diff --git a/sw/snRuntime/src/dma.h b/sw/snRuntime/src/dma.h
index fb39f1942..578cba15d 100644
--- a/sw/snRuntime/src/dma.h
+++ b/sw/snRuntime/src/dma.h
@@ -233,6 +233,30 @@ inline snrt_dma_txid_t snrt_dma_load_2d_tile(
     );
 }
 
+/// Transfer a tile and transpose it
+inline void snrt_dma_load_2d_tile_transpose(
+    void *dst, void *src, size_t tile_x1_idx, size_t tile_x0_idx,
+    size_t tile_x1_size, size_t tile_x0_size, size_t full_x0_size,
+    uint32_t prec) {
+    size_t src_offset = 0;
+    // Advance src array in x0 and x1 dimensions, and convert to byte offset
+    src_offset += tile_x0_idx * tile_x0_size;
+    src_offset += tile_x1_idx * tile_x1_size * full_x0_size;
+    src_offset *= prec;
+    // Initiate transfer
+    for (uint32_t i = 0; i < tile_x0_size; i++)
+    {
+        snrt_dma_start_2d(dst + i * tile_x1_size * prec, // dst
+                          src + src_offset + i * prec, // src
+                          prec,  // size
+                          prec,  // dst_stride
+                          full_x0_size * prec, // src_stride
+                          tile_x1_size         // repeat
+        );
+        
+    }
+}
+
 /// Store a 2D-tile of shape (tile_x1_size, tile_x0_size) to the 2D array
 /// of shape (full_x1_size, full_x0_size). The specific tile is selected
 /// by the (tile_x1_idx, tile_x0_idx) tuple. Every element in the src and