ballet: Add Reed-Solomon module #244
Merged
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
ptaffet-jump
force-pushed
the
ptaffet/reedsol
branch
2 times, most recently
from
9f4eb6c to
204b32a
Compare
ptaffet-jump
changed the title
ptaffet-jump
changed the title
ptaffet-jump
force-pushed
the
ptaffet/reedsol
branch
from
a129527 to
424039c
Compare
ptaffet-jump
force-pushed
the
ptaffet/simd_bytes
branch
2 times, most recently
from
d380bf9 to
3441519
Compare
ptaffet-jump
force-pushed
the
ptaffet/reedsol
branch
from
424039c to
330f549
Compare
ptaffet-jump
force-pushed
the
ptaffet/simd_bytes
branch
from
3441519 to
5dc640d
Compare
ptaffet-jump
force-pushed
the
ptaffet/reedsol
branch
from
330f549 to
63a8fd9
Compare
ptaffet-jump
force-pushed
the
ptaffet/reedsol
branch
2 times, most recently
from
60f93fb to
ab1620c
Compare
jumpsiegel
force-pushed
the
ptaffet/reedsol
branch
from
ab1620c to
81cf0c1
Compare
ptaffet-jump
force-pushed
the
ptaffet/reedsol
branch
from
81cf0c1 to
7ea7ca2
Compare
ptaffet-jump
force-pushed
the
ptaffet/reedsol
branch
from
7ea7ca2 to
e5d74c2
Compare
From review. Mostly cosmetic stuff. The most significant change is the Galois field math implementation can be selected at compile time independent of build target. As part of this, fd_reedsol_internal.h and fd_reedsol_pi.h were merged into an fd_reedsol_private.h. The rest is mostly naming tweaks, inclusion tweaks, macro robustness, error naming strerror functions and the like.
ptaffet-jump
force-pushed
the
ptaffet/reedsol
branch
from
5c2e0b7 to
6c4789e
Compare
mmcgee-jump
reviewed
Sep 11, 2023
| /* Include the constants in one central spot */ | ||
|
|
||
| #if FD_REEDSOL_ARITH_IMPL==0 | ||
| FD_IMPORT_BINARY( fd_reedsol_arith_consts_generic_mul, "src/ballet/reedsol/constants/generic_constants.bin" ); |
There was a problem hiding this comment.
Can you encode these dependencies into the Makefile
mmcgee-jump
approved these changes
Sep 11, 2023
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.
Adds high performance Reed-Solomon encoding and recovery, currently configured for up to 67 data shreds and 67 parity shreds (inclusive). Tuned for GFNI (~130 Gbps on the common 32/32 encoding case), but also relatively high performance on AVX2 (~50 Gbps for 32/32 encoding). Uses the
FD_HAS_GFNIflag. Depends on the SIMD changes in #250, so we probably want to merge that PR first.