diff --git a/.gitignore b/.gitignore
index 92937d98af8f13c2fc9e76ec511209346a7ec9ed..b3362e161148121344637b129d15d4457092c566 100644
--- a/.gitignore
+++ b/.gitignore
@@ -3,3 +3,4 @@
 **/*.out
 **/*.err
 **/*.debug
+**/*.pptx
diff --git a/External_Functions/compile.mk b/External_Functions/compile.mk
index ac3ddeb6eb78b559bc0d6b397443033557c0ebe1..dc591802170f462c5fe6bb73e823189b3ad1b511 100644
--- a/External_Functions/compile.mk
+++ b/External_Functions/compile.mk
@@ -12,10 +12,10 @@ CPP=g++
 MPICC=mpicc
 NVCC=nvcc
 CFLAGS=-O3 -lm -Wall -mavx -march=ivybridge -mtune=ivybridge -lrt
-#CPU_COMPILE= $(CC) $(CFLAGS) -I$(EXT_DIR)
-#CPU_COMPILE_OMP = $(CPU_COMPILE) -fopenmp
-#MPI_COMPILE= $(MPICC) -I$(EXT_DIR)
-#MPI_OMP_COMPILE= $(MPI_COMPILE) -fopenmp
+CPU_COMPILE= $(CC) $(CFLAGS) -I$(EXT_DIR)
+CPU_COMPILE_OMP = $(CPU_COMPILE) -fopenmp
+MPI_COMPILE= $(MPICC) -I$(EXT_DIR)
+MPI_OMP_COMPILE= $(MPI_COMPILE) -fopenmp
 GPU_MPI_CXX = $(NVCC) -L $(I_MPI_ROOT)/lib64 -lmpi -ccbin mpiicc
 LDFLAGS ?=-L $(CUDA_PREFIX)/lib64 -lcudart -lcublas -lcusparse -lm -lrt 
 GPU_COMPILE = $(NVCC) -I $(CUDA_PREFIX)/include  -arch sm_35 -I$(EXT_DIR) $(LDFLAGS)
@@ -25,11 +25,11 @@ CPU_COMPILE_CUDA = $(CPP) $(CFLAGS) -I$(EXT_DIR) $(LDFLAGS)
 #compile with icc
 ICC =icc
 MPICC=mpiicc
-ICFLAGS=-O3 -Wall -axCORE-AVX2,CORE-AVX-I -lrt -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread -lm
-CPU_COMPILE= $(ICC) $(ICFLAGS) -I$(EXT_DIR)
-CPU_COMPILE_OMP = $(CPU_COMPILE) -qopenmp
-MPI_COMPILE= $(MPICC) $(ICFLAGS) -I$(EXT_DIR)
-MPI_OMP_COMPILE= $(MPI_COMPILE) -mt_mpi -qopenmp
+ICFLAGS=-O3 -Wall -axCORE-AVX2,CORE-AVX-I 
+#CPU_COMPILE= $(ICC) $(ICFLAGS) -I$(EXT_DIR)
+#CPU_COMPILE_OMP = $(CPU_COMPILE) -qopenmp
+#MPI_COMPILE= $(MPICC) $(ICFLAGS) -I$(EXT_DIR)
+#MPI_OMP_COMPILE= $(MPI_COMPILE) -mt_mpi -qopenmp
 
 ifeq ($(DEBUG), 1)
 	CPU_COMPILE += -D_DEBUG_
diff --git a/Serial/Makefile b/Serial/Makefile
index e650cf858745d84e7552d25e8bf8c3d143246efd..0cc479f0079c1249d8742291f70edcac68cfbbbb 100644
--- a/Serial/Makefile
+++ b/Serial/Makefile
@@ -7,7 +7,7 @@ PROGRAMS= Serial.exe
 all: $(PROGRAMS)
 
 Serial.exe: $(OBJECTS) $(SOURCE)
-	$(CPU_COMPILE) $(SOURCE) -o $@ $(OBJECTS)
+	$(CPU_COMPILE) $(SOURCE) -o $@ $(OBJECTS) -I$(BLASROOT)/include -L$(BLASROOT)/lib -lopenblas -lpthread -lrt -lm -lgfortran
 
 %.o: $(EXT_DIR)%.c
 	$(CPU_COMPILE_OBJ) -o $@ $<
diff --git a/Serial/Serial.c b/Serial/Serial.c
index f4b06deea10e1dfe2aa2ff22ad12203c39438451..ffb76de7b1576023d1cfca03e4a902cd3f615bc6 100644
--- a/Serial/Serial.c
+++ b/Serial/Serial.c
@@ -12,8 +12,7 @@
 #include "matrix_op.h"
 #include "util.h"
 #include "input.h"
-#include "mkl.h"
-#include "mkl_blas.h"
+//#include <cblas.h>
 
 int main(int argc, char **argv)
 {
diff --git a/Serial/Serial.slurm b/Serial/Serial.slurm
index b967290e7458d087c2095a0d967802915d494674..ea755f1caa75f6b09d70cc6b1430bdbf90f8404c 100644
--- a/Serial/Serial.slurm
+++ b/Serial/Serial.slurm
@@ -14,10 +14,10 @@
 #SBATCH --ntasks=1     # Number of processor cores (i.e. tasks)
 #SBATCH --nodes=1    # Number of nodes requested
 #SBATCH --ntasks-per-node=1     # Tasks per node
-#SBATCH --cpus-per-task=1     # Threads per task
+#SBATCH --cpus-per-task=40     # Threads per task
 #SBATCH --time=00:40:00   # walltime
 #SBATCH --mem=50G   # memory per NODE
-#SBATCH --partition=taskp  # Partition
+#SBATCH --partition=fat  # Partition
 #SBATCH --account=testproj  # Accounting project
 
 ## LOAD MODULES ##
@@ -32,7 +32,7 @@ module load cuda
 
 ## Change this to the directory of your executable!
 gpu_prog="./Serial.exe"
-
+export OPENBLAS_NUM_THREADS=40
 for n;
 do
 	srun $gpu_prog $n $n
diff --git a/User_Guide.pdf b/User_Guide.pdf
new file mode 100755
index 0000000000000000000000000000000000000000..2d85feb9f2f8ee542789513a8b9a2d55401f5974
Binary files /dev/null and b/User_Guide.pdf differ
diff --git a/presentation.pdf b/presentation.pdf
new file mode 100755
index 0000000000000000000000000000000000000000..c8db7419dd0747b7a9c6edf58de68f84803487fe
Binary files /dev/null and b/presentation.pdf differ