diff --git a/include/ck_tile/core/numeric/integral_constant.hpp b/include/ck_tile/core/numeric/integral_constant.hpp
index 879f9565b8..ea7a67abcc 100644
--- a/include/ck_tile/core/numeric/integral_constant.hpp
+++ b/include/ck_tile/core/numeric/integral_constant.hpp
@@ -33,7 +33,7 @@ template <index_t v>
 using number = constant<v>;
 
 template <long_index_t v>
-using long_number = integral_constant<long_index_t, v>;
+using long_number = constant<v>;
 
 template <bool b>
 using bool_constant = constant<b>;
diff --git a/include/ck_tile/core/tensor/shuffle_tile.hpp b/include/ck_tile/core/tensor/shuffle_tile.hpp
index a756679bd9..502b7560a4 100644
--- a/include/ck_tile/core/tensor/shuffle_tile.hpp
+++ b/include/ck_tile/core/tensor/shuffle_tile.hpp
@@ -10,6 +10,7 @@
 #include "ck_tile/core/algorithm/coordinate_transform.hpp"
 #include "ck_tile/core/algorithm/space_filling_curve.hpp"
 #include "ck_tile/core/container/container_helper.hpp"
+#include "ck_tile/core/container/thread_buffer.hpp"
 #include "ck_tile/core/container/statically_indexed_array.hpp"
 #include "ck_tile/core/numeric/math.hpp"
 #include "ck_tile/core/utility/type_traits.hpp"
@@ -98,8 +99,8 @@ CK_TILE_DEVICE void shuffle_tile_impl_in_thread(OutTensor& out_tensor, const InT
     static_assert(num_access > 0, "wrong! num_access should be larger than 0");
 
     // in/out vectors to be transposed
-    statically_indexed_array<InVec, num_vec_in> in_vectors;
-    statically_indexed_array<OutVec, num_vec_out> out_vectors;
+    thread_buffer<InVec, num_vec_in> in_vectors;
+    thread_buffer<OutVec, num_vec_out> out_vectors;
 
     // loop over SFC and do transpose
     static_for<0, num_access, 1>{}([&](auto iAccess) {
diff --git a/include/ck_tile/core/utility/transpose_vectors.hpp b/include/ck_tile/core/utility/transpose_vectors.hpp
index acd5dd7b1d..7eb7af1073 100644
--- a/include/ck_tile/core/utility/transpose_vectors.hpp
+++ b/include/ck_tile/core/utility/transpose_vectors.hpp
@@ -5,6 +5,7 @@
 
 #include "ck_tile/core/config.hpp"
 #include "ck_tile/core/container/array.hpp"
+#include "ck_tile/core/container/thread_buffer.hpp"
 #include "ck_tile/core/utility/bit_cast.hpp"
 #include "ck_tile/core/utility/functional.hpp"
 
@@ -25,7 +26,7 @@ struct transpose_vectors
     using VX = array<S, s_per_x>;
     using VY = array<S, s_per_y>;
 
-    CK_TILE_DEVICE void operator()(const array<VX, NX>& vx_tuple, array<VY, NY>& vy_tuple)
+    CK_TILE_DEVICE void operator()(const thread_buffer<VX, NX>& vx_tuple, thread_buffer<VY, NY>& vy_tuple)
     {
         constexpr auto I1 = number<1>{};
         constexpr auto I2 = number<2>{};