[A5] Add buffer-id sync ops (get_buf/rls_buf)#169
Merged
zhangstevenunity merged 1 commit intoMar 3, 2026
Conversation
Introduce pto.get_buf/pto.rls_buf to model A5 BufID synchronization and lower them to CCEC builtins get_buf/rls_buf in EmitC. Also add an InjectSync .pto smoke sample + runop guard to ensure lowering stays intact. Tests: - ninja -C build ptoas _pto - PYTHONPATH=... bash test/samples/runop.sh all
liggest
pushed a commit
to liggest/PTOAS
that referenced
this pull request
Apr 27, 2026
* feat: add TileOps templates and basic test cases for tcolexpand operations * test: add tcolexpand operators test cases * fix: 添加TODO说明tcolexpanddiv需要高精度版本 * feat: fp32使用vexpdif实现tcolexpandexpdif，fp16使用vsub+vexp * fix: add PR386 license headers to template and test files - Add license headers to 7 tcolexpand*_template.py files - Add license headers to test case files (CMakeLists.txt, compare.py, launch.cpp, main.cpp, gen_data.py, cases.py) * feat: register tcolexpand operators in CMakeLists.txt * fix: replace aclFloat16 with uint16_t in tcolexpand test cases - Replace aclFloat16 with uint16_t in main.cpp and launch.cpp (16 files) - Remove duplicate license headers in 5 launch.cpp files - Fix .pto comments: aclFloat16 -> fp16 - Remove unnecessary #include "acl/acl.h" from launch.cpp files - Align with tpartmax implementation pattern --------- Co-authored-by: User <user@example.com>
KurrinQu
pushed a commit
to KurrinQu/PTOAS
that referenced
this pull request
Apr 28, 2026
* feat: add TileOps templates and basic test cases for tcolexpand operations * test: add tcolexpand operators test cases * fix: 添加TODO说明tcolexpanddiv需要高精度版本 * feat: fp32使用vexpdif实现tcolexpandexpdif，fp16使用vsub+vexp * fix: add PR386 license headers to template and test files - Add license headers to 7 tcolexpand*_template.py files - Add license headers to test case files (CMakeLists.txt, compare.py, launch.cpp, main.cpp, gen_data.py, cases.py) * feat: register tcolexpand operators in CMakeLists.txt * fix: replace aclFloat16 with uint16_t in tcolexpand test cases - Replace aclFloat16 with uint16_t in main.cpp and launch.cpp (16 files) - Remove duplicate license headers in 5 launch.cpp files - Fix .pto comments: aclFloat16 -> fp16 - Remove unnecessary #include "acl/acl.h" from launch.cpp files - Align with tpartmax implementation pattern --------- Co-authored-by: User <user@example.com>
Zhendong404
pushed a commit
to Zhendong404/PTOAS
that referenced
this pull request
May 1, 2026
* feat: add TileOps templates and basic test cases for tcolexpand operations * test: add tcolexpand operators test cases * fix: 添加TODO说明tcolexpanddiv需要高精度版本 * feat: fp32使用vexpdif实现tcolexpandexpdif，fp16使用vsub+vexp * fix: add PR386 license headers to template and test files - Add license headers to 7 tcolexpand*_template.py files - Add license headers to test case files (CMakeLists.txt, compare.py, launch.cpp, main.cpp, gen_data.py, cases.py) * feat: register tcolexpand operators in CMakeLists.txt * fix: replace aclFloat16 with uint16_t in tcolexpand test cases - Replace aclFloat16 with uint16_t in main.cpp and launch.cpp (16 files) - Remove duplicate license headers in 5 launch.cpp files - Fix .pto comments: aclFloat16 -> fp16 - Remove unnecessary #include "acl/acl.h" from launch.cpp files - Align with tpartmax implementation pattern --------- Co-authored-by: User <user@example.com>
FangRui0
pushed a commit
to FangRui0/PTOAS
that referenced
this pull request
May 14, 2026
* feat: add TileOps templates and basic test cases for tcolexpand operations * test: add tcolexpand operators test cases * fix: 添加TODO说明tcolexpanddiv需要高精度版本 * feat: fp32使用vexpdif实现tcolexpandexpdif，fp16使用vsub+vexp * fix: add PR386 license headers to template and test files - Add license headers to 7 tcolexpand*_template.py files - Add license headers to test case files (CMakeLists.txt, compare.py, launch.cpp, main.cpp, gen_data.py, cases.py) * feat: register tcolexpand operators in CMakeLists.txt * fix: replace aclFloat16 with uint16_t in tcolexpand test cases - Replace aclFloat16 with uint16_t in main.cpp and launch.cpp (16 files) - Remove duplicate license headers in 5 launch.cpp files - Fix .pto comments: aclFloat16 -> fp16 - Remove unnecessary #include "acl/acl.h" from launch.cpp files - Align with tpartmax implementation pattern --------- Co-authored-by: User <user@example.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
pto.get_buf/pto.rls_buf.PTOToEmitCto the CCEC builtin intrinsicsget_buf(...)/rls_buf(...).Notes
.ptosmoke sample + runner guard to ensure the lowering keeps producingget_buf/rls_bufcalls.Tests
ninja -C build ptoas _ptoPYTHONPATH=<mlir_core>:<PTOAS build/python> bash test/samples/runop.sh all