[GitHub] [incubator-tvm] petrex commented on issue #4087: rocm backend: crash with LLVM 8

2019-11-04 Thread GitBox
petrex commented on issue #4087: rocm backend: crash with LLVM 8 URL: https://github.com/apache/incubator-tvm/issues/4087#issuecomment-549553057 @t-vi are you planning to upstream the change? thx This is an automated message

[GitHub] [incubator-tvm] t-vi commented on issue #4087: rocm backend: crash with LLVM 8

2019-11-04 Thread GitBox
t-vi commented on issue #4087: rocm backend: crash with LLVM 8 URL: https://github.com/apache/incubator-tvm/issues/4087#issuecomment-549555891 Yes, sorry, I've been travelling but should be submitting the PR this week. This

[GitHub] [incubator-tvm] tqchen commented on issue #4248: About operators are not implemented

2019-11-04 Thread GitBox
tqchen commented on issue #4248: About operators are not implemented URL: https://github.com/apache/incubator-tvm/issues/4248#issuecomment-549565779 consolidate to https://github.com/apache/incubator-tvm/issues/2591 would also be great if we can open new threads in the discuss forum

[GitHub] [incubator-tvm] tqchen closed issue #4248: About operators are not implemented

2019-11-04 Thread GitBox
tqchen closed issue #4248: About operators are not implemented URL: https://github.com/apache/incubator-tvm/issues/4248 This is an automated message from the Apache Git Service. To respond to the message, please log on to

[GitHub] [incubator-tvm] ZihengJiang merged pull request #4252: CI trigger after repo move

2019-11-04 Thread GitBox
ZihengJiang merged pull request #4252: CI trigger after repo move URL: https://github.com/apache/incubator-tvm/pull/4252 This is an automated message from the Apache Git Service. To respond to the message, please log on to

[GitHub] [incubator-tvm] KimBioInfoStudio commented on issue #4248: About operators are not implemented

2019-11-04 Thread GitBox
KimBioInfoStudio commented on issue #4248: About operators are not implemented URL: https://github.com/apache/incubator-tvm/issues/4248#issuecomment-549635171 this op can easily add with using numpy, but we want more tvmic op

[GitHub] [incubator-tvm] jwfromm commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations

2019-11-04 Thread GitBox
jwfromm commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations URL: https://github.com/apache/incubator-tvm/pull/4242#discussion_r342339719 ## File path: topi/python/topi/x86/batch_matmul.py ## @@ -18,43 +18,70 @@ """x86

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations

2019-11-04 Thread GitBox
comaniac commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations URL: https://github.com/apache/incubator-tvm/pull/4242#discussion_r342347907 ## File path: topi/python/topi/x86/batch_matmul.py ## @@ -18,43 +18,70 @@ """x86

[GitHub] [incubator-tvm] kimishpatel commented on a change in pull request #4243: Fix broken loop partitioning due to recent changes.

2019-11-04 Thread GitBox
kimishpatel commented on a change in pull request #4243: Fix broken loop partitioning due to recent changes. URL: https://github.com/apache/incubator-tvm/pull/4243#discussion_r342390422 ## File path: src/pass/loop_partition.cc ## @@ -513,17 +513,19 @@ Stmt

[GitHub] [incubator-tvm] kimishpatel commented on issue #4243: Fix broken loop partitioning due to recent changes.

2019-11-04 Thread GitBox
kimishpatel commented on issue #4243: Fix broken loop partitioning due to recent changes. URL: https://github.com/apache/incubator-tvm/pull/4243#issuecomment-549672648 @ZihengJiang ping. This is an automated message from the

[GitHub] [incubator-tvm] jroesch commented on issue #4241: [Dynamic Shape] Add Graph Dispatcher

2019-11-04 Thread GitBox
jroesch commented on issue #4241: [Dynamic Shape] Add Graph Dispatcher URL: https://github.com/apache/incubator-tvm/pull/4241#issuecomment-549631335 I will review later this week. This is an automated message from the Apache

[GitHub] [incubator-tvm] tqchen commented on issue #4281: [RUTNIME] Support C++ RPC

2019-11-10 Thread GitBox
tqchen commented on issue #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#issuecomment-552244083 Thanks @FrozenGene @weberlo ! This is an automated message from the Apache Git Service.

