1. 08 Jul, 2021 1 commit
  2. 27 Jun, 2021 2 commits
    • Shucai Xiao's avatar
      Merge branch 'develop' into scatter-op · 4351f46c
      Shucai Xiao authored
      4351f46c
    • Shucai Xiao's avatar
      Inline subgraph (#802) · bc52a8a8
      Shucai Xiao authored
      
      
      * Add definitions for all pointwise operators
      
      * Formatting
      
      * Add cpp generator class
      
      * Formatting
      
      * Move compilation to core
      
      * Formatting
      
      * Add clock to tmp name
      
      * Add dynamic loader
      
      * Formatting
      
      * Add tests for code gen
      
      * Formatting
      
      * Add test for literals
      
      * Formatting
      
      * Use with_char
      
      * Add missing header
      
      * Fix mismerge
      
      * Ignore tidy warning
      
      * Fxx gcc 5 errors
      
      * Apply fixits
      
      * Skip signed bitwise of status
      
      * Remove unused parameters
      
      * Explicitly add c++14 flag
      
      * Fix tidy warning
      
      * unify the compute function signature
      
      * clang format
      
      * make another change
      
      * unify the compute function
      
      * clang format
      
      * remove unnecessary code
      
      * more refinement about the operator compute funciton
      
      * clang format
      
      * add an overload function
      
      * clang format
      
      * add support for axes inputs for sequeeze/unsqueeze/reduce_sum
      
      * clang format
      
      * fix build problems
      
      * backup code changes
      
      * clang format
      
      * Add tuple type to shape class
      
      * Formatting
      
      * fix a bug in parsing quantizelinear operator
      
      * clang format
      
      * fix a cppcheck error
      
      * disable different versions of unit tests for different onnx version
      
      * clang format
      
      * upgrade onnx to 1.8
      
      * update onnx to 1.8.1
      
      * disable two more real models
      
      * clang format
      
      * Make data member private
      
      * Formatting
      
      * Add sub arguments
      
      * Formatting
      
      * Trun clang format off
      
      * Disable clang-format
      
      * fix review comments
      
      * fix the function of assign axes in parsing the squeeze operator
      
      * add unit tests and fix a bug
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * fix a build error
      
