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

v4.2 release. (#2587)

Browse Source 
* Fix default cluster callback values to 1 to avoid profiler failure when these values are not set in command line.

* v4.2 release.
This commit is contained in:
Junkai-Wu
2025-08-23 06:11:24 +08:00
committed by GitHub
parent 11cad1f67b
commit a49a78ffef
351 changed files with 28182 additions and 2032 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
include/cute/numeric/arithmetic_tuple.hpp
View File

@@ -469,7 +469,9 @@ CUTE_HOST_DEVICE void print(ArithmeticTupleIterator<ArithTuple> const& iter)
template <class T, int... Ns>
CUTE_HOST_DEVICE void print(ScaledBasis<T,Ns...> const& e)
{
print(e.value()); (void(printf("@%d", Ns)), ...);
print(e.value());
// Param pack trick to print in reverse
[[maybe_unused]] int dummy; (dummy = ... = (void(printf("@%d", Ns)), 0));
}
#if !defined(__CUDACC_RTC__)
@@ -482,7 +484,9 @@ CUTE_HOST std::ostream& operator<<(std::ostream& os, ArithmeticTupleIterator<Ari
template <class T, int... Ns>
CUTE_HOST std::ostream& operator<<(std::ostream& os, ScaledBasis<T,Ns...> const& e)
{
os << e.value(); (void(os << "@" << Ns), ...);
os << e.value();
// Param pack trick to print in reverse
[[maybe_unused]] int dummy; (dummy = ... = (void(os << "@" << Ns),0));
return os;
}
#endif