Closed
Conversation
VectorDB Benchmark - Ready To Run
Post one of the command below. Only members with write access can trigger runs. Available Modes
Infrastructure
Both servers start on demand and are always terminated after the run — pass or fail. How Correctness Benchmarking Works
|
- Skip the post-build ndd symlink when the binary is already named 'ndd' to prevent a self-referential symlink on generic CPU builds - Add AVX2 SIMD paths for fp16↔fp32 vector conversion and scaled quantization, filling the gap between AVX-512 and scalar fallback - Refactor AVX-512 quantization block to use scoped variables and support runtime dispatch via NDD_RUNTIME_X86_DISPATCH
Introduces a new --x86 / USE_X86=ON build option for users without a specific SIMD target. Enables NDD_RUNTIME_X86_DISPATCH at configure time, produces the ndd-x86 binary, and documents the option in the install script help text, getting-started guide, and README.
|
Closing the PR for the time being, as multiple internal conditions need to be re-implemented for desired performance. Currently, the system and compiles runs in -x86, taking the baseline as avx2 for missing avx512 flags, causing a dip in performance. |
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pull Request
Summary
This PR removes the need to be extremely rigid in the way compiation for different CPU capabilities is done. AVX2 AVX512 etc. A good way to do things is to be able to compile the code in a generic fashion and enable higher capabilities based on the CPU we are running on currently.
Type of Change