      * backup code changes
      
      * clang format
      
      * add more unit tests and add parsing opset version
      
      * clang format
      
      * Improve visiting tuples
      
      * Formatting
      
      * fix cppcheck error
      
      * adding installing the onnx package
      
      * resolve no protobuf compiler
      
      * add an inline subgraph pass
      
      * clang format
      
      * Add more argument tests
      
      * Formatting
      
      * Handle tuple in load
      
      * Formatting
      
      * code backup
      
      * clang format
      
      * Remove .o files
      
      * Add tuple type to api
      
      * Formatting
      
      * fix build errors
      
      * clang format
      
      * code backup
      
      * code backup
      
      * add unit tests for the inline subgraph
      
      * clang format
      
      * refine the inline subgraph and parse if operator
      
      * clang format
      
      * fix cppcheck issue
      
      * clang format
      
      * add unit test for inline subgraph pass
      
      * clang format
      
      * fix format issue
      
      * remove the context from the if operator
      
      * clang format
      
      * simplify the compute functions
      
      * Fix tidy warnings
      
      * fix cppcheck error
      
      * clang format
      
      * fix cppcheck error
      
      * Fix tidy warnings
      
      * fix a cppcheck error
      
      * clang format
      
      * Add a test for share method
      
      * Formatting
      
      * Add a test cpp_type
      
      * add unit tests for more code coverage
      
      * clang format
      
      * add unit tests to have more code coverage
      
      * clang format
      
      * try a comment in jenkins build
      
      * include the install onnnx line
      
      * code backup
      
      * reorder the dependenciesd installed
      
      * refine dockerfile
      
      * fix review comments
      
      * clang format
      
      * remove unnecessary overload function
      
      * fix cppcheck error
      
      * change back the argument test
      
      * Suppress tidy warning
      
      * add the operator get_tuple_elem
      
      * clang format
      
      * add get_tuple_elem to operator include file
      
      * chang if to support multiple operation outputs
      
      * clang format
      
      * optimize inline subgraph
      
      * clang format
      
      * code backup
      
      * clang format
      
      * fix bug
      
      * refine unit tests for tuple output of the if operator
      
      * clang format
      
      * refine a instruction replacement code
      
      * add a unit test and sort all the unit tests alphabetically
      
      * fix cppcheck error
      
      * add more unit tests for multiple op outputs
      
      * clang format
      
      * fix cppcheck error
      
      * Update pass manager to get modules after every pass
      
      * more unit test to cover more scenarios
      
      * clang format
      
      * fixed a bug in a unit test
      
      * add more tests
      
      * clang format
      
      * add more unit tests to have more code coverage
      
      * fix a bug in a unit test
      
      * Add program overload for module
      
      * Formatting
      
      * Hash modules for quicker lookup of modules
      
      * Bump file version
      
      * Add methods to remove modules
      
      * Formatting
      
      * add the tuple type to the support list
      
      * Eliminate unused modules
      
      * Formatting
      
      * Fix test errors
      
      * Foramtting
      
      * Fix tidy issues
      
      * fix problem related to inline subgraph
      
      * clang format
      
      * fix review comments
      
      * fix review comments
      
      * fix review comments
      
      * fix review comments
      
      * clang format
      
      * fix a unit test
      
      * one more code change
      
      * remove an optimization related to the if operator
      
      * clang format
      
      * fix review comments
      Co-authored-by: default avatarPaul <pfultz2@yahoo.com>
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      bc52a8a8
  3. 25 Jun, 2021 11 commits
  4. 23 Jun, 2021 1 commit
  5. 20 Jun, 2021 1 commit
  6. 16 Jun, 2021 1 commit
    • Shucai Xiao's avatar
      Resize linear mode support (#819) · 4fe71058
      Shucai Xiao authored
      
      
      * backup implementation of resize enhancement
      
      * clang format
      
      * code backup for the resize
      
      * clang format
      
      * fix build error for resize operator
      
      * clang format
      
      * tmp code backup
      
      * clang format
      
      * code backup
      
      * clang format
      
      * remove changes in parse_resize
      
      * remove unnecessary changes
      
      * clang format
      
      * add unit test for the bug
      
      * clang format
      
      * remove print code
      
      * remove a semi-colon
      
      * clang format
      
      * fix a tidy error
      
      * clang format
      
      * add contiguous for nonstd input for the resize operator
      
      * clang format
      
      * code backup
      
      * clang format
      
      * fix build error
      
      * code backup
      
      * clang format
      
      * code backup
      
      * code backup
      
      * clang format
      
      * add unit tests for resize_linear
      
      * clang format
      
      * refine a function name
      
      * clang format
      
      * fix cppcheck error
      
      * clang format
      
      * fix cppcheck error
      
      * fix review comments
      
      * clang format
      
      * backup code changes
      
      * clang format
      
      * add unit tests for resize operator
      
      * clang format
      
      * remove an unused header file
      
      * remove an unused header file
      
      * remove unrelated unit tests
      
      * refine parsing resize inputs
      
      * clang format
      
      * fix cppcheck error
      
      * fix cppcheck error
      
      * remove unnecessary code
      
      * clang format
      
      * fix cppcheck error
      
      * clang format
      
      * fixed a bug
      
      * clang format
      
      * fix review comments
      
      * clang format
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      4fe71058
  7. 15 Jun, 2021 1 commit
    • Shucai Xiao's avatar
      Int8 gemm support (#811) · 39bc6161
      Shucai Xiao authored
      
      
      * add a flag to indicate int8x4 input format
      
      * clang format
      
      * code backup
      
      * clang format
      
      * code backup
      
      * clang format
      
      * code backup
      
      * clang format
      
      * code backup
      
      * clang format
      
      * code backup
      
      * clang format
      
      * remove log info
      
      * remove unnecessary changes
      
      * fix cppcheck error
      
      * add unit tests to have more code coverage
      
      * clang format
      
      * add debug info
      
      * remove log info
      
      * fix cppcheck error
      
      * clang format
      
      * clang format
      
      * add one more unit tests for more scenarios
      
      * fix cppcheck error
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * rename p to m
      
      * fix review comments
      
      * refine unit tests
      
      * clang format
      
      * refine unit tests and fixed a bug
      
      * clang format
      
      * fix build error related to rocm4.2
      
      * fix a bug related to alpha and beta
      
      * refine two unit tests related to int8_gemm
      
      * fix cppcheck error
      
      * refine unit test to pass on mi100
      
      * add unit test for packing int8 args
      
      * clang format
      
      * change unit tests back
      
      * disable some unit tests for gpu
      
      * clang format
      
      * refine unit tests to run on mi100
      
      * clang format
      
      * refine unit tests
      
      * refine unit tests
      
      * clang format
      
      * change back a unit test
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      39bc6161
  8. 11 Jun, 2021 3 commits
    • Cagri Eryilmaz's avatar
      Nfnet example (#849) · 0e5682cd
      Cagri Eryilmaz authored
      
      
      * Initial commit for NFNet inference example.
      
      * updates to notebook and readme
      
      * slice op parser changes for nfnet
      
      * ort comparison script
      
      * initial functional notebook example for nfnet-f0
      
      * requirements file and update on onnx file pointer
      
      * update intro text, add second inference for time measurement
      
      * update to nfnet readme
      
      * removing artifact update to parse_slice.cpp, needed updates are in other branch
      
      * typo in nfnet readme
      
      * update to main examples readme
      
      * Initial commit for NFNet inference example.
      
