Index* for new types #461
Merged
Index* for new types #461
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
|
cc: @wickedfoo |
|
|
||
| for (long i = threadIdx.x; i < sliceSize; i += blockDim.x) { | ||
| // Torch indices are 1-based (hence the +1) | ||
| base[i * sliceStride] = (float) i + 1.0f; | ||
| base[i * sliceStride] = (long) i + 1; |
There was a problem hiding this comment.
you can remove the (long), it's already long
|
I think it looks good to me, besides the topk issues (it won't work for some tensors with more than 2^31 - 1 elements). should add an assertion to topk that you aren't calling it on a tensor where the slice size that you are top-k-ing is > 2^31 - 1 elements. (also sorry, github notifications have been going to my spam gmail for the past couple of months, hopefully i'll get them now) |
This was referenced Aug 12, 2016
|
fixes #463 |
|
fixes jcjohnson/densecap#26 and jcjohnson/densecap#22 |
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Outdated suggestions cannot be applied.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.
This makes the index* methods to use CudaLongTensor for indices.
Adds index* for all CUDA types (except indexAdd because need to implement atomicAdd for non float / int types)
Also changes the sort and topK API accordingly (but doesn't add new types in them yet)
Checklist before merging: