CUTLASS 3.6.0 (#1850)

* v3.6 * update changelog * update readme * fix typo * fixing typos * hopper gemm with weight prefetch --------- Co-authored-by: yuzhai <yuzhai@nvidia.com> Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
2024-10-09 15:33:27 -04:00
parent 0837a2a00a
commit cc3c29a81a
354 changed files with 105937 additions and 8197 deletions
@@ -35,6 +35,24 @@
 namespace cute
 {

+/// Generic add
+template <class C, class A, class B>
+CUTE_HOST_DEVICE constexpr
+void
+add(C& c, A const& a, B const& b)
+{
+  c = a + b;
+}
+
+/// Generic multiply
+template <class C, class A, class B>
+CUTE_HOST_DEVICE constexpr
+void
+mul(C& c, A const& a, B const& b)
+{
+  c = a * b;
+}
+
 /// Generic fused multiply-add
 template <class D, class A, class B, class C>
 CUTE_HOST_DEVICE constexpr