OpenCL: Double the performance of shared AES-CBC-decrypt #5606
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
Ensure AES_cbc_decrypt() utilizes the parallel capability of the bitsliced AES code when more than one block is decrypted at once. For encryption this is not possible as the IV for block n is unknown until block n-1 has been encrypted. The potential boost is great (over 2x seen with AES-ECB) but none of our current formats use AES-CBC enough for this to make a significant difference, at least not with their (often small) test vectors. See openwall#5594.
streebog256crypt-opencl worked fine, but warnings were emitted.
Seen with PoCL 5.0+debian: "loop not unrolled: the optimizer was unable to perform the requested transformation; the transformation might be disabled or specified as part of an unsupported transformation ordering"
Change function declarations from "static" to "inline". The latter may be redefined in opencl_misc.h to suit the target. We should probably drop that potential (and possibly confusing) redefinition and define a DECLSPEC macro for this, like in hashcat, but that's another issue.
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Outdated suggestions cannot be applied.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.
Ensure AES_cbc_decrypt() utilizes the parallel capability of the bitsliced AES code when more than one block is decrypted at once. For encryption this is not possible as the IV for block n is unknown until block n-1 has been encrypted.
The potential boost is great (over 2x seen with AES-ECB) but none of our current formats use AES-CBC enough for this to make a significant difference, at least not with their (often small) test vectors.
See #5594.
Also a few commits that gets rid of OpenCL build warnings.