RPP Exclusive-Or on HOST and HIP

CHANGELOG.md

@@ -2,9 +2,16 @@
 
 Full documentation for RPP is available at [https://rocm.docs.amd.com/projects/rpp/en/latest](https://rocm.docs.amd.com/projects/rpp/en/latest)
 
+## (Unreleased) RPP 1.9.9
+
+### Changed
+
+* RPP Tensor Exclusive-Or support on HOST and HIP
+
 ## (Unreleased) RPP 1.9.4
 
-### Changes
+### Changed
+
 * AMD Clang is now the default CXX and C compiler
 * RPP Tensor Box Filter support on HOST
 

CMakeLists.txt

@@ -43,7 +43,7 @@ endif()
 set(CMAKE_CXX_STANDARD 17)
 
 # RPP Version
-set(VERSION "1.9.4")
+set(VERSION "1.9.9")
 
 # Set Project Version and Language
 project(rpp VERSION ${VERSION} LANGUAGES CXX)

include/rpp_version.h

@@ -40,7 +40,7 @@ extern "C" {
 // NOTE: IMPORTANT: Match the version with CMakelists.txt version
 #define RPP_VERSION_MAJOR 1
 #define RPP_VERSION_MINOR 9
-#define RPP_VERSION_PATCH 4
+#define RPP_VERSION_PATCH 9
 #ifdef __cplusplus
 }
 #endif

include/rppt_tensor_logical_operations.h

@@ -86,6 +86,50 @@ RppStatus rppt_bitwise_and_host(RppPtr_t srcPtr1, RppPtr_t srcPtr2, RpptDescPtr
 RppStatus rppt_bitwise_and_gpu(RppPtr_t srcPtr1, RppPtr_t srcPtr2, RpptDescPtr srcDescPtr, RppPtr_t dstPtr, RpptDescPtr dstDescPtr, RpptROIPtr roiTensorPtrSrc, RpptRoiType roiType, rppHandle_t rppHandle);
 #endif // GPU_SUPPORT
 
+/*! \brief Exclusive OR computation on HOST backend for a NCHW/NHWC layout tensor
+ * \details This function computes exclusive OR of corresponding pixels for a batch of RGB(3 channel) / greyscale(1 channel) images with an NHWC/NCHW tensor layout.<br>
+ *          srcPtr depth ranges - Rpp8u (0 to 255), Rpp16f (0 to 1), Rpp32f (0 to 1), Rpp8s (-128 to 127).
+ *          dstPtr depth ranges - Will be same depth as srcPtr.
+ * \image html img150x150.png Sample Input1
+ * \image html img150x150_2.png Sample Input2
+ * \image html logical_operations_exclusive_or_img150x150.png Sample Output
+ * \param [in] srcPtr1 source1 tensor in HOST memory
+ * \param [in] srcPtr2 source2 tensor in HOST memory
+ * \param [in] srcDescPtr source tensor descriptor (Restrictions - numDims = 4, offsetInBytes >= 0, dataType = U8/F16/F32/I8, layout = NCHW/NHWC, c = 1/3)
+ * \param [out] dstPtr destination tensor in HOST memory
+ * \param [in] dstDescPtr destination tensor descriptor (Restrictions - numDims = 4, offsetInBytes >= 0, dataType = U8/F16/F32/I8, layout = NCHW/NHWC, c = same as that of srcDescPtr)
+ * \param [in] roiTensorPtrSrc ROI data in HOST memory, for each image in source tensor (2D tensor of size batchSize * 4, in either format - XYWH(xy.x, xy.y, roiWidth, roiHeight) or LTRB(lt.x, lt.y, rb.x, rb.y))
+ * \param [in] roiType ROI type used (RpptRoiType::XYWH or RpptRoiType::LTRB)
+ * \param [in] rppHandle RPP HOST handle created with <tt>\ref rppCreateWithBatchSize()</tt>
+ * \return A <tt> \ref RppStatus</tt> enumeration.
+ * \retval RPP_SUCCESS Successful completion.
+ * \retval RPP_ERROR* Unsuccessful completion.
+ */
+RppStatus rppt_exclusive_or_host(RppPtr_t srcPtr1, RppPtr_t srcPtr2, RpptDescPtr srcDescPtr, RppPtr_t dstPtr, RpptDescPtr dstDescPtr, RpptROIPtr roiTensorPtrSrc, RpptRoiType roiType, rppHandle_t rppHandle);
+
+#ifdef GPU_SUPPORT
+/*! \brief Exclusive OR computation on HIP backend for a NCHW/NHWC layout tensor
+ * \details This function computes exclusive OR of corresponding pixels for a batch of RGB(3 channel) / greyscale(1 channel) images with an NHWC/NCHW tensor layout.<br>
+ *          srcPtr depth ranges - Rpp8u (0 to 255), Rpp16f (0 to 1), Rpp32f (0 to 1), Rpp8s (-128 to 127).
+ *          dstPtr depth ranges - Will be same depth as srcPtr.
+ * \image html img150x150.png Sample Input1
+ * \image html img150x150_2.png Sample Input2
+ * \image html logical_operations_exclusive_or_img150x150.png Sample Output
+ * \param [in] srcPtr1 source1 tensor in HIP memory
+ * \param [in] srcPtr2 source2 tensor in HIP memory
+ * \param [in] srcDescPtr source tensor descriptor (Restrictions - numDims = 4, offsetInBytes >= 0, dataType = U8/F16/F32/I8, layout = NCHW/NHWC, c = 1/3)
+ * \param [out] dstPtr destination tensor in HIP memory
+ * \param [in] dstDescPtr destination tensor descriptor (Restrictions - numDims = 4, offsetInBytes >= 0, dataType = U8/F16/F32/I8, layout = NCHW/NHWC, c = same as that of srcDescPtr)
+ * \param [in] roiTensorPtrSrc ROI data in HIP memory, for each image in source tensor (2D tensor of size batchSize * 4, in either format - XYWH(xy.x, xy.y, roiWidth, roiHeight) or LTRB(lt.x, lt.y, rb.x, rb.y))
+ * \param [in] roiType ROI type used (RpptRoiType::XYWH or RpptRoiType::LTRB)
+ * \param [in] rppHandle RPP HIP handle created with <tt>\ref rppCreateWithStreamAndBatchSize()</tt>
+ * \return A <tt> \ref RppStatus</tt> enumeration.
+ * \retval RPP_SUCCESS Successful completion.
+ * \retval RPP_ERROR* Unsuccessful completion.
+ */
+RppStatus rppt_exclusive_or_gpu(RppPtr_t srcPtr1, RppPtr_t srcPtr2, RpptDescPtr srcDescPtr, RppPtr_t dstPtr, RpptDescPtr dstDescPtr, RpptROIPtr roiTensorPtrSrc, RpptRoiType roiType, rppHandle_t rppHandle);
+#endif // GPU_SUPPORT
+
 /*! \brief Bitwise OR computation on HOST backend for a NCHW/NHWC layout tensor
  * \details This function computes bitwise OR of corresponding pixels for a batch of RGB(3 channel) / greyscale(1 channel) images with an NHWC/NCHW tensor layout.<br>
  *          srcPtr depth ranges - Rpp8u (0 to 255), Rpp16f (0 to 1), Rpp32f (0 to 1), Rpp8s (-128 to 127).