[GitHub] [incubator-tvm] tqchen merged pull request #4281: [RUTNIME] Support C++ RPC

2019-11-10 Thread GitBox
tqchen merged pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub

[GitHub] [incubator-tvm] yzhliu edited a comment on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate

2019-11-10 Thread GitBox
yzhliu edited a comment on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-550417287 # Build and Test * Increate the robuteness of CI test ([#2841](https://github.com/dmlc/tvm/pull/2841),

[GitHub] [incubator-tvm] yzhliu removed a comment on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate

2019-11-10 Thread GitBox
yzhliu removed a comment on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-552266647 # Build and Test * Increate the robuteness of CI test ([#2841](https://github.com/dmlc/tvm/pull/2841),

[GitHub] [incubator-tvm] yzhliu commented on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate

2019-11-10 Thread GitBox
yzhliu commented on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-552266647 # Build and Test * Increate the robuteness of CI test ([#2841](https://github.com/dmlc/tvm/pull/2841),

[GitHub] [incubator-tvm] jwfromm commented on a change in pull request #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth

2019-11-10 Thread GitBox
jwfromm commented on a change in pull request #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth URL: https://github.com/apache/incubator-tvm/pull/4271#discussion_r344565585 ## File path: tests/python/frontend/onnx/test_forward.py ## @@ -77,22

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module

2019-11-10 Thread GitBox
junrushao1994 commented on a change in pull request #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module URL: https://github.com/apache/incubator-tvm/pull/4289#discussion_r344524435 ## File path: include/tvm/runtime/module.h ## @@ -71,7 +70,11 @@

[GitHub] [incubator-tvm] tqchen commented on issue #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module

2019-11-10 Thread GitBox
tqchen commented on issue #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module URL: https://github.com/apache/incubator-tvm/pull/4289#issuecomment-552255958 The main reason for the ffi_util.h is to keep these functionalities internal, as we do not want to expose these

[GitHub] [incubator-tvm] yzhliu commented on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation.

2019-11-10 Thread GitBox
yzhliu commented on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation. URL: https://github.com/apache/incubator-tvm/pull/4249#issuecomment-552275667 Thanks @anijain2305 @FrozenGene @jackwish @tqchen

[GitHub] [incubator-tvm] yzhliu merged pull request #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation.

2019-11-10 Thread GitBox
yzhliu merged pull request #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation. URL: https://github.com/apache/incubator-tvm/pull/4249 This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] cchung100m commented on a change in pull request #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth

2019-11-10 Thread GitBox
cchung100m commented on a change in pull request #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth URL: https://github.com/apache/incubator-tvm/pull/4271#discussion_r344558194 ## File path: tests/python/frontend/onnx/test_forward.py ## @@ -85,6

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #4277: [ARM][Topi] Improving Int8 Perf in Spatial Conv2D schedule.

2019-11-10 Thread GitBox
FrozenGene commented on a change in pull request #4277: [ARM][Topi] Improving Int8 Perf in Spatial Conv2D schedule. URL: https://github.com/apache/incubator-tvm/pull/4277#discussion_r344568267 ## File path: topi/python/topi/arm_cpu/conv2d_spatial_pack.py ## @@ -93,24

[GitHub] [incubator-tvm] hello-hzb commented on issue #2954: [RFC][AUTOTVM] Auto-Schedule from Compute Declaration

2019-11-10 Thread GitBox
hello-hzb commented on issue #2954: [RFC][AUTOTVM] Auto-Schedule from Compute Declaration URL: https://github.com/apache/incubator-tvm/issues/2954#issuecomment-552306982 @merrymercy Hi Zheng, My team has paied attension to your auto-scheduler work for a few days. No update for a

[GitHub] [incubator-tvm] jackwish commented on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation.

