RPP Emboss on HOST and HIP by Srihari-mcw · Pull Request #515 · r-abishek/rpp

Srihari-mcw · 2025-10-30T13:50:19Z

The EMBOSS function applies a convolution operator to a 2D image array to generate an array containing difference values that represent edges in the original image
Optimized the code using AVX2 instructions on the HOST backend for all kernel sizes (3, 5, 7, and 9) for all the bit depths
Added QA support and generated the golden outputs for U8 and F32 bit depths

…_saturation

…and resolved all the comment

…oved

… conditional statements

Srihari-mcw · 2025-11-03T18:47:53Z

Please add documentation sample image changes @RooseweltMcW
Also pls check why the commit names are again in your name, please try avoiding this henceforth

api/rppt_tensor_filter_augmentations.h

* Docs - Bump rocm-docs-core[api_reference] from 1.10.0 to 1.11.0 in /docs/sphinx (r-abishek#487) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.10.0 to 1.11.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.10.0...v1.11.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * RPP Fog augmentation on HOST and HIP (r-abishek#446) * adds Fog tensor support * modified comments minor fix in HIP kernel * changed c style casting to static_cast inside HIP kernel modified few variable names * added note in documentation added fog test case to randomOutputCase in HIP and HOST test suites * Introduced Greyness factor on Host FOG Kernel * Introduced Greyness factor on HIP Side * Added Grey scale support for Raw C code and PLN3 variant * Modified Converstion factor variable * Doxygen Outputs changed * Variable name changes * Changes in HUe Saturation Matrix * Fix output issue * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Updates to 1.9.10 including fog feature --------- Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Lakshmi Kumar <lakshmi.kumar@amd.com> Co-authored-by: Rajy Rawther <Rajy.MeeyakhanRawther@amd.com> Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * RPP Warp Perspective on HOST and HIP (r-abishek#451) * Make initial changes for raw CPP version of warp perspective * Fix calls to compute_warp_perspective_src_loc function * Update changes to go through nearest neighbours case * AVX HOST codes for warp perspective initial * Fixes for accuracy in warp perspective * More fixes for accuracy in warp perspective * Update the cide for AVX version of Planar to Planar * Add bilinear u8 host code for warp perspective * Make updates to include functions for F32 data type * Make updates to use cast instead of set and fix issues with raw C implementation * Add i8 host codes * Add updates for F16 Bilinear Code * Update the initial HIP code for warp perspective * Update fixes for HIP code * Add Warp Perspective Nearest Neighbors F16 code for PKD3_to_PLN3 and PLN3_to_PLN3 * Add updates for PLN to PLN configuration * Add updates for PKD3 to PKD3 case * Rename variables * Update changes to log images separately for Bilinear and Nearest Neighbors * fixed bug in raw c code of PKD-PLN variant * minor bug fix for F16 PLN variants * minor fixes in HOST test suite * Update the HIP code for review comments and refactoring of device functions * Update the comments alignment * Rename functions and add cases in HOST and HIP runTests.py * Update indentations for compuatations and rename vectors * Update documentations and add more reference variables * Make more formatting changes * Make further updates by including test cases * Make updates to use reinterpret cast * Update reinterpret casts for PLN to PLN configuration u8 and i8 codes * Make updates to enclose code inside AVX2 flag * Make further changes to update type casting * Update the version * Make updates to add warp perspective image * Modify comments, update CHANGELOG and update flags * Update further comments in warp perspective * Add more comments for warp perspective * Update based on further review comments * Update the case number for warp_perspective in common.py * Address review comments * Make initial changes for raw CPP version of warp perspective * Fix calls to compute_warp_perspective_src_loc function * Update changes to go through nearest neighbours case * AVX HOST codes for warp perspective initial * Fixes for accuracy in warp perspective * More fixes for accuracy in warp perspective * Update the cide for AVX version of Planar to Planar * Add bilinear u8 host code for warp perspective * Make updates to include functions for F32 data type * Make updates to use cast instead of set and fix issues with raw C implementation * Add i8 host codes * Add updates for F16 Bilinear Code * Update the initial HIP code for warp perspective * Update fixes for HIP code * Add Warp Perspective Nearest Neighbors F16 code for PKD3_to_PLN3 and PLN3_to_PLN3 * Add updates for PLN to PLN configuration * Add updates for PKD3 to PKD3 case * Rename variables * Update changes to log images separately for Bilinear and Nearest Neighbors * fixed bug in raw c code of PKD-PLN variant * minor bug fix for F16 PLN variants * minor fixes in HOST test suite * Update the HIP code for review comments and refactoring of device functions * Update the comments alignment * Rename functions and add cases in HOST and HIP runTests.py * Update indentations for compuatations and rename vectors * Update documentations and add more reference variables * Make more formatting changes * Make further updates by including test cases * Make updates to use reinterpret cast * Update reinterpret casts for PLN to PLN configuration u8 and i8 codes * Make updates to enclose code inside AVX2 flag * Make further changes to update type casting * Make updates to add warp perspective image * Modify comments, update CHANGELOG and update flags * Update further comments in warp perspective * Add more comments for warp perspective * Update based on further review comments * Update the case number for warp_perspective in common.py * Address review comments * Fix conflits with warp perspective * Update version details * Merge branch 'ar/opt_warp_perspective' of https://github.com/r-abishek/rpp into opt_warp_perspective_rebased * Update version to 1.9.10 including warp perspective * Updates to convert to XYWH from LTRB instead of opposite * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Revert changes and convert to ltrb instead of xywh --------- Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Rajy Rawther <Rajy.MeeyakhanRawther@amd.com> Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Package - Updates and bugfixes (r-abishek#488) * Package - remove clang from test * CMakeLists - remove BUILD_WITH_AMD_ADVANCE * Package - Add OMP dependency * Find Packages - Updates * Test Package - Deps * Test - backend Info * Tests - Fix HIP Test Add * Test - Add HIP Path * Test - Find HIP Updates * Tests - Fix HIP compilation * Jenkins - Fix Test (r-abishek#489) * Jenkins - Fix Test * Test - Create sepreate test folder * FileSystem - Find and process * Find Filesystem - Updates * Test - Compiler Updates * Docs - Bump rocm-docs-core[api_reference] from 1.11.0 to 1.12.0 in /docs/sphinx (r-abishek#491) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.11.0 to 1.12.