feat(ggml): vectorize row conversion functions #16587
Closed
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
added 4 commits
October 11, 2025 12:07
…e across SIMD registers and store in vector-sized chunks, while retaining the scalar tail for leftover elements and non-SIMD builds.
Vectorized the following functions in ggml.c for improved performance on x86 architectures: - ggml_fp16_to_fp32_row: using F16C intrinsics. - ggml_fp32_to_fp16_row: using F16C intrinsics. - ggml_bf16_to_fp32_row: using AVX2 and AVX512F intrinsics. This change follows the existing pattern of using direct SIMD intrinsic checks in this file.
github-actions
bot
added
the
ggml
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Outdated suggestions cannot be applied.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.
Vectorizes the following functions in ggml.c on x86:
ggml_fp16_to_fp32_row: using F16C intrinsics.
ggml_fp32_to_fp16_row: using F16C intrinsics.
ggml_bf16_to_fp32_row: using AVX2 and AVX512F intrinsics.