2019-11-10 Thread GitBox
jackwish commented on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation. URL: https://github.com/apache/incubator-tvm/pull/4249#issuecomment-552263685 That sounds good, thank you :) @anijain2305

[GitHub] [incubator-tvm] junrushao1994 commented on issue #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module

2019-11-10 Thread GitBox
junrushao1994 commented on issue #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module URL: https://github.com/apache/incubator-tvm/pull/4289#issuecomment-552277277 @tqchen The use case of the class `FFIUtil` makes sense to me now, but I think it would be great to have

[GitHub] [incubator-tvm] tqchen commented on issue #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module

2019-11-10 Thread GitBox
tqchen commented on issue #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module URL: https://github.com/apache/incubator-tvm/pull/4289#issuecomment-552280462 I thought a bit about Object::Internal, but eventually chose the name FFIUtil because it also has a name for

[GitHub] [incubator-tvm] jwfromm commented on issue #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth

2019-11-10 Thread GitBox
jwfromm commented on issue #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth URL: https://github.com/apache/incubator-tvm/pull/4271#issuecomment-552280147 I've added onnxruntime to the docker image in PR #4299. Once it's merged the tests in this PR should be able

[GitHub] [incubator-tvm] jwfromm opened a new pull request #4299: [CI] Add onnxruntime to CI Image

2019-11-10 Thread GitBox
jwfromm opened a new pull request #4299: [CI] Add onnxruntime to CI Image URL: https://github.com/apache/incubator-tvm/pull/4299 As discussed in PR #4271, using the caffe runtime for our onnx testing is not a good long term solution due to lack of op support. Instead, we should be using

[GitHub] [incubator-tvm] jwfromm edited a comment on issue #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth

2019-11-10 Thread GitBox
jwfromm edited a comment on issue #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth URL: https://github.com/apache/incubator-tvm/pull/4271#issuecomment-552280147 I've added onnxruntime to the docker image in PR #4299. Once it's merged and the CI image is rebuilt

[GitHub] [incubator-tvm] tqchen commented on issue #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module

2019-11-10 Thread GitBox
tqchen commented on issue #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module URL: https://github.com/apache/incubator-tvm/pull/4289#issuecomment-552281875 after thinking a bit more, i agree that ObjectInternal could indeed be a better name, I just pushed a change to

[GitHub] [incubator-tvm] optima2005 opened a new pull request #4300: [Relay][Frontend][Tensorflow]Add conv2d_transpose

2019-11-10 Thread GitBox
optima2005 opened a new pull request #4300: [Relay][Frontend][Tensorflow]Add conv2d_transpose URL: https://github.com/apache/incubator-tvm/pull/4300 Hi, This PR is to fix #4263 After investigation, I found this operation has been implemented in relay cc codes and been working in

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module

2019-11-10 Thread GitBox
junrushao1994 commented on a change in pull request #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module URL: https://github.com/apache/incubator-tvm/pull/4289#discussion_r344525003 ## File path: src/runtime/micro/tcl_socket.h ## @@ -18,7 +18,6 @@

[GitHub] [incubator-tvm] yongwww opened a new pull request #4301: [TF][TEST] add test_forward_reduce_any back

2019-11-10 Thread GitBox
yongwww opened a new pull request #4301: [TF][TEST] add test_forward_reduce_any back URL: https://github.com/apache/incubator-tvm/pull/4301 the test case was removed in #4181 for some reason @tqchen @soiferj @zhiics

[GitHub] [incubator-tvm] anijain2305 commented on issue #4277: [ARM][Topi] Improving Int8 Perf in Spatial Conv2D schedule.

