leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 29 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 15:21:31 -05:00
committed by GitHub
co-authored by Pradeep Ramani
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
include/cutlass/fast_math.h
+5 -2
View File
@@ -187,7 +187,7 @@ CUTLASS_CONSTEXPR_IF_CXX17
value_t lcm(value_t a, value_t b) {
value_t temp = gcd(a, b);
return temp ? (cutlass::abs_for_integer(a) / temp * cutlass::abs_for_integer(b)) : 0;
return temp ? (cutlass::abs_for_integer(a) / temp * cutlass::abs_for_integer(b)) : value_t();
}
/**
@@ -207,8 +207,11 @@ template <typename value_t>
CUTLASS_HOST_DEVICE
constexpr
value_t lcm_cxx11(value_t a, value_t b) {
return gcd_cxx11(a, b) ? (cutlass::abs_for_integer(a) / gcd_cxx11(a, b) * cutlass::abs_for_integer(b)) : 0;
return gcd_cxx11(a, b) ? (cutlass::abs_for_integer(a) / gcd_cxx11(a, b) *
cutlass::abs_for_integer(b))
: value_t();
}
/// Returns the smallest value in the half-open range [a, a+b) that is a multiple of b
CUTLASS_HOST_DEVICE
CUTLASS_CONSTEXPR_IF_CXX17