Add Testing Results in this repository

Author: yangyang14641

Code Test/Dell XPS8900/Testing on Intel Core i7 CPU/Test 1/fox_floats_timer_caching_omp_fileIO_benchmark.c renamed to Code Test/Dell XPS8900/Testing on Intel Core i7 CPU/TraceAnalyzer/fox_floats_timer_caching_omp_fileIO_benchmark.c

@@ -38,7 +38,7 @@
 
 
 // define problem scale, matrix row/col size 
-#define PROBLEM_SCALE 64
+#define PROBLEM_SCALE 4096
 
 // define whether or not Print Matices in the Command Line
 #define PRINT_A 0
@@ -54,7 +54,7 @@
 #define FLOAT_MPI MPI_DOUBLE
 
 // Define threads speed-up affnity in the computing
-#define NUM_THREADS 1
+#define NUM_THREADS 2
 // Define threads affinity "scatter" or "compact" 
 #define AFFINITY "KMP_AFFINITY = compact"
 

Code Test/Dell XPS8900/Testing on Intel Core i7 CPU/Test 1/fox_floats_timer_caching_omp_fileIO_benchmark.c~ renamed to Code Test/Dell XPS8900/Testing on Intel Core i7 CPU/TraceAnalyzer/fox_floats_timer_caching_omp_fileIO_benchmark.c~

@@ -38,7 +38,7 @@
 
 
 // define problem scale, matrix row/col size 
-#define PROBLEM_SCALE 64
+#define PROBLEM_SCALE 4096
 
 // define whether or not Print Matices in the Command Line
 #define PRINT_A 0
@@ -54,7 +54,7 @@
 #define FLOAT_MPI MPI_DOUBLE
 
 // Define threads speed-up affnity in the computing
-#define NUM_THREADS 1
+#define NUM_THREADS 2
 // Define threads affinity "scatter" or "compact" 
 #define AFFINITY "KMP_AFFINITY = compact"
 

Code Test/Dell XPS8900/Testing on Intel Core i7 CPU/Test 1/serial_matrix_multiplication_benchmark.c renamed to Code Test/Dell XPS8900/Testing on Intel Core i7 CPU/TraceAnalyzer/serial_matrix_multiplication_benchmark.c

@@ -18,7 +18,7 @@
 
 
 // define problem scale, matrix row/col size 
-#define PROBLEM_SCALE 64
+#define PROBLEM_SCALE 4096
 
 // define float precision, 4 byte single-precision float or 8 byte double-precision float
 #define FLOAT double

Code Test/Dell XPS8900/Testing on Intel Core i7 CPU/Test 1/serial_matrix_multiplication_benchmark.c~ renamed to Code Test/Dell XPS8900/Testing on Intel Core i7 CPU/TraceAnalyzer/serial_matrix_multiplication_benchmark.c~

@@ -18,7 +18,7 @@
 
 
 // define problem scale, matrix row/col size 
-#define PROBLEM_SCALE 64
+#define PROBLEM_SCALE 4096
 
 // define float precision, 4 byte single-precision float or 8 byte double-precision float
 #define FLOAT double

Code Test/PKU-HPC/Testing on Intel Xeon E5 CPUs/ProblemScale/1024*1024/fox_floats_timer_caching_omp_fileIO_benchmark.971146.a4u23n11.out

@@ -0,0 +1,12 @@
+icc: remark #10397: optimization reports are generated in *.optrpt files in the output location
+srun: Warning: can't honor --ntasks-per-node set to 2 which doesn't match the requested tasks 8 with the number of requested nodes 8. Ignoring --ntasks-per-node.
+We read the order of the matrices from A.dat is
+ 1024
+Read A from A.dat
+Read B from B.dat
+Write C into the C.dat
+Write split of local matrix A into local_A.dat
+Write split of local matrix B into local_B.dat
+Write split of local matrix C into local_C.dat
+Parallel Fox Matrix Multiplication Elapsed time:
+     4.83388900756835937500E-02 seconds

Code Test/PKU-HPC/Testing on Intel Xeon E5 CPUs/ProblemScale/1024*1024/fox_floats_timer_caching_omp_fileIO_benchmark.971147.a4u03n03.out

@@ -0,0 +1,12 @@
+icc: remark #10397: optimization reports are generated in *.optrpt files in the output location
+Generate and write matrix A
+Generate and write matrix B
+We read the order of the matrices from A.dat is
+ 1024
+Read matrix A
+Read matrix B
+Start C = A*B
+C = A*B finished
+Serial Matrix Multiplication Elapsed time:
+     4.67198848724365234375E-01 seconds
+Write result C = A*B to a file C.dat