Some changes

- Replaced DTFFT_WITHOUT_FFTW with DTFFT_WITH_FFTW - Added new error code: DTFFT_ERROR_INVALID_AUX - Plan execution returns first detected error code, instead of last - Fixed bug with 3d z-slab in-place transpose-only plan execution
ShatrovOA · Oct 13, 2024 · 1dfa52e · 1dfa52e
1 parent 373f544
commit 1dfa52e
Show file tree

Hide file tree

Showing 37 changed files with 179 additions and 159 deletions.
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -4,7 +4,7 @@ project(dtFFT VERSION 0.2.0
               HOMEPAGE_URL "https://github.com/ShatrovOA/dtFFT"
               LANGUAGES Fortran C CXX)
 
-option(DTFFT_WITHOUT_FFTW "Build dtFFT without FFTW support" OFF)
+option(DTFFT_WITH_FFTW "Build dtFFT with FFTW support" OFF)
 option(DTFFT_WITH_MKL "Build dtFFT with MKL DFTI support" OFF)
 option(DTFFT_WITH_CUFFT "Build dtFFT with cufft support" OFF)
 # option(DTFFT_WITH_KFR "Build dtFFT with KFR support" OFF)
@@ -64,11 +64,11 @@ end program"
 HAVE_BLOCK_STATEMENT
 SRC_EXT .F90)
 
-if( DTFFT_WITHOUT_FFTW
+if( NOT DTFFT_WITH_FFTW
     AND NOT DTFFT_WITH_MKL
     # AND NOT DTFFT_WITH_KFR
-    AND NOT DTFFT_WITH_CUFFT
-    AND NOT DTFFT_WITH_VKFFT
+    # AND NOT DTFFT_WITH_CUFFT
+    # AND NOT DTFFT_WITH_VKFFT
 )
   set ( DTFFT_TRANSPOSE_ONLY ON )
 endif()

diff --git a/README.md b/README.md
@@ -1,7 +1,7 @@
 # dtFFT -  DataTyped Fast Fourier Transform
 
 [![Status](https://img.shields.io/badge/status-stable-brightgreen.svg)]()
-![Build Status](https://github.com/ShatrovOA/dtFFT/actions/workflows/main.yml/badge.svg)
+[![dtfft workflow](https://github.com/ShatrovOA/dtFFT/actions/workflows/main.yml/badge.svg)](https://github.com/ShatrovOA/dtFFT/actions/workflows/main.yml)
 [![codecov](https://codecov.io/gh/ShatrovOA/dtFFT/graph/badge.svg?token=6BI4AQVH7Z)](https://codecov.io/gh/ShatrovOA/dtFFT)
 [![License](https://img.shields.io/github/license/ShatrovOA/dtFFT?color=brightgreen&logo=License)]()
 
@@ -60,15 +60,15 @@ To build this library modern (2008+) Fortran compiler is required. This library
 
