Add grouped gemm instances for RDNA4 (#3237)

* wip: grouped_gemm implementation based on wmma kernel + example for fp16

* chore: clean up grouped_gem_wmma_splitk_fp16 example

* chore: add cmake options to fully disable XDL or WMMA kernels

* feat: add tests for grouped gemma wmma instances for f16 and bf16 (all layouts)

* chore: add grouped gemm wmma bf16 example

* refactor: reuse more code between instance factory functions

* chore: turn test failure if not all batch sizes are supported into a warning

* chore: made failing of test on unsupported instances conditional to not break old tests

* chore: add log message to failure case where AK1/BK1/KBatch is too high for K value

* fix: issue with new overloads of GridwiseGemm_wmma_cshuffle_v3::Run()

* fix: stray comma after parameter list

* fix: compilation issues on RDNA3 and tests failing due to unsupported problems still being ran

* chore: update copyright in header comments

* nit: minor feebdack

* refactor: unified XDL / wma tests

* fix: properly disable FP8 instances when ONLY targeting gfx11

* refactor: add v3 suffix to grouped_gemm device struct name

* fix: small typos in example code

* fix: fully exclude xdl/wmma instances when using the corresponding cmake flags

* chore: remove unused destructor and added pipeline support checks to remove unnecessary paths

* fix: make sure to not add instance library to group if library was skipped

* fix: make sure xdl grouped gemm doesnt fail the new test

* fix: explicitly exclude test if no xdl/wmma support, as pattern matching fails in this case

* fix: examples not working since dependent types and functions were moved to ck namespace in develop

* fix: tests failing when compiling for just gfx11 due to trying to run unsupported instances

* chore: replace/add copyright headers with new format

profiler/include/profiler/profile_grouped_gemm_impl.hpp

@@ -42,10 +42,11 @@ bool profile_grouped_gemm_impl(int do_verification,
                                const std::vector<int>& StrideAs,
                                const std::vector<int>& StrideBs,
                                const std::vector<int>& StrideCs,
-                               const std::vector<int>& kbatches = {},
-                               int n_warmup                     = 1,
-                               int n_iter                       = 10,
-                               int instance_index               = -1)
+                               const std::vector<int>& kbatches   = {},
+                               int n_warmup                       = 1,
+                               int n_iter                         = 10,
+                               int instance_index                 = -1,
+                               bool fail_if_no_supported_instance = false)
 {
     bool pass = true;
     // TODO: Fixme - we do not pass compute data type here but need it
@@ -225,6 +226,7 @@ bool profile_grouped_gemm_impl(int do_verification,
         }
     }
     // profile device GEMM instances
+    int instances_supporting_all_batch_sizes = 0;
     for(auto& gemm_ptr : op_ptrs)
     {
         auto argument_ptr =
@@ -268,6 +270,7 @@ bool profile_grouped_gemm_impl(int do_verification,
             kbatch_list = kbatches;
         }
 
+        bool all_batch_sizes_supported = true;
         for(std::size_t j = 0; j < kbatch_list.size(); j++)
         {
             auto kbatch_curr = kbatch_list[j];
@@ -367,10 +370,30 @@ bool profile_grouped_gemm_impl(int do_verification,
             }
             else
             {
+                all_batch_sizes_supported = false;
                 std::cout << "Instance: " << gemm_name << ", does not support this GEMM problem"
                           << std::endl;
             }
         }
+
+        // If all batch sizes were supported by this instance, the instance can be marked as
+        // 'supported' for this problem
+        if(all_batch_sizes_supported)
+        {
+            ++instances_supporting_all_batch_sizes;
+        }
+    }
+
+    // Warn if not a single instance was supported
+    if(instances_supporting_all_batch_sizes == 0)
+    {
+        std::cout << "Warning! No instance found that supported all of the batch sizes."
+                  << std::endl;
+
+        if(fail_if_no_supported_instance)
+        {
+            return false;
+        }
     }
 
     if(time_kernel)
@@ -384,6 +407,7 @@ bool profile_grouped_gemm_impl(int do_verification,
         std::cout << "grouped_gemm_instance (" << instance_index << "/" << num_kernel << "): Passed"
                   << std::endl;
     }
+
     return pass;
 }