Test suite - Add QA pass/fail tests for F32 bit depth by r-abishek · Pull Request #665 · ROCm/rpp

r-abishek · 2026-01-27T04:25:57Z

The PR adds necessary changes to pass internal QA testing support for F32 bit depth for next set of 10 functions -
pixelate, resize, rotate, lens_correction, resize_crop_mirror, tensor_sum, tensor_min, tensor_max, tensor_mean, tensor_stddev

Add range checks rpp_pixel_check_0to1 to ensure F32 bit depth QA test pass.
Add necessary bin files for reference output.

* Removed memcpy and used hipHostMalloc for allocation : blend * Removed memcpy and used hipHostMalloc for allocation : brightness * Removed memcpy and used hipHostMalloc for allocation : color cast * Removed memcpy and used hipHostMalloc for allocation : color twist * Removed memcpy and used hipHostMalloc for allocation : contrast * Removed memcpy and used hipHostMalloc for allocation : crop mirror normalize * Removed memcpy and used hipHostMalloc for allocation : Exposure * Removed memcpy and used hipHostMalloc for allocation : Gamma correction * Removed memcpy and used hipHostMalloc for allocation : gaussian filter * Removed memcpy and used hipHostMalloc for allocation : Noise * Removed memcpy and used hipHostMalloc for allocation : Non linear blend * Removed memcpy and used hipHostMalloc for allocation : Resize mirror normalize * Removed memcpy and used hipHostMalloc for allocation : Water * Added hipHostFree for all kernels in test suite * Added hipHostFree for all kernels in test suite * Removed memcpy and used hipHostMalloc for allocation : Flip, spatter, rcm, color temperature * Resolved copilot review comments * Updated version * Removed unused parameter * Updated version in cmakeList * removed the host to device mem copies for warp affine and rotate * Updated version * Removed comment * Updated Chnagelog file * Update patch version from 2.2.0 to 2.2.1 * Update CHANGELOG * Address copilot comments for HIP HOST consistent allocation * Documentation changes for updated memcpy changes * Update ricap outer API to use pinned memory and remove mem copy * Fix memory allocation and deallocation for permutationTensor * Update api/rppt_tensor_effects_augmentations.h Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Fix spelling of noiseProbability and saltProbability * Fix deallocation --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: hmaddise <HazarathKumar.Maddisetty@amd.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

F32 QA test suite upgradation

Copilot

Pull request overview

This PR adds QA testing support for F32 bit depth across 10 functions (pixelate, resize, rotate, lens_correction, resize_crop_mirror, tensor_sum, tensor_min, tensor_max, tensor_mean, tensor_stddev). Changes include adding F32-specific reference output data structures, implementing range checks, updating comparison functions with per-function tolerance cutoffs, fixing scaling issues in JPEG compression distortion, and correcting bilinear interpolation boundary calculations.

Changes:

Added F32 reference output maps for tensor reduction operations (min/max/sum/mean/stddev)
Updated comparison functions to accept test case parameter for dynamic tolerance thresholds
Fixed JPEG compression quantization and scaling logic to match HOST reference implementation
Corrected boundary limits in bilinear interpolation to prevent out-of-bounds reads

Reviewed changes

Copilot reviewed 13 out of 25 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
utilities/test_suite/rpp_test_suite_image.h	Added F32 reference outputs for tensor operations and updated comparison functions with test case parameters
utilities/test_suite/common.py	Enabled HOST support for jpeg_compression_distortion
utilities/test_suite/HOST/Tensor_image_host.cpp	Extended QA comparison to support F32 bit depth for tensor reduction operations
utilities/test_suite/HIP/Tensor_image_hip.cpp	Added qualityTensor parameter and extended F32 QA support
src/modules/tensor/rppt_tensor_geometric_augmentations.cpp	Added qualityTensor parameter to GPU function signature
src/modules/tensor/hip/kernel/jpeg_compression_distortion.cpp	Refactored quantization to use runtime scaling and added input scaling functions
src/modules/tensor/cpu/kernel/warp_affine.cpp	Optimized AVX computations using FMA instructions and fixed source location calculations
src/modules/tensor/cpu/kernel/resize_crop_mirror.cpp	Added clamping for bilinear interpolation source locations and corrected boundary margins
src/modules/tensor/cpu/kernel/resize.cpp	Increased buffer size for transpose operations and corrected bilinear boundary margins
src/modules/tensor/cpu/kernel/lens_correction.cpp	Optimized camera coordinate computation using FMA instructions
src/modules/tensor/cpu/kernel/jpeg_compression_distortion.cpp	Removed quantization table clamping to match reference behavior
src/include/tensor/hip_tensor_executors.hpp	Added qualityTensor parameter to function declaration
api/rppt_tensor_geometric_augmentations.h	Updated GPU API signature with qualityTensor parameter

