Added gemm timming and small change to the printing to make it more readable.

theano/misc/check_blas.py

@@ -91,15 +91,19 @@ if __name__ == "__main__":
         Cpu tested: Xeon E5345(2.33Ghz, 8M L2 cache, 1333Mhz FSB), Xeon E5430(2.66Ghz, 12M L2 cache, 1333Mhz FSB),
                     Xeon E5450(3Ghz, 12M L2 cache, 1333Mhz FSB), Xeon X5560(2.8Ghz, 12M L2 cache, 6.4GT/s QPI, hyper-threads enabled?)
                     Core 2 E8500, Core i7 930(2.8Ghz, hyper-threads enabled), Core i7 950(3.07GHz, hyper-threads enabled)
+                    Xeon X5550(2.67GHz, 8M l2 cache?, hyper-threads enabled)
 
 
         Lib tested:
             * numpy with ATLAS from distribution(FC9) package (1 thread)
             * manually compiled numpy and ATLAS with 2 threads
             * goto 1.26 with 1, 2, 4 and 8 threads.
-                          Xeon   Xeon   Xeon  Core2 i7    i7     Xeon
-        lib/nb threads    E5345  E5430  E5450 E8500 930   950    X5560
+            * goto2 1.13 compiled with multiple thread enabled.
             
+                          Xeon   Xeon   Xeon  Core2 i7    i7     Xeon   Xeon
+        lib/nb threads    E5345  E5430  E5450 E8500 930   950    X5560  X5550
+
+        numpy 1.3.0 blas                                                775.92s
         numpy_FC9_atlas/1 39.2s  35.0s  30.7s 29.6s 21.5s 19.60s
         goto/1            18.7s  16.1s  14.2s 13.7s 16.1s 14.67s
         numpy_MAN_atlas/2 12.0s  11.6s  10.2s  9.2s  9.0s
@@ -110,19 +114,25 @@ if __name__ == "__main__":
         openblas/2                                         7.16s
         openblas/4                                         3.71s
         openblas/8                                         3.70s
+        mkl 11.0.083/1            7.97s
         mkl 10.2.2.025/1                                         13.7s
         mkl 10.2.2.025/2                                          7.6s
         mkl 10.2.2.025/4                                          4.0s
         mkl 10.2.2.025/8                                          2.0s
-        mkl 11.0.083/1           7.97s
+        goto2 1.13/1                                                     14.37s
+        goto2 1.13/2                                                      7.26s
+        goto2 1.13/4                                                      3.70s
+        goto2 1.13/8                                                      1.94s
+        goto2 1.13/16                                                     3.16s
 
         Test time in float32 with cuda 3.0.14
         (cuda version 3.2RC and up are supposed to have faster gemm on the GTX4?? card)
-        cpu/cuda version
+        gpu/cuda version
         GTX580/3.2        0.20s
         GTX480/3.2        0.24s
         GTX480/3.0        0.27s
         GTX470/3.2        0.29s
+        M2070/3.2         0.32s
         GTX470/3.0        0.34s
         GTX285/3.0        0.40s
         GT220/3.2RC       5.15s