LHC@home

sixtrack-production task with 243k seconds duration with Linux (451.07)!
is this a record?

On this one?
https://lhcathome.cern.ch/lhcathome/show_host_detail.php?hostid=10492037
It has only 2 GB RAM. ???
Did you run it on real hardware or a virtual host?

Well, you don't have an SSE2 version! I KNOW you should have....
I just wonder if this isn't some manifestation of a very old ifort
issue where Intel wouldn't use SSE2 on AMD hardware....but
since this is non-SSE version........there must be some kind of
emulation... memory required is about 64MB.

Eric.

sixtrack-production task with 243k seconds duration with Linux (451.07)!
is this a record?

---

My E-450 AMD CPU uses sse2.
Tullio

Eric,

with or without sse2, no problem,
we be happy to see that new sixtrack is on the way.

This WU say uploading, but don't do this:

https://lhcathome.cern.ch/lhcathome/result.php?resultid=153142268

Have someone more possibility to see whats wrong?

Sorry I can'h help with this. I'll pass it on.
(We have been having upload, even download, problems for quite
some time now, like years! I have made many suggestions but await a fix.)

Maybe you could turn on some file transfer debug options for the
event log and send it to eric.mcintosh@cern.ch. Eric.

This WU say uploading, but don't do this:

https://lhcathome.cern.ch/lhcathome/result.php?resultid=153142268

Have someone more possibility to see whats wrong?

---

This WU had 350k Duration-time and finished without sse2, sse3 or pni.

https://lhcathome.cern.ch/lhcathome/workunit.php?wuid=73276367

This WU had 350k Duration-time and finished without sse2, sse3 or pni.

https://lhcathome.cern.ch/lhcathome/workunit.php?wuid=73276367

I think I shall beat your record with a SixTrack task running on the HP laptop on Linux 64-bit, no sse2 or pni. 342k at 77%.
Tullio

Not yet.I made 349,883.83 s on my last completed and validated task. Next one is going to be late, so I shall abort it and start running SETI@home tasks in a competition sponsored by SETI Germany.
Tullio

So the competition is more important than the underlying science ?

Bill F

---

In October 1969 I took an oath to support and defend the Constitution of the United States against all enemies, foreign and domestic;
There was no expiration date.

I was an alpha tester at Test4Theory@home on invitation by dr.Segal. Now all LHC@home tasks except SixTrack fail on my three PCs, two Linux and one Windows 10. I have done my part in science, see "SU(n,1) representation for the harmonic oscillator", in Nuovo Cimento,Vol.51b,1967 pag. 195-198.
Tullio

I was glad to see that day when Boinc started and I got to leave Seti Classic and never return.

I have been here since 2004 24/7 and was the original alpha Test for Theory (T4T aka vLHC) member and the only one to do that from the beginning until the last day (and Einstein started a couple months later so I have been there since 2005)

With Alpha and CMS since day one and vLHC-dev

To me Cern is much more important than just wasting time and money looking for aliens and I doubt we will ever find a way to even fly across our galaxy let alone the billions of other galaxies......be surprised if we even land on Mars and do something since we never did anything on the Moon (we should have something built there on the Moon by now so we could make several trips and actually stay there and do more than dig some dirt and fly back)

---

Volunteer Mad Scientist For Life

SETI@home is pioneering in the use of GPU boards as coprocessors,like Einstein@home, which runs SETI@home post processing Nebula in its Atlas cluster. This is science too. The Piz Daint Swiss cluster in Lugano has risen to the third place in the Top500 list, after two Chinese clusters, by the use of nVidia GPU boards.
Tullio

18/08/2017 19:26:36 | LHC@home | update requested by user
18/08/2017 19:26:39 | LHC@home | Sending scheduler request: Requested by user.
18/08/2017 19:26:39 | LHC@home | Reporting 2 completed tasks
18/08/2017 19:26:39 | LHC@home | Requesting new tasks for CPU
18/08/2017 19:26:40 | LHC@home | Scheduler request completed: got 0 new tasks
18/08/2017 19:26:40 | LHC@home | No tasks sent
18/08/2017 19:26:40 | LHC@home | No tasks are available for SixTrack
18/08/2017 19:26:40 | LHC@home | No tasks are available for CMS Simulation
18/08/2017 19:26:40 | LHC@home | No tasks are available for LHCb Simulation
18/08/2017 19:26:40 | LHC@home | No tasks are available for Theory Simulation
18/08/2017 19:26:40 | LHC@home | No tasks are available for ATLAS Simulation
18/08/2017 19:26:40 | LHC@home | No tasks are available for ALICE Simulation
18/08/2017 19:26:40 | LHC@home | Message from server: VirtualBox is not installed

Beginning to run low across my boxes.