      * updates to notebook and readme
      
      * slice op parser changes for nfnet
      
      * ort comparison script
      
      * initial functional notebook example for nfnet-f0
      
      * requirements file and update on onnx file pointer
      
      * update intro text, add second inference for time measurement
      
      * update to nfnet readme
      
      * removing artifact update to parse_slice.cpp, needed updates are in other branch
      
      * typo in nfnet readme
      
      * update to main examples readme
      
      * remove duplicate import
      
      * formatting
      
      * updates to readme, notebook cleanup, remove not-needed requirement artifact
      
      * Update README.md
      
      * Apply suggestions from code review
      Co-authored-by: default avatarkahmed10 <15948690+kahmed10@users.noreply.github.com>
      Co-authored-by: default avatarkahmed10 <15948690+kahmed10@users.noreply.github.com>
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      0e5682cd
    • Paul Fultz II's avatar
    • Paul's avatar
      Bump version · 8d6140a1
      Paul authored
      8d6140a1
  9. 10 Jun, 2021 2 commits
    • Cagri Eryilmaz's avatar
      Update parse slice (#847) · ade97057
      Cagri Eryilmaz authored
      
      
      * init reverseOp branch: ref op + ref test. WIP
      
      * first passing basic test
      
      * cleanup
      
      * additional axis implementation
      
      * additional test
      
      * ref op implementation vec to int for axis
      
      * ref op test change for axis
      
      * initial gpu files and test
      
      * updates to implementation and test
      
      * fixed some issues
      
      * clang format
      
      * cleanup
      
      * formatting
      
      * removing comments
      
      * changes to parse_slice.cpp debug copy
      
      * cleanup + additional axis  for reverse instruction
      
      * formatting
      
      * remove local size, back to default
      
      * update tests: replace with std functions
      
      * multiple axis for reverse op
      
      * fix a build error
      
      * clang format
      
      * changes to parse_slice.cpp debug copy
      
      * cleanup + additional axis  for reverse instruction
      
      * formatting
      
      * axes update to parse slice
      
      * typo
      
      * more tests
      
      * fix a bug for the reverse device function
      
      * clang format
      
      * fix a bug
      
      * clang format
      
      * ref test updates, multiaxis
      
      * formatting
      
      * formatting, cleanup bool op
      
      * casting for tidy warning
      
      * tidy fix
      
      * remove bool, add steps, check only negative axis
      
      * clang-format
      
      * step op for parse slice
      
      * cleanup & format
      
      * missing axis for logsoftmax_nonstd_input_test
      
      * updated onnx file for logsoftmax_nonstd_input_test
      
      * updates to parse slice. tests for slice+reverse, slice+step+reverse
      
      * removing tests for slice+step+reverse as step requires normalization, will move it to other branch. removed related lines and tests
      
      * duplicate test removal
      
      * some refinement of the code
      
      * clang format
      
      * undefined behavior fix
      
      * undef behavior v2
      
      * formatting
      
      * formatting & updates
      
      * change to parse slice
      
      * update to parse_slice for undef/asan + test update
      
      * formatting
      
      * remove header, no if
      
      * assertions + change the loop from axis to steps for logsoftmax test segfault
      Co-authored-by: default avatarShucai Xiao <Shucai.Xiao@amd.com>
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      ade97057
    • Paul Fultz II's avatar
      Dont match or bind to global instructions (#826) · c72a047f
      Paul Fultz II authored
      
      
      * Add optional header
      
      * Formatting
      
      * Use optional in the matcher
      
      * Foramtting
      
      * Remove program from tests
      
      * Formatting
      
      * Dont bind or match non-local variables
      
      * Formatting
      
      * Fix gcc 5 error
      
      * Format
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      c72a047f
  10. 09 Jun, 2021 2 commits
  11. 08 Jun, 2021 1 commit
    • Cagri Eryilmaz's avatar
      Reverse Op (#846) · 9c54fc4f
      Cagri Eryilmaz authored
      
      
      * init reverseOp branch: ref op + ref test. WIP
      
      * first passing basic test
      
      * cleanup
      
      * additional axis implementation
      
      * additional test
      
      * ref op implementation vec to int for axis
      
      * ref op test change for axis
      
      * initial gpu files and test
      
      * updates to implementation and test
      
      * fixed some issues
      
      * clang format
      
      * cleanup
      
      * formatting
      
      * removing comments
      
      * remove local size, back to default
      
      * update tests: replace with std functions
      
      * multiple axis for reverse op
      
      * fix a build error
      
      * clang format
      
      * more tests
      
      * fix a bug for the reverse device function
      
      * clang format
      
      * fix a bug
      
      * clang format
      
      * ref test updates, multiaxis
      
      * formatting
      Co-authored-by: default avatarShucai Xiao <Shucai.Xiao@amd.com>
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      9c54fc4f
  12. 07 Jun, 2021 2 commits
  13. 02 Jun, 2021 1 commit
  14. 27 May, 2021 1 commit
  15. 26 May, 2021 2 commits
  16. 25 May, 2021 1 commit
  17. 24 May, 2021 2 commits
    • Shucai Xiao's avatar
      Bug split optimization (#817) · b847e868
      Shucai Xiao authored
      
      
      * backup implementation of resize enhancement
      
      * clang format
      
      * code backup for the resize
      
      * clang format
      
      * fix build error for resize operator
      
      * clang format
      
      * tmp code backup
      
      * clang format
      
      * remove changes in parse_resize
      
      * remove unnecessary changes
      
      * clang format
      
      * add unit test for the bug
      
      * clang format
      
      * remove print code
      
      * remove a semi-colon
      
      * clang format
      
      * fix a tidy error
      
      * fix review comments
      
      * clang format
      Co-authored-by: default avatarPaul Fultz II <pfultz2@yahoo.com>
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      b847e868
    • Paul Fultz II's avatar
      Compute dominators (#525) · 7ab06956
      Paul Fultz II authored
      
      
      * rename merge_from to merge_to
      
      * refine comments
      
      * code backup
      
      * clang format
      
      * The first version that can reduce scratch memory usage
      
      * code backup
      
      * clang format
      
      * code backup
      
      * clang format
      
      * fixed a bug related to removing gemm copy
      
      * clang format
      
      * code backup
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * fix unit test failure
      
      * code backup
      
      * clang format
      
      * code base for further investigation
      
      * code with both the forward and backward approach to compute the conflict table
      
      * clang format
      
      * clang format
      
      * backup changes
      
      * remove unnecessary file
      
      * remove unnecessary code
      
      * code backup
      
      * clang format
      
      * code backup
      
      * clang format'
      
      * fix a bug in the code
      
      * clang format
      
      * code backup
      
      * clang format
      
      * remove unused code
      
      * remove unused code
      
      * rename some functions
      
      * remove print code
      
      * code backup
      
      * add dominator to scheduling
      
      * add dominator algorithm to remove unnecessary conflicts
      
      * Remove comment
      
      * Use erase_if instead
      
      * Formatting
      
      * Code clean up:
      
      * Formatting
      
      * Add dominator info class
      
      * Formatting
      
      * Add dom_info
      
      * Formatting
      
      * Add test case and fix some bugs
      
      * Formatting
      
      * Add unit test for scheduler
      
      * Formatting
      
      * Use index map instead of distance
      
      * Formatting
      
      * Add memory coloring test
      
      * Check for conflict in memory coloring
      
      * Formatting
      
      * Use 1 stream by default
      
      * Update to use modules
      
      * Formatting
      
      * Skip live on entry check
      
      * Formatting
      
      * Formatting
      
      * Fix tidy warning
      
      * Fix tidy warning
      
      * Formatting
      
      * Add nolint
      
      * Use C++17 to build everything when using clang
      
      * Remove input names
      
      * Formatting
      
      * Remove input names
      
      * Keep order of params
      
      * Formatting
      Co-authored-by: default avatarShucai Xiao <Shucai.Xiao@amd.com>
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      7ab06956
  18. 23 May, 2021 1 commit
  19. 11 May, 2021 1 commit
  20. 07 May, 2021 1 commit
    • Paul Fultz II's avatar
      Update dead_code_elimination to remove unused modules (#820) · 43230d29
      Paul Fultz II authored
      * Update pass manager to get modules after every pass
      
      * Add program overload for module
      
      * Formatting
      
      * Hash modules for quicker lookup of modules
      
      * Bump file version
      
      * Add methods to remove modules
      
      * Formatting
      
      * Eliminate unused modules
      
      * Formatting
      
      * Fix test errors
      
      * Foramtting
      
      * Fix tidy issues
      43230d29
  21. 06 May, 2021 1 commit
  22. 03 May, 2021 1 commit
    • Cagri Eryilmaz's avatar
      BERT SQuAD Example - Updates (#815) · a2e33148
      Cagri Eryilmaz authored
      
      
      * update to readme for pip3 upgrade, needed for tf2.4. requirement file change. initial commit for bert example update
      
      * remove tokenization.py file
      
      * added tokenizers and bertwordpiecetokenizer to main file
      
      * added tokenizers to requirements file
      
      * changes to run_onnx_squad after importing tokenizers module, to replace py file
      
      * additional post processing tokenizer change in run_onnx_squad.py
      
      * changes to notebook after tokenizers
      
      * cleanup notebook output cells
      
      * typo in readme
      
      * formatting on py file
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      a2e33148