leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

v3.9 (#2185)

Browse Source 
* v3.8 update x

* fix blackwell gg

* doc change

* doc change

* doc change

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
This commit is contained in:
Yujia Zhai
2025-03-21 01:52:23 -04:00
committed by GitHub
co-authored by yuzhai Haicheng Wu Haicheng Wu
parent 8c4d1dc47d
commit 62750a2b75
334 changed files with 91517 additions and 2656 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/cute/numeric/arithmetic_tuple.hpp
+11 -10
View File
@@ -370,12 +370,21 @@ safe_div(ScaledBasis<T,M> const& b, U const& u)
template <class T, int M, class U>
CUTE_HOST_DEVICE constexpr
auto
shape_div(ScaledBasis<T,M> const& b, U const& u)
ceil_div(ScaledBasis<T,M> const& b, U const& u)
{
auto t = shape_div(b.value(), u);
auto t = ceil_div(b.value(), u);
return ScaledBasis<decltype(t),M>{t};
}
template <class T, int N>
CUTE_HOST_DEVICE constexpr
auto
abs(ScaledBasis<T,N> const& e)
{
auto t = abs(e.value());
return ScaledBasis<decltype(t),N>{t};
}
// Equality
template <class T, int N, class U, int M>
CUTE_HOST_DEVICE constexpr
@@ -399,14 +408,6 @@ operator==(T const&, ScaledBasis<U,M> const&) {
return {};
}
// Abs
template <class T, int N>
CUTE_HOST_DEVICE constexpr
auto
abs(ScaledBasis<T,N> const& e) {
return ScaledBasis<decltype(abs(e.value())),N>{abs(e.value())};
}
// Multiplication
template <class A, class T, int N>
CUTE_HOST_DEVICE constexpr