Add perfmodels for overlap

tools/perfmodels/sampling/codelets/44/overlap_sleep_1024_24.attila

@@ -0,0 +1,128 @@
+##################
+# Performance Model Version
+44
+
+####################
+# COMBs
+# number of combinations
+4
+####################
+# COMB_1
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+0
+####################
+# DEV_0
+# device id 
+0
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cpu0_impl0 (Comb1)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	8.457435e+01   	8.456846e+01   	6.080896e+05   	5.145841e+07   	7190
+
+####################
+# COMB_0
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+0
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda0_impl0 (Comb0)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	8.959785e+01   	8.957735e+01   	1.959505e+05   	1.756781e+07   	2187
+
+####################
+# COMB_2
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+2
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda2_impl0 (Comb2)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	9.097446e+01   	8.933429e+01   	2.547285e+03   	2.318591e+05   	28
+
+####################
+# COMB_3
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+1
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda1_impl0 (Comb3)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	9.082936e+01   	9.075245e+01   	5.368015e+04   	4.878224e+06   	591
+

tools/perfmodels/sampling/codelets/44/overlap_sleep_1024_24.mirage

@@ -0,0 +1,128 @@
+##################
+# Performance Model Version
+44
+
+####################
+# COMBs
+# number of combinations
+4
+####################
+# COMB_1
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+0
+####################
+# DEV_0
+# device id 
+0
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cpu0_impl0 (Comb1)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	8.457435e+01   	8.456846e+01   	6.080896e+05   	5.145841e+07   	7190
+
+####################
+# COMB_0
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+0
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda0_impl0 (Comb0)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	8.959785e+01   	8.957735e+01   	1.959505e+05   	1.756781e+07   	2187
+
+####################
+# COMB_2
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+2
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda2_impl0 (Comb2)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	9.097446e+01   	8.933429e+01   	2.547285e+03   	2.318591e+05   	28
+
+####################
+# COMB_3
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+1
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda1_impl0 (Comb3)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	9.082936e+01   	9.075245e+01   	5.368015e+04   	4.878224e+06   	591
+

tools/perfmodels/sampling/codelets/44/overlap_sleep_1024_24.sirocco

@@ -0,0 +1,158 @@
+##################
+# Performance Model Version
+44
+
+####################
+# COMBs
+# number of combinations
+4
+####################
+# COMB_1
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+0
+####################
+# DEV_0
+# device id 
+0
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cpu0_impl0 (Comb1)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	8.457435e+01   	8.456846e+01   	6.080896e+05   	5.145841e+07   	7190
+
+####################
+# COMB_0
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+0
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda0_impl0 (Comb0)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	8.959785e+01   	8.957735e+01   	1.959505e+05   	1.756781e+07   	2187
+
+####################
+# COMB_2
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+2
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda2_impl0 (Comb2)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	9.097446e+01   	8.933429e+01   	2.547285e+03   	2.318591e+05   	28
+
+####################
+# COMB_3
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+1
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda1_impl0 (Comb3)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	9.082936e+01   	9.075245e+01   	5.368015e+04   	4.878224e+06   	591
+
+####################
+# COMB_4
+# number of types devices
+1
+####################
+# DEV_0
+# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4, MPI_MS - 5)
+1
+####################
+# DEV_0
+# device id 
+3
+####################
+# DEV_0
+# number of cores 
+1
+##########
+# number of implementations
+1
+#####
+# Model for cuda3_impl0 (Comb4)
+# number of entries
+1
+# sumlnx	sumlnx2		sumlny		sumlnxlny	alpha		beta		n	minx		maxx
+0.000000e+00   	0.000000e+00   	0.000000e+00   	0.000000e+00   	nan            	nan            	0	0              	0              
+# a		b		c
+nan            	nan            	nan            
+# hash		size		flops		mean (us)	dev (us)	sum		sum2		n
+a3d3725e	1024           	0.000000e+00   	9.097446e+01   	8.933429e+01   	2.547285e+03   	2.318591e+05   	28
+