricing on the GTX470. They came back with $520 AUD. By my reckoning it should have been $380 AUD. I took the recommended price in USD and converted to AUD, so they are all trying to make big bucks at the moment. Too pricey for me.

---

BOINC blog

I was hassling my computer shop for pricing on the GTX470. They came back with $520 AUD. By my reckoning it should have been $380 AUD. I took the recommended price in USD and converted to AUD, so they are all trying to make big bucks at the moment. Too pricey for me.

AFAIK computer component are pretty pricy in Australia...

---

Where's the 480 cuda-cores?

It's just a reporting artifact. The device query code assumes 8 cores/sm (15.8=120). Fermis actually have 32 (15.32=480).

Regarding the shader detection issue I'd trust that MJH knows what he's talking about. So it shouldn't affect crunching speed and it's the GPU-Grid client which needs an update to report the correct number. It's neither the nVidia driver nor BOINC.

Furthermore it's clear that the actual crunching kernel needs to be updated. So I'm not sure if we can take any more from the current discussion than "don't rush to buy a Fermi for GPU-Grid". Which we couldn't anyway, even if we wanted to ;)

MrS

---

Scanning for our furry friends since Jan 2002

Have you tried a later BOINC version? 6.10.43 isn't too bad. It would be interesting to see what it reports for the card. I suspect that it too may need to be tweaked to correctly report things.

Apparently BOINC also assumes 8 shaders/processor. Compute capability 1.x cards have 8 shaders/processor and 2.x (Fermi reports compute capability of 2.0) have 32 shaders/processor. They are changing it now.

---

BOINC blog

UK Fermi online prices:

The GTX 480 will be from about £439 Including Vat (£375 to £381 ex vat).
The GTX 470 will be from about £299 Including Vat (£260 to £282 ex vat).

Gigabyte, Asus, Zotac and Gainward versions will be available from the 12th Apr.

So far only default clocks.

Just a digression. We had tried some Gainward GTX275 cards in the past and they did not work at all due to very poor cooling.

gdf