simple implementation for N,M are both multiple of 8

4 files changed, 33 insertions, 9 deletions

diff --git a/cachelab-handout/.gitignore b/cachelab-handout/.gitignore
new file mode 100644
index 0000000..50eaddd
--- /dev/null
+++ b/cachelab-handout/.gitignore
@@ -0,0 +1,6 @@
+.csim_results
+.marker
+csim_results
+test-trans
+trace.*
+tracegen
diff --git a/cachelab-handout/Makefile b/cachelab-handout/Makefile
index 6fc127d..249098e 100644
--- a/cachelab-handout/Makefile
+++ b/cachelab-handout/Makefile
@@ -8,22 +8,20 @@ CFLAGS = -g -Wall -Werror -std=c99 -m64
 CXX = g++
 CXXFLAGS = -g -Wall -Werror -std=c++17 -m64
 
-# all: csim test-trans tracegen
-# 	# Generate a handin tar file each time you compile
-# 	-tar -cvf ${USER}-handin.tar  csim.c trans.c 
+all: csim test-trans tracegen
 
 csim: csim.cc cachelab.c cachelab.h
 	$(CC) $(CFLAGS) -c cachelab.c -o cachelab.o
 	$(CXX) $(CXXFLAGS) -o csim csim.cc cachelab.o -lm
 
-# test-trans: test-trans.c trans.o cachelab.c cachelab.h
-# 	$(CC) $(CFLAGS) -o test-trans test-trans.c cachelab.c trans.o 
+test-trans: test-trans.c trans.o cachelab.c cachelab.h
+	$(CC) $(CFLAGS) -o test-trans test-trans.c cachelab.c trans.o 
 
-# tracegen: tracegen.c trans.o cachelab.c
-# 	$(CC) $(CFLAGS) -O0 -o tracegen tracegen.c trans.o cachelab.c
+tracegen: tracegen.c trans.o cachelab.c
+	$(CC) $(CFLAGS) -O0 -o tracegen tracegen.c trans.o cachelab.c
 
-# trans.o: trans.c
-# 	$(CC) $(CFLAGS) -O0 -c trans.c
+trans.o: trans.c
+	$(CC) $(CFLAGS) -O0 -c trans.c
 
 #
 # Clean the src dirctory
diff --git a/cachelab-handout/csim b/cachelab-handout/csim
new file mode 100755
index 0000000..5d4de8a
--- /dev/null
+++ b/cachelab-handout/csim
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;
+                }
+            }
+        }
+    }
 }
 
 /*