I had some come down. Killing my PCs.
I'm only allowing them to run on PCs I'm not using as it makes everything drop to an unbearable crawl

Uh, that's strange.
How many concurrent gpu wus are you crunching? What is your gpu? Entry level??

I'm running an Nvidia 2080ti. The GPU-Z program indicates that a single workload uses an average of 7% of my GPU and the GPU is frequently IDLE. When I run two workloads simultaneously, the GPU load goes to 23% average.

The early workloads took 40-60 seconds instead of 1 hour like the CPU and generated 5 to 10 times the credits. WorldCommunityGrid uses COMPUTE time to rank users.

I imagine that the project will make some adjustments/improvements over time. Since the GPU version requires 100% of a CPU (for me), they can use VTUNE to optimze that half of the program.

I had some come down. Killing my PCs.
I'm only allowing them to run on PCs I'm not using as it makes everything drop to an unbearable crawl

Uh, that's strange.
How many concurrent gpu wus are you crunching? What is your gpu? Entry level??

I'm running an Nvidia 2080ti. The GPU-Z program indicates that a single workload uses an average of 7% of my GPU and the GPU is frequently IDLE. When I run two workloads simultaneously, the GPU load goes to 23% average.

The early workloads took 40-60 seconds instead of 1 hour like the CPU and generated 5 to 10 times the credits. WorldCommunityGrid uses COMPUTE time to rank users.

I imagine that the project will make some adjustments/improvements over time. Since the GPU version requires 100% of a CPU (for me), they can use VTUNE to optimze that half of the program.

My gpu is at nearly idle until it gets a couple minutes into the task then it takes off. I use msiafterburner to monitor it.

I had some come down. Killing my PCs.
I'm only allowing them to run on PCs I'm not using as it makes everything drop to an unbearable crawl

Uh, that's strange.
How many concurrent gpu wus are you crunching? What is your gpu? Entry level??

The laptop has a Radeon RX460, the desktop an Nvidia GTX750.
2 GPU tasks run at a time on the 4-core laptop, just 1 on the 16-core desktop (don't know why). Both die a horrible death.

---

I had some come down. Killing my PCs.
I'm only allowing them to run on PCs I'm not using as it makes everything drop to an unbearable crawl

Uh, that's strange.
How many concurrent gpu wus are you crunching? What is your gpu? Entry level??

The laptop has a Radeon RX460, the desktop an Nvidia GTX750.
2 GPU tasks run at a time on the 4-core laptop, just 1 on the 16-core desktop (don't know why). Both die a horrible death.

I would think maybe memory as the 750 only has 1 maybe 2gb of ram while the 460 can have 4gb of ram on it

I had some come down. Killing my PCs.
I'm only allowing them to run on PCs I'm not using as it makes everything drop to an unbearable crawl

Uh, that's strange.
How many concurrent gpu wus are you crunching? What is your gpu? Entry level??

The laptop has a Radeon RX460, the desktop an Nvidia GTX750.
2 GPU tasks run at a time on the 4-core laptop, just 1 on the 16-core desktop (don't know why). Both die a horrible death.

I would think maybe memory as the 750 only has 1 maybe 2gb of ram while the 460 can have 4gb of ram on it

You're right - that explains it

Laptop: Coprocessors [2] AMD AMD Radeon R7 Graphics (4096MB) OpenCL: 2.0
Desktop: Coprocessors NVIDIA NVIDIA GeForce GTX 750 (2048MB) driver: 465.89 OpenCL: 3.0

---

I had some come down. Killing my PCs.
I'm only allowing them to run on PCs I'm not using as it makes everything drop to an unbearable crawl

Uh, that's strange.
How many concurrent gpu wus are you crunching? What is your gpu? Entry level??

The laptop has a Radeon RX460, the desktop an Nvidia GTX750.
2 GPU tasks run at a time on the 4-core laptop, just 1 on the 16-core desktop (don't know why). Both die a horrible death.

I would think maybe memory as the 750 only has 1 maybe 2gb of ram while the 460 can have 4gb of ram on it

You're right - that explains it

Laptop: Coprocessors [2] AMD AMD Radeon R7 Graphics (4096MB) OpenCL: 2.0
Desktop: Coprocessors NVIDIA NVIDIA GeForce GTX 750 (2048MB) driver: 465.89 OpenCL: 3.0

WOO HOO!!!
I have a stack of 70Ti gpu's in storage right now that only have 1gb of ram and 1 750Ti that has 2 gb of ram also in storage. I was going to setup a mining rig and even had it built and ready to run but the 3??? series gpu hit the market and there was no chance I could do anything constructive with it. I thought about crunching with them, and I still may, but not right now.

From developer site:
Revision 61646

Fix OpenCL build.

Missing include for function within #ifdefs

---

Another interesting project: OpenMM+Pytorch+Gpu

---

Nice news ... glad to be able to assit in fighting Corona ...

By the way: Any chance that we will get GPU appications, too ?

It's hard to see my CPU struggle at 89°C while my NVIDIA RTX 2080super is on half-astronomic diet, munching away Milkywa@home workunits in 2'30" each while crunching Folding@home in parallel.

Seneca
0=0

WCG has a working GPU app for Covid workunits... I'm running both WCG and Rosetta on my 3 crunchers

It's hard to see my CPU struggle at 89°C while my NVIDIA RTX 2080super is on half-astronomic diet, munching away Milkywa@home workunits in 2'30" each while crunching Folding@home in parallel.

How do you do this at the same time? Crunch Boinc and Folding@home I mean?

From Foldit:

Another reason is that the AlphaFold algorithm runs much less efficiently on common CPUs than on GPUs, which many players may not have. If you ran AlphaFold on your CPU at home, it might take an hour to get a result back. However, if we use our GPUs at IPD, the actual processing will go much faster. Since most of our recent Science puzzles have had fewer than 100 active players at a time, we think that players can get results faster if we process AlphaFold jobs on our server GPUs.

So, seems that some simulations may be done on our gpus (if they want).

---

Accellerating RosetTAFold

NVIDIA just released an open-source optimized implementation that uses 9x less memory and is up to 21x faster than the baseline official implementation.
SE(3)-Transformers are useful in dealing with problems with geometric symmetries, like small molecules processing, protein refinement, or point cloud applications. They can be part of larger drug discovery models, like RoseTTAFold and this replication of AlphaFold2

---

I took the liberty of citing it on GPUGrid.
I think they are more likely to send us stuff.

PS - Why don't you do SiDock? They might be interested for their new GPU app, or thereafter.
You could answer their questions better than I could.

---