Merge pull request #138 from guacamoleo/develop-squash2

AutoGemm main merge

Author: Timmy

.gitignore

@@ -20,3 +20,6 @@
 
 # flags.txt file
 *flags.txt
+
+# vim temp files
+.*.swp

doc/performance/clBLAS_2.6.0/S9150/dtrsm_192.csv

@@ -1,31 +1,31 @@
 m,n,k,lda,ldb,ldc,offa,offb,offc,alpha,beta,order,transa,transb,side,uplo,diag,function,device,library,label,GFLOPS
-192,192,192,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,8.9202
-384,384,384,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,46.185
-576,576,576,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,126.686
-768,768,768,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,235.366
-960,960,960,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,375.406
-1152,1152,1152,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,475.497
-1344,1344,1344,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,599.527
-1536,1536,1536,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,437.835
-1728,1728,1728,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,778.815
-1920,1920,1920,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,845.844
-2112,2112,2112,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,969.624
-2304,2304,2304,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,943.48
-2496,2496,2496,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1026.58
-2688,2688,2688,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1074.56
-2880,2880,2880,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1102.6
-3072,3072,3072,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,848.076
-3264,3264,3264,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1010.06
-3456,3456,3456,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1034.51
-3648,3648,3648,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1059.02
-3840,3840,3840,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1037.95
-4032,4032,4032,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1103.8
-4224,4224,4224,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1109.83
-4416,4416,4416,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1096.15
-4608,4608,4608,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1055.28
-4800,4800,4800,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1140.07
-4992,4992,4992,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1152.31
-5184,5184,5184,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1165.47
-5376,5376,5376,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1152.36
-5568,5568,5568,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1193.66
-5760,5760,5760,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,S9150,1199.05
+192,192,192,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,8.9202
+384,384,384,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,46.185
+576,576,576,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,126.686
+768,768,768,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,235.366
+960,960,960,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,375.406
+1152,1152,1152,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,475.497
+1344,1344,1344,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,599.527
+1536,1536,1536,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,437.835
+1728,1728,1728,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,778.815
+1920,1920,1920,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,845.844
+2112,2112,2112,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,969.624
+2304,2304,2304,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,943.48
+2496,2496,2496,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1026.58
+2688,2688,2688,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1074.56
+2880,2880,2880,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1102.6
+3072,3072,3072,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,848.076
+3264,3264,3264,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1010.06
+3456,3456,3456,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1034.51
+3648,3648,3648,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1059.02
+3840,3840,3840,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1037.95
+4032,4032,4032,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1103.8
+4224,4224,4224,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1109.83
+4416,4416,4416,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1096.15
+4608,4608,4608,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1055.28
+4800,4800,4800,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1140.07
+4992,4992,4992,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1152.31
+5184,5184,5184,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1165.47
+5376,5376,5376,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1152.36
+5568,5568,5568,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1193.66
+5760,5760,5760,0,0,0,0,0,0,1.0,1.0,column,none,none,right,upper,unit,dtrsm,gpu,clblas,s9150_dtrsm_14502,1199.05