From 4c3db4aa74348d5cf41c43140d2a59d6fe2c8374 Mon Sep 17 00:00:00 2001
From: _ov4 <ov4@ov4.org>
Date: Tue, 21 Jul 2026 14:49:23 +0000
Subject: simple implementation for N,M are both multiple of 8

---
 cachelab-handout/trans.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'cachelab-handout/trans.c')

diff --git a/cachelab-handout/trans.c b/cachelab-handout/trans.c
index e40f6fc..d8f221b 100644
--- a/cachelab-handout/trans.c
+++ b/cachelab-handout/trans.c
@@ -22,6 +22,26 @@ int is_transpose(int M, int N, int A[N][M], int B[M][N]);
 char transpose_submit_desc[] = "Transpose submission";
 void transpose_submit(int M, int N, int A[N][M], int B[M][N])
 {
+    int i, j, tmp, i2, j2;
+    const int blockSize = 8;
+
+    // given N, M are multiples of blockSize
+    // just to test
+    for (i = 0; i < N/blockSize; i++)
+    {
+        for (j = 0; j < M/blockSize; j++)
+        {
+            // now i, j are indecies of smaller groups
+            for (i2 = 0; i2 < blockSize; i2++)
+            {
+                for (j2 = 0; j2 < blockSize; j2++)
+                {
+                    tmp = A[i*blockSize + i2][j*blockSize + j2];
+                    B[j*blockSize + j2][i*blockSize + i2] = tmp;
+                }
+            }
+        }
+    }
 }
 
 /* 
-- 
cgit v1.3.1-4-g156e