Title: AMFE — SIMD-Ready Branchless Filtering for High-Volume Prime Generation

Intel® oneAPI Math Kernel Library

Ask questions and share information with other developers who use Intel® Math Kernel Library.

Title: AMFE — SIMD-Ready Branchless Filtering for High-Volume Prime Generation

5 Views

Hi Intel oneMKL team,

I developed AMFE, a lightweight branchless filtering layer for primality testing pipelines. It is designed to be SIMD-Ready and highly parallel.

Benchmark Results (10M RSA-grade candidates):
• ~33% rejection rate of composite candidates
• 2.2x speedup (4.25ms vs 10.43ms baseline)
• 1.88B candidates/sec throughput
• 0 false negatives

Technical Highlights:
• Branchless LUT (no runtime modulo/division)
• SIMD-Ready for AVX2/AVX-512
• Rust + Rayon (parallel execution)
• Production-ready, Dockerized

Technical PDF attached.

I'm looking for feedback from Intel performance engineers on:
1. SIMD/AVX2 optimization opportunities
2. Potential integration with Intel IPP Cryptography or oneMKL
3. Performance tuning for Xeon Scalable processors

Thank you for your time.

Best regards,
Azeddine Ennabati

120 KB

Link Copied

0 Replies

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.