fix clang format

include/ck_tile/core/arch/amd_buffer_addressing.hpp

@@ -34,8 +34,8 @@ CK_TILE_DEVICE int32x4_t make_wave_buffer_resource(const void* ptr, uint32_t siz
     return r;
 }
 
-
-CK_TILE_DEVICE __amdgpu_buffer_rsrc_t make_wave_buffer_resource_new(const void* ptr, uint32_t size = 0xffffffff)
+CK_TILE_DEVICE __amdgpu_buffer_rsrc_t make_wave_buffer_resource_new(const void* ptr,
+                                                                    uint32_t size = 0xffffffff)
 {
     auto p = const_cast<remove_cv_t<void>*>(ptr);
     return __builtin_amdgcn_make_buffer_rsrc(p, 0, size, CK_TILE_BUFFER_RESOURCE_3RD_DWORD);
@@ -906,8 +906,8 @@ CK_TILE_DEVICE_EXTERN float llvm_amdgcn_raw_buffer_atomic_add_fp32(
     index_t glc_slc) __asm("llvm.amdgcn.raw.buffer.atomic.fadd.f32.v4i32");
 
 // buffer atomic-max fp64
-CK_TILE_DEVICE_EXTERN double
-llvm_amdgcn_raw_buffer_atomic_max_fp64(double vdata,
+CK_TILE_DEVICE_EXTERN double llvm_amdgcn_raw_buffer_atomic_max_fp64(
+    double vdata,
     int32x4_t rsrc, // dst_wave_buffer_resource
     int voffset,    // dst_thread_addr_offset
     int soffset,    // dst_wave_addr_offset
@@ -977,7 +977,8 @@ amd_buffer_load_impl_with_bytes(__amdgpu_buffer_rsrc_t src_wave_buffer_resource,
 
     if constexpr(N == 1)
     {
-        return bit_cast<rtn_type>(__builtin_amdgcn_raw_buffer_load_b8(src_wave_buffer_resource,
+        return bit_cast<rtn_type>(
+            __builtin_amdgcn_raw_buffer_load_b8(src_wave_buffer_resource,
                                                 src_thread_addr_offset,
                                                 src_wave_addr_offset,
                                                 static_cast<index_t>(coherence)));
@@ -1076,7 +1077,8 @@ amd_buffer_load_impl_with_bytes(__amdgpu_buffer_rsrc_t src_wave_buffer_resource,
 template <typename T,
           index_t N,
           amd_buffer_coherence_enum coherence = amd_buffer_coherence_enum::coherence_default>
-CK_TILE_DEVICE thread_buffer<T, N> amd_buffer_load_impl(__amdgpu_buffer_rsrc_t src_wave_buffer_resource,
+CK_TILE_DEVICE thread_buffer<T, N>
+amd_buffer_load_impl(__amdgpu_buffer_rsrc_t src_wave_buffer_resource,
                      index_t src_thread_addr_offset,
                      index_t src_wave_addr_offset)
 {
@@ -1352,7 +1354,8 @@ CK_TILE_DEVICE void amd_async_buffer_load(CK_TILE_LDS_ADDR T* smem,
 
 template <index_t N,
           amd_buffer_coherence_enum coherence = amd_buffer_coherence_enum::coherence_default>
-CK_TILE_DEVICE void amd_buffer_store_impl_with_bytes(const thread_buffer<int8_t, N> src_thread_data,
+CK_TILE_DEVICE void
+amd_buffer_store_impl_with_bytes(const thread_buffer<int8_t, N> src_thread_data,
                                  __amdgpu_buffer_rsrc_t dst_wave_buffer_resource,
                                  index_t dst_thread_addr_offset,
                                  index_t dst_wave_addr_offset)
@@ -2081,7 +2084,8 @@ template <typename T,
           index_t N,
           amd_buffer_coherence_enum coherence = amd_buffer_coherence_enum::coherence_default,
           bool pre_nop                        = false>
-CK_TILE_DEVICE void amd_async_buffer_load_with_oob_raw(T* smem,
+CK_TILE_DEVICE void
+amd_async_buffer_load_with_oob_raw(T* smem,
                                    const __amdgpu_buffer_rsrc_t src_wave_buffer_resource,
                                    index_t src_thread_element_offset,
                                    index_t src_linear_element_offset,
@@ -2103,7 +2107,8 @@ template <typename T,
           index_t N,
           amd_buffer_coherence_enum coherence = amd_buffer_coherence_enum::coherence_default,
           bool oob_conditional_check          = false>
-CK_TILE_DEVICE void amd_async_buffer_load_with_oob(CK_TILE_LDS_ADDR T* smem,
+CK_TILE_DEVICE void
+amd_async_buffer_load_with_oob(CK_TILE_LDS_ADDR T* smem,
                                const __amdgpu_buffer_rsrc_t src_wave_buffer_resource,
                                index_t src_thread_element_offset,
                                index_t src_linear_element_offset,