Merge branch 'main' of github.com:lanl/benchmarks

doc/sphinx/02_amg/mem.gp

@@ -9,7 +9,7 @@ set ylabel "FOM"
 set xrange [10:40]
 set key left top
 
-set yrange [1.0e+6: 1.0e+7]
+set yrange [1.0e+6: 2.0e+7]
 set grid
 show grid
 

doc/sphinx/02_amg/roci_1_120.csv

@@ -1,8 +1,8 @@
 No. cores,Actual,Ideal
-1,8.6459E+06,8.6459E+06
-2,1.4987E+07,1.7292E+07
-4,2.9222E+07,3.4583E+07
-8,5.5766E+07,6.9167E+07
-16,9.5407E+07,1.3833E+08
-32,1.4029E+08,2.7667E+08
-64,2.2887E+08,5.5333E+08
+1,1.2053E+07,1.2053E+07
+2,2.3748E+07,2.4106E+07
+4,4.4537E+07,4.8212E+07
+8,8.1841E+07,9.6424E+07
+16,1.5018E+08,1.9285E+08
+32,2.6169E+08,3.8570E+08
+64,4.0990E+08,7.7139E+08

doc/sphinx/02_amg/roci_1_160.csv

@@ -1,8 +1,8 @@
 No. cores,Actual,Ideal
-1,8.4644E+06,8.4644E+06
-2,1.2983E+07,1.6929E+07
-4,2.7064E+07,3.3857E+07
-8,5.0436E+07,6.7715E+07
-16,1.0227E+08,1.3543E+08
-32,1.3856E+08,2.7086E+08
-64,2.3692E+08,5.4172E+08
+1,1.1871E+07,1.1871E+07
+2,2.2864E+07,2.3743E+07
+4,4.3908E+07,4.7486E+07
+8,8.2382E+07,9.4972E+07
+16,1.5050E+08,1.8994E+08
+32,2.7485E+08,3.7989E+08
+64,4.7192E+08,7.5977E+08

doc/sphinx/02_amg/roci_1_200.csv

@@ -1,8 +1,8 @@
 No. cores,Actual,Ideal
-1,8.4267E+06,8.4267E+06
-2,1.2526E+07,1.6853E+07
-4,2.4576E+07,3.3707E+07
-8,5.0598E+07,6.7413E+07
-16,9.3217E+07,1.3483E+08
-32,1.2682E+08,2.6965E+08
-64,2.3377E+08,5.3931E+08
+1,1.1677E+07,1.1677E+07
+2,2.2162E+07,2.3354E+07
+4,4.2170E+07,4.6708E+07
+8,8.3668E+07,9.3415E+07
+16,1.4897E+08,1.8683E+08
+32,2.7608E+08,3.7366E+08
+64,5.0217E+08,7.4732E+08

doc/sphinx/02_amg/roci_2_200.csv

@@ -1,8 +1,8 @@
 No. cores,Actual,Ideal
-1,1.7980E+06,1.7980E+06
-2,3.2662E+06,3.5961E+06
-4,6.2277E+06,7.1922E+06
-8,1.2149E+07,1.4384E+07
-16,2.2796E+07,2.8769E+07
-32,2.8885E+07,5.7538E+07
-64,4.6850E+07,1.1508E+08
+1,2.7956E+06,2.7956E+06
+2,5.0762E+06,5.5913E+06
+4,9.3707E+06,1.1183E+07
+8,1.7585E+07,2.2365E+07
+16,3.2401E+07,4.4730E+07
+32,5.8306E+07,8.9460E+07
+64,1.0401E+08,1.7892E+08

doc/sphinx/02_amg/roci_2_256.csv

@@ -1,8 +1,8 @@
 No. cores,Actual,Ideal
-1,1.7267E+06,1.7267E+06
-2,3.0559E+06,3.4535E+06
-4,5.8681E+06,6.9069E+06
-8,1.1919E+07,1.3814E+07
-16,2.0471E+07,2.7628E+07
-32,2.7253E+07,5.5255E+07
-64,4.5270E+07,1.1051E+08
+1,2.5400E+06,2.5400E+06
+2,4.6956E+06,5.0801E+06
+4,8.5277E+06,1.0160E+07
+8,1.6098E+07,2.0320E+07
+16,2.9559E+07,4.0640E+07
+32,5.5629E+07,8.1281E+07
+64,1.0656E+08,1.6256E+08

