feat: GF-T standalone smul + sadd datapath cores (microsequencer) - #1863
Merged
Conversation
gft_smul.t27 (signed GF-T16 multiply) and gft_sadd.t27 (signed GF-T16 add) -- the two GF-T ops exposed as standalone modules (previously only helper fns). Tests 3/3 each PASS. Purpose: shared datapath cores for a microsequenced full 2-layer backprop. Instead of many multipliers (naive backprop ~22M, over the ~17M ceiling), an FSM reuses ONE smul + ONE sadd + gft_madd, feeding operands cycle-by-cycle -> tiny area. Forward once, intermediates in registers, updates sequenced. Refs #1764 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Contributor
Contributor
|
📓 NotebookLM Notebook linked to this PR
This notebook contains session context, decisions, and artifacts for this work. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
gft_smul.t27 (signed GF-T16 multiply) and gft_sadd.t27 (signed GF-T16 add) exposed as standalone modules. Tests 3/3 each. Purpose: shared datapath cores for a microsequenced full 2-layer backprop -- an FSM reuses ONE smul + ONE sadd + gft_madd (feeding operands cycle-by-cycle) instead of many multipliers, so the design fits under the ~17M ceiling. Forward once, intermediates in registers, updates sequenced. docs/NOW.md updated. Refs #1764