[WIP] ggml-hexagon: convert f32 to f16 - fa opt part3 #19282
+75
−144
Conversation
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
…dant checks for FP32
… handling for unused elements
github-actions
bot
added
the
ggml
chraac
commented
Feb 3, 2026
| const uint8_t * q_ptr_vtcm = dma_queue_pop(dma).dst; | ||
| uint8_t * q_ptr_vtcm = dma_queue_pop(dma).dst; | ||
| if (is_q_fp32) { | ||
| hvx_copy_f16_f32_aa(q_ptr_vtcm, q_ptr_vtcm, DK); // inplace convert f32 to f16 |
Contributor
Author
There was a problem hiding this comment.
Pre-conversion to F16: Converted the row to F16 upfront to avoid repeated on-the-fly conversion in the code below.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Key changes
hvx_mad_f32_f16_aa_rx2) for FP16 inputs with separate scaling factors.Implementation Details
hvx_mad_f32_f16_aa_rx2: A /new HVX intrinsic wrapper allowing efficient accumulation of two FP16 vectors.Performance
TODO: Add benchmarks comparisons (e.g., token/s improvements on target hardware).