CUTLASS 3.3.0 (#1167)

* Release 3.3.0

Adds support for mixed precision GEMMs On Hopper and Ampere
Adds support for < 16B aligned GEMMs on Hopper
Enhancements to EVT
Enhancements to Python interface
Enhancements to Sub-byte type handling in CuTe
Several other bug-fixes and performance improvements.

* minor doc update
This commit is contained in:
Pradeep Ramani
2023-11-02 08:09:05 -07:00
committed by GitHub
parent 922fb5108b
commit c008b4aea8
263 changed files with 16214 additions and 5008 deletions

View File

@ -41,13 +41,14 @@ namespace cute
template <class T, size_t N>
struct array
{
using value_type = T;
using element_type = T;
using value_type = remove_cv_t<T>;
using size_type = size_t;
using difference_type = ptrdiff_t;
using reference = value_type&;
using const_reference = const value_type&;
using pointer = value_type*;
using const_pointer = const value_type*;
using reference = element_type&;
using const_reference = const element_type&;
using pointer = element_type*;
using const_pointer = const element_type*;
using iterator = pointer;
using const_iterator = const_pointer;
@ -190,20 +191,21 @@ struct array
}
}
value_type __elems_[N > 0 ? N : 1];
element_type __elems_[N];
};
template <class T>
struct array<T, 0>
{
using value_type = T;
using element_type = T;
using value_type = remove_cv_t<T>;
using size_type = size_t;
using difference_type = ptrdiff_t;
using reference = value_type&;
using const_reference = const value_type&;
using pointer = value_type*;
using const_pointer = const value_type*;
using reference = element_type&;
using const_reference = const element_type&;
using pointer = element_type*;
using const_pointer = const element_type*;
using const_iterator = const_pointer;
using iterator = const_iterator;