Vectors: use __AVX512ER__ instead of __knl__
Vectors: Add helper function for floating point comparison
Vectors: Allow disabling AVX512 instructions
Vectors: Provide missing function vec_store_partial_prepare_fixed
Vectors: Implement kpown
Vectors: Correct function name
Vectors: Improve efficiency of logical operations on AVX512
Vectors: Clean up mask handling
Vectors: Improve efficiency of masked moves and stores
Vectors: Correct error in AVX512 sqrt implementation
sqrt(0) led to nan.
Vectors: Insert some empty lines to make code more readable
Vectors: Add operator<<(ostream&, ...) for C++ vector type
Vectors: Add partial aligned store operations for C++ vector class
Vectors: Add C++ class for boolean vectors (i.e. mask vectors)
Vectors: Use "void" for unused template type
Vectors: Add namespace end comments
Vectors: Correct return type of any()
Vectors: Small change to masked store operations
Vectors: Implement masked load operations
Vectors: Add function to convert store masks to boolean vectors
Vectors: Implement a few missing k4pown functions
This pull request mostly add better support for the AVX512 instructions found in KNL and modern Intel Xeon / Core iN CPUs.
There is one bugfix commit “Correct error in AVX512 sqrt implemention” which is important for those architectures (eg to compute sqrt(detg)).
Vectors: Add helper function for floating point comparison
Vectors: Allow disabling AVX512 instructions
Vectors: Provide missing function vec_store_partial_prepare_fixed
Vectors: Implement kpown
Vectors: Correct function name
Vectors: Improve efficiency of logical operations on AVX512
Vectors: Clean up mask handling
Vectors: Improve efficiency of masked moves and stores
Vectors: Correct error in AVX512 sqrt implementation
sqrt(0) led to nan.
Vectors: Insert some empty lines to make code more readable
Vectors: Add operator<<(ostream&, ...) for C++ vector type
Vectors: Add partial aligned store operations for C++ vector class
Vectors: Add C++ class for boolean vectors (i.e. mask vectors)
Vectors: Use "void" for unused template type
Vectors: Add namespace end comments
Vectors: Correct return type of any()
Vectors: Small change to masked store operations
Vectors: Implement masked load operations
Vectors: Add function to convert store masks to boolean vectors
Vectors: Implement a few missing k4pown functions
This pull request mostly add better support for the AVX512 instructions found in KNL and modern Intel Xeon / Core iN CPUs.
There is one bugfix commit “Correct error in AVX512 sqrt implemention” which is important for those architectures (eg to compute sqrt(detg)).