Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bindless][CUDA] Add support for cubemaps #1433

Merged
merged 1 commit into from
Apr 8, 2024

Conversation

Seanst98
Copy link
Contributor

@Seanst98 Seanst98 commented Mar 12, 2024

Add enum to ur_mem_type_t to represent cubemap image type

Add device aspects for cubemap support:

  • UR_DEVICE_INFO_CUBEMAP_SUPPORT_EXP
  • UR_DEVICE_INFO_CUBEMAP_SEAMLESS_FILTERING_SUPPORT_EXP

Add structs/enums for cubemap sampling:

  • ur_exp_sampler_cubemap_properties_t struct to enable seamless filtering between cubemap faces
  • ur_exp_sampler_cubemap_filter_mode_t enum to enable distinguishing between cubemap seamless filtering options

Corresponding DPC++ PR: intel/llvm#12996

@codecov-commenter
Copy link

codecov-commenter commented Mar 12, 2024

Codecov Report

Attention: Patch coverage is 1.42857% with 69 lines in your changes are missing coverage. Please review.

Project coverage is 12.40%. Comparing base (78ef1ca) to head (bda7c56).
Report is 188 commits behind head on main.

Files Patch % Lines
include/ur_print.hpp 0.00% 57 Missing ⚠️
source/loader/ur_print.cpp 0.00% 8 Missing ⚠️
tools/urinfo/urinfo.hpp 0.00% 4 Missing ⚠️

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #1433      +/-   ##
==========================================
- Coverage   14.82%   12.40%   -2.42%     
==========================================
  Files         250      241       -9     
  Lines       36220    36311      +91     
  Branches     4094     4113      +19     
==========================================
- Hits         5369     4506     -863     
- Misses      30800    31801    +1001     
+ Partials       51        4      -47     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@Seanst98
Copy link
Contributor Author

Friendly ping @oneapi-src/unified-runtime-cuda-write, @oneapi-src/unified-runtime-maintain, and @JackAKirk for reviews/approvals

@Seanst98 Seanst98 force-pushed the sean/cubemaps-UR branch 3 times, most recently from 747e022 to bda7c56 Compare March 20, 2024 10:32
@Seanst98 Seanst98 force-pushed the sean/cubemaps-UR branch 4 times, most recently from 872548b to d7ec89a Compare April 2, 2024 09:44
@Seanst98 Seanst98 added the ready to merge Added to PR's which are ready to merge label Apr 2, 2024
Add enum to ur_mem_type_t to represent cubemap image type

Add device aspects for cubemap support:

 - UR_DEVICE_INFO_CUBEMAP_SUPPORT_EXP
 - UR_DEVICE_INFO_CUBEMAP_SEAMLESS_FILTERING_SUPPORT_EXP

Add structs/enums for cubemap sampling:

 - ur_exp_sampler_cubemap_properties_t struct to enable seamless filtering
   between cubemap faces
 - ur_exp_sampler_cubemap_filter_mode_t enum to enable distinguishing
   between cubemap seamless filtering options
@aarongreig aarongreig added the v0.9.x Include in the v0.9.x release label Apr 2, 2024
@kbenzie kbenzie added specification Changes or additions to the specification cuda CUDA adapter specific issues labels Apr 3, 2024
@aarongreig aarongreig merged commit cac3de1 into oneapi-src:main Apr 8, 2024
51 checks passed
@aarongreig
Copy link
Contributor

aarongreig commented Apr 8, 2024

#1433 has merged, please rebase and update the UR tag @Seanst98

edit: (on the llvm PR, where I meant to post this comment)

kbenzie pushed a commit to kbenzie/unified-runtime that referenced this pull request Apr 8, 2024
[Bindless][CUDA] Add support for cubemaps
aarongreig added a commit to aarongreig/unified-runtime that referenced this pull request Apr 9, 2024
…s-UR"

This reverts commit cac3de1, reversing
changes made to befdc7c.
martygrant pushed a commit to intel/llvm that referenced this pull request Apr 9, 2024
Add cubemap support:
 - Allocation and freeing of cubemapped images
 - Unsampled fetching and writing, and sampled reading
 - Device queries for cubemap support
 - Testing for both unsampled and sampled cubemap examples
 - Update the spec with cubemap support

Remove `const` and `&` qualifiers from spec and implementation for
handle parameters in `write_xxx` functions.

Corresponding UR PR:
oneapi-src/unified-runtime#1433

---------

Co-authored-by: Przemek Malon <przemek.malon@codeplay.com>
@kbenzie kbenzie mentioned this pull request Apr 16, 2024
19 tasks
@Seanst98 Seanst98 deleted the sean/cubemaps-UR branch April 17, 2024 14:14
kbenzie pushed a commit that referenced this pull request Apr 17, 2024
[Bindless][CUDA] Add support for cubemaps
kbenzie pushed a commit to kbenzie/llvm that referenced this pull request Apr 18, 2024
Add cubemap support:
 - Allocation and freeing of cubemapped images
 - Unsampled fetching and writing, and sampled reading
 - Device queries for cubemap support
 - Testing for both unsampled and sampled cubemap examples
 - Update the spec with cubemap support

Remove `const` and `&` qualifiers from spec and implementation for
handle parameters in `write_xxx` functions.

Corresponding UR PR:
oneapi-src/unified-runtime#1433

---------

Co-authored-by: Przemek Malon <przemek.malon@codeplay.com>

Resolved Conflicts in:
- Due to not cherry-picking intel#12840
  - sycl/include/sycl/detail/pi.h
- Due to not cherry-picking intel#13181
  - sycl/include/sycl/device_aspect_macros.hpp
  - sycl/include/sycl/info/aspects.def
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cuda CUDA adapter specific issues ready to merge Added to PR's which are ready to merge specification Changes or additions to the specification v0.9.x Include in the v0.9.x release
Projects
None yet
Development

Successfully merging this pull request may close these issues.

7 participants