 | Option   | Possible values | Default value | Description |
 | -------- | ------- | -------- | ------- |
-| DTFFT_WITHOUT_FFTW | on / off | off | Build dtFFT without FFTW support. When `OFF` user need to set `FFTWDIR` environmental variable in order to find FFTW3. Both single and double precision versions are required |
+| DTFFT_WITH_FFTW | on / off | off | Build dtFFT with FFTW support. When enabled user need to set `FFTWDIR` environmental variable in order to find FFTW3 located in custom directory. Both single and double precision versions of library are required |
 | DTFFT_WITH_MKL | on / off | off | Build dtFFT with MKL DFTI support |
 | DTFFT_BUILD_TESTS | on / off | off | Build tests |
 | DTFFT_ENABLE_COVERAGE | on / off | off | Build coverage of library. Only possible with gfortran |
 | DTFFT_BUILD_SHARED | on / off | on | Build shared library |
 | DTFFT_USE_MPI | on / off | on | Use Fortran `mpi` module instead of `mpi_f08` |
 | DTFFT_BUILD_C_CXX_API | on / off | on | Build C/C++ API |
 | DTFFT_ENABLE_PERSISTENT_COMM | on / off | off | In case you are planning to execute plan multiple times then it can be very beneficial to use persistent communications. But user must aware that such communications are created at first call to `execute` or `transpose` subroutines and pointers are saved internally inside MPI. All other plan executions will use those pointers. Take care not to free them. |
-| DTFFT_WITH_CALIPER | on / off | off | Enable library profiler via Caliper. Additional parameter is required to find caliper: `Dcaliper_DIR` |
+| DTFFT_WITH_CALIPER | on / off | off | Enable library profiler via Caliper. Additional parameter is required to find caliper: `caliper_DIR` |
 | DTFFT_MEASURE_ITERS | positive integer | 2 | Number of iterations to run in order to find best plan when passing `DTFFT_MEASURE` or `DTFFT_PATIENT` to effort_flag parameter during plan creation |
 | DTFFT_FORWARD_X_Y | 1 / 2 | 2 | Default id of transposition plan for X -> Y transpose which will be used if plan created with `DTFFT_ESTIMATE` and `DTFFT_MEASURE` effort_flags |
 | DTFFT_BACKWARD_X_Y | 1 / 2 | 2 | Default id of transposition plan for Y -> X transpose which will be used if plan created with `DTFFT_ESTIMATE` and `DTFFT_MEASURE` effort_flags |

diff --git a/include/dtfft.h b/include/dtfft.h
@@ -65,6 +65,7 @@ typedef struct dtfft_plan_t *dtfft_plan;
 #define DTFFT_ERROR_INVALID_R2R_KINDS CONF_DTFFT_ERROR_INVALID_R2R_KINDS
 #define DTFFT_ERROR_R2C_TRANSPOSE_PLAN CONF_DTFFT_ERROR_R2C_TRANSPOSE_PLAN
 #define DTFFT_ERROR_INPLACE_TRANSPOSE CONF_DTFFT_ERROR_INPLACE_TRANSPOSE
+#define DTFFT_ERROR_INVALID_AUX CONF_DTFFT_ERROR_INVALID_AUX
 #define DTFFT_ERROR_R2R_FFT_NOT_SUPPORTED CONF_DTFFT_ERROR_R2R_FFT_NOT_SUPPORTED
 #define DTFFT_ERROR_CUFFTMP_2D_PLAN CONF_DTFFT_ERROR_CUFFTMP_2D_PLAN
 
@@ -82,9 +83,9 @@ do {                                                                          \
 
 // dtFFT transpose_type flags
 
-// Perform XYZ --> YXZ --> ZXY transposition
+// Perform XYZ --> YXZ --> ZXY plan execution
 #define DTFFT_TRANSPOSE_OUT CONF_DTFFT_TRANSPOSE_OUT
-// Perform ZXY --> YXZ --> XYZ transposition
+// Perform ZXY --> YXZ --> XYZ plan execution
 #define DTFFT_TRANSPOSE_IN CONF_DTFFT_TRANSPOSE_IN
 
