diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index b9b7c687de336d4f5b27f14ef77f0d2784a16c20..9bf46dd37cefd43f766d165689f0d432908b0e06 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -2164,29 +2164,27 @@ intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx_block6-complex-av
 
 #real avx2 block2, complex avx2 block1 (emulated)
 
-# todo: (pkus) I commented out the emulated tests for the process of rebase
-# todo: they should be enabled again
-#intel-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block2-complex-avx2_block1-kernel-jobs:
-  #tags:
-    #- emulated
-  #script:
-    #- ./autogen.sh
-    #- ./configure CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block2-kernel-only --with-complex-avx2-block1-kernel-only --enable-single-precision
-    #- make -j 8
-    #- export OMP_NUM_THREADS=2
-    #- export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
-    #- /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
-
-#gfortran-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block1-complex-avx2_block1-kernel-jobs:
-  #tags:
-    #- emulated
-  #script:
-    #- ./autogen.sh
-    #- ./configure FC=mpif90 CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=haswell -mavx2 -mfma" SCALAPACK_LDFLAGS="$MKL_GFORTRAN_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_GFORTRAN_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block2-kernel-only --with-complex-avx2-block1-kernel-only --enable-single-precision
-    #- make -j 8
-    #- export OMP_NUM_THREADS=2
-    #- export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
-    #- /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
+intel-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block2-complex-avx2_block1-kernel-jobs:
+  tags:
+    - emulated
+  script:
+    - ./autogen.sh
+    - ./configure CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block2-kernel-only --with-complex-avx2-block1-kernel-only --enable-single-precision
+    - make -j 8
+    - export OMP_NUM_THREADS=2
+    - export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
+    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
+
+gfortran-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block1-complex-avx2_block1-kernel-jobs:
+  tags:
+    - emulated
+  script:
+    - ./autogen.sh
+    - ./configure FC=mpif90 CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=haswell -mavx2 -mfma" SCALAPACK_LDFLAGS="$MKL_GFORTRAN_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_GFORTRAN_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block2-kernel-only --with-complex-avx2-block1-kernel-only --enable-single-precision
+    - make -j 8
+    - export OMP_NUM_THREADS=2
+    - export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
+    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
 
       ##gfortran-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block2-complex-avx2_block1-kernel-special-gcov-jobs:
       ##  tags:
@@ -2200,17 +2198,17 @@ intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx_block6-complex-av
       ##    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
       ##      #    - ./test_scripts/get_coverage_summary.sh
 
-##real avx2 block2, complex avx2 block1 (emulated)
+#real avx2 block2, complex avx2 block1 (emulated)
 
-#intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx2_block2-complex-avx2_block1-kernel-jobs:
-  #tags:
-    #- emulated
-  #script:
-    #- ./autogen.sh
-    #- ./configure CFLAGS="-march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_NO_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_NO_OMP"  --with-ftimings --with-redirect --with-real-avx2-block2-kernel-only --with-complex-avx2-block1-kernel-only --enable-single-precision
-    #- make -j 8
-    #- export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
-    #- /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
+intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx2_block2-complex-avx2_block1-kernel-jobs:
+  tags:
+    - emulated
+  script:
+    - ./autogen.sh
+    - ./configure CFLAGS="-march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_NO_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_NO_OMP"  --with-ftimings --with-redirect --with-real-avx2-block2-kernel-only --with-complex-avx2-block1-kernel-only --enable-single-precision
+    - make -j 8
+    - export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
+    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
 
       ##gfortran-single-precision-mpi-noopenmp-ftimings-redirect-real-avx2_block2-complex-avx2_block1-kernel-jobs:
       ##  tags:
@@ -2224,29 +2222,29 @@ intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx_block6-complex-av
       ##      #    - ./test_scripts/get_coverage_summary.sh
 
 
-##real avx2 block4, complex avx2 block2 (emulated)
-
-#intel-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block4-complex-avx2_block2-kernel-jobs:
-  #tags:
-    #- emulated
-  #script:
-    #- ./autogen.sh
-    #- ./configure CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block4-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
-    #- make -j 8
-    #- export OMP_NUM_THREADS=2
-    #- export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
-    #- /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
-
-#gfortran-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block4-complex-avx2_block2-kernel-jobs:
-  #tags:
-    #- emulated
-  #script:
-    #- ./autogen.sh
-    #- ./configure FC=mpif90 CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=haswell -mavx2 -mfma" SCALAPACK_LDFLAGS="$MKL_GFORTRAN_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_GFORTRAN_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block4-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
-    #- make -j 8
-    #- export OMP_NUM_THREADS=2
-    #- export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
-    #- /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
+#real avx2 block4, complex avx2 block2 (emulated)
+
+intel-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block4-complex-avx2_block2-kernel-jobs:
+  tags:
+    - emulated
+  script:
+    - ./autogen.sh
+    - ./configure CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block4-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
+    - make -j 8
+    - export OMP_NUM_THREADS=2
+    - export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
+    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
+
+gfortran-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block4-complex-avx2_block2-kernel-jobs:
+  tags:
+    - emulated
+  script:
+    - ./autogen.sh
+    - ./configure FC=mpif90 CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=haswell -mavx2 -mfma" SCALAPACK_LDFLAGS="$MKL_GFORTRAN_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_GFORTRAN_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block4-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
+    - make -j 8
+    - export OMP_NUM_THREADS=2
+    - export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
+    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
 