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

utilities/test_suite/rpp_test_suite_image.h

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

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

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

F32 QA resolved copilot review comments

codecov · 2026-01-29T09:02:13Z

Codecov Report

❌ Patch coverage is 98.50746% with 4 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/modules/tensor/cpu/kernel/lens_correction.cpp	66.67%	4 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop     #665      +/-   ##
===========================================
- Coverage    92.65%   92.65%   -0.00%     
===========================================
  Files          194      194              
  Lines        82918    82926       +8     
===========================================
+ Hits         76827    76833       +6     
- Misses        6091     6093       +2

Files with missing lines	Coverage Δ
.../tensor/cpu/kernel/jpeg_compression_distortion.cpp	`95.87% <100.00%> (-<0.01%)`	⬇️
src/modules/tensor/cpu/kernel/resize.cpp	`99.11% <100.00%> (ø)`
...c/modules/tensor/cpu/kernel/resize_crop_mirror.cpp	`100.00% <100.00%> (ø)`
src/modules/tensor/cpu/kernel/warp_affine.cpp	`100.00% <100.00%> (ø)`
.../tensor/hip/kernel/jpeg_compression_distortion.cpp	`98.89% <100.00%> (-0.25%)`	⬇️
...les/tensor/rppt_tensor_geometric_augmentations.cpp	`96.79% <100.00%> (+0.01%)`	⬆️
src/modules/tensor/cpu/kernel/lens_correction.cpp	`88.60% <66.67%> (-0.10%)`	⬇️