 // Flags for transpose only plans
@@ -128,7 +129,7 @@ do {                                                                          \
 */
 // Create transpose only plan, no executor needed
 #define DTFFT_EXECUTOR_NONE CONF_DTFFT_EXECUTOR_NONE
-#ifndef DTFFT_WITHOUT_FFTW
+#ifdef DTFFT_WITH_FFTW
 // Use FFTW3
 #define DTFFT_EXECUTOR_FFTW3 CONF_DTFFT_EXECUTOR_FFTW3
 #endif
@@ -279,6 +280,8 @@ dtfft_execute(dtfft_plan plan, void *in, void *out, const int transpose_type, vo
   *                                   - `DTFFT_TRANSPOSE_Y_TO_X`
   *                                   - `DTFFT_TRANSPOSE_Y_TO_Z` (3d plan only)
   *                                   - `DTFFT_TRANSPOSE_Z_TO_Y` (3d plan only)
+  *                                   - `DTFFT_TRANSPOSE_X_TO_Z` (3d plan only)
+  *                                   - `DTFFT_TRANSPOSE_Z_TO_X` (3d plan only)
   *
   * \return `DTFFT_SUCCESS` if plan was executed, error code otherwise
 */
@@ -309,11 +312,8 @@ dtfft_destroy(dtfft_plan *plan);
   * \param[out]     out_starts      Starts of local portion of data in 'fourier' space in reversed order
   * \param[out]     out_counts      Sizes  of local portion of data in 'fourier' space in reversed order
   * \param[out]     alloc_size      Minimum number of elements needs to be allocated for `in`, `out` or `aux` buffers:
-  *
   *                                   - C2C plan: 2 * `alloc_size` * sizeof(double/float) or `alloc_size` * sizeof(dtfft_complex/dtfftf_complex)
-  *
   *                                   - R2R plan: `alloc_size` * sizeof(double/float)
-  *
   *                                   - R2C plan: `alloc_size` * sizeof(double/float)
   * \return `DTFFT_SUCCESS` if call was successfull, error code otherwise
 */
@@ -328,11 +328,8 @@ dtfft_get_local_sizes(dtfft_plan plan, int *in_starts, int *in_counts, int *out_
   *
   * \param[in]      plan            Plan handle
   * \param[out]     alloc_size      Minimum number of elements needs to be allocated for `in`, `out` or `aux` buffers:
-  *
   *                                   - C2C plan: 2 * `alloc_size` * sizeof(double/float) or `alloc_size` * sizeof(dtfft_complex/dtfftf_complex)
-  *
   *                                   - R2R plan: `alloc_size` * sizeof(double/float)
-  *
   *                                   - R2C plan: `alloc_size` * sizeof(double/float)
   * \return `DTFFT_SUCCESS` if call was successfull, error code otherwise
 */

diff --git a/include/dtfft.hpp b/include/dtfft.hpp
@@ -119,8 +119,10 @@ namespace dtfft
   * \param[in]      transpose_type  Type of transpose:
   *                                   - `DTFFT_TRANSPOSE_X_TO_Y`
   *                                   - `DTFFT_TRANSPOSE_Y_TO_X`
-  *                                   - `DTFFT_TRANSPOSE_Y_TO_Z`
-  *                                   - `DTFFT_TRANSPOSE_Z_TO_Y`
+  *                                   - `DTFFT_TRANSPOSE_Y_TO_Z` (3d plan only)
+  *                                   - `DTFFT_TRANSPOSE_Z_TO_Y` (3d plan only)
+  *                                   - `DTFFT_TRANSPOSE_X_TO_Z` (3d plan only)
+  *                                   - `DTFFT_TRANSPOSE_Z_TO_X` (3d plan only)
   *
   * \return Status code of method execution
 */
@@ -139,8 +141,10 @@ namespace dtfft
   * \param[in]      transpose_type  Type of transpose:
   *                                   - `DTFFT_TRANSPOSE_X_TO_Y`
   *                                   - `DTFFT_TRANSPOSE_Y_TO_X`
-  *                                   - `DTFFT_TRANSPOSE_Y_TO_Z`
-  *                                   - `DTFFT_TRANSPOSE_Z_TO_Y`
+  *                                   - `DTFFT_TRANSPOSE_Y_TO_Z` (3d plan only)
+  *                                   - `DTFFT_TRANSPOSE_Z_TO_Y` (3d plan only)
+  *                                   - `DTFFT_TRANSPOSE_X_TO_Z` (3d plan only)
+  *                                   - `DTFFT_TRANSPOSE_Z_TO_X` (3d plan only)
   *
   * \return Status code of method execution
 */
@@ -153,11 +157,8 @@ namespace dtfft
 /** \brief Wrapper around `get_local_sizes`
   *
   * \param[out]     alloc_size      Minimum number of elements needs to be allocated for `in`, `out` or `aux` buffers:
-  *
   *                                   - C2C plan: 2 * `alloc_size` * sizeof(double/float) or `alloc_size` * sizeof(dtfft_complex/dtfftf_complex)
-  *
   *                                   - R2R plan: `alloc_size` * sizeof(double/float)
-  *
   *                                   - R2C plan: `alloc_size` * sizeof(double/float)
   *
   * \return Status code of method execution
@@ -175,11 +176,8 @@ namespace dtfft
   * \param[out]   out_starts            Starts of local portion of data in 'fourier' space in reversed order
   * \param[out]   out_counts            Sizes  of local portion of data in 'fourier' space in reversed order
   * \param[out]   alloc_size            Minimum number of elements needs to be allocated for `in`, `out` or `aux` buffers:
-  *
   *                                       - C2C plan: 2 * `alloc_size` * sizeof(double/float) or `alloc_size` * sizeof(dtfft_complex/dtfftf_complex)
-  *
   *                                       - R2R plan: `alloc_size` * sizeof(double/float)
-  *
   *                                       - R2C plan: `alloc_size` * sizeof(double/float)
   *
   * \return Status code of method execution
@@ -197,11 +195,8 @@ namespace dtfft
   * \param[out]   out_starts            Starts of local portion of data in 'fourier' space in reversed order
   * \param[out]   out_counts            Sizes  of local portion of data in 'fourier' space in reversed order
   * \param[out]   alloc_size            Minimum number of elements needs to be allocated for `in`, `out` or `aux` buffers:
-  *
   *                                       - C2C plan: 2 * `alloc_size` * sizeof(double/float) or `alloc_size` * sizeof(dtfft_complex/dtfftf_complex)
-  *
   *                                       - R2R plan: `alloc_size` * sizeof(double/float)
-  *
   *                                       - R2C plan: `alloc_size` * sizeof(double/float)
   *
   * \return Status code of method execution