       ##gfortran-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block4-complex-avx2_block2-kernel-special-gcov-jobs:
       ##  tags:
@@ -2261,17 +2259,17 @@ intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx_block6-complex-av
       ##      #    - ./test_scripts/get_coverage_summary.sh
 
 
-##real avx2 block4, complex avx2 block2 (emulated)
+#real avx2 block4, complex avx2 block2 (emulated)
 
-#intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx2_block4-complex-avx2_block2-kernel-jobs:
-  #tags:
-    #- emulated
-  #script:
-    #- ./autogen.sh
-    #- ./configure CFLAGS="-march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_NO_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_NO_OMP"  --with-ftimings --with-redirect --with-real-avx2-block4-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
-    #- make -j 8
-    #- export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
-    #- /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
+intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx2_block4-complex-avx2_block2-kernel-jobs:
+  tags:
+    - emulated
+  script:
+    - ./autogen.sh
+    - ./configure CFLAGS="-march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_NO_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_NO_OMP"  --with-ftimings --with-redirect --with-real-avx2-block4-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
+    - make -j 8
+    - export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
+    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
 
       ##gfortran-single-precision-mpi-noopenmp-ftimings-redirect-real-avx2_block4-complex-avx2_block2-kernel-jobs:
       ##  tags:
@@ -2285,29 +2283,29 @@ intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx_block6-complex-av
       ###    - ./test_scripts/get_coverage_summary.sh
 
 
-###real avx2 block6, complex avx2 block2
-
-#intel-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block6-complex-avx2_block2-kernel-jobs:
-  #tags:
-    #- emulated
-  #script:
-    #- ./autogen.sh
-    #- ./configure CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block6-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
-    #- make -j 8
-    #- export OMP_NUM_THREADS=2
-    #- export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
-    #- /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
-
-#gfortran-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block6-complex-avx2_block2-kernel-jobs:
-  #tags:
-    #- emulated
-  #script:
-    #- ./autogen.sh
-    #- ./configure FC=mpif90 CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=haswell -mavx2 -mfma" SCALAPACK_LDFLAGS="$MKL_GFORTRAN_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_GFORTRAN_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block6-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
-    #- make -j 8
-    #- export OMP_NUM_THREADS=2
-    #- export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
-    #- /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
+##real avx2 block6, complex avx2 block2
+
+intel-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block6-complex-avx2_block2-kernel-jobs:
+  tags:
+    - emulated
+  script:
+    - ./autogen.sh
+    - ./configure CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block6-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
+    - make -j 8
+    - export OMP_NUM_THREADS=2
+    - export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
+    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
+
+gfortran-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block6-complex-avx2_block2-kernel-jobs:
+  tags:
+    - emulated
+  script:
+    - ./autogen.sh
+    - ./configure FC=mpif90 CFLAGS="-O3 -march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=haswell -mavx2 -mfma" SCALAPACK_LDFLAGS="$MKL_GFORTRAN_SCALAPACK_MPI_OMP" SCALAPACK_FCFLAGS="$MKL_GFORTRAN_SCALAPACK_FCFLAGS_MPI_OMP" --enable-openmp  --with-ftimings --with-redirect --with-real-avx2-block6-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
+    - make -j 8
+    - export OMP_NUM_THREADS=2
+    - export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
+    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
 
       ##gfortran-single-precision-mpi-openmp-ftimings-redirect-real-avx2_block6-complex-avx2_block2-kernel-special-gcov-jobs:
       ##  tags:
@@ -2322,17 +2320,17 @@ intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx_block6-complex-av
       ###    - ./test_scripts/get_coverage_summary.sh
 
 
-##real avx2 block6, complex avx2 block2 (emulated)
+#real avx2 block6, complex avx2 block2 (emulated)
 
-#intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx2_block6-complex-avx2_block2-kernel-jobs:
-  #tags:
-    #- emulated
-  #script:
-    #- ./autogen.sh
-    #- ./configure CFLAGS="-march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_NO_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_NO_OMP"  --with-ftimings --with-redirect --with-real-avx2-block6-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
-    #- make -j 8
-    #- export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
-    #- /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
+intel-single-precision-mpi-noopenmp-ftimings-redirect-real-avx2_block6-complex-avx2_block2-kernel-jobs:
+  tags:
+    - emulated
+  script:
+    - ./autogen.sh
+    - ./configure CFLAGS="-march=haswell -mavx2 -mfma" FCFLAGS="-O3 -march=core-avx2" SCALAPACK_LDFLAGS="$MKL_INTEL_SCALAPACK_MPI_NO_OMP" SCALAPACK_FCFLAGS="$MKL_INTEL_SCALAPACK_FCFLAGS_MPI_NO_OMP"  --with-ftimings --with-redirect --with-real-avx2-block6-kernel-only --with-complex-avx2-block2-kernel-only --enable-single-precision
+    - make -j 8
+    - export LD_LIBRARY_PATH=$MKL_HOME/lib/intel64:$LD_LIBRARY_PATH
+    - /home/elpa/bin/sde-external-7.45.0-2016-05-09-lin/sde -hsw -- make check TEST_FLAGS='100 25 16'
 
       ##gfortran-single-precision-mpi-noopenmp-ftimings-redirect-real-avx2_block6-complex-avx2_block2-kernel-jobs:
       ##  tags: