[Einstein Toolkit] #765: NaNChecker should not reduce in local mode

List overview All Threads
Download

newer

older

[Einstein Toolkit] #753: prototype...

[Einstein Toolkit] #221:...

Einstein Toolkit

3 Mar 2012 3 Mar '12

9:08 a.m.

#765: NaNChecker should not reduce in local mode -----------------------------------+---------------------------------------- Reporter: eschnett | Owner: Type: defect | Status: new Priority: major | Milestone: Component: EinsteinToolkit thorn | Version: Keywords: | -----------------------------------+---------------------------------------- The NaNChecker calls reduction operations in local mode. This does not quite work if a process has more than one component of the grid, and deadlocks if processes have different numbers of components.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Show replies by date

Einstein Toolkit

3 Mar 3 Mar

9:41 a.m.

New subject: [Einstein Toolkit] #765: NaNChecker should not reduce in local mode

#765: NaNChecker should not reduce in local mode ------------------------------------+--------------------------------------- Reporter: eschnett | Owner: Type: defect | Status: new Priority: major | Milestone: Component: EinsteinToolkit thorn | Version: Resolution: | Keywords: ------------------------------------+---------------------------------------

Comment (by knarf):

I use it for simulations on one MPI processor but multiple levels and components there. What is the symptom I should see in that case? False positives?

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765#comment:1 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

9:52 a.m.

New subject: [Einstein Toolkit] #765: NaNChecker should not reduce in local mode

Comment (by eschnett):

In your case (same number of components on each process), the bit mask seems to be reset for each component.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765#comment:2 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

10:25 a.m.

New subject: [Einstein Toolkit] #765: NaNChecker should not reduce in local mode

Comment (by knarf):

That would mean potentially missing NaNs, right?

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765#comment:3 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

1:12 p.m.

New subject: [Einstein Toolkit] #765: NaNChecker should not reduce in local mode

Comment (by eschnett):

If there are nans, the NaNChecker will find some nans. However, the bit mask in the output nanmask may be inconsistent.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765#comment:4 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

20 Mar 20 Mar

11:16 a.m.

New subject: [Einstein Toolkit] #765: NaNChecker should not reduce in local mode

Comment (by rhaas):

The attached patch splits NaNCheckers operation into a local search routine followed by a per-level reduction. It does not use ENTER_LEVEL_MODE to not rely on Carpet's code (ie. to compile without Carpet present). Note that NaNChecker does not trigger the warning in CarpetReduce since it uses reducelocalscalar so does not reduce a grid function (it seems to end up in ReduceArrays inside of CarpetReduce). I attach a test for NaNChecker (using PUGH, which is likely fragily since it relies on IEEE floating point math to create NaNs on the grid).

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765#comment:5 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

11:16 a.m.

New subject: [Einstein Toolkit] #765: NaNChecker should not reduce in local mode

#765: NaNChecker should not reduce in local mode ------------------------------------+--------------------------------------- Reporter: eschnett | Owner: Type: defect | Status: review Priority: major | Milestone: Component: EinsteinToolkit thorn | Version: Resolution: | Keywords: ------------------------------------+--------------------------------------- Changes (by rhaas):

* status: new => review

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765#comment:6 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

12:17 p.m.

New subject: [Einstein Toolkit] #765: NaNChecker should not reduce in local mode

#765: NaNChecker should not reduce in local mode ------------------------------------+--------------------------------------- Reporter: eschnett | Owner: Type: defect | Status: review Priority: major | Milestone: Component: EinsteinToolkit thorn | Version: Resolution: | Keywords: ------------------------------------+---------------------------------------

Comment (by eschnett):

Please apply.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765#comment:7 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

12:34 p.m.

New subject: [Einstein Toolkit] #765: NaNChecker should not reduce in local mode

#765: NaNChecker should not reduce in local mode ------------------------------------+--------------------------------------- Reporter: eschnett | Owner: Type: defect | Status: review Priority: major | Milestone: Component: EinsteinToolkit thorn | Version: Resolution: | Keywords: ------------------------------------+---------------------------------------

Comment (by rhaas):

It's in cacutscode, I cannot apply it myself.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765#comment:8 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

Einstein Toolkit

26 Mar 26 Mar

10:18 p.m.

New subject: [Einstein Toolkit] #765: NaNChecker should not reduce in local mode

#765: NaNChecker should not reduce in local mode ------------------------------------+--------------------------------------- Reporter: eschnett | Owner: Type: defect | Status: closed Priority: major | Milestone: Component: EinsteinToolkit thorn | Version: Resolution: fixed | Keywords: ------------------------------------+--------------------------------------- Changes (by rhaas):

* status: review => closed * resolution: => fixed

Comment:

I knew there was something that I had outstanding to commit :-) Though I had thought it was the change to IOJpeg. Applied.

-- Ticket URL: https://trac.einsteintoolkit.org/ticket/765#comment:9 Einstein Toolkit http://einsteintoolkit.org The Einstein Toolkit

5309

Age (days ago)

5333

Last active (days ago)

trac@lists.einsteintoolkit.org

9 comments

1 participants

tags (0)

participants (1)

Einstein Toolkit