Make code compile again; still an error with single precision float

Makefile.am

@@ -132,7 +132,6 @@ endif
 if WITH_REAL_AVX_BLOCK4_KERNEL
   libelpa@SUFFIX@_la_SOURCES += src/elpa2_kernels/elpa2_kernels_real_avx-avx2_4hv_double_precision.c
 if WANT_SINGLE_PRECISION_REAL
-    e ./configure SCALAPACK_LDFLAGS="-L$MKLROOT/lib/intel64 -lmkl_scalapack_lp64 -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lmkl_blacs_intelmpi_lp64 -lpthread -lm -Wl,-rpath,$MKL_HOME/lib/intel64 -L/afs/ipp/.cs/cuda/6.5/amd64_sles11/lib64 -lcublas -I/afs/ipp/.cs/cuda/6.5/amd64_sles11/include" SCALAPACK_FCFLAGS="-L$MKLROOT/mkl/lib/intel64 -lmkl_scalapack_lp64 -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lmkl_blacs_intelmpi_lp64 -lpthread -I$MKLROOT/include/intel64/lp64 -L/afs/ipp/.cs/cuda/6.5/amd64_sles11/lib64 -lcublas -I/afs/ipp/.cs/cuda/6.5/amd64_sles11/include"  --prefix=/home/amarek/ELPA_GPU CFLAGS="-O2" CXXFLAGS="-O2" FCFLAGS="-O0" --enable-gpu-support --with-cuda-path=/afs/ipp/.cs/cuda/6.5/amd64_sles11/
   libelpa@SUFFIX@_la_SOURCES += src/elpa2_kernels/elpa2_kernels_real_avx-avx2_4hv_single_precision.c
 endif
 endif
@@ -507,11 +506,12 @@ TESTS = $(check_SCRIPTS)
 #	echo '$(wrapper)./elpa2_test_real_default_kernel_qr_decomposition@SUFFIX@' > $@
 #	chmod +x $@
 
-if WANT_SINGLE_PRECISION_REAL
+#if WANT_SINGLE_PRECISION_REAL
 #elpa2_test_real_default_kernel_qr_decomposition_single_precision@SUFFIX@.sh:
 #	echo '$(wrapper)./elpa2_test_real_default_kernel_qr_decomposition_single_precision@SUFFIX@' > $@
 #	chmod +x $@
-endif
+#endif
+
 # Preprocessed files (just used for manual inspection)
 mod_precision.i: $(top_srcdir)/src/mod_precision.F90
 	$(CPP) $(CPPFLAGS) -I$(top_builddir)/ -I$(top_srcdir)/ -c $(top_srcdir)/src/mod_precision.F90 -o $@

src/elpa2.F90

@@ -586,7 +586,7 @@ contains
     endif
 
     if (useQRActual) then
-      if (mod(na,nblk) .ne. 0) then
+      if (mod(na,2) .ne. 0) then
         if (wantDebug) then
           write(error_unit,*) "solve_evp_real_2stage: QR-decomposition: blocksize does not fit with matrixsize"
         endif

test/fortran_test_programs/test_elpa2_real_qr_default_kernel_single.F90

@@ -152,9 +152,9 @@ program test_real2_default_kernel_qr_decomposition_single_precision
    !endif
 
    ! override nblk
-   !   nblk = 2
-   !   na   = 4000
-   !   nev  = 1500
+      nblk = 2
+      na   = 4000
+      nev  = 1500
 
    ! make sure na, nbl is even
    if (mod(nblk,2 ) .ne. 0) then