| AArch64 | |
| ppc64le | |
| s390x | |
| x86-64 |
- Fix issues with big.LITTLE CPUs e.g. Intel Alder Lake - Improved C API error messages - Improved C/C++ API documentation
- Update to primesieve-7.6
- Update to primesieve-11.1 - Vectorized pre-sieving algorithm using x64 SSE2 and ARM NEON - Added POPCNT algorithm for x64 & AArch64 - Fix -Wstrict-prototypes warnings
- Update to primesieve-11.0 - primesieve version now match libprimesieve version (.so version) - Added new primesieve::iterator::jump_to() method (C++ API) - Added new primesieve_jump_to() function (C API) - Mark primesieve_skipto() as deprecated - Fix use after free in primesieve::iterator::clear() - Fix use after free in primesieve_iterator_clear() - Fix potential memory leak in malloc_vector.hpp
- Update to primesieve-8.0 - Added multiarch support (POPCNT, BMI2, AVX512) for x64 CPUs - Generating an array (or vector) of primes is up to 20% faster - Main CMakeLists.txt has been split up into multiple modules - Improved documentation of C & C++ APIs
- Update to primesieve-7.9 - Reduced memory usage and faster initialization - Reduced branch mispredictions by up to 30% - Improved nth prime approximation - Increase max sieve array size to 8 KiB
- Update to primesieve-7.8 - Improved pre-sieving, up to 10% speedup - Improved primesieve::iterator, up to 15% speedup - C++ refactoring: get rid of using namespace std
- Update to primesieve-7.5
- Trim subjective parts from description.
- Fix review issues - Fix rpmlint warnings - Convert Fedora spec file to openSUSE format