Blockwise/Groupwise kernel improvement and programatic dependent launch enablement (#2161)

Co-authored-by: dePaul Miller <23461061+depaulmillz@users.noreply.github.com>
2025-03-10 14:36:11 -04:00
parent df18f5e4f5
commit 06e560d98a
3 changed files with 24 additions and 3 deletions
@@ -46,6 +46,11 @@
     defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 900 && defined(__CUDA_ARCH_FEAT_SM90_ALL))
    #define CUTLASS_GDC_ENABLED
  #endif
+  #if (defined(CUTLASS_ENABLE_GDC_FOR_SM100) && \
+     __CUDACC_VER_MAJOR__ >= 12 && \
+     defined(__CUDA_ARCH__) && __CUDA_ARCH__ == 1000 && defined(__CUDA_ARCH_FEAT_SM100_ALL))
+    #define CUTLASS_GDC_ENABLED
+  #endif
 #endif

 namespace cutlass {