1. 26 Feb, 2021 1 commit
    • Paul Fultz II's avatar
      Add more supported operators and optimizations for the cpu backend (#746) · a0b570b2
      Paul Fultz II authored
      
      
      * Add eliminate_data_type pass
      
      * Formatting
      
      * Auto convert quant ops
      
      * Formatting
      
      * Flip the order of decompose
      
      * Compute max size differently
      
      * Formatting
      
      * Clamp values in convert
      
      * Formatting
      
      * Fix loss of precision in reduce
      
      * Formatting
      
      * Fix bugs in reduction
      
      * Fix accumulator type in reference softmax implementation
      
      * Formatting
      
      * Update convert test
      
      * Remove unused variables
      
      * Remove unnecessary quant_dot check
      
      * Formatting
      
      * Add tests
      
      * Formatting
      
      * Remove unused code
      
      * Remove duplicate ops
      
      * Remove blaze dependency
      
      * Use set since shape::type_t is no hashable on gcc 5
      
      * Formatting
      
      * Add dnnl binary op
      
      * Formatting
      
      * Add binary and eltwise
      
      * Formatting
      
      * Add softmax
      
      * Formatting
      
      * Remove unused operators
      
      * Add missing files
      
      * Formatting
      
      * Add lrn
      
      * Formatting
      
      * Add deconvolution
      
      * Formatting
      
      * Change allocate default
      
      * Add reorder
      
      * Formatting
      
      * Add reductions
      
      * Formatting
      
      * Sort lines
      
      * Change literals in another loop
      
      * Add pow operator
      
      * Formatting
      
      * Add pow operator
      
      * Formatting
      
      * Make sure shapes are packed
      
      * Allow broadcasted inputs
      
      * Remove unused operators
      
      * Simplify functions
      
      * Remove softmax
      
      * Add sub and erf functions
      
      * Formatting
      
      * Fix bug
      
      * Formatting
      
      * Improve parallism
      
      * Formatting
      
      * Allow multiple batch dimensions
      
      * Formatting
      
      * Move literal transforms out of lowering
      
      * Formatting
      
      * Add gather operator
      
      * Sort lines
      
      * Add early exit for carry
      
      * Formatting
      
      * Add missing concat
      
      * Rename macro
      
      * Fix deep nesting
      
      * Formatting
      
      * Fix cppcheck issues
      
      * Remov else
      
      * Move attribute to typedef
      
      * Formatting
      
      * Disable maybe-uninitialized warning since its broken on gcc
      
      * Add constexpr default constructor
      
      * Formatting
      
      * Fix compiler warnings
      
      * Fix adjust_allocation test
      Co-authored-by: default avatarShucai Xiao <shucai@gmail.com>
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      a0b570b2
  2. 06 Jan, 2021 1 commit
    • Shucai Xiao's avatar
      Module impl (#678) · c9b86f1c
      Shucai Xiao authored
      
      
      * add an api get_main_module
      
      * clang format
      
      * modify onnx unit test for module
      
      * clang format
      
      * refactor ops unit test with the get_main_module
      
      * clang format
      
      * code backup
      
      * clang format
      
      * refine module c api
      
      * add python api for module
      
      * clang format
      
      * fix a python api issue
      
      * clang format
      
      * fix cppcheck error
      
      * clang format
      
      * refine unit tests changes
      
      * clang format
      
      * code backup
      
      * code backup
      
      * clang format
      
      * defer some changes to later PRs
      
      * change return of get_main_module from ref to pointer
      
      * clang format
      
      * add unit tests for the get_main_module_api
      
      * clang format
      
      * fix cppcheck error
      
      * clang format
      
      * fix cppcheck error
      
      * clang format
      
      * add more unit tests for more code change coverage
      
      * clang format
      
      * fixed a unit test error
      
      * clang format
      
      * fix unit test
      
      * clang format
      
      * code backup
      
      * code change for more code coverage
      
      * change program to module in various passes and matcher
      
      * clang format
      
      * modify the pass API
      
      * code backup
      
      * code backup
      
      * clang format
      
      * code backup
      
      * clang format
      
      * Add option to no generate a destroy method
      
      * Formatting
      
      * fix some review comments
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * clang format
      
      * code backup
      
      * code backup
      
      * clang format
      
      * fix cppcheck errors
      
      * clang format
      
      * clang format
      
      * fix build errors
      
      * clang format
      
      * modify gpu unit tests to using module
      
      * clang format
      
      * fix cppcheck error
      
      * clang format
      
      * Add flag to enable cpu backend
      
      * Make buffers shared
      
      * Enable optimizations
      
      * Formatting
      
      * fix review comments
      
      * code backup
      
      * clang format
      
      * code backup
      
      * clang format
      
      * fix a bug related to a unit test
      
      * clang format
      
      * clang format
      
      * fix a build error
      
      * remove unnecessary code
      
      * remove unnecessary files
      
      * code backup
      
      * clang format
      
      * remove the compile function from the module class
      
      * clang format
      
      * clang format
      
      * remove the context parameter from the from_value method of the module class
      
      * code refinement
      
      * clang format
      
      * merge changes from develop branch
      
      * clang format
      
      * fix cppcheck error
      
      * clang format
      
      * fix a build error
      
      * fixed a merge error
      
      * fix cppcheck error
      
      * fixed review comments
      
      * clang format
      
      * fix cppcheck error
      
      * fix a cppcheck error
      
      * fix cppcheck error
      
      * fix build error caused by merge
      
      * Add missing has_op function
      
      * Formatting
      
      * merge changes from develop branch
      
      * fix a cppcheck error
      
      * fixed some review comments
      
      * clang format
      
      * remove the begin/end function of the program class
      
      * clang format
      
      * refine code and fix cppcheck error
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * add unit tests for more code coverage
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * fix a build error in debug mode
      
      * clang format
      Co-authored-by: default avatarPaul <pfultz2@yahoo.com>
      c9b86f1c
  3. 14 Dec, 2020 1 commit
    • Paul Fultz II's avatar
      Use dnnl for cpu backend (#688) · 406afeb8
      Paul Fultz II authored
      
      
      * Add flag to enable cpu backend
      
      * Make buffers shared
      
      * Enable optimizations
      
      * Add onednn
      
      * Formatting
      
      * Formatting
      
      * Add dnnl header
      
      * Formatting
      
      * Rewrite rnn first
      
      * Formatting
      
      * Call reference implementation
      
      * Formatting
      
      * Make literal data shared
      
      * Formatting
      
      * Add convolution
      
      * Formatting
      
      * Compensate for dilation
      
      * Formatting
      
      * Use name/make_op instead
      
      * Formatting
      
      * Rename gemm header
      
      * Formatting
      
      * Add dnnl convolution/gemm operators
      
      * Formatting
      
      * Add eliminate_contiguous
      
      * Add faster pointwise operators
      
      * Formatting
      
      * Formatting
      
      * Formatting
      
      * Add dnnl op class
      
      * Formatting
      
      * Add add op
      
      * Formatting
      
      * Add concat operator
      
      * Formatting
      
      * Add more ops
      
      * Create descriptor during finalization
      
      * Formatting
      
      * Dont rewrite pooling
      
      * Enable memory coloring
      
      * Formatting
      
      * Add output aliases
      
      * Formatting
      
      * Fix errors
      
      * Formatting
      
      * Convert literals
      
      * Add missing file
      
      * Remove batch_norm
      
      * Formatting
      
      * Use strides
      
      * Formatting
      
      * Add some debug checks
      
      * Formatting
      
      * Fix big in adjusting shape for gemm
      
      * Formatting
      
      * Fix fallback dot operator
      
      * Zero initialize buffers
      
      * Add suport for group convolutions
      
      * Formatting
      
      * Make adjust allocation target independent
      
      * Formatting
      
      * Enable adjust_allocation for gpu/cpu
      
      * Formatting
      
      * Add copy to allocation model
      
      * Formatting
      
      * Add copy operator
      
      * Formatting
      
      * Better handling of output parameters in adjust_allocation
      
      * Formatting
      
      * Build with dnnl
      
      * Make dnnl required
      
      * Fix compile error
      
      * Tidy fixes
      
      * Formatting
      
      * Tidy fixes
      
      * Formatting
      
      * Fix more tidy issues
      
      * Formatting
      
      * Add mul op
      
      * Add mul op
      
      * Set c compiler to clang as well
      
      * Compensate for normalized compute shape
      
      * Formatting
      
      * Fix cppcheck errors
      
      * Formatting
      
      * Add onednn library to hcc
      
      * Guard clang pragmas
      
      * Disable cpu mode for gcc for now
      
      * Leave it enabled it for gcc 7
      
      * Fix cppcheck suppresion
      
      * Fix compile error on gcc 5
      
      * Remove unused code
      Co-authored-by: default avatarShucai Xiao <shucai.xiao@amd.com>
      Co-authored-by: default avatarmvermeulen <5479696+mvermeulen@users.noreply.github.com>
      406afeb8
  4. 11 Nov, 2020 1 commit
  5. 15 Nov, 2019 1 commit
    • Paul Fultz II's avatar
      Add option to do offload copying automatically (#403) · 81b0ff5d
      Paul Fultz II authored
      * Add compiler options
      
      * Add copy operators
      
      * Formatting
      
      * Use run_passes in tests
      
      * Formatting
      
      * Use run_pass in schedule test
      
      * Formatting
      
      * Add compile_options to get_passes in target
      
      * Formatting
      
      * Offload copy option
      
      * Formatting
      
      * Copy using pinned memory
      
      * Formatting
      
      * Improve performance of gpu copying
      
      * Formatting
      
      * Dont copy
      
      * Formatting
      
      * Always make an extra copy
      
      * Formatting
      
      * Remove unused write op
      
      * Add missing include
      
      * Remove copy_to_gpu function in python api
      
      * Make offload copy disabled by default on C++
      
      * Formatting
      
      * Fix tidy issues
      
      * Formatting
      
      * Fix namespace
      
      * Fix python tests
      
      * Turn clang format off since its broken
      
      * Fix compile error on gcc 5
      
      * Remove commented code
      81b0ff5d
  6. 04 May, 2019 1 commit
  7. 03 May, 2019 2 commits
  8. 02 May, 2019 1 commit
  9. 01 May, 2019 1 commit
  10. 23 Apr, 2019 5 commits
  11. 22 Apr, 2019 1 commit
  12. 19 Apr, 2019 2 commits