Skip to content
Snippets Groups Projects
Select Git revision
  • clockwork default
  • clockwork-v0.6
  • master
  • v0.6.0
  • v0.5
  • v0.4
  • v0.3
  • v0.2
  • v0.1rc
9 results
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.029Dec272625242322191817151413116543130Nov2827252321181615141312111098632130Oct2726252422211918171615141312111098765432129Sep2827262524232221201817131211108765432131Aug30292827262524232221201918171514131110987532131Jul28272625242320191817161514131211109876543130Jun292726232220181716151211105432131May30252423222120181716151412119876543229Apr272625242221201817161514121098231Mar2926251714131211753228Feb27262524222120171613121110987654231Jan302824232220191817161513121110865431Dec301112542129Nov28272625191817642128Oct272623222119181615141312Re-organize the test cases for tensorize. (#736)[SCHEDULE] New Reduction Mode for Tensorize (#727)[TOPI]Support dim-0 tensor in topi broadcast/reduce (#731)[TOPI] CUDNN integration (#730)[TOPI] add extern schedule for cudnn and miopen (#724)update dmlc-core (#728)[TOPI] 1bit dense operator on x86_64 (#629)[ROCM] MIOpen contrib for convolution kernels (#722)[CODEGEN] update codegen for vector operation (#711)[CODEGEN] enable static handle cache (#723)Fix dependency problem of reducer condition (#712) (#721)Update metal_module.mmAdded a regression test for #696 (#720)During tensorize, call Simplify on algorithm and intrinsic definitions before CanonicalSimplify. This will prevent a number of false tensorize mismatches. (#718)removed non-determinism from CanonicalSimplify (#704)Halide -> HalideIR (#698)fix cudnn output shape (#708)Make duplicated function name checker working (#705)Simplify expressions early on (#702)1) Make unroll code reusable 2) reduce non-determinisim in CanonicalSimplify (#701)Fix long for windows in cuda (#700)[CODEGEN] add fp16 and fp64 enable pragma for opencl (#697)[CODEGEN] add callback post proc for opencl (#692)Port build_module.py to C++ (#667)[CI] Enable llvm in CPU test (#688)Support rank-0 tensor (#687)[RANDOM] Init contrib.random Library (#684)Consider variable range information during simplification of tensorize expressions (#674)[CUDA] Enable int64 (#683)[APP] fix gradle build for Android build (#685)fix name bug in test_pass_inject_double_buffer (#678)fix parameter name in UnrollLoop (#679)[ANDROID][RPC] Remove binary distro jar (#677)[ARITH] Upgrade CanonicalSimplify to Simplify Mod (#676)[TOPI] Fix for pooling (#673)[PASS] Allow compact checking when strides is available (#669)Documentation correction (#665)[PASS/SETUP] Fix minior issues (#663)[CONTRIB] MPS DNN Dense (#615)Fixed nnvm issue #239 (#660)