2019-11-10 Thread GitBox
anijain2305 commented on issue #4277: [ARM][Topi] Improving Int8 Perf in Spatial Conv2D schedule. URL: https://github.com/apache/incubator-tvm/pull/4277#issuecomment-552290839 @jackwish Thanks! Can you please review and let me know if you have more comments? @ajtulloch Let me know

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #4277: [ARM][Topi] Improving Int8 Perf in Spatial Conv2D schedule.

2019-11-10 Thread GitBox
FrozenGene commented on a change in pull request #4277: [ARM][Topi] Improving Int8 Perf in Spatial Conv2D schedule. URL: https://github.com/apache/incubator-tvm/pull/4277#discussion_r344559034 ## File path: topi/python/topi/arm_cpu/conv2d_spatial_pack.py ## @@ -93,24

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module

2019-11-10 Thread GitBox
tqchen commented on a change in pull request #4289: [RUNTIME][REFACTOR] Use object protocol to support runtime::Module URL: https://github.com/apache/incubator-tvm/pull/4289#discussion_r344549075 ## File path: include/tvm/runtime/module.h ## @@ -71,7 +70,11 @@ class

[GitHub] [incubator-tvm] jwfromm commented on a change in pull request #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth

2019-11-10 Thread GitBox
jwfromm commented on a change in pull request #4271: [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth URL: https://github.com/apache/incubator-tvm/pull/4271#discussion_r344549188 ## File path: tests/python/frontend/onnx/test_forward.py ## @@ -85,6

[GitHub] [incubator-tvm] yzhliu merged pull request #4083: [tutorial] Relay pass infra tutorial

2019-11-10 Thread GitBox
yzhliu merged pull request #4083: [tutorial] Relay pass infra tutorial URL: https://github.com/apache/incubator-tvm/pull/4083 This is an automated message from the Apache Git Service. To respond to the message, please log on

[GitHub] [incubator-tvm] yzhliu commented on issue #4083: [tutorial] Relay pass infra tutorial

2019-11-10 Thread GitBox
yzhliu commented on issue #4083: [tutorial] Relay pass infra tutorial URL: https://github.com/apache/incubator-tvm/pull/4083#issuecomment-552304594 Thanks @zhiics @billzorn @MarisaKirisame @yongwww This is an automated

[GitHub] [incubator-tvm] tqchen commented on issue #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on issue #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#issuecomment-551981112 split then check creates additional data structures such as vector and string(additional data structures), which can be avoided as you can simply do

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344290100 ## File path: apps/cpp_rpc/rpc_server.cc ## @@ -0,0 +1,363 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344289033 ## File path: apps/cpp_rpc/rpc_server.cc ## @@ -0,0 +1,363 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344290589 ## File path: apps/cpp_rpc/rpc_server.cc ## @@ -0,0 +1,363 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344292628 ## File path: src/common/socket.h ## @@ -468,7 +524,134 @@ class TCPSocket : public Socket { } return ndone;

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344288861 ## File path: apps/cpp_rpc/rpc_server.cc ## @@ -0,0 +1,363 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344288460 ## File path: apps/cpp_rpc/rpc_env.h ## @@ -0,0 +1,84 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344289079 ## File path: apps/cpp_rpc/rpc_server.cc ## @@ -0,0 +1,363 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344293102 ## File path: apps/cpp_rpc/rpc_tracker_client.h ## @@ -0,0 +1,249 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344291055 ## File path: src/common/socket.h ## @@ -62,6 +65,25 @@ inline std::string GetHostName() { return

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344293873 ## File path: apps/cpp_rpc/rpc_env.cc ## @@ -0,0 +1,248 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344288617 ## File path: apps/cpp_rpc/rpc_env.h ## @@ -0,0 +1,84 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344291688 ## File path: src/common/socket.h ## @@ -62,6 +65,25 @@ inline std::string GetHostName() { return