... and 1 file with indirect coverage changes

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

* Travis CI - key error fix * Fix Bug in ColorTwist (#6) (#8) (#9) * Added golden outputs and resolved HOST backend * Updated bin files for median filter and resize crop mirror * Updated bin files * Updated bin files for the next set of kernel F32 QA * Updated bin files for jpeg_compression_distortion * Fixed resize QA failures * Fix for Resize bilinear F32 QA HOST and HIP * Fix for lens correction QA f32 for HOST and HIP for 1e-4 precision * Fixed HIP rcm QA * updates for warp Affine F32 QA * Fix for RCM QA match for U8 and F32 updates AVX * Fix for lens correction AVX * Removed space * Fixed warp affine for every other varient with the updated changes * Add fixes to match precision in quantization * Fix Precision mismatches * Update default cutoff to 1e-5 and specialized cutoff to 1e-4 * F32 QA Fix * Made Quality percentage as arg from testsuite * Resolved copilot comments * Resolved the copilot comments * Resolved Codex comments * HOST and HIP - pinned buffers for respective API (ROCm#628) * Removed memcpy and used hipHostMalloc for allocation : blend * Removed memcpy and used hipHostMalloc for allocation : brightness * Removed memcpy and used hipHostMalloc for allocation : color cast * Removed memcpy and used hipHostMalloc for allocation : color twist * Removed memcpy and used hipHostMalloc for allocation : contrast * Removed memcpy and used hipHostMalloc for allocation : crop mirror normalize * Removed memcpy and used hipHostMalloc for allocation : Exposure * Removed memcpy and used hipHostMalloc for allocation : Gamma correction * Removed memcpy and used hipHostMalloc for allocation : gaussian filter * Removed memcpy and used hipHostMalloc for allocation : Noise * Removed memcpy and used hipHostMalloc for allocation : Non linear blend * Removed memcpy and used hipHostMalloc for allocation : Resize mirror normalize * Removed memcpy and used hipHostMalloc for allocation : Water * Added hipHostFree for all kernels in test suite * Added hipHostFree for all kernels in test suite * Removed memcpy and used hipHostMalloc for allocation : Flip, spatter, rcm, color temperature * Resolved copilot review comments * Updated version * Removed unused parameter * Updated version in cmakeList * removed the host to device mem copies for warp affine and rotate * Updated version * Removed comment * Updated Chnagelog file * Update patch version from 2.2.0 to 2.2.1 * Update CHANGELOG * Address copilot comments for HIP HOST consistent allocation * Documentation changes for updated memcpy changes * Update ricap outer API to use pinned memory and remove mem copy * Fix memory allocation and deallocation for permutationTensor * Update api/rppt_tensor_effects_augmentations.h Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Fix spelling of noiseProbability and saltProbability * Fix deallocation --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: hmaddise <HazarathKumar.Maddisetty@amd.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * resolved review comments * minor comment change * Resolved copilot review comments * Update src/modules/tensor/cpu/kernel/resize.cpp Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/modules/tensor/cpu/kernel/resize.cpp Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/modules/tensor/hip/kernel/jpeg_compression_distortion.cpp Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Updated test suite and resoled review comments * Updated HIP for F32 QA reduction function cases --------- Co-authored-by: Kiriti Gowda <kiriti.nageshgowda@amd.com> Co-authored-by: Lokesh Bonta <lokeswara@multicorewareinc.com> Co-authored-by: sampath117 <snehaa@multicorewareinc.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: ManasaDattaT <tammisetti.manasadatta@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: hmaddise <HazarathKumar.Maddisetty@amd.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Lakshmi Kumar <lakshmi.kumar@amd.com>