doc/sphinx/02_amg/roci_2_320.csv

@@ -1,8 +1,8 @@
 No. cores,Actual,Ideal
-1,1.6485E+06,1.6485E+06
-2,2.8577E+06,3.2970E+06
-4,5.3917E+06,6.5940E+06
-8,1.1154E+07,1.3188E+07
-16,2.1099E+07,2.6376E+07
-32,2.6207E+07,5.2752E+07
-64,4.2568E+07,1.0550E+08
+1,2.3462E+06,2.3462E+06
+2,4.2833E+06,4.6925E+06
+4,7.8280E+06,9.3849E+06
+8,1.5619E+07,1.8770E+07
+16,2.8615E+07,3.7540E+07
+32,5.2880E+07,7.5079E+07
+64,9.5875E+07,1.5016E+08

doc/sphinx/02_amg/roci_mem.csv

@@ -1,5 +1,5 @@
 GB,Problem 1,Problem 2
-10,8.6128E+06,1.8494E+06
-20,8.4654E+06,1.7930E+06
-30,8.4068E+06,1.7416E+06
-40,8.3174E+06,1.7258E+06
+10,1.2197E+07,2.8391E+06
+20,1.2055E+07,2.7853E+06
+30,1.1929E+07,2.6162E+06
+40,1.1904E+07,2.5890E+06

doc/sphinx/09_Microbenchmarks/M5_DGEMM/DGEMM.rst

@@ -40,32 +40,34 @@ Run Rules
 Building
 ========
 
-Makefiles are provided for the intel and gcc compilers. Before building, load the compiler and blas libraries into the PATH and LD_LIBRARY_PATH. 
+Load the compiler; make and enter a build directory.
 
 .. code-block:: bash
 
-    cd src
-    patch -p1 < ../dgemm_omp_fixes.patch
-    make CFLAGS=-I<openblas_include_dir>
+    cmake -DBLAS_NAME=<blas library name> ..
+    make
 
 ..
 
-If using a different compiler, copy and modify the simple makefiles to apply the appropriate flags.
-
-If using a different blas library than mkl or openblas, modify the C source file to use the correct header and dgemm command.
+Current `BLAS_NAME` options are mkl, cblas (openblas), essl, or the raw coded (OpenMP threaded) dgemm.
+The `BLAS_NAME` argument is required.
+If the headers or libraries aren't found provide `BLAS_LIB_DIR`, `BLAS_INCLUDE_DIR`, or `BLAS_ROOT` to cmake.
+If using a different blas library, modify the C source file to use the correct header and dgemm command.
 
 Running
 =======
 
 DGEMM uses OpenMP but does not use MPI.
 
-Set the number of OpenMP threads before running.
+Set the number of OpenMP threads and other OMP characteristics with export.
+The following were used for the Crossroads (:ref:`GlobalSystemATS3`) system.
 
 .. code-block:: bash
 
-    export OPENBLAS_NUM_THREADS=<nthreads>
+    export OPENBLAS_NUM_THREADS=<nthreads> #MKL INHERITS FROM OMP_NUM_THREADS.
     export OMP_NUM_THREADS=<nthreads>
     export OMP_PLACES=cores
+    export OMP_PROC_BIND=close
 
 ..
 

