Skip to content

Latest commit

 

History

History
60 lines (52 loc) · 3.24 KB

CHANGES.md

File metadata and controls

60 lines (52 loc) · 3.24 KB

Changes

Version 1.2.4

  • Adds experimental HEXL-FPGA compatibility for dyadic multiply and key switch (intel#109)
  • Adds vcpkg example of how to use previous hexl versions (intel#103)
  • Adds benchmarking montgomery multiplication (intel#94)
  • Moves to compiling with minimum C++ 17
  • Updates to documentation

Version 1.2.3

  • Fix to EltwiseReduceMod on AVX512-DQ processors (intel#86)
  • Update minimum CMake version to 3.13
  • Fixes 3rd-party dependency commits (intel#85)

Version 1.2.2

  • Fixes Barrett reduce native benchmark (intel#65)
  • Fixes 32 bit invntt (intel#73)
  • Fixes CMake 3.13 compilation (intel#67)
  • Added information of HElib integration to README (intel#63)
  • Added random number generator which generates a vector of specified size with random values drawn uniformly from [0, modulus) (intel#62)
  • Added random input values for benchmarks (intel#66)
  • Uses Generalized Barrett Reduction algorithm for EltwiseMultMod (intel#68)
  • Avoids memcpy operations on NTT (intel#72)
  • Added performance tips to README (intel#74)
  • Improves performance of Barrett Reduction (intel#75)

Version 1.2.1

Version 1.2.0

  • Large performance improvement in large (N >= 16384) AVX512 NTTs via recursive implementations
  • Slight performance improvements in AVX512IFMA NTT
  • Slight performance improvements in element-wise modular multiplication
  • Implement optimized AVX512DQ NTT for moduli < 32 bits
  • Expands public API to include number theory, NTT twiddle factors
  • Remove HEXL_DEBUG and HEXL_EXPORT options. The behavior now is to always export the cmake configuration files, and HEXL_DEBUG is enabled iff the CMAKE_BUILD_TYPE=Debug
  • Added pkgconfig support

Version 1.1.1

  • Fix Google benchmark branch to point to "main" instead of "master"

Version 1.1.0

  • Added vector-vector and vector-scalar EltwiseSubMod
  • Added vector-scalar version of EltwiseAddMod
  • Added generic 128-bit division for Windows build
  • Documentation hosted on a separate branch
  • Enabled custom allocator for NTT class
  • Fixed argument order in EltwiseReduceMod
  • Fixed build warnings on Windows and Mac

Version 1.0.1

  • Removed intel- prefix from headers and library name
  • Fixed CMake variables from 3rd party libraries from leaking
  • Fixed warnings when HEXL_DEBUG=ON