Cleanup DMA transpose (#1889)

Xilinx · Oct 30, 2024 · a2ed6f5 · a2ed6f5
1 parent c267c7b
commit a2ed6f5
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 7 deletions.
diff --git a/programming_examples/basic/dma_transpose/aie2.py b/programming_examples/basic/dma_transpose/aie2.py
@@ -56,8 +56,8 @@ def sequence(A, B, C):
                     metadata=of_in,
                     bd_id=1,
                     mem=A,
-                    sizes=[1, K, M, 1],
-                    strides=[1, 1, K, 1],
+                    sizes=[1, 1, K, M],
+                    strides=[1, 1, 1, K],
                     issue_token=True,
                 )
                 npu_dma_memcpy_nd(metadata=of_out, bd_id=0, mem=C, sizes=[1, 1, 1, N])

diff --git a/programming_examples/basic/dma_transpose/test.cpp b/programming_examples/basic/dma_transpose/test.cpp
@@ -186,11 +186,11 @@ int main(int argc, const char *argv[]) {
   std::vector<uint32_t> refVecA(N);
 
   // Doing a transpose on the source vector to produce a ref vector
-  for (uint32_t i = 0; i < M; i++) {
-    for (uint32_t j = 0; j < K; j++) {
-      uint32_t src_index = i * K + j;
-      uint32_t dst_index = j * M + i;
-      refVecA[dst_index] = srcVecA[src_index];
+  uint32_t dst_index = 0;
+  for (uint32_t i = 0; i < K; i++) {
+    for (uint32_t j = 0; j < M; j++) {
+      uint32_t src_index = j * K + i;
+      refVecA[dst_index++] = srcVecA[src_index];
     }
   }