---

SETI@home is pioneering in the use of GPU boards as coprocessors,like Einstein@home, which runs SETI@home post processing Nebula in its Atlas cluster. This is science too. The Piz Daint Swiss cluster in Lugano has risen to the third place in the Top500 list, after two Chinese clusters, by the use of nVidia GPU boards.
Tullio

Yes that is why I have been with the Einstein Project for 13 years and have 9 GeForce cards that have been running for years doing GPU only tasks since they are 20 times faster than CPU tasks and how I got 318,000,000 credits there......can't do that with just CPU's.

I also built all of mine so I could set computers side by side to share the power supplies to run those GeForce cards so I didn't have to replace all of the power supplies and that way every other computer borrows power for just running the video cards with these 850watt power supplies.

And at the same time run all the different Cern alpha-beta tests and tasks.

So I sure don't need seti to test video cards or get in a GPU competition.

---

Volunteer Mad Scientist For Life

Not getting any LHC tasks.

LHC status shows a hosts up but SixTrack Unsent taks at 0.


21/08/2017 7:31:45 p.m. | LHC@home | update requested by user
21/08/2017 7:31:48 p.m. | LHC@home | Sending scheduler request: Requested by user.
21/08/2017 7:31:48 p.m. | LHC@home | Requesting new tasks for CPU
21/08/2017 7:31:52 p.m. | LHC@home | Scheduler request completed: got 0 new tasks
21/08/2017 7:31:52 p.m. | LHC@home | No tasks sent
21/08/2017 7:31:52 p.m. | LHC@home | No tasks are available for SixTrack

---

Not getting any LHC tasks.

LHC status shows a hosts up but SixTrack Unsent taks at 0.


21/08/2017 7:31:45 p.m. | LHC@home | update requested by user
21/08/2017 7:31:48 p.m. | LHC@home | Sending scheduler request: Requested by user.
21/08/2017 7:31:48 p.m. | LHC@home | Requesting new tasks for CPU
21/08/2017 7:31:52 p.m. | LHC@home | Scheduler request completed: got 0 new tasks
21/08/2017 7:31:52 p.m. | LHC@home | No tasks sent
21/08/2017 7:31:52 p.m. | LHC@home | No tasks are available for SixTrack

Many times the server can say there is plenty of certain tasks yet you can't get them because they could actually already be gone and waiting for a new batch.

That is when you see the entire Server Status Running

And as far as the SixTracks,those are all running on the many hosts we have here that only run SixTracks (since they probably are not fans of running the VirtualBox and all that goes with it)

And other tasks such as Theory tasks they can go even faster since the most are usually 200 and just myself I get over 50 every day all at once (like right now)

---

Volunteer Mad Scientist For Life

Well, you don't have an SSE2 version! I KNOW you should have....
I just wonder if this isn't some manifestation of a very old ifort
issue where Intel wouldn't use SSE2 on AMD hardware....but
since this is non-SSE version........there must be some kind of
emulation... memory required is about 64MB.

Eric.

Have at the moment for the new AMD Ryzen sse2 tasks with Windows x86 and not x64?
https://lhcathome.cern.ch/lhcathome/results.php?hostid=10548292

This WorkUnit's use x86 or i686-Linux on x64-Computer:
workspace1_hl13_phaseNoHL_31.24_30.34_oct_0_B1__51__s__62.31_60.32__8_10__5__15_1_sixvf_boinc12217_0

This WorkUnit's use x86 or i686-Linux on x64-Computer:
workspace1_hl13_phaseNoHL_31.24_30.34_oct_0_B1__51__s__62.31_60.32__8_10__5__15_1_sixvf_boinc12217_0

Might it be a simple re-assessment of the CPU performance with x86?