Write NULL to pointers before using them as a destination for device memory allocation. #2
Conversation
This file contains 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
…memory allocation. On a 64-bit architecture, compiling a GHC program that uses the cuda package with -O sometimes leaves garbage in the high 4 bytes of device pointers. The CUDA SDK samples seem to NULL out pointers before using them as a destination for device memory allocation, but I couldn't find any documentation that this is required. However, this patch solves all my crashing problems.
tmcdonell
added a commit
that referenced
this pull request
Sep 1, 2012
Write NULL to pointers before using them as a destination for device memory allocation.
|
huh, this is odd. I test on a 64-bit ubuntu box, but have not run into this issue before. What machine / SDK version are you running? |
|
64-bit Ubuntu 12.04 with the CUDA 4.2 SDK. It only showed up when I compiled with -O though. |
mrakgr
added a commit
to mrakgr/cuda
that referenced
this pull request
Dec 2, 2016
As before, I've modified the file by changing `CUDA_PATH` to `CUDA_PATH_V7_5` and pointed the library directories to the correct location. It might be worth checking out whether like on Windows, Linux also has `CUDA_PATH_V7_5` before accepting this fix.
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Outdated suggestions cannot be applied.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.
On a 64-bit architecture, compiling a GHC program that uses the cuda package
with -O sometimes leaves garbage in the high 4 bytes of device pointers. The
CUDA SDK samples seem to NULL out pointers before using them as a destination
for device memory allocation, but I couldn't find any documentation that this is
required. However, this patch solves all my crashing problems.