Merge branch 'develop' of...

Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into navi3x_mD_batchedGEMM_GroupConvFwd

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

@@ -185,9 +185,7 @@ struct GridwiseSparseEmbeddingsForwardLayernorm
                         },
                         Number<NumEmbeddings>{});
                     auto out_data_refs = generate_tie(
-                        [&](auto output_index_) -> auto& {
-                            return acc_thread_buf(Number<register_offset>{});
-                        },
+                        [&](auto) -> auto& { return acc_thread_buf(Number<register_offset>{}); },
                         Number<1>{});
                     unpack2(emb_elementwise_op, out_data_refs, in_data_refs);
                 });

test/grouped_gemm/grouped_gemm_fp16.cpp

@@ -2,6 +2,7 @@
 // Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
 
 #include <iostream>
+#include <random>
 
 #include "profiler/profile_grouped_gemm_impl.hpp"
 
@@ -18,7 +19,10 @@ using Col = ck::tensor_layout::gemm::ColumnMajor;
 template <typename ALayout, typename BLayout, typename CLayout>
 bool TestGroupedGemm()
 {
-    int group_count = rand() % 10 + 1;
+
+    std::mt19937 gen(19391);
+    std::uniform_int_distribution<> distrib(1, 10);
+    int group_count = distrib(gen);
 
     // GEMM shape
     std::vector<ck::tensor_operation::device::GemmDesc> gemm_descs;
@@ -29,9 +33,9 @@ bool TestGroupedGemm()
 
     for(int i = 0; i < group_count; i++)
     {
-        Ms.push_back(256 + 256 * (rand() % 10));
-        Ns.push_back(256 + 256 * (rand() % 10));
-        Ks.push_back(128 + 128 * (rand() % 10));
+        Ms.push_back(256 + 256 * distrib(gen));
+        Ns.push_back(256 + 256 * distrib(gen));
+        Ks.push_back(128 + 128 * distrib(gen));
 
         StrideAs.push_back(std::is_same<Row, ALayout>::value ? Ks[i] : Ms[i]);
         StrideBs.push_back(std::is_same<Row, BLayout>::value ? Ns[i] : Ks[i]);