microbenchmarks/dgemm/src/CMakeLists.txt

@@ -0,0 +1,86 @@
+################################################################################
+# NOTES ON COMPILATION
+################################################################################
+
+# Load the modules for each libary and the environment variables will be set
+# correctly (load cmake, compiler, blas library)
+
+# Enbable debug mode by passing -DCMAKE_BUILD_TYPE=Debug to CMake, default is
+# Release
+
+cmake_minimum_required(VERSION 3.11)
+
+project(DGEMM
+VERSION 1.0
+DESCRIPTION "DGEMM tests the performance of BLAS libraries"
+LANGUAGES C)
+
+site_name( SITENAME )
+
+if ( NOT DEFINED BLAS_NAME )
+  message( SEND_ERROR "BLAS NAME MUST BE SPECIFIED: cblas, mkl, essl or raw")
+endif()
+
+string( TOUPPER ${BLAS_NAME} BLAS_NAME_UPPER )
+
+if ( NOT DEFINED CMAKE_BUILD_TYPE )
+  set(CMAKE_BUILD_TYPE "Release" )
+endif()
+
+set( CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DUSE_${BLAS_NAME_UPPER}")
+
+set( CMAKE_C_FLAGS_DEBUG "-Wall -O0 -g" )
+set( CMAKE_VERBOSE_MAKEFILE "TRUE" )
+if (CMAKE_C_COMPILER_ID STREQUAL "GNU" )
+    set( CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fopenmp")
+    set( CMAKE_C_FLAGS_RELEASE "-ffast-math -mavx2 -ftree-vectorizer-verbose=3 -O3 -funroll-loops -fno-var-tracking-assignments")
+elseif( CMAKE_C_COMPILER_ID MATCHES "Intel" )
+    set( CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -openmp")
+    set( CMAKE_C_FLAGS_RELEASE "-O3 -fp-speculation=fast -fp-model=precise -qno-opt-dynamic-align")
+elseif( CMAKE_C_COMPILER_ID STREQUAL "Cray" )
+    set( CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fopenmp")
+    set( CMAKE_C_FLAGS_RELEASE "-O3")
+endif()
+
+if (CMAKE_BUILD_TYPE  STREQUAL "Release" )
+  set( CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${CMAKE_C_FLAGS_RELEASE}")
+elseif (CMAKE_BUILD_TYPE  STREQUAL "Debug" )
+  set( CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${CMAKE_C_FLAGS_DEBUG}")
+endif()
+
+# Summary of user-selectable build options
+message( "\nBuild Summary:\n")
+message( STATUS "Machine name    : ${SITENAME}")
+message( STATUS "CMAKE_BUILD_TYPE: ${CMAKE_BUILD_TYPE}")
+message( STATUS "Compiler        : ${CMAKE_C_COMPILER_ID} ${CMAKE_C_COMPILER}")
+message( STATUS "BLAS            : ${BLAS_NAME}")
+message( STATUS "-----------------------------------")
+message( STATUS "Compiler Flags (All)    : ${CMAKE_C_FLAGS}")
+message( STATUS "Compiler Flags (Debug)  : ${CMAKE_C_FLAGS_DEBUG}")
+message( STATUS "Compiler Flags (Release): ${CMAKE_C_FLAGS_RELEASE}")
+message("\n")
+
+add_executable(dgemm mt-dgemm.c)
+
+if ( DEFINED BLAS_ROOT )
+  target_link_directories( dgemm PRIVATE "${BLAS_ROOT}/lib")
+  target_include_directories( dgemm PRIVATE "${BLAS_ROOT}/include")
+endif()
+
+if ( DEFINED BLAS_LIB_DIR )
+  target_link_directories( dgemm PRIVATE ${BLAS_LIB_DIR} )
+endif()
+
+if ( DEFINED BLAS_INCLUDE_DIR )
+  target_include_directories( dgemm PRIVATE ${BLAS_INCLUDE_DIR} )
+endif()
+
+if ( ${BLAS_NAME} STREQUAL "mkl" )
+  set( CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -qmkl=parallel")
+elseif ( ${BLAS_NAME} STREQUAL "cblas" )
+  target_link_libraries( dgemm LINK_PUBLIC "openblas")
+elseif ( ${BLAS_NAME} STREQUAL "essl" )
+  target_link_libraries( dgemm LINK_PUBLIC "essl")
+endif()
+
+

microbenchmarks/dgemm/src/mt-dgemm.c

@@ -3,16 +3,21 @@
 #include <stdlib.h>
 #include <sys/time.h>
 
+#define BLAS_LIB "nolib"
+
 #ifdef USE_MKL
 #include "mkl.h"
+#define BLAS_LIB "mkl"
 #endif
 
 #ifdef USE_CBLAS
 #include "cblas.h"
+#define BLAS_LIB "cblas"
 #endif
 
 #ifdef USE_ESSL
 #include "essl.h"
+#define BLAS_LIB "essl"
 #endif
 
 #define DGEMM_RESTRICT __restrict__
@@ -107,6 +112,8 @@ int main(int argc, char* argv[]) {
 	}
 
 	printf("Performing multiplication...\n");
+	printf("Using Blas Type: %s\n", BLAS_LIB);
+	printf("Iteration #:\n");
 
 	const double start = get_seconds();
 
@@ -142,7 +149,12 @@ int main(int argc, char* argv[]) {
 			}
 		}
 #endif
+		if ( r%10 == 0 ) {
+			printf("%d, ", r);
+			fflush(stdout); 
+		}
 	}
+	printf("\n");
 
 	// ------------------------------------------------------- //
 	// VENDOR NOTIFICATION: END MODIFIABLE REGION