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

CUTLASS 3.4.0 (#1286)

Browse Source 
* CUTLASS 3.4.0

* Update CHANGELOG.md

---------

Co-authored-by: Pradeep Ramani <prramani@nvidia.com>
This commit is contained in:
Pradeep Ramani
2023-12-29 12:21:31 -08:00
committed by GitHub
parent b7508e3379
commit 8236f30675
211 changed files with 11409 additions and 2763 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/cute/numeric/arithmetic_tuple.hpp
View File

@ -181,7 +181,7 @@ template <class T0, class T1, class... Ts>
CUTE_HOST_DEVICE constexpr
auto
make_inttuple_iter(T0 const& t0, T1 const& t1, Ts const&... ts) {
return make_tuple_iter(cute::make_tuple(t0, t1, ts...));
return make_inttuple_iter(cute::make_tuple(t0, t1, ts...));
}
//

2
include/cute/numeric/integral_constant.hpp
View File

@ -148,7 +148,9 @@ using _96 = Int<96>;
using _128 = Int<128>;
using _192 = Int<192>;
using _256 = Int<256>;
using _384 = Int<384>;
using _512 = Int<512>;
using _768 = Int<768>;
using _1024 = Int<1024>;
using _2048 = Int<2048>;
using _4096 = Int<4096>;

4
include/cute/numeric/math.hpp
View File

@ -97,7 +97,7 @@ template <class T, class U,
__CUTE_REQUIRES(is_std_integral<T>::value &&
is_std_integral<U>::value)>
CUTE_HOST_DEVICE constexpr
auto
cute::common_type_t<T, U>
gcd(T t, U u) {
while (true) {
if (t == 0) { return u; }
@ -112,7 +112,7 @@ template <class T, class U,
__CUTE_REQUIRES(is_std_integral<T>::value &&
is_std_integral<U>::value)>
CUTE_HOST_DEVICE constexpr
auto
cute::common_type_t<T, U>
lcm(T const& t, U const& u) {
return (t / gcd(t,u)) * u;
}