[CK_TILE] Tileloop persistent gemm - resubmit (#2299)

* Reapply "[CK_TILE] Tile loop persistent gemm kernel (#2191)" (#2293)

This reverts commit 0c8aea8cb4.

* Add missing header for kentry

---------

Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>

[ROCm/composable_kernel commit: 1c6f83df6c]

example/ck_tile/03_gemm/gemm_basic.cpp

@@ -18,9 +18,12 @@ template <typename ADataType,
           typename CDataType,
           typename ALayout,
           typename BLayout,
-          typename CLayout>
+          typename CLayout,
+          bool Persistent>
 float gemm_calc(const ck_tile::GemmHostArgs& args, const ck_tile::stream_config& s)
 {
+    if constexpr(Persistent)
+        std::cout << "WARNING: Ignoring persistent kernel option for basic gemm." << std::endl;
     // The kPadM, kPadN, kPadK & kBlockPerCu should also come from the Codegen part.
     constexpr bool kPadM = false;
     constexpr bool kPadN = false;