Add deployment flow on MAGIA V2 (upstream) - #59
Open
callme-sam wants to merge 316 commits into
Open
Conversation
…ve common dir at test top-dir
If compiled with optimization (-O1/2/3), the compiler prematurely reuses a scalar register to load the multiplier constant (COEF) before the second vector initialization (vfmv.v.f v8, %0) is completed. This register contention causes the vector accumulator v8 to be initialized with the coefficient value instead of ZERO, invalidating the reduction. Fixed by enforcing explicit vector register allocation.
Limitations: - no auto_pad - no ceil_mode (floor only) - no asymmetric padding - output length must be precomputed - stride must be multiple of power-of-two
Limitations: - no auto_pad - no ceil_mode (floor only) - no asymmetric padding - no storage order - no indices output - output length must be precomputed - stride must be multiple of power-of-two
Previously only 2
Previously only axis=-1 where supported
Accumulation in fp32 is under #ifdef and can be enabled with #define Implemented to test difference in accuracy
scalar version of sigmoid is under #ifdef and can be enabled with #define Implemented to test difference in accuracy
Both versions are under #ifdef and can be enabled with #define Implemented in an attempt to improve the accuracy of the yolo deployment
For better accuracy enable the scalar/wide sigmoid via #define in kernel task source file
The data translation unit only included <stdint.h>, so 'float16' was undefined there when compiling with GCC_MULTILIB
The public header was committed empty by mistake. GCC_PULP only warns and links anyway, but GCC_MULTILIB rejects it as an error
Contributor
Author
|
test results |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
No description provided.