Files
kompute/CHANGELOG.md
Alejandro Saucedo df5477a2d7 Prep release 0.6.0
2021-01-31 12:00:00 +00:00

13 KiB

Changelog

v0.6.0

Full Changelog

Implemented enhancements:

Fixed bugs:

  • [PYTHON] Support string parameter instead of list for eval_algo_data when passing raw shader as string #93
  • [PYTHON] Fix log_level on the python implementation (using pybind's logging functions) #92

Closed issues:

  • Add documentation for custom operations #128
  • Numpy Array Support and Work Group Configuration in Python Kompute #124
  • Remove references to spdlog in python module #122
  • Setup automated CI testing for PRs using GitHub actions #114
  • Python example type error (pyshader). #111
  • Update all references to operations to not use template #101
  • Getting a undefined reference error while creating a Kompute Manager #100

Merged pull requests:

v0.5.1 (2020-11-12)

Full Changelog

Implemented enhancements:

  • Remove the template params from OpAlgoBase for dispatch layout #57
  • Enable layout to be configured dynamically within shaders #26
  • replaced "static unsigned const" to "static const unsigned" to avoid SWIG parsing error. #95 (0x0f0f0f)
  • Added python bindings with kp as python module #88 (axsaucedo)

Closed issues:

  • Support for MoltenVK? #96
  • Update all examples to use spir-v bytes by default #86

Merged pull requests:

v0.5.0 (2020-11-08)

Full Changelog

Implemented enhancements:

Closed issues:

  • Examples segfault (Linux / mesa / amdgpu) #84
  • Kompute support for newer Vulkan HPP headers #81

v0.4.1 (2020-11-01)

Full Changelog

Implemented enhancements:

  • Upgrade build to support VulkanHPP 1.2.154 < 1.2.158 #82
  • Add Android example for Kompute #23
  • Fix compatibility for Vulkan HPP 1.2.155 and above #83 (axsaucedo)
  • codespell spelling fixes #80 (pH5)

Closed issues:

  • Android example throws runtime error. #77
  • Document the utilities to convert shaders into C++ header files #53
  • Document the three types of memory ownership in classes - never, optional and always #31

Merged pull requests:

  • Add link to official Vulkan website to download the SDK #79 (DonaldWhyte)
  • 77 Fix end to end examples by creating tensors on separate sequence #78 (axsaucedo)

v0.4.0 (2020-10-18)

Full Changelog

Implemented enhancements:

  • Error compiling on ubuntu 20.04 #67
  • Add explicit multi-threading interfaces to ensure correctness when running in parallel #51

Fixed bugs:

  • Ensure sequences are cleared when begin is run #74

Merged pull requests:

  • 74 Fixing manager default sequence creation #75 (axsaucedo)
  • Adding Asynchronous Processing Capabilities with Multiple Queue Support #73 (axsaucedo)
  • Fix README typo #71 (nihui)

v0.3.2 (2020-10-04)

Full Changelog

Implemented enhancements:

  • Fix compiler errors on compilers other than msvc #66 (Dudecake)

Fixed bugs:

  • Fix bug in OpAlgoRhsLhs #61

Closed issues:

  • Change c++ to 14 from 17 for support with older frameworks #59

Merged pull requests:

  • Updated readme and single kompute for 0.3.2 #69 (axsaucedo)
  • Added android example and upgraded build configurations #68 (axsaucedo)
  • Added readme to explain high level explanation for Godot example #65 (axsaucedo)
  • Removing vulkan dependencies in examples #64 (axsaucedo)
  • Updated godot example to use logistic regression usecase #63 (axsaucedo)

v0.3.1 (2020-09-20)

Full Changelog

Implemented enhancements:

  • Add example of how vulkan kompute can be used for ML in Godot Game Engine #60

Merged pull requests:

v0.3.0 (2020-09-19)

Full Changelog

Implemented enhancements:

  • Make Kompute installable locally to work with examples #58
  • Remove ability to copy output parameters from OpAlgoBase now that there's OpTensorSync #56

0.3.0 (2020-09-13)

Full Changelog

Implemented enhancements:

  • Add tests and documentation for loops passing data to/from device #50
  • Add preSubmit function to OpBase to account for multiple eval commands in parallel #47
  • Remove vulkan commandbuffer from Tensor #42
  • Provide further granularity on handling staging tensors #40
  • Create operation to copy data from local to device memory with staging #39
  • Add more advanced ML implementations (starting with LR, then DL, etc) #19

Fixed bugs:

  • OpCreateTensor doesn't map data into GPU with OpCreateTensor for host tensors #43

v0.2.0 (2020-09-05)

Full Changelog

Implemented enhancements:

  • Migrate to GTest #37
  • Move all todos in the code into github issues #33
  • Remove spdlog as a required dependency #30
  • Improve access to tensor underlying data for speed and ease of access #18
  • Enable for compute shaders to be provided in raw form #17
  • Enable OpCreateTensor for more than 1 tensor #13
  • Add specialisation data to algorithm with default tensor size #11
  • Add documentation with Doxygen and Sphinx #9

Fixed bugs:

  • Diagnose memory profiling to ensure there are no memory leaks on objects created [CPU] #15

Merged pull requests:

v0.1.0 (2020-08-28)

Full Changelog

* This Changelog was automatically generated by github_changelog_generator