Merge remote-tracking branch 'origin/develop' into aosewski/ggemm_multi_d2

include/ck/tensor_operation/gpu/device/masking_specialization.hpp

@@ -53,7 +53,10 @@ struct MaskOutUpperTrianglePredicate
 template <typename MaskOutPredicate>
 struct C0MatrixMask_impl
 {
-    C0MatrixMask_impl(index_t NRaw) : NRaw_(NRaw), predicate_(MaskOutPredicate{}) {}
+    __host__ __device__ C0MatrixMask_impl(index_t NRaw)
+        : NRaw_(NRaw), predicate_(MaskOutPredicate{})
+    {
+    }
 
     __host__ __device__ constexpr bool IsNOutOfBound(/*index_t m, */ index_t n) const
     {

include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp

@@ -116,7 +116,7 @@ struct GridwiseBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
 
     using ThisThreadBlock = ThisThreadBlock<BlockSize>;
 
-    using GridwiseGemmPipe = GridwiseGemmPipeline_v1<NumGemm0KPrefetchStage>;
+    using GridwiseGemmPipe = GridwiseGemmPipeline_v1<NumGemm0KPrefetchStage, true, true>;
 
     // ck::Tuple<const D0DataType1*, const D0DataType2*, ...>
     static constexpr auto MakeD0sGridPointer()