Merge pull request #7117 from tensor-tang/benchmark

update alexnet inference benchmark data on MKL

benchmark/IntelOptimizedPaddle.md

@@ -93,6 +93,15 @@ Test on batch size 1, 2, 4, 8, 16 on Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz
 | MKLML     | 22.74  | 41.56  | 81.22  | 133.47 | 210.53 |
 | MKL-DNN   | 175.10 | 272.92 | 450.70 | 512.00 | 600.94 |
 
+- Alexnet
+
+| BatchSize | 1      | 2      | 4      | 8      | 16     |
+|-----------|--------|--------|--------|--------|--------|
+| OpenBLAS  |    |   |   |   |    |
+| MKLML     | 21.32  | 36.55  | 73.06  | 131.15 | 192.77 |
+| MKL-DNN   | 442.91 | 656.41 | 719.10 | 847.68 | 850.51 |
+
+chart TBD
 
 ### Laptop
 TBD