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344288316 ## File path: apps/cpp_rpc/rpc_env.h ## @@ -0,0 +1,84 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344289337 ## File path: apps/cpp_rpc/rpc_server.cc ## @@ -0,0 +1,363 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344289224 ## File path: apps/cpp_rpc/rpc_server.cc ## @@ -0,0 +1,363 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344292057 ## File path: src/common/socket.h ## @@ -62,6 +65,25 @@ inline std::string GetHostName() { return

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344289299 ## File path: apps/cpp_rpc/rpc_server.cc ## @@ -0,0 +1,363 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344288389 ## File path: apps/cpp_rpc/rpc_env.h ## @@ -0,0 +1,84 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
FrozenGene commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344347149 ## File path: apps/cpp_rpc/rpc_env.h ## @@ -0,0 +1,84 @@ +/* + * Licensed to the Apache Software Foundation (ASF)

[GitHub] [incubator-tvm] ajtulloch commented on issue #4277: [ARM][Topi] Improving Int8 Perf in Spatial Conv2D schedule.

2019-11-08 Thread GitBox
ajtulloch commented on issue #4277: [ARM][Topi] Improving Int8 Perf in Spatial Conv2D schedule. URL: https://github.com/apache/incubator-tvm/pull/4277#issuecomment-551993046 @FrozenGene wow, those are very impressive results. Congratulations, looking forward to the talk and the code :)

[GitHub] [incubator-tvm] yzhliu commented on issue #4104: Fix the TF tutorial to run against TF2.0 and TF1.x

2019-11-08 Thread GitBox
yzhliu commented on issue #4104: Fix the TF tutorial to run against TF2.0 and TF1.x URL: https://github.com/apache/incubator-tvm/pull/4104#issuecomment-551897488 @ic could you retrigger the CI by push a trivial commit? This

[GitHub] [incubator-tvm] tqchen commented on issue #4284: [TEST][FLAKY] darknet/test_forward.py::test_forward_conv_batch_norm

2019-11-08 Thread GitBox
tqchen commented on issue #4284: [TEST][FLAKY] darknet/test_forward.py::test_forward_conv_batch_norm URL: https://github.com/apache/incubator-tvm/issues/4284#issuecomment-551929915 cc @srkreddy1238 can you take a look? This

[GitHub] [incubator-tvm] tqchen opened a new issue #4284: [TEST][FLAKY] tests/python/frontend/darknet/test_forward.py::test_forward_conv_batch_norm

2019-11-08 Thread GitBox
tqchen opened a new issue #4284: [TEST][FLAKY] tests/python/frontend/darknet/test_forward.py::test_forward_conv_batch_norm URL: https://github.com/apache/incubator-tvm/issues/4284

[GitHub] [incubator-tvm] anijain2305 commented on issue #4282: Add test for the qnn_add operator

2019-11-08 Thread GitBox
anijain2305 commented on issue #4282: Add test for the qnn_add operator URL: https://github.com/apache/incubator-tvm/pull/4282#issuecomment-551935940 If I understand tolerance correctly, I think atol of 1 is good for integers and current implementation. Let me know if I am wrong.

[GitHub] [incubator-tvm] tqchen commented on issue #4280: [tvm][runtime] A minimum runtime for external library

2019-11-08 Thread GitBox
tqchen commented on issue #4280: [tvm][runtime] A minimum runtime for external library URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-551960356 As a followup thread about what we might be able to benefit from in terms of external module, it would be great if we have

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library

2019-11-08 Thread GitBox
tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-551960356 As a followup thread about what we might be able to benefit from in terms of external module, it would be great if we

[GitHub] [incubator-tvm] anijain2305 edited a comment on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation.

2019-11-08 Thread GitBox
anijain2305 edited a comment on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation. URL: https://github.com/apache/incubator-tvm/pull/4249#issuecomment-551966857 @FrozenGene I made it work. The workload had to be modified. I tried with my 2 conv network.

[GitHub] [incubator-tvm] anijain2305 commented on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation.