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.11.0...v1.12.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Docs - Bump rocm-docs-core[api_reference] from 1.12.0 to 1.12.1 in /docs/sphinx (r-abishek#495) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.12.0 to 1.12.1. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.12.0...v1.12.1) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Updates and Fixes - Compiler & Libs (r-abishek#493) * Test Suite - Fix HIP Link * Tests - HIP Updates * Test - Link OpenCV * Test - Link dir updates * CMakeLists - Updates * Test Package - Deps * CXX Compiler & ROCm path updates * ROCm Path - Display info * OpenMP - Updates * Package Deps - Remove OpenMP * jpeg * Compiler updates - C++ 14 Removal (r-abishek#496) * pthread removal * c++14 removal --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Docs - Bump rocm-docs-core[api_reference] from 1.12.1 to 1.13.0 in /docs/sphinx (r-abishek#500) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.12.1 to 1.13.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.12.1...v1.13.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * zigzag ordering * zigzag ordering * Compiler updates - C++ 14 Removal (r-abishek#496) * pthread removal * c++14 removal --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Readme & Package - Updates (r-abishek#503) * Readme - Updates * Package - Deps to OpenMP * Tests - Rename tensor tests for clarity (r-abishek#469) * Rename Tensor_host to Tensor_image_host, and runTests to runImageTests * Rename Tensor_hip to Tensor_image_hip, and runTests to runImageTests * Rename all readme runTests.py to runImageTests.py --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * minor changes * Tests - Rename tensor tests for clarity (r-abishek#469) * Rename Tensor_host to Tensor_image_host, and runTests to runImageTests * Rename Tensor_hip to Tensor_image_hip, and runTests to runImageTests * Rename all readme runTests.py to runImageTests.py --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * RPP Threshold - HOST and HIP implementation (r-abishek#456) * added initial support for U8 PLN1-PLN1 variant * added support for U8 PKD3, PLN3 variants * modified algorithm to give RGB output for RGB images * moved common code outside the layout branch conditions * added support for toggle variation of U8 * added golden output for threshold * added threshold output for doxygen * added support for F32 bit depth * added support for I8 bitdepth * added F16 bitdepth support * added HIP support for U8 bitdepth * made changes to support remaining bitdepths * fixed output issues with I8 variant * removed commented code in HOST * added threshold test case in maps used in common.py * modified RPP_VERSION_MINOR value and changelog * fixed issues with doxygen modified globalThreads_x value for HIP kernel * made changes in I8 variants as per review comments * added more details for threshold documentation * Update version to 1.9.10 including threshold * Remove duplicate definitions of functions and minor bug fix * Minor docs fix * Minor docs fix --------- Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * RPP Rain augmentation - HOST and HIP implementation (r-abishek#463) * Add Intial u8 implementation for Rain * Add I8 implementation and Changes based on the Review comments * Initial HIP implementation Add F32 and F16 Tensor Implementation * Add test case for Rain in HIP test suite code cleanup * minor code cleanup * Modified func names and removed unnecessary code * Resolve Review comments * replaced pinned memory with HIP memory for Rain Layer computation * Modified RGB Rain Mask to planar Rain Mask in HIP * Address review comments * Add Rain compute function * Add version changes and Resolve review comments * fix build warnings * Fix the outputs of f16 toggle variants * Revert Rain width changes * Fix pln3 outputs for u8 and i8 bitdepths * Resolve review comments * Modified load and store routines for planar cases * Resolve review comments * Modify docs image * Fix versioning * Updates to 1.9.10 including rain feature --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * Docs - Created a more comprehensive installation from the readme information (r-abishek#504) Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Test suite build fix - Lock to specific 'nifti_clib' commit (r-abishek#506) * Lock nifti_clib commit in readme * Lock nifti_clib commit in common.groovy * Change to sudo apt install half in common.groovy * Debugging stage * Test Package - Updates (r-abishek#507) * Test suite - Error code detection and display (r-abishek#483) * experimental changes to detect error and print in the end in image test suite * Error handling added for host side * Error detection implemented on HIP SIDE * Voxel test suite changes * Changed variable name to camelCase * Changes in srcpath * Changes in Voxel test suite for nonQA case * Consolidated the repeated code and move it as common code * Minor changes based on review commands * Modification for bitDepth in voxel host * Merge with develop branch * Fix on error code display and gaussian Filter * F string bug is resolved * Fix for CI failure and some improvement in error detection * Changes based on review comments * Fix for rain and warp_perspective issue of unable to open file * Enhanced display for non implimented functionality --------- Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: dineshbabu-ravichandran <dineshbabu.ravichandran@multicorewareinc.com> Co-authored-by: dineshbabu-ravichandran <dineshbabu.ravichandran@multicoreinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> * Test Suite - ENUMs for all augmentations to enhance test suite readability (r-abishek#499) * initial commit * removed the usage of supported case list on HOST backend * Add Augmentation enum * removed supported caselists from all the python scripts in HIP backend * replacing case numbers with the enum's on the test suite files * Fix Indentation * Add enums for the swith cases * update Enum's for new cases * Fix errors in unit tests * Semicolon typo fix * Fix the test case naming in QA mode * removes unncessary print statements --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * OpenMP - Updates (r-abishek#510) * Update common.groovy * Fixes for Segmentation fault * Docs - Bump rocm-docs-core[api_reference] from 1.13.0 to 1.14.1 in /docs/sphinx (r-abishek#511) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.13.0 to 1.14.1. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.13.0...v1.14.1) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Test - Change sprintf to snprintf (r-abishek#512) Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Jpeg PKD3 to PKD3 till DCT INV * RPP Bitwise - XOR on HOST and HIP (r-abishek#464) * Update the initial CODE for HIP Implementation of Exclusive OR * Add exclusive_or.hpp hip file * Update the code for initial HOST Code * Make SSE based updatess for exclusive or * Update the code for AVX2 implementation of U8 code * Uncomment pragma * Initial commit for I8 * Add I8 case * Fix issues with PKD3 to PLN3 i8 implementation * Initial updates based on self review * More updates * More cleanup * Update separate code for PLN3 to PLN3 U8 * Update separate code for PLN3 to PLN3 I8 * Update separate code for PLN3 to PLN3 F32 * Fix compilation issues * Fix accuracy issues for PLN3 to PLN3 * Add comments and formatting * Rearrange the function declarations * Add golden outputs for exclusive or * Add AVX2 flags wherever necessary * Update the code to have updated F16 load functions * HIP Code Updates * F16 PLN3 to PLN3 Updates * Update outputs * Rearrange XOR GPU function header * Add empty line * Update aligned length * Updates to make F16 outputs consistent with other bit depths * Add std::nearbyintf in exclusive or hip code * Update the code to use predefined zero vectors * Update to use existing rpp_load96_u8_avx instead of rpp_load96_u8pln3_to_u8pln3 * Update the version * Update changelog * Update CHANGELOG.md * Updates to fix more merge conflicts * Update version to 1.9.10 including exclusive or * Remove duplicate definitions of functions * Updates to just have u8 version of exclusive OR * Fix issues with xor after changes * Update changes to rename exclusive OR to bitwise xor and retain U8 data type alone * Update test suite to have only U8 bit depth * Update test suite to have only U8 bit depth on HOST also * Update condition for data type check * Update condition again for data type check --------- Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Docs - miscellaneous changes (r-abishek#508) * added the image from whatis/readme to the front page * added back the misisng install file into the TOC * added a note about CPU being HOST; added audio functionality; modified the toc * added a reference file for the api that acts as the anchor for a sublist in the toc * Fixing problems with api ref links * Still trying to fix the problems with api ref links --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * jpeg PKD3 to PKD3 with a little distortion * Docs - Bump rocm-docs-core[api_reference] from 1.14.1 to 1.15.0 in /docs/sphinx (r-abishek#515) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.14.1 to 1.15.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.14.1...v1.15.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Jpeg u8 all layouts * Jpeg all layouts U8, F32 * Jpeg Compression all variants in all layouts * Package - Updates for RPM (r-abishek#519) * JPEG Compression distortion * PKD3 PLN3 QA * Docs - Bump rocm-docs-core[api_reference] from 1.15.0 to 1.17.0 in /docs/sphinx (r-abishek#521) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.15.0 to 1.17.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.15.0...v1.17.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * CMakeLists - gfx updates (r-abishek#516) * gfx updates * rocm version check for targets * Use rocm_check_target_ids if available * move gfx942 to default list --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Cordell Bloor <Cordell.Bloor@amd.com> * RPP Restructure - Consolidate handle creation and destruction APIs (r-abishek#513) * Changed to rppcreateHost and rppCreateGPU * Added rppCreate for HOST and HIP * Completely removed RppCreateHOST and rppCreateHIP on BatchPD. * Destroy HOST and GPU is removed * Changes based on review comments * Separated thread and stream as a separate argument * Retained setStream api and related functions * Minor docs fix * Removed empty line * Update CHANGELOG.md * Update CHANGELOG.md version to 1.9.11 * Update CMakeLists.txt version to 1.9.11 * Update rpp_version.h version to 1.9.11 * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md for rppCreate and rpp Destroy * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md * Update CHANGELOG.md for RPP 2.0.0 * Update CMakeLists.txt for RPP 2.0.0 * Update rpp_version.h for RPP 2.0.0 --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * RPP Tensor Support - Bitwise NOT, Bitwise AND, Bitwise OR (r-abishek#520) * Add Initial implementation of Bitwise NOT in HOST backend * Add HIP Implementation for Bitwise Not kernel * Add Bitwise NOT implementation for I8, F32 and F16 bitdepths * Fix output issues for float variants * code cleanup * Modify aligned Length for pln3-pln3 conversion * Modified the casting style and updated doc images * update augmentations maps in test suite * Changes for converting bitwise or and and into u8 bitdepth * Changes for solving build errors * bitwise and & or for u8 on HOST * Minor changes to resolve error due to merging * Limited only support for U8 * Renaming from logical to bitwise * Golden output file is added * Changes based on review comments * REmoved changes in host_logical_operationss.hpp * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Docs - Bump rocm-docs-core[api_reference] from 1.17.0 to 1.17.1 in /docs/sphinx (r-abishek#523) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.17.0 to 1.17.1. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.17.0...v1.17.1) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * RPP Test Suite - Bugfixes for Gaussian filter and QA test summary (r-abishek#524) * Fix the summary and fix the unit test issues of Gaussian filter * Fix performance tests summary table * fix unit test path * revert change * revert changes --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * compact code * corrections after merge * minor modification * minor modification * revert changes * cleanup the code * revert merge changes * cleanup the code * updated the doxygen comments and cleanup * resolve review comments * Fix review comments * resolve merge issues * resolve review comments * cleanup the code * Resolve review comments * Optimize dct fwd and inverse functions * resolve review comments * categorized the code * moved common code of all function * Add comments for load/store functions * Update license to 2025 * Update CHANGELOG.md * Fix docs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Lakshmi Kumar <lakshmi.kumar@amd.com> Co-authored-by: Rajy Rawther <Rajy.MeeyakhanRawther@amd.com> Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: ManasaDattaT <tammisetti.manasadatta@multicorewareinc.com> Co-authored-by: Hansel Yang <hansyang@amd.com> Co-authored-by: dineshbabu-ravichandran <dineshbabu.ravichandran@multicorewareinc.com> Co-authored-by: dineshbabu-ravichandran <dineshbabu.ravichandran@multicoreinc.com> Co-authored-by: root <root@ixt-sjc2-52.local.lan> Co-authored-by: Cordell Bloor <Cordell.Bloor@amd.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

