Correction for bufferSize methods #357
Open
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
tfalders
requested review from
jzuniga-amd,
cgmb,
qjojo,
EdDAzevedo,
jmachado-amd and
a team
as code owners
Comment on lines
+15
to
+18
| * hipsolverXorgbr_bufferSize, hipsolverXorgqr_bufferSize, hipsolverXorgtr_bufferSize, hipsolverXormqr_bufferSize, hipsolverXormtr_bufferSize, | ||
| hipsolverXgesvd_bufferSize, hipsolverXgesvdj_bufferSize, hipsolverXgesvdBatched_bufferSize, hipsolverXgesvdaStridedBatched_bufferSize, | ||
| hipsolverXsyevd_bufferSize, hipsolverXsyevdx_bufferSize, hipsolverXsyevj_bufferSize, hipsolverXsyevjBatched_bufferSize, | ||
| hipsolverXsygvd_bufferSize, hipsolverXsygvdx_bufferSize, hipsolverXsygvj_bufferSize, hipsolverXsytrd_bufferSize, hipsolverXsytrf_bufferSize |
There was a problem hiding this comment.
Suggested change
| * hipsolverXorgbr_bufferSize, hipsolverXorgqr_bufferSize, hipsolverXorgtr_bufferSize, hipsolverXormqr_bufferSize, hipsolverXormtr_bufferSize, | |
| hipsolverXgesvd_bufferSize, hipsolverXgesvdj_bufferSize, hipsolverXgesvdBatched_bufferSize, hipsolverXgesvdaStridedBatched_bufferSize, | |
| hipsolverXsyevd_bufferSize, hipsolverXsyevdx_bufferSize, hipsolverXsyevj_bufferSize, hipsolverXsyevjBatched_bufferSize, | |
| hipsolverXsygvd_bufferSize, hipsolverXsygvdx_bufferSize, hipsolverXsygvj_bufferSize, hipsolverXsytrd_bufferSize, hipsolverXsytrf_bufferSize | |
| * `hipsolverXorgbr_bufferSize`, `hipsolverXorgqr_bufferSize`, `hipsolverXorgtr_bufferSize`, `hipsolverXormqr_bufferSize`, `hipsolverXormtr_bufferSize`, | |
| `hipsolverXgesvd_bufferSize`, `hipsolverXgesvdj_bufferSize`, `hipsolverXgesvdBatched_bufferSize`, `hipsolverXgesvdaStridedBatched_bufferSize`, | |
| `hipsolverXsyevd_bufferSize`, `hipsolverXsyevdx_bufferSize`, `hipsolverXsyevj_bufferSize`, `hipsolverXsyevjBatched_bufferSize`, | |
| `hipsolverXsygvd_bufferSize`, `hipsolverXsygvdx_bufferSize`, `hipsolverXsygvj_bufferSize`, `hipsolverXsytrd_bufferSize`, and`hipsolverXsytrf_bufferSize` |
There was a problem hiding this comment.
It looks like none of the other functions in the changelog use this formatting. I'd prefer to remain consistent.
amd-jnovotny
approved these changes
Jan 22, 2025
cgmb
reviewed
Feb 25, 2025
A hacky way to do this is to get the value of bufferSize returned for two different precisions (e.g. since and double) and compare the results. Before this change, the values will be different. After this change, they should theoretically be the same, though I may need to verify that to be 100% sure. Aside from that, I'm not sure. |
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.
As pointed out by @EdDAzevedo, many bufferSize methods in cuSOLVER return
lworksuch that the workspace size (in bytes) issizeof(T) * lwork. With the rocSOLVER backend, these methods are currently outputtinglworksuch that the workspace is of sizelwork. This PR corrects this oversight and makes the rocSOLVER backend consistent with cuSOLVER.