* add support for dilate in HOST backend * minor fix in changelog * added golden outputs remove commented code * resolve build errors * Add padding changes in HIP backend * fix sigsev issues * fix QA for 9x9 kernel * Add if condition for pack function and template for unpack and signext function * Fix the rename of preLoadRows and max Comments * Fix Fix remane of Loader and MorphVecLoader * Fix empty space, dilate_row_hip_compute function, removed if & else and aligned indent R. * Fix remove whitespace and restored all unnecessary changes. * Fix remove precision line and reverted back to static cast. * Fix remove empty line, rename of kernelSze & padPolicy and remove {} for single line condition * Fix Indentation of IF condition. * resolved review comments * resolve review comments * Test suite - Add QA pass/fail tests for F32 bit depth (#665) * Travis CI - key error fix * Fix Bug in ColorTwist (#6) (#8) (#9) * Added golden outputs and resolved HOST backend * Updated bin files for median filter and resize crop mirror * Updated bin files * Updated bin files for the next set of kernel F32 QA * Updated bin files for jpeg_compression_distortion * Fixed resize QA failures * Fix for Resize bilinear F32 QA HOST and HIP * Fix for lens correction QA f32 for HOST and HIP for 1e-4 precision * Fixed HIP rcm QA * updates for warp Affine F32 QA * Fix for RCM QA match for U8 and F32 updates AVX * Fix for lens correction AVX * Removed space * Fixed warp affine for every other varient with the updated changes * Add fixes to match precision in quantization * Fix Precision mismatches * Update default cutoff to 1e-5 and specialized cutoff to 1e-4 * F32 QA Fix * Made Quality percentage as arg from testsuite * Resolved copilot comments * Resolved the copilot comments * Resolved Codex comments * HOST and HIP - pinned buffers for respective API (#628) * Removed memcpy and used hipHostMalloc for allocation : blend * Removed memcpy and used hipHostMalloc for allocation : brightness * Removed memcpy and used hipHostMalloc for allocation : color cast * Removed memcpy and used hipHostMalloc for allocation : color twist * Removed memcpy and used hipHostMalloc for allocation : contrast * Removed memcpy and used hipHostMalloc for allocation : crop mirror normalize * Removed memcpy and used hipHostMalloc for allocation : Exposure * Removed memcpy and used hipHostMalloc for allocation : Gamma correction * Removed memcpy and used hipHostMalloc for allocation : gaussian filter * Removed memcpy and used hipHostMalloc for allocation : Noise * Removed memcpy and used hipHostMalloc for allocation : Non linear blend * Removed memcpy and used hipHostMalloc for allocation : Resize mirror normalize * Removed memcpy and used hipHostMalloc for allocation : Water * Added hipHostFree for all kernels in test suite * Added hipHostFree for all kernels in test suite * Removed memcpy and used hipHostMalloc for allocation : Flip, spatter, rcm, color temperature * Resolved copilot review comments * Updated version * Removed unused parameter * Updated version in cmakeList * removed the host to device mem copies for warp affine and rotate * Updated version * Removed comment * Updated Chnagelog file * Update patch version from 2.2.0 to 2.2.1 * Update CHANGELOG * Address copilot comments for HIP HOST consistent allocation * Documentation changes for updated memcpy changes * Update ricap outer API to use pinned memory and remove mem copy * Fix memory allocation and deallocation for permutationTensor * Update api/rppt_tensor_effects_augmentations.h Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Fix spelling of noiseProbability and saltProbability * Fix deallocation --------- Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: hmaddise <HazarathKumar.Maddisetty@amd.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * resolved review comments * minor comment change * Resolved copilot review comments * Update src/modules/tensor/cpu/kernel/resize.cpp Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/modules/tensor/cpu/kernel/resize.cpp Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/modules/tensor/hip/kernel/jpeg_compression_distortion.cpp Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Updated test suite and resoled review comments * Updated HIP for F32 QA reduction function cases --------- Co-authored-by: Kiriti Gowda <kiriti.nageshgowda@amd.com> Co-authored-by: Lokesh Bonta <lokeswara@multicorewareinc.com> Co-authored-by: sampath117 <snehaa@multicorewareinc.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: ManasaDattaT <tammisetti.manasadatta@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: hmaddise <HazarathKumar.Maddisetty@amd.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Lakshmi Kumar <lakshmi.kumar@amd.com> * Erode - HOST and HIP update (#666) * added initial api support for erode * added support for U8 and I8 bitdepths for 3, 5, 7, 9 kernel sizes * added F16 and F32 bitdepth support * added generic kernel support * added golden outputs removed commented code * fix build errors * Fix build and test_suite errors * revert padding changes * updated erode HIP kernel with latest changes * Add F32 QA * minor formatting fixes * minor comment fix * resolve copilot comments * resolve review comments * resolved review comments * Add unpack templating changes and fix segmentation issue * Fix PKD to PKD kernel 9 for Pack and Unpack changes. * Add and template signext function * Fix min Comments * Fix one min Comments * Add unroll and rename of preLoadRows * Fix remane of Loader and MorphVecLoader * Add empty line before comment * Fix remove empty line, rename of kernelSze & padPolicy and remove {} for single line condition * resolved review comments * fix build warnings --------- Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Mukesh Jayakodi <mukesh.jayakodi@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: HazarathKumarM <119284987+HazarathKumarM@users.noreply.github.com> Co-authored-by: Lakshmi Kumar <lakshmi.kumar@amd.com> * fix build errors --------- Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: HazarathKumarM <hazarathkumar@multicorewareinc.com> Co-authored-by: Mukesh Jayakodi <mukesh.jayakodi@multicorewareinc.com> Co-authored-by: Kiriti Gowda <kiritigowda@gmail.com> Co-authored-by: HazarathKumarM <119284987+HazarathKumarM@users.noreply.github.com> Co-authored-by: Kiriti Gowda <kiriti.nageshgowda@amd.com> Co-authored-by: Lokesh Bonta <lokeswara@multicorewareinc.com> Co-authored-by: sampath117 <snehaa@multicorewareinc.com> Co-authored-by: Srihari-mcw <srihari@multicorewareinc.com> Co-authored-by: ManasaDattaT <tammisetti.manasadatta@multicorewareinc.com> Co-authored-by: hmaddise <HazarathKumar.Maddisetty@amd.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Lakshmi Kumar <lakshmi.kumar@amd.com>

kiritigowda and others added 30 commits December 22, 2025 12:56

Travis CI - key error fix

516ea9b

Fix Bug in ColorTwist (#6) (#8) (#9)