diff --git a/include/dtfft_config.h.in b/include/dtfft_config.h.in
@@ -1,11 +1,11 @@
 #ifndef DTFFT_CONFIG_H
 #define DTFFT_CONFIG_H
 
-#cmakedefine DTFFT_WITHOUT_FFTW
+#cmakedefine DTFFT_WITH_FFTW
 #cmakedefine DTFFT_WITH_MKL
-#cmakedefine DTFFT_WITH_CUFFT
-#cmakedefine DTFFT_WITH_KFR
-// #cmakedefine DTFFT_WITH_VKFFT
+/* #cmakedefine DTFFT_WITH_CUFFT */
+/* #cmakedefine DTFFT_WITH_KFR */
+/* #cmakedefine DTFFT_WITH_VKFFT */
 #cmakedefine DTFFT_TRANSPOSE_ONLY
 
 
@@ -40,9 +40,9 @@
 #define CONF_DTFFT_EXECUTOR_NONE 0
 #define CONF_DTFFT_EXECUTOR_FFTW3 +1
 #define CONF_DTFFT_EXECUTOR_MKL +2
-#define CONF_DTFFT_EXECUTOR_CUFFT +3
+/* #define CONF_DTFFT_EXECUTOR_CUFFT +3 */
 /* #define CONF_DTFFT_EXECUTOR_KFR +4 */
-#define CONF_DTFFT_EXECUTOR_VKFFT +5
+/* #define CONF_DTFFT_EXECUTOR_VKFFT +5 */
 
 #define CONF_DTFFT_SUCCESS 0
 #define CONF_DTFFT_ERROR_MPI_FINALIZED (-1)
@@ -60,6 +60,7 @@
 #define CONF_DTFFT_ERROR_INVALID_R2R_KINDS 12
 #define CONF_DTFFT_ERROR_R2C_TRANSPOSE_PLAN 13
 #define CONF_DTFFT_ERROR_INPLACE_TRANSPOSE 14
+#define CONF_DTFFT_ERROR_INVALID_AUX 15
 #define CONF_DTFFT_ERROR_R2R_FFT_NOT_SUPPORTED 101
 #define CONF_DTFFT_ERROR_CUFFTMP_2D_PLAN 200
 

diff --git a/src/dtfft.F90 b/src/dtfft.F90
@@ -47,7 +47,7 @@ module dtfft
 
 ! 1d FFT External Executor types
 public :: DTFFT_EXECUTOR_NONE
-#ifndef DTFFT_WITHOUT_FFTW
+#ifdef DTFFT_WITH_FFTW
 public  :: DTFFT_EXECUTOR_FFTW3
 #endif
 #ifdef DTFFT_WITH_MKL