diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt
index 0c98b6efa..ff94d1fcc 100644
--- a/src/CMakeLists.txt
+++ b/src/CMakeLists.txt
@@ -39,7 +39,7 @@ else()
   find_package(ISMRMRD 1.4.2 REQUIRED)
   # Add ISMRMRD to search path for FFTW3
   set(CMAKE_MODULE_PATH "${CMAKE_MODULE_PATH};${ISMRMRD_DIR}")
-  find_package(FFTW3 COMPONENTS single REQUIRED)
+  find_package(FFTW3 COMPONENTS single double threads REQUIRED)
   ADD_SUBDIRECTORY(xGadgetron)
   set(SIRF_BUILT_WITH_ISMRMRD TRUE PARENT_SCOPE)
   set(ISMRMRD_VERSION ${ISMRMRD_VERSION} PARENT_SCOPE)
diff --git a/src/Registration/cReg/NiftyAladinSym.cpp b/src/Registration/cReg/NiftyAladinSym.cpp
index 84793f82c..79e8832b7 100644
--- a/src/Registration/cReg/NiftyAladinSym.cpp
+++ b/src/Registration/cReg/NiftyAladinSym.cpp
@@ -33,7 +33,11 @@ limitations under the License.
 #include "sirf/Reg/NiftiImageData3D.h"
 #include "sirf/Reg/NiftiImageData3DDeformation.h"
 #include "sirf/Reg/NiftiImageData3DDisplacement.h"
+// Compatibility with NiftyReg builds where _reg_aladin.h still references
+// InputTransform while only TransformationMatrix is declared.
+#define InputTransform TransformationMatrix
 #include <_reg_aladin_sym.h>
+#undef InputTransform
 
 using namespace sirf;
 
diff --git a/src/xGadgetron/cGadgetron/FourierEncoding.cpp b/src/xGadgetron/cGadgetron/FourierEncoding.cpp
index 161de4656..98af3a320 100644
--- a/src/xGadgetron/cGadgetron/FourierEncoding.cpp
+++ b/src/xGadgetron/cGadgetron/FourierEncoding.cpp
@@ -154,6 +154,7 @@ void sirf::CartesianFourierEncoding::forward(MRAcquisitionData& ac, const CFImag
         int kz = nz/2 - kz_lim.center + acq.idx().kspace_encode_step_2;
 
         for (unsigned int c = 0; c < nc; c++) {
+#pragma omp parallel for
             for (unsigned int s = 0; s < nx; s++) {
                 acq.data(s, c) = ci(s, ky, kz, c);
             }
@@ -212,6 +213,7 @@ void sirf::CartesianFourierEncoding::backward(CFImage& img, const MRAcquisitionD
         int z = nz/2 - kz_lim.center + acq.idx().kspace_encode_step_2;
     
         for (unsigned int c = 0; c < nc; c++) {
+#pragma omp parallel for
             for (unsigned int s = 0; s < readout; s++) {
                 ci(s, y, z, c) += acq.data(s, c);
             }