Add a new gemm pipeline based on ComputeV4 which utilizes async copy API (#2949)

* check in pipeline and policy

for async  load in mi350, need to make sure TileAccessPattern is warp_raked or block_raked

solve merge conflicts

* fix cmakelists

* make it build

* fix? buffer async fence

* relax fences; it appears it only is needed between pairs of ping-pongs

* remove fences

* remove fences

* cleanup and reformat

* add steps annotations

* comment all pipeline steps / remove unexplainable syncs

* clang-format

* add comment

* cleanup kernel types for test

* fix comment

* fix hardcoded warp size

* faithfully copy block gemm from compute v4 policy to async policy

* make async test gfx950 only

* fix cmake logic

* set separate compile options for async

* refine comment in policy

* try update hotloop scheduler

* cleanup comments

* test more K block sizes

* unhardcode Ks, sort of

* add large odd test case

* fix build for quant

* add comment to hot loop scheduler and rename enum

* reformat

* reword the pipeline description

* reformat

* address review / add static asserts / typo fix

* update changelog

include/ck_tile/core/arch/arch.hpp

@@ -275,4 +275,20 @@ CK_TILE_DEVICE static constexpr auto get_device_arch()
     return gfx12_t{};
 #endif
 }
+
+enum LLVMSchedGroupMask : int32_t
+{
+    NONE       = 0,
+    ALU        = 1 << 0,
+    VALU       = 1 << 1,
+    SALU       = 1 << 2,
+    MFMA       = 1 << 3,
+    VMEM       = 1 << 4,
+    VMEM_READ  = 1 << 5,
+    VMEM_WRITE = 1 << 6,
+    DS         = 1 << 7,
+    DS_READ    = 1 << 8,
+    DS_WRITE   = 1 << 9,
+    ALL        = (DS_WRITE << 1) - 1,
+};
 } // namespace ck_tile