73e6f31

Added golden outputs and resolved HOST backend

d25aeda

Updated bin files for median filter and resize crop mirror

b4e4153

Updated bin files

e59c033

Updated bin files for the next set of kernel F32 QA

7a2d46f

Updated bin files for jpeg_compression_distortion

67429cd

Fixed resize QA failures

0e18158

Fix for Resize bilinear F32 QA HOST and HIP

15d4716

Fix for lens correction QA f32 for HOST and HIP for 1e-4 precision

417cb26

Fixed HIP rcm QA

f8234c8

updates for warp Affine F32 QA

b43bf9e

Fix for RCM QA match for U8 and F32 updates AVX

09d1288

Fix for lens correction AVX

9acbf25

Removed space

b092b1c

Fixed warp affine for every other varient with the updated changes

3d98a42

Add fixes to match precision in quantization

48f704c

Fix Precision mismatches

0fba494

Update default cutoff to 1e-5 and specialized cutoff to 1e-4

0fbe2a1

F32 QA Fix

8951bc7

Made Quality percentage as arg from testsuite

6219425

Resolved copilot comments

a0cbdd3

Resolved the copilot comments

679d899

Resolved Codex comments

cd375a3

resolved review comments

82515a7

minor comment change

da2ed27

Resolved copilot review comments

9deaf25

Merge pull request #534 from RooseweltMcW/apr/f32_qa_set2

99db80d

F32 QA test suite upgradation

Merge branch 'ROCm:develop' into ar/test_suite_upgrade_13_f32qa

228738f

r-abishek requested a review from Copilot January 27, 2026 04:25

r-abishek added the enhancement New feature or request label Jan 27, 2026

Copilot AI reviewed Jan 27, 2026

View reviewed changes

r-abishek and others added 6 commits January 26, 2026 20:28

Update src/modules/tensor/cpu/kernel/resize.cpp

3fe814a

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Update src/modules/tensor/cpu/kernel/resize.cpp

1e97d40

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Update src/modules/tensor/hip/kernel/jpeg_compression_distortion.cpp

b4633e4

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Updated test suite and resoled review comments

7e4122f

Updated HIP for F32 QA reduction function cases

17e4214

Merge pull request #557 from RooseweltMcW/apr/f32_qa_set2

b8c72e1

F32 QA resolved copilot review comments

rrawther approved these changes Jan 29, 2026

View reviewed changes

SundarRajan98 added the ci:precheckin label Jan 29, 2026

kiritigowda self-assigned this Feb 3, 2026

kiritigowda and others added 3 commits February 3, 2026 11:03

Merge branch 'develop' into ar/test_suite_upgrade_13_f32qa

61b75b9

Merge branch 'develop' into ar/test_suite_upgrade_13_f32qa

bb59ddd

Merge branch 'develop' into ar/test_suite_upgrade_13_f32qa

99f7411

LakshmiKumar23 merged commit 9fa34ad into ROCm:develop Feb 11, 2026
6 checks passed

SundarRajan98 mentioned this pull request Feb 12, 2026

Update jpegCompressionDistortion API ROCm/MIVisionX#1616

Merged

1 task

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Test suite - Add QA pass/fail tests for F32 bit depth#665

Test suite - Add QA pass/fail tests for F32 bit depth#665
LakshmiKumar23 merged 39 commits intoROCm:developfrom
r-abishek:ar/test_suite_upgrade_13_f32qa

r-abishek commented Jan 27, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

codecov bot commented Jan 29, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

10 participants

Conversation

r-abishek commented Jan 27, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

codecov bot commented Jan 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

10 participants

codecov bot commented Jan 29, 2026 •

edited

Loading