Gemm reduce examples int4/int8/fp32/bf16 (#368)

* GEMM + Reduce max fp16+fp32

* GEmm + Max bf16 + int8

* Refactor common definitions.

* Refactor common func of mean meansquare example.

* More examples for mean meansquare.

* Update int8 examples and skip them cause of random errors.

* Int4 examples.

* Fix examples for max int4/8

* Tensor conversion for int4 input data for mean meansquare example.

* Remove int4 mean_meansquare example

* Fix int8 mean_meansquare example.

-All ReductionAccData and R<N>DataType have to be F32. The INT32 data
type is giving wrong results.

* Guard int4 with ifdef

* Change int8 example to add_addsquare due to div rounding err.

* Clang format

* Change the return type of common function.

* Get back int8 example with division.

* Remove int8 mean meansquare.

* Use proper cast for BF16 data type.

* Use ck::literals.

* Use proper data type for host tensors & reference.

- Use ReduceAccDataType for reference gemm output data type.
- Cast host reference output tensor to EDataType
- Fix ifdefs for int4.

Co-authored-by: Adam Osewski <aosewski@amd.com>

[ROCm/composable_kernel commit: d00e6115b9]

library/include/ck/library/utility/host_tensor.hpp

@@ -259,7 +259,7 @@ struct Tensor
         Tensor<OutT> ret(mDesc);
         for(size_t i = 0; i < mData.size(); i++)
         {
-            ret.mData[i] = static_cast<OutT>(mData[i]);
+            ret.mData[i] = ck::type_convert<OutT>(mData[i]);
         }
         return ret;
     }