…ocs/sphinx (r-abishek#515) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.14.1 to 1.15.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.14.1...v1.15.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Docs - Bump rocm-docs-core[api_reference] from 1.10.0 to 1.11.0 in /docs/sphinx (r-abishek#487) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.10.0 to 1.11.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.10.0...v1.11.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * RPP Fog augmentation on HOST and HIP (r-abishek#446) * adds Fog tensor support * modified comments minor fix in HIP kernel * changed c style casting to static_cast inside HIP kernel modified few variable names * added note in documentation added fog test case to randomOutputCase in HIP and HOST test suites * Introduced Greyness factor on Host FOG Kernel * Introduced Greyness factor on HIP Side * Added Grey scale support for Raw C code and PLN3 variant * Modified Converstion factor variable * Doxygen Outputs changed * Variable name changes * Changes in HUe Saturation Matrix * Fix output issue * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Updates to 1.9.10 including fog feature --------- Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Lakshmi Kumar <lakshmi.kumar@amd.com> Co-authored-by: Rajy Rawther <Rajy.MeeyakhanRawther@amd.com> Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * RPP Warp Perspective on HOST and HIP (r-abishek#451) * Make initial changes for raw CPP version of warp perspective * Fix calls to compute_warp_perspective_src_loc function * Update changes to go through nearest neighbours case * AVX HOST codes for warp perspective initial * Fixes for accuracy in warp perspective * More fixes for accuracy in warp perspective * Update the cide for AVX version of Planar to Planar * Add bilinear u8 host code for warp perspective * Make updates to include functions for F32 data type * Make updates to use cast instead of set and fix issues with raw C implementation * Add i8 host codes * Add updates for F16 Bilinear Code * Update the initial HIP code for warp perspective * Update fixes for HIP code * Add Warp Perspective Nearest Neighbors F16 code for PKD3_to_PLN3 and PLN3_to_PLN3 * Add updates for PLN to PLN configuration * Add updates for PKD3 to PKD3 case * Rename variables * Update changes to log images separately for Bilinear and Nearest Neighbors * fixed bug in raw c code of PKD-PLN variant * minor bug fix for F16 PLN variants * minor fixes in HOST test suite * Update the HIP code for review comments and refactoring of device functions * Update the comments alignment * Rename functions and add cases in HOST and HIP runTests.py * Update indentations for compuatations and rename vectors * Update documentations and add more reference variables * Make more formatting changes * Make further updates by including test cases * Make updates to use reinterpret cast * Update reinterpret casts for PLN to PLN configuration u8 and i8 codes * Make updates to enclose code inside AVX2 flag * Make further changes to update type casting * Update the version * Make updates to add warp perspective image * Modify comments, update CHANGELOG and update flags * Update further comments in warp perspective * Add more comments for warp perspective * Update based on further review comments * Update the case number for warp_perspective in common.py * Address review comments * Make initial changes for raw CPP version of warp perspective * Fix calls to compute_warp_perspective_src_loc function * Update changes to go through nearest neighbours case * AVX HOST codes for warp perspective initial * Fixes for accuracy in warp perspective * More fixes for accuracy in warp perspective * Update the cide for AVX version of Planar to Planar * Add bilinear u8 host code for warp perspective * Make updates to include functions for F32 data type * Make updates to use cast instead of set and fix issues with raw C implementation * Add i8 host codes * Add updates for F16 Bilinear Code * Update the initial HIP code for warp perspective * Update fixes for HIP code * Add Warp Perspective Nearest Neighbors F16 code for PKD3_to_PLN3 and PLN3_to_PLN3 * Add updates for PLN to PLN configuration * Add updates for PKD3 to PKD3 case * Rename variables * Update changes to log images separately for Bilinear and Nearest Neighbors * fixed bug in raw c code of PKD-PLN variant * minor bug fix for F16 PLN variants * minor fixes in HOST test suite * Update the HIP code for review comments and refactoring of device functions * Update the comments alignment * Rename functions and add cases in HOST and HIP runTests.py * Update indentations for compuatations and rename vectors * Update documentations and add more reference variables * Make more formatting changes * Make further updates by including test cases * Make updates to use reinterpret cast * Update reinterpret casts for PLN to PLN configuration u8 and i8 codes * Make updates to enclose code inside AVX2 flag * Make further changes to update type casting * Make updates to add warp perspective image * Modify comments, update CHANGELOG and update flags * Update further comments in warp perspective * Add more comments for warp perspective * Update based on further review comments * Update the case number for warp_perspective in common.py * Address review comments * Fix conflits with warp perspective * Update version details * Merge branch 'ar/opt_warp_perspective' of https://github.com/r-abishek/rpp into opt_warp_perspective_rebased * Update version to 1.9.10 including warp perspective * Updates to convert to XYWH from LTRB instead of opposite * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Revert changes and convert to ltrb instead of xywh --------- Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Rajy Rawther <Rajy.MeeyakhanRawther@amd.com> Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Package - Updates and bugfixes (r-abishek#488) * Package - remove clang from test * CMakeLists - remove BUILD_WITH_AMD_ADVANCE * Package - Add OMP dependency * Find Packages - Updates * Test Package - Deps * Test - backend Info * Tests - Fix HIP Test Add * Test - Add HIP Path * Test - Find HIP Updates * Tests - Fix HIP compilation * Jenkins - Fix Test (r-abishek#489) * Jenkins - Fix Test * Test - Create sepreate test folder * FileSystem - Find and process * Find Filesystem - Updates * Test - Compiler Updates * Docs - Bump rocm-docs-core[api_reference] from 1.11.0 to 1.12.0 in /docs/sphinx (r-abishek#491) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.11.0 to 1.12.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.11.0...v1.12.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Docs - Bump rocm-docs-core[api_reference] from 1.12.0 to 1.12.1 in /docs/sphinx (r-abishek#495) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.12.0 to 1.12.1. