Memoona-Ishaq: Implemented CUDA matrix multiplication

README.md

@@ -101,9 +101,20 @@ For each test case (0 through 9, using the same `data` folder from Assignment 2)
 
 **Example Table Format**:
 
+
 | Test Case | Dimensions (\( m \times n \times p \)) | Naive CPU (s) | Blocked CPU (s) | Parallel CPU (s) | Naive CUDA (s) | Tiled CUDA (s) | Tiled CUDA Speedup (vs. Naive CUDA) | Tiled CUDA Speedup (vs. Parallel CPU) |
 |-----------|----------------------------------------|---------------|-----------------|------------------|----------------|----------------|-------------------------------------|---------------------------------------|
-|         |                         |      |           |             |          |          |                               |                                 |
+|    0     |  64 × 64 × 64  | 0.001001 | 0.001113  | 0.000689 | 0.000119616 | 8.5792e-05  | 1.39426× | 8.031× |
+|    1     | 128 × 64 × 128 | 0.00402  | 0.004486  | 0.001657 | 0.000167456 | 0.000128192 | 1.30629× | 12.929× |
+|    2     | 100 × 128 × 56 | 0.003187 | 0.003269  | 0.001493 | 0.000149856 | 0.000107232 | 1.39749× | 13.926× |
+|    3     | 128 × 64 × 128 | 0.004022 | 0.004537  | 0.001496 | 0.000165856 | 0.00012576  | 1.31883× | 11.897× |
+|    4     | 32 × 128 × 32  | 0.000495 | 0.000581  | 0.000409 | 0.000115776 | 8.0032e-05  | 1.44662× | 5.111× |
+|    5     | 200 × 100 × 256| 0.022739 | 0.023197  | 0.007493 | 0.000292928 | 0.000254496 | 1.15101× | 29.442× |
+|    6     | 256 × 256 × 256| 0.071375 | 0.074834  | 0.023848 | 0.000438624 | 0.00039328  | 1.1153×  | 60.635× |
+|    7     | 256 × 300 × 256| 0.192763 | 0.123731  | 0.039704 | 0.00048016  | 0.000390176 | 1.23062× | 101.788× |
+|    8     | 64 × 128 × 64  | 0.003011 | 0.003006  | 0.002531 | 0.000138368 | 9.8176e-05  | 1.40939× | 25.788× |
+|    9     | 256 × 256 × 257| 0.076047 | 0.077694  | 0.039918 | 0.00040576  | 0.00038672  | 1.04923× | 103.217× |
+
 
 ---