Fixed issues with LibDevice integration. #784
Merged
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Outdated suggestions cannot be applied.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.
Fixes #781.
The issue with JN is that we are generating the wrong NVVM/LLVM code, used for extracting the PTX. It does not support the .NET type names of
int
,long
,uint
andulong
. Instead, we use the typesi32
andi64
.Upon further testing, also discovered an issue with
Half
type. The generated PTX uses theb32
register, and the NVVM code uses thei16
type.@m4rs-mt I have based this commit on the ILGPU v1.1.0 tag, in case we wanted to do create an ILGPU v1.1.1 patch release.