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.12.0...v1.12.1) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Updates and Fixes - Compiler & Libs (r-abishek#493) * Test Suite - Fix HIP Link * Tests - HIP Updates * Test - Link OpenCV * Test - Link dir updates * CMakeLists - Updates * Test Package - Deps * CXX Compiler & ROCm path updates * ROCm Path - Display info * OpenMP - Updates * Package Deps - Remove OpenMP * jpeg * Compiler updates - C++ 14 Removal (r-abishek#496) * pthread removal * c++14 removal --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Docs - Bump rocm-docs-core[api_reference] from 1.12.1 to 1.13.0 in /docs/sphinx (r-abishek#500) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.12.1 to 1.13.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.12.1...v1.13.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * zigzag ordering * zigzag ordering * Compiler updates - C++ 14 Removal (r-abishek#496) * pthread removal * c++14 removal --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Readme & Package - Updates (r-abishek#503) * Readme - Updates * Package - Deps to OpenMP * Tests - Rename tensor tests for clarity (r-abishek#469) * Rename Tensor_host to Tensor_image_host, and runTests to runImageTests * Rename Tensor_hip to Tensor_image_hip, and runTests to runImageTests * Rename all readme runTests.py to runImageTests.py --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * minor changes * Tests - Rename tensor tests for clarity (r-abishek#469) * Rename Tensor_host to Tensor_image_host, and runTests to runImageTests * Rename Tensor_hip to Tensor_image_hip, and runTests to runImageTests * Rename all readme runTests.py to runImageTests.py --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * RPP Threshold - HOST and HIP implementation (r-abishek#456) * added initial support for U8 PLN1-PLN1 variant * added support for U8 PKD3, PLN3 variants * modified algorithm to give RGB output for RGB images * moved common code outside the layout branch conditions * added support for toggle variation of U8 * added golden output for threshold * added threshold output for doxygen * added support for F32 bit depth * added support for I8 bitdepth * added F16 bitdepth support * added HIP support for U8 bitdepth * made changes to support remaining bitdepths * fixed output issues with I8 variant * removed commented code in HOST * added threshold test case in maps used in common.py * modified RPP_VERSION_MINOR value and changelog * fixed issues with doxygen modified globalThreads_x value for HIP kernel * made changes in I8 variants as per review comments * added more details for threshold documentation * Update version to 1.9.10 including threshold * Remove duplicate definitions of functions and minor bug fix * Minor docs fix * Minor docs fix --------- Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * RPP Rain augmentation - HOST and HIP implementation (r-abishek#463) * Add Intial u8 implementation for Rain * Add I8 implementation and Changes based on the Review comments * Initial HIP implementation Add F32 and F16 Tensor Implementation * Add test case for Rain in HIP test suite code cleanup * minor code cleanup * Modified func names and removed unnecessary code * Resolve Review comments * replaced pinned memory with HIP memory for Rain Layer computation * Modified RGB Rain Mask to planar Rain Mask in HIP * Address review comments * Add Rain compute function * Add version changes and Resolve review comments * fix build warnings * Fix the outputs of f16 toggle variants * Revert Rain width changes * Fix pln3 outputs for u8 and i8 bitdepths * Resolve review comments * Modified load and store routines for planar cases * Resolve review comments * Modify docs image * Fix versioning * Updates to 1.9.10 including rain feature --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> * Docs - Created a more comprehensive installation from the readme information (r-abishek#504) Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Test suite build fix - Lock to specific 'nifti_clib' commit (r-abishek#506) * Lock nifti_clib commit in readme * Lock nifti_clib commit in common.groovy * Change to sudo apt install half in common.groovy * Debugging stage * Test Package - Updates (r-abishek#507) * Test suite - Error code detection and display (r-abishek#483) * experimental changes to detect error and print in the end in image test suite * Error handling added for host side * Error detection implemented on HIP SIDE * Voxel test suite changes * Changed variable name to camelCase * Changes in srcpath * Changes in Voxel test suite for nonQA case * Consolidated the repeated code and move it as common code * Minor changes based on review commands * Modification for bitDepth in voxel host * Merge with develop branch * Fix on error code display and gaussian Filter * F string bug is resolved * Fix for CI failure and some improvement in error detection * Changes based on review comments * Fix for rain and warp_perspective issue of unable to open file * Enhanced display for non implimented functionality --------- Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: dineshbabu-ravichandran <dineshbabu.ravichandran@multicorewareinc.com> Co-authored-by: dineshbabu-ravichandran <dineshbabu.ravichandran@multicoreinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> * Test Suite - ENUMs for all augmentations to enhance test suite readability (r-abishek#499) * initial commit * removed the usage of supported case list on HOST backend * Add Augmentation enum * removed supported caselists from all the python scripts in HIP backend * replacing case numbers with the enum's on the test suite files * Fix Indentation * Add enums for the swith cases * update Enum's for new cases * Fix errors in unit tests * Semicolon typo fix * Fix the test case naming in QA mode * removes unncessary print statements --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * OpenMP - Updates (r-abishek#510) * Update common.groovy * Fixes for Segmentation fault * Docs - Bump rocm-docs-core[api_reference] from 1.13.0 to 1.14.1 in /docs/sphinx (r-abishek#511) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.13.0 to 1.14.1. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.13.0...v1.14.1) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Test - Change sprintf to snprintf (r-abishek#512) Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Jpeg PKD3 to PKD3 till DCT INV * RPP Bitwise - XOR on HOST and HIP (r-abishek#464) * Update the initial CODE for HIP Implementation of Exclusive OR * Add exclusive_or.hpp hip file * Update the code for initial HOST Code * Make SSE based updatess for exclusive or * Update the code for AVX2 implementation of U8 code * Uncomment pragma * Initial commit for I8 * Add I8 case * Fix issues with PKD3 to PLN3 i8 implementation * Initial updates based on self review * More updates * More cleanup * Update separate code for PLN3 to PLN3 U8 * Update separate code for PLN3 to PLN3 I8 * Update separate code for PLN3 to PLN3 F32 * Fix compilation issues * Fix accuracy issues for PLN3 to PLN3 * Add comments and formatting * Rearrange the function declarations * Add golden outputs for exclusive or * Add AVX2 flags wherever necessary * Update the code to have updated F16 load functions * HIP Code Updates * F16 PLN3 to PLN3 Updates * Update outputs * Rearrange XOR GPU function header * Add empty line * Update aligned length * Updates to make F16 outputs consistent with other bit depths * Add std::nearbyintf in exclusive or hip code * Update the code to use predefined zero vectors * Update to use existing rpp_load96_u8_avx instead of rpp_load96_u8pln3_to_u8pln3 * Update the version * Update changelog * Update CHANGELOG.md * Updates to fix more merge conflicts * Update version to 1.9.10 including exclusive or * Remove duplicate definitions of functions * Updates to just have u8 version of exclusive OR * Fix issues with xor after changes * Update changes to rename exclusive OR to bitwise xor and retain U8 data type alone * Update test suite to have only U8 bit depth * Update test suite to have only U8 bit depth on HOST also * Update condition for data type check * Update condition again for data type check --------- Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Docs - miscellaneous changes (r-abishek#508) * added the image from whatis/readme to the front page * added back the misisng install file into the TOC * added a note about CPU being HOST; added audio functionality; modified the toc * added a reference file for the api that acts as the anchor for a sublist in the toc * Fixing problems with api ref links * Still trying to fix the problems with api ref links --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * jpeg PKD3 to PKD3 with a little distortion * Docs - Bump rocm-docs-core[api_reference] from 1.14.1 to 1.15.0 in /docs/sphinx (r-abishek#515) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.14.1 to 1.15.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.14.1...v1.15.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Jpeg u8 all layouts * Jpeg all layouts U8, F32 * Jpeg Compression all variants in all layouts * Package - Updates for RPM (r-abishek#519) * JPEG Compression distortion * PKD3 PLN3 QA * Docs - Bump rocm-docs-core[api_reference] from 1.15.0 to 1.17.0 in /docs/sphinx (r-abishek#521) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.15.0 to 1.17.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.15.0...v1.17.0) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * CMakeLists - gfx updates (r-abishek#516) * gfx updates * rocm version check for targets * Use rocm_check_target_ids if available * move gfx942 to default list --------- Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Cordell Bloor <Cordell.Bloor@amd.com> * RPP Restructure - Consolidate handle creation and destruction APIs (r-abishek#513) * Changed to rppcreateHost and rppCreateGPU * Added rppCreate for HOST and HIP * Completely removed RppCreateHOST and rppCreateHIP on BatchPD. * Destroy HOST and GPU is removed * Changes based on review comments * Separated thread and stream as a separate argument * Retained setStream api and related functions * Minor docs fix * Removed empty line * Update CHANGELOG.md * Update CHANGELOG.md version to 1.9.11 * Update CMakeLists.txt version to 1.9.11 * Update rpp_version.h version to 1.9.11 * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md for rppCreate and rpp Destroy * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * Update CHANGELOG.md * Update CHANGELOG.md for RPP 2.0.0 * Update CMakeLists.txt for RPP 2.0.0 * Update rpp_version.h for RPP 2.0.0 --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> * RPP Tensor Support - Bitwise NOT, Bitwise AND, Bitwise OR (r-abishek#520) * Add Initial implementation of Bitwise NOT in HOST backend * Add HIP Implementation for Bitwise Not kernel * Add Bitwise NOT implementation for I8, F32 and F16 bitdepths * Fix output issues for float variants * code cleanup * Modify aligned Length for pln3-pln3 conversion * Modified the casting style and updated doc images * update augmentations maps in test suite * Changes for converting bitwise or and and into u8 bitdepth * Changes for solving build errors * bitwise and & or for u8 on HOST * Minor changes to resolve error due to merging * Limited only support for U8 * Renaming from logical to bitwise * Golden output file is added * Changes based on review comments * REmoved changes in host_logical_operationss.hpp * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * Docs - Bump rocm-docs-core[api_reference] from 1.17.0 to 1.17.1 in /docs/sphinx (r-abishek#523) Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.17.0 to 1.17.1. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](ROCm/rocm-docs-core@v1.17.0...v1.17.1) --- updated-dependencies: - dependency-name: rocm-docs-core[api_reference] dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * RPP Test Suite - Bugfixes for Gaussian filter and QA test summary (r-abishek#524) * Fix the summary and fix the unit test issues of Gaussian filter * Fix performance tests summary table * fix unit test path * revert change * revert changes --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> * compact code * corrections after merge * minor modification * minor modification * revert changes * cleanup the code * revert merge changes * cleanup the code * updated the doxygen comments and cleanup * resolve review comments * Fix review comments * resolve merge issues * resolve review comments * cleanup the code * Resolve review comments * Optimize dct fwd and inverse functions * resolve review comments * categorized the code * moved common code of all function * Add comments for load/store functions * Update license to 2025 * Update CHANGELOG.md * Fix docs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Lakshmi Kumar <lakshmi.kumar@amd.com> Co-authored-by: Rajy Rawther <Rajy.MeeyakhanRawther@amd.com> Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: ManasaDattaT <tammisetti.manasadatta@multicorewareinc.com> Co-authored-by: Hansel Yang <hansyang@amd.com> Co-authored-by: dineshbabu-ravichandran <dineshbabu.ravichandran@multicorewareinc.com> Co-authored-by: dineshbabu-ravichandran <dineshbabu.ravichandran@multicoreinc.com> Co-authored-by: root <root@ixt-sjc2-52.local.lan> Co-authored-by: Cordell Bloor <Cordell.Bloor@amd.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

r-abishek · 2026-02-18T00:48:38Z

@HazarathKumarM ToT merge and Unified API changes to be reflected.

HazarathKumarM · 2026-02-18T04:02:08Z

@HazarathKumarM ToT merge and Unified API changes to be reflected.

Done

r-abishek

@HazarathKumarM Please address these.

r-abishek · 2026-02-18T23:11:21Z

src/include/common/cpu/rpp_cpu_filter.hpp

+inline void flip_kernel(Rpp32f *filterTensor, int kernelSize)
+{
+    Rpp32f temp[kernelSize * kernelSize];
+    for (int i = 0; i < kernelSize; i++)


@HazarathKumarM Why do we need the flip_kernel() function?
*filterTensor seems to be a hard coded 3/5/7/9 size kernel that can be pre-flipped and hardcoded?

r-abishek · 2026-02-18T23:11:50Z

src/modules/tensor/cpu/kernel/emboss.cpp

+        Rpp32f kernel[9] = {
+            -2.0f, -1.0f,  0.0f,
+            -1.0f,  1.0f,  1.0f,
+             0.0f,  1.0f,  2.0f


These can be pre-flipped and stored?

r-abishek · 2026-02-18T23:13:02Z

api/rppt_tensor_filter_augmentations.h

+ * \image html filter_augmentations_emboss_kSize3_img150x150.png Sample 3x3 Output
+ * \image html filter_augmentations_emboss_kSize5_img150x150.png Sample 5x5 Output
+ * \image html filter_augmentations_emboss_kSize7_img150x150.png Sample 7x7 Output
+ * \image html filter_augmentations_emboss_kSize9_img150x150.png Sample 9x9 Output


@HazarathKumarM These png files dont seem to be part of the PR

r-abishek · 2026-02-18T23:15:01Z

src/modules/tensor/hip/kernel/emboss.cpp

+    const float baseKernel[9] = {
+        -2.0f, -1.0f,  0.0f,
+        -1.0f,  1.0f,  1.0f,
+         0.0f,  1.0f,  2.0f


Same comment for the HIP side - Cant the hardcoded baseKernel be pre-flipped - then we avoid flip_kernel() function entirely?

r-abishek · 2026-02-18T23:15:43Z

src/modules/tensor/hip/kernel/emboss.cpp

+    // Apply strength scaling
+    for (int i = 0; i < 81; i++)
+        filter[i] = baseKernel[i] * clampedStrength;
+    flip_kernel(filter, 9);


Same comment for all kernel sizes for HOST and HIP

RooseweltMcW and others added 30 commits May 6, 2025 22:07

Added Hue and Saturation for HOST backend with QA for U8

d5c3b7c

Modiified name for avx and sse parameters

20986b6

Added Hue and Saturation for HIP

7673044

Added Hue and Saturation in HIP backend

0a52564

Added Hue and Saturation for HIP backend

8c9ab1c

Merge remote-tracking branch 'origin/apr/hue_saturation' into apr/hue…

66d653b

…_saturation

Added F32 QA for Hue and Saturaton and made SSE and AVX code generic …

5bfafe8

…and resolved all the comment

Removed : HueParam to match batchPD output -2.0f is done which is rem…

ea34560

…oved

Updated : Golden Output for Hue U8

80d685d

Modified : Hue and Saturation PlN1 not supported condition

51ab30d

Added : Emboss HOST backend with normal C and AVX implementation

b57aaef

Added Golden output for U8 and F32 Emboss

e774fe8

Added : doc image for Hue and Saturation

b9985d2

Modified : Name change for each image format

453b746

Modified : Parameter passing for Hue and Saturation HIP backend

a14a5e4

Modified Hue and saturation HIP parameter passing

25c3b31

Final commit for Hue and Saturation

7ccd6b5

Merge branch 'apr/hue_saturation' into apr/emboss_dropout

4177bd4

Added HIP support for Emboss

79bc25e

Added emboss HIP backend with extended kernel support

db7f750

Added QA golden output for U8 and F32

d7ee52d

Added HIP code for emboss with median filter fix

b1bb38a

Emboss and gaussian filter fix for padding and QA outputs generated

617e567

stash : Raw C 3x3 fix with padding

946c068

Fixed pkd varients convolution function

336852b

QA and pln1 and pln3 fix for emboss

d4aa41f

Fix for kernelSize 9 HOST

60bfb6a

SSE, AVX implementation for Emboss with QA for U8 variant

8eb9cc3

Updated pad logic to handle border cases seperately for performance

985e2c8

Updated for performance testing

7e98036

HazarathKumarM added 6 commits October 29, 2025 04:00

Resolved and deleted unwanted files

8ff3b2b

Deleted conversion files

c887793

Updated spacing and minimalized the border clamping logic to use less…

3479370

… conditional statements

Updated emboss HIP with higher precision modifications

67c6394

Updated inline comments

0a309bf

Updated code to avoid redundant conditional statements in RawC

cfd0555

Srihari-mcw commented Nov 3, 2025

View reviewed changes

api/rppt_tensor_filter_augmentations.h Outdated Show resolved Hide resolved

Srihari-mcw added 3 commits November 17, 2025 23:03

Make changes to emboss to be consistent with gaussian filter changes

93c7102

Compilation and accuracy fixes

5d4312c

Update the condition for padding in emboss

93319fb

r-abishek changed the title ~~Apr/emboss dropout~~ RPP Emboss on HOST and HIP Dec 31, 2025

Merge remote-tracking branch 'tot/develop' into apr/emboss_dropout

a48205f

HazarathKumarM added 2 commits February 17, 2026 21:42

Merge branch 'develop' into apr/emboss_dropout

8d6f487

updated unified api for emboss

74141cc

r-abishek requested changes Feb 18, 2026

View reviewed changes

r-abishek assigned HazarathKumarM Feb 18, 2026

r-abishek added the enhancement New feature or request label Feb 18, 2026

r-abishek changed the base branch from develop to ar/emboss February 18, 2026 23:27

HazarathKumarM added 2 commits February 19, 2026 06:05

resolve review comments

32a586f

cleanup

5a144a2

HazarathKumarM force-pushed the apr/emboss_dropout branch from f5c99e7 to 5a144a2 Compare February 19, 2026 12:12

r-abishek approved these changes Feb 20, 2026

View reviewed changes

r-abishek merged commit 5b8156a into r-abishek:ar/emboss Feb 20, 2026

Conversation

Srihari-mcw commented Oct 30, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Srihari-mcw commented Nov 3, 2025

Uh oh!

Uh oh!

r-abishek commented Feb 18, 2026

Uh oh!

HazarathKumarM commented Feb 18, 2026

Uh oh!

r-abishek left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

Srihari-mcw commented Oct 30, 2025 •

edited

Loading