1. 06 Apr, 2020 6 commits
  2. 05 Apr, 2020 4 commits
    • [Relay][Topi][AutoTVM] Winograd support for Conv3D (#5186) · 02eb1833
      * Functional conv3d winograd working.
      
      * Formatted python code.
      
      * registered conv3d winograd compute and started adding relay without_weight_transform operator.
      
      * Add topi testing for conv3d winograd.
      
      * Format file.
      
      * small tweak to unrolling to prevent build sticking.
      
      * Refactoring convolution ops in relay.
      
      * Refactored relay convolutions.
      
      * Bug fixes.
      
      * Fixed static bug in convolution.
      
      * Added conv3d alter op layout and related support.
      
      * Bug fixes and testing done.
      
      * Fix a few autotvm bugs.
      
      * Drop silly debug print.
      
      * Removed debug_skip_region.
      
      * Add variant of conv3d_winograd that doesn't transform depth.
      
      * initial infrastructure done for depthless conv.
      
      * Fix no_depth schedule bugs.
      
      * automatic topi switching between depth and depthless winograd.
      
      * Fixed bug in schedule.
      
      * lint fixes.
      
      * Removed indents in convolution.cc
      
      * missed a few indents oops.
      
      * fixed flop count.
      
      * One more small tweak.
      
      * Change kernel pack inner axes order.
      
      * Style changes.
      
      * Comment fixes.
      Josh Fromm committed
    • [Fix][VM] Fix copy constructor (#5237) · c76cbd8d
      ga committed
    • [Relay][ADT]Static Tensor Array (#5103) · b5352ee2
      * Add other static tensor array ops
      
      * Add tensor array get data
      
      * Minor refactor
      
      * Fix pylint
      
      * Update docstring
      
      * Make get data more generic
      
      * Improve test
      
      * Improve split test
      
      * Improve get data
      
      * Minor fix
      
      * Further improvement for static shape
      
      * Improve shape parsing
      
      * Unify get_static_name
      Yao Wang committed
    • [REFACTOR][TIR] Migrate all low-level passes to the Pass Manager. (#5233) · e63e08fe
      * [REFACTOR][TIR] Migrate all low-level passes to the Pass Manager.
      
      This PR migrates the tvm.lower to return IRModule of PrimFuncs
      instead of the LoweredFuncs.
      
      * Remove LoweredFunc.
      Tianqi Chen committed
  3. 04 Apr, 2020 3 commits
  4. 03 Apr, 2020 8 commits
    • [REFACTOR][TIR] Migrate most of low-level build to use the Pass Manager. (#5225) · 75e936e1
      * [REFACTOR][TIR] Migrate most of low-level build to use the Pass Manager.
      
      - SplitHostDevice
      - ThreadSync
      - BindDevice
      - LowerThreadAllreduce
      - Provide a temp fix for printing IRModule with PrimFunc before the formal text printer.
      
      * Address comments, fix tests.
      
      * Fix relay tests
      
      * Explicit move
      Tianqi Chen committed
    • [RELAY] Non-recursive Graph Vistor and Rewriter (#4886) · 7de8a539
      * First pass a defining a non-recursive Graph Vistor and Rewriter
      
      autoformat
      
      remove a currently empty test until testing is solidfied
      
      * Make CalcDep from Dead Code Elimination non-recursive
      
      * Partially working, not passing all tests yet
      
      passes tests when disabling GetExprRefCount, I think I have a bug in visit counting
      
      fix GetExprRefCount
      
      Fix a subtle bug with nested recursive/non-recursive scopes
      
      * Refactor
      
      * improve comments
      
      * respond to review comments on comments
      
      * Fix a problem with default recursion for dataflow nodes
      
      mark DataflowVisitor methods as override
      
      * implement ScopeMutator
      
      * convert forward_rewrite to ScopeMutator, remove DataflowMutator
      
      * rewrite ExprRewriter and convert fast_math to use it
      
      * switch BiasAddSimplifier to ExprRewriter
      
      fix a clang warning
      
      fix cpp lint
      
      fix doc param error
      
      * respond to review comments
      
      * fix a typo in the iterative looping
      
      * add a regression test for GetExprRefCount issue
      
      * Normalize naming
      
      * fix lint
      
      * First pass a defining a non-recursive Graph Vistor and Rewriter
      
      autoformat
      
      remove a currently empty test until testing is solidfied
      
      * Make CalcDep from Dead Code Elimination non-recursive
      
      * Partially working, not passing all tests yet
      
      passes tests when disabling GetExprRefCount, I think I have a bug in visit counting
      
      fix GetExprRefCount
      
      Fix a subtle bug with nested recursive/non-recursive scopes
      
      * Refactor
      
      * improve comments
      
      * respond to review comments on comments
      
      * Fix a problem with default recursion for dataflow nodes
      
      mark DataflowVisitor methods as override
      
      * implement ScopeMutator
      
      * convert forward_rewrite to ScopeMutator, remove DataflowMutator
      
      * rewrite ExprRewriter and convert fast_math to use it
      
      * switch BiasAddSimplifier to ExprRewriter
      
      fix a clang warning
      
      fix cpp lint
      
      fix doc param error
      
      * respond to review comments
      
      * fix a typo in the iterative looping
      
      * add a regression test for GetExprRefCount issue
      
      * Normalize naming
      
      * fix lint
      
      * respond to review comments
      Matthew Brookhart committed
    • [RELAY][FIX] Fix hang in MergeCompilerRegions (#5227) · 54975a3f
      For certain network topologies, MCR could hang.
      This patch fixes that case.
      
      Change-Id: I3edd8a8a6b452b2b838b777720adea22a3b995b4
      mbaret committed
    • [KERAS]Upsample3d & ZeroPadding3d op (#5125) · b796c13c
      * [KERAS]upsampling3d and zeropadding3d op
      
      * [KERAS]upsampling3d and zeropadding3d test case
      
      * Review comments updated
      Samuel committed
    • [CodeGen][CUDA] Fix bugs (#5209) · 316ce055
      - Support vectorized casts
      
      - It is incorrect to extract elements from int8x4 with
      
         0x000000ff & (x >> i * 8)
      
        as this value is of type int in C/C++. If this expression
        is used for sign extensions, the sign bit will be wrong.
        Simply use C style casts instead and sign bits will just work.
      
      Signed-off-by: Wei Pan <weip@nvidia.com>
      Wei Pan committed
  5. 02 Apr, 2020 12 commits
  6. 01 Apr, 2020 7 commits