1. 19 Jun, 2022 5 commits
  2. 18 Jun, 2022 2 commits
  3. 17 Jun, 2022 12 commits
  4. 16 Jun, 2022 2 commits
  5. 04 Feb, 2022 5 commits
  6. 03 Feb, 2022 13 commits
    • Elen Kalda's avatar
      [microNPU] Enable network tests for U65 256 mac variant (#10159) · bec72f12
      Elen Kalda authored
      Currently we run the network tests only on one NPU variant, so this
      patch is to enable all the currently supported variants.
      
      Change-Id: Ic18054fb4ba19eb28b99ff4439e5a36e57199763
      bec72f12
    • Siva's avatar
      OpenCL debug runtime timer handler added. (#10140) · 0482cdca
      Siva authored
      0482cdca
    • Yuanjing Shi's avatar
      remove async tst (#10160) · cfc8db0a
      Yuanjing Shi authored
      cfc8db0a
    • Siyuan Feng's avatar
    • lhutton1's avatar
      [microNPU] Fix layout assignment in layout optimizer pass (#10143) · a8741e2d
      lhutton1 authored
      Fixes the layout optimizer incorrectly assigning layouts for graphs with
      more complex topologies than previously considered. Specifically, this
      commit now ensures that intermediate layouts match (e.g. parent output =
      child input) and that all consumers are taken into account when altering
      the output layout - something not done previously due to an incorrect
      traversal order.
      
      Previously, the input layout was always altered if the producer was an
      NPU operation without regard to the output layout of that operation.
      Additionally, is was possible for the output layout to be incorrectly
      set due to a depth-first post-order of traversal of the graph, meaning
      it was possible for not all consumers to be taken into account when
      altering the layout.
      
      Now the `AnalyzeConsumers` pass is run before `LayoutOptimization` which
      determines a mapping from NPU operation to list of boolean values that
      represent whether or not each consumer is an NPU operation. Since this
      is completed before `LayoutOptimization`, all consumers are guaranteed
      to be taken into account when altering the output layout. In turn, the
      input layouts can correctly be determined by checking whether the output
      of the producer will be altered.
      
      Change-Id: I04e9605da65fa9f12801109dd50c5e3f08cbc73c
      a8741e2d
    • Christopher Sidebottom's avatar
      [CI] Update ci_arm and ci_lint (#10146) · 87365934
      Christopher Sidebottom authored
      This includes sccache, and these are the less troublesome images.
      
      Also see #10120 for update issue.
      87365934
    • Eric Lunderberg's avatar
      [TVMScript] Support T.buffer_decl using data pointer from Let/Allocate (#10099) · 455c02a8
      Eric Lunderberg authored
      * [TVMScript] Added unit tests demonstrating desired functionality
      
      * [TVMScript] Implemented parsing of T.Ptr[...]
      
      These can be generated when exporting to TVMscript, but were not
      parsable after being generated.
      
      * [TVMScript] Updated buffer_var printing
      
      LetStmt and AllocateNode can both be used to generate handles that are
      used in Buffer objects.  In these cases, the Buffer declarations must
      go after the handle declaration, not in the function header.
      
      * Moved printing of var and buffer_decl into separate statements.
      
      * Updated following @shingjan's review comments.
      455c02a8
    • Matthew Barrett's avatar
      [microNPU][3] Plan generation for the cascader (#9890) · f2b7e82a
      Matthew Barrett authored
      * [microNPU][3] Plan generation for the cascader
      
      The cascader creates 'Plans' which describe how
      to schedule subgraphs. As part of the cascading
      algorithm, it's necessary to explore a large
      variety of Plans which are Pareto optimal (in
      terms of memory usage and performance). This is
      done by the Plan generation algorithm.
      
      This commit adds the TensorConfig and Plan data
      structures which hold information on how to schedule
      the tensors/operators. Additionally, it includes
      functions to calculate Pareto frontiers which are
      used to cull sub-optimal Plans.
      
      Change-Id: Ia358b2a1b29bd810df4441027752ced75812ad4e
      
      * Fixes to lint/test
      
      Change-Id: If4e083a3c96af75a8ffa72510704818d21a477d9
      
      * Improve python docs
      
      Change-Id: I831137f8235665bc20ab4c060cc7049ffd48088a
      
      * Fix enum hashing issue with old gcc
      
      Change-Id: Ifbe97eb33b1ef313710f24c687a8155421a3c195
      f2b7e82a
    • Kirill Snezhko's avatar
      Remove javah support (#10104) · 9518b7eb
      Kirill Snezhko authored
      * Remove javah support
      
      * Remove unused compiler option
      
      * Osx pom.xml update
      9518b7eb
    • cyx666's avatar
    • Mehrdad Hessar's avatar
      [microTVM][Zephyr] Update RVM to Zephyr 2.7 (#10138) · 506bc3c6
      Mehrdad Hessar authored
      * Update to zephyr2.7 and Refactor
      
      * Temporary for testing
      
      * Update cmake version
      
      * fix import path and format
      
      * Fix test script
      
      * address comments
      
      * fix path
      
      * fix image name
      506bc3c6
    • wrongtest's avatar
      d436a10a
    • Ashutosh Parkhi's avatar
  7. 02 Feb, 2022 1 commit
    • lhutton1's avatar
      [microNPU] Add support for transpose convolution (#9855) · 2e6702c1
      lhutton1 authored
      Adds support for legalizing transpose convolution to
      a microNPU conv2d operation for the case when strides==(2, 2),
      dilation==(1, 1) and no padding of the output is required.
      
      Change-Id: I485e2571913b3dcd7c75c46304f2f9a82f630ee0
      2e6702c1