2019-11-08 Thread GitBox
anijain2305 commented on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation. URL: https://github.com/apache/incubator-tvm/pull/4249#issuecomment-551966857 @FrozenGene I made it work. The workload had to be modified. I tried with my 2 conv network. It

[GitHub] [incubator-tvm] FrozenGene commented on issue #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
FrozenGene commented on issue #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#issuecomment-551969728 @tqchen Wish I have solved many comments. I also replace SelectHelper into PoolHelper. Remained: Ideally, we should just use

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4282: Add test for the qnn_add operator

2019-11-08 Thread GitBox
anijain2305 commented on a change in pull request #4282: Add test for the qnn_add operator URL: https://github.com/apache/incubator-tvm/pull/4282#discussion_r344305651 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -624,17 +661,23 @@ def

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4282: Add test for the qnn_add operator

2019-11-08 Thread GitBox
anijain2305 commented on a change in pull request #4282: Add test for the qnn_add operator URL: https://github.com/apache/incubator-tvm/pull/4282#discussion_r344304495 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -545,34 +561,55 @@ def

[GitHub] [incubator-tvm] adityaatluri commented on a change in pull request #4234: Auto TensorCore CodeGen

2019-11-08 Thread GitBox
adityaatluri commented on a change in pull request #4234: Auto TensorCore CodeGen URL: https://github.com/apache/incubator-tvm/pull/4234#discussion_r344321090 ## File path: src/pass/tensor_core.cc ## @@ -0,0 +1,1247 @@ +/* + * Licensed to the Apache Software Foundation

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
FrozenGene commented on a change in pull request #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#discussion_r344347686 ## File path: apps/cpp_rpc/rpc_server.cc ## @@ -0,0 +1,363 @@ +/* + * Licensed to the Apache Software Foundation

[GitHub] [incubator-tvm] tqchen commented on issue #4281: [RUTNIME] Support C++ RPC

2019-11-08 Thread GitBox
tqchen commented on issue #4281: [RUTNIME] Support C++ RPC URL: https://github.com/apache/incubator-tvm/pull/4281#issuecomment-551928185 @weberlo @srkreddy1238 @snowolfhawk it would be great if you can also help to review the PR

[GitHub] [incubator-tvm] anijain2305 commented on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation.

2019-11-08 Thread GitBox
anijain2305 commented on issue #4249: [TOPI][AlterOpLayout][ARM] Enabling NHWC to NCHW layout transformation. URL: https://github.com/apache/incubator-tvm/pull/4249#issuecomment-551951671 I tried to call AtlerOpLayout() before extracting the tasks, it was able to extract the NCHW convs

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library

2019-11-08 Thread GitBox
tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-551957000 To followup on the discussion thread. While we understand that the current PR achieves the purpose of supporting

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library

2019-11-08 Thread GitBox
tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-551957000 To followup on the discussion thread. While we understand that the current PR achieves the purpose of supporting

[GitHub] [incubator-tvm] weberlo edited a comment on issue #4274: [µTVM] Enable AutoTVM for ARM STM32F746XX Boards

2019-11-08 Thread GitBox
weberlo edited a comment on issue #4274: [µTVM] Enable AutoTVM for ARM STM32F746XX Boards URL: https://github.com/apache/incubator-tvm/pull/4274#issuecomment-551330769 @tqchen It looks like the CI doesn't allow assembly---namely,

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library

2019-11-08 Thread GitBox
tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-551957000 To followup on the discussion thread. While we understand that the current PR achieves the purpose of supporting

[GitHub] [incubator-tvm] kevinthesun opened a new pull request #4285: Fix tf reshape

2019-11-08 Thread GitBox
kevinthesun opened a new pull request #4285: Fix tf reshape URL: https://github.com/apache/incubator-tvm/pull/4285 Move symbolic related logic after infer value is failed. This is an automated message from the Apache Git

[GitHub] [incubator-tvm] tqchen commented on issue #4280: [tvm][runtime] A minimum runtime for external library

2019-11-08 Thread GitBox
tqchen commented on issue #4280: [tvm][runtime] A minimum runtime for external library URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-551957000 To followup on the discussion thread. While we understand that the current PR achieves the purpose of supporting external

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library

2019-11-08 Thread GitBox
tqchen edited a comment on issue #4280: [tvm][runtime] A minimum runtime for external library URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-551957000 To followup on the discussion thread. While we understand that the current PR achieves the purpose of supporting

[GitHub] [incubator-tvm] kevinthesun commented on issue #4188: [RFC][AutoTVM] Selective Tuning

2019-11-05 Thread GitBox
kevinthesun commented on issue #4188: [RFC][AutoTVM] Selective Tuning URL: https://github.com/apache/incubator-tvm/issues/4188#issuecomment-549959110 @comaniac Thank you for these data. Can you update in the main thread? This

[GitHub] [incubator-tvm] soiferj commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations

2019-11-05 Thread GitBox
soiferj commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations URL: https://github.com/apache/incubator-tvm/pull/4242#discussion_r342734128 ## File path: topi/python/topi/x86/batch_matmul.py ## @@ -18,43 +18,70 @@ """x86

[GitHub] [incubator-tvm] comaniac commented on issue #4188: [RFC][AutoTVM] Selective Tuning

2019-11-05 Thread GitBox
comaniac commented on issue #4188: [RFC][AutoTVM] Selective Tuning URL: https://github.com/apache/incubator-tvm/issues/4188#issuecomment-549974311 Updated. This is an automated message from the Apache Git Service. To respond

[GitHub] [incubator-tvm] comaniac opened a new pull request #4260: [TOPI] Fix bug in Winograd on CUDA

2019-11-05 Thread GitBox
comaniac opened a new pull request #4260: [TOPI] Fix bug in Winograd on CUDA URL: https://github.com/apache/incubator-tvm/pull/4260 Several topics [1, 2, 3] in the discuss mention that the conv2d failed to pass the shape checking in the runtime after the conv2d has been tuned by AutoTVM.

[GitHub] [incubator-tvm] jwfromm edited a comment on issue #4242: [AutoTVM] Add batch_matmul to tunable operations

2019-11-05 Thread GitBox
jwfromm edited a comment on issue #4242: [AutoTVM] Add batch_matmul to tunable operations URL: https://github.com/apache/incubator-tvm/pull/4242#issuecomment-550086640 @icemelon9, autotuning seems to yield speedups around 20% faster than the base configuration on a 32 core CPU. Again,

[GitHub] [incubator-tvm] CoinCheung opened a new issue #4261: DepthWise Transposed Conv error

2019-11-05 Thread GitBox
CoinCheung opened a new issue #4261: DepthWise Transposed Conv error URL: https://github.com/apache/incubator-tvm/issues/4261 A short version of my code is: ```python import onnx import torch import torch.nn as nn import tvm import tvm.relay as relay class

[GitHub] [incubator-tvm] tqchen commented on issue #4261: DepthWise Transposed Conv error

2019-11-05 Thread GitBox
tqchen commented on issue #4261: DepthWise Transposed Conv error URL: https://github.com/apache/incubator-tvm/issues/4261#issuecomment-550113671 Thanks for reporting the problem, it would be great if you can open a new trouble shooting thread on https://discuss.tvm.ai/ where the community

[GitHub] [incubator-tvm] tqchen closed issue #4261: DepthWise Transposed Conv error

2019-11-05 Thread GitBox
tqchen closed issue #4261: DepthWise Transposed Conv error URL: https://github.com/apache/incubator-tvm/issues/4261 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub

[GitHub] [incubator-tvm] snowolfhawk commented on issue #1756: [RUNTIME][RPC]C++ RPC Server

2019-11-05 Thread GitBox
snowolfhawk commented on issue #1756: [RUNTIME][RPC]C++ RPC Server URL: https://github.com/apache/incubator-tvm/pull/1756#issuecomment-550116962 @yagnasrinath Currently i apply this