Tags: fiona-gladwin/rpp
Tags
RPP - float, int & tensor support: required for RALI-SOW3 (ROCm#32) * Changed Channel extract and channel combine function call * updated erode dilate kernals [OCL] * Non Working [FULLY BUILD] code for min_max_loc and mean_stddev * Updated Rain GPU kernel for multiple destination image calls [OCL] * Updated Median, Non Max and Histogram and added support for mean * Updated tensor [OCL] * updated table lookup [OCL] * small updates in mean and stddev [OCL] * Full functioning code for mean and standard deviation [OCL] * Added Support to Min Max Location [OCL] * Added support for gaussian_image_pyramid [OCL] * Added support for laplacian_image_pyramid [OCL] * small modification in LIP [OCL] * small modification in Min Max Location and Mean stddev [OCL] * box filter hisEq [OCL] * Added support for gaussian filter * Added support for bin in Histogram [OCL] * updated sobel [OCL] * Update in Temperature [CPU] * FIX SNP CPU half noise issue [OCL] * fin small change in Absolute difference [OCL] * Small changes in Custom convolution and table lookup [OCL} * Fix regressions due to scripting [cl & CPU]. * fix histogram [OCL] * Updated snow [OCL] * updated snow [CPU] * small update in Snow [OCL] * Modify filter_operations to add gaussian_filter with same backend as blur * Fix issue with rain Grey Scale [OCL] * Fix Rain GPU Transparancy [OCL] * Add Kernel Caching using Map/Kernelmanger * Resolved histogram grayscale issue in GPU * Resolved histogram grayscale issue in GPU * Fix the bug in warp affine planar call * Fix issue with resize crop validation [cl & CPU]. * Cl_enque_buffer, the argument is set to CL_FALSE * Fix Gamma correction [OCL] * minor changes to gamma_correction, vignette commons, flip functionalities * Fix Jitter with new Implementation [CPU & OCL] * Modify brightness bug that gave patches in output * Fix the buy with Lens correction [OCL]. * Fix Median filter issue * Modify rotate to match GPU functionality * Fix median filter * merge abi-dev-host-ms4 to main-hipcl-dev * Fix a round about fix for Hue and Saturation Shift * Modify scale to match GPU functionality * Fix a round about fix for Hue and Saturation Shift * Fix syntax error in hsvkernel * changed CL_False to CL_True in minmax location * Resolve merg * Modify warp affine to match GPU - inversion exists * Add validation for Warp Affine Matrix * changes in Warp Affine * Add Blocking calls [CL_TRUE flag is on] * Removed validation printf statements in the library * Removed a syntax error * Add extra validation for contrast * Fix issue with rain [CPU] * Added support to new Pixelate [OCL & CPU] * Fix issue with Fish eye [OCL] * Modify Histogram Implementation * Histogram Balance Fix * Update Readme.md Amended the list * Update Readme.md * Fix Histogram Planar Version * Add new support to Histogram [OCL] * Remove all files to include batch version * Move Mem-Mgmt_HIP branch files to master * Update Readme.md * Put all the recent changes or RPP here * Fix Border issues in crop mirror normalize and crop * Fix Crop mirror normalize border issue * Add RPP UnitTests * Add f32 support for crop_mirror_normalize * Add f32 support for crop * Add f32 support for resize_crop_mirror * Add f32 support for resize and resize_crop * Add f32 support for color_twist * Correct blur * Add f32 support for rotate * Add f16 host support for rotate, resize, resize_crop, crop, resize_crop_mirror, crop_mirror_normalize, color_twist * Major changes to host test suite * Separate host test suites for pkd3 and pln1 * modify rpp_unittests host * correct additional folder creation and readme * Minor correction in pln1/pkd3 host test scripts * Add basic float tensor support * Add FP32 and FP16 support for Crop function * Fix bug in crop * crop mirror normalize report * Float Support for Rotate GPU * Add Kernel Support in OCL for colorTwist and resize funtionalities * Add float support for ColorTwist and Resize Crop Mirror - FP16 and FP32 * Code Refactoring and Rotate Support for FP16 and FP32 * Fix Rotate Float issue * Fix FP32 Rotate Issue * Add Resize Function * Add Resize Crop Mirror in GPU OCL * Fix Typo * Add Resize Crop GPU FP16 and FP32 support * Update rppdefs.h * Crop Mirror Normalize Support is added * Support for ColorTwist in Float space * Update Colortwwist.cl - temp * Remove MIOPEN dependency in RPP build set-up * Update colortwist.cl * Fix Bug in ColorTwist * Fix Bug in ColorTwist (#6) * API refactoring for fused_functions * Fix make_data-type bug and code formatting * Testsuite for Float Support Functions * Removed the brace in switchcase * Add free statements for unreleased memomry and f16 fix for colortwist * rename folders * Fix Resize for U8 case * minor change in BatchPD host * Fix type error in resize.cl * Fix float errors for resize fucntions * foramt file * Fix Bug in ColorTwist (#6) (ROCm#8) * Fix Bug in ColorTwist (#6) (ROCm#8) (ROCm#9) * Update * update (ROCm#10) * Fix Bug in ColorTwist (#6) * Fix Bug in ColorTwist (#6) (ROCm#8) (ROCm#9) * Update * Format files * New Changes (ROCm#11) * Fix Bug in ColorTwist (#6) * Fix Bug in ColorTwist (#6) (ROCm#8) (ROCm#9) * Update * Format files * Correct f16 color twist host bug * Change test suite to input 0-1 normalized values for all f16/f32 functionalities * Refactor API code for geometry_transforms * Added Testsuite for Float Functions in OCL * AMD Docs * Create install.rst * Update index.rst * Add host support for u8->f16 and u8->f32 for resize, crop, crop_mirror_normalize * Add host support in test suite for u8->f16 and u8->f32 for resize, crop, crop_mirror_normalize * Add host support for i8 in resize, crop, cmn, rotate, resize_crop, resize_crop_mirror and color_twist * Add host test suite support for i8 * Add host support for u8->i8 in crop, resize, crop_mirror_normalize * modify test suite * Add host plan1 test suite to SOW3_HOST * crop mirror normalize full support in w.r.t type change and layout change * Add API calls for CMN function for new set of variations * Fix bug with respect to I8 * change type info in kernels * Fix cmn bub * Support I8 for Rotate * Int 8 support for colortwist and code refactoring * Add int8 support for resize crop mirror function * resize crop mirror int8 support is added * Crop various variations are added * Add crop support for all the conversions * Add host support for resize outputFormatToggle * Add host support for crop outputFormatToggle * Add host support for rotate outputFormatToggle * Add host support for resize_crop outputFormatToggle * Add host support for resize_crop_mirror outputFormatToggle * Add host support for crop_mirror_normalize outputFormatToggle * Add host support for color_twist outputFormatToggle and all other pln->pkd support * Add missing pln3 API for crop host * Major modifications in test suite and ReadMe for pkd3, pln3 and pln1 inputs for host * Modify resize kernel * Add outputtoggle in the API and functions * Add new changes to all the fused function w.r.t to outputFormatToggle * Add pln3 api for Crop on GPU * add missing API for resize cro * Fix compilation bugs * Remove unnecessary functions and fix build bug * Add ocl testing framework * Fix bug in rotate helper * Minor temp changes in test code to accomodate PKD3 input U8 cases with toggle format * Correct resize_u8_i8_pkd * Fix resize kenel issues for output toogle change * colortwist bug fix * Fix colortwist bug * resize tensor fix * Minor mods to both pln3 and pkd3 test suite to accomodate CMN's ability to do U8 format toggles * Corrections in PLN3 input funcitons for host * Fix bugs in Fused function new code * Add changes relatedd to planar format in padded * Fix issues with pln3 colortwist * Fix issue with test suite * Add pln3 testing and fix issues * Modify a few things in test script * Fix pln3 issue for FP16 for Rotate * Fix index issues with Test suit * Add output layout toggle for host API * ix pln3 issues in test suite Fix pln1 issues in testsuite Fix other minor bugs * Change paramerter order in resize pd pln host * remove print statements * Update README.MD * Codacy issues corrections in utilities/rpp-unittests * Codacy issues corrections for resize kernel * Codacy issues corrections in utilities/rpp-unittests OCL/HIP * Codacy issues corrections in utilities/rpp-unittests * Codacy issues corrections in utilities/rpp-unittests * Fix some codecy issues * Remove some Codecy issues in rpp unnittests * Remove a few codecy issues * Remove Print statements Co-authored-by: Muthukumaravel <muthukumaravel@multicorewareinc.com> Co-authored-by: shobana-mcw <shobana@multicorewareinc.com> Co-authored-by: r-abishekmcw <abishek@multicorewareinc.com> Co-authored-by: LokeshBonta <you@example.com> Co-authored-by: Reza <Seyedreza.Najafi@amd.com> Co-authored-by: Swetha B S <swetha@multicorewareinc.com>