Gpu code #58
Open
Gpu code #58
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ded cuda and hip Makefile.ac
…rc/cuda/part_gpu.h
… not being found by the cuda library
… b to stop an error related to prototype overloading in dummy.c in src/cuda
… task.c and h queue.h and removed unused vars from runner_doiact_functions_hydro_gpu.h
…n main dir instead of src
…off because I have not made gpu tasks yet
…Not sure where the issue is
… tasks. Code now hangs so there must be some issue with task activation. problem for tomorrow!
|
This is the current state of the gpu code as implemented in the latest SWIFT version. It's not working properly yet as I think there is an issue with the GPU task activation (the code hangs before the first time step) and I need to implement a mechanism for creating deps for unpack tasks whic do not belong to a cell |
…ave been source of hanging bug. Not the case :(
… deps for unpack tasks. CPU version works perfectly but GPU code now hangs for some reason
…gpu and re-worked runner_main_clean.cu but code still hangs
…gpu and re-worked runner_main_clean.cu but code still hangs
…. Removed them all and code still hangs. Will copy back previous files innext commit
…ing to with not unskipping tasks properly. IFDEFs are totally correct and code does not hang when GPU code commented out
…ng. Code is doing something but I don't think it's actually progressing through time steps
…y be one function with if statement or some sort of variable over-loading to allow one function to work on 3 different data types. Something for another day!
…runner_main and pack and launch functions
…much clean of un-necessary allocations. There are some counters that need to be remove eventually as they are just for debugging and timing but left in for now
…w move onto sorting out recursion through sub_pair tasks.
…s about negative wait though when using recursion through pair tasks
…only have been done once for the top level task. Moved decrementing from the GPU launch function into runner_main so that s->waiting only decremented once per top level task
…npacking but I still need to sort out the counters for all eventualities
…rse->pack->offload->re-pack_if_necessary->offload_again_if_necessary
…(probably). Need to figure out how to get the locking/unlocking business to work properly though as I am now unpacking to a few unlocked cells
…resho.ym edited to allow recursion). The code now hangs trying to lock a pair of cells. Commented out the lock/unlock mechanism to confirm that code does not give correct results without locking cells
… pointers to cii_l and cjj_l are incorrect. Need to go through the algorithm again and double check I'm using the right indices and re-setting indices correctly
abouzied-nasar
force-pushed
the
gpu_code
branch
from
5ea6952 to
bcf3a54
Compare
…he new top_task->ci/cj arrays. Code now crashes when trying to recurse and add entries to the top_task->ci/cj arrays
abouzied-nasar
force-pushed
the
gpu_code
branch
from
bcf3a54 to
e3cf866
Compare
…till get same issue. It is not because of how I am allocating the arrays the issue is in how I am managing the counting and book keeping
…ys and still get same issue. It is not because of how I am allocating the arrays the issue is in how I am managing the counting and book keeping" This reverts commit 1625f17.
…same counter for recursion and for offload and unpacking. Seems a bit better but code still crashes trying toe write somewhere that doesn't exist in the counter arrays. The counter for n_leaves_found seems iffy as it has gone up to 30 with this configuration which seems way too much for what should be one level of recursion
…ting n_packed per top level task. Tested on 1 thread and code is running fine
…when run on multi threads. Also, since problem gets worse in parallel there's probz an issue with locking/unlocking DEBUG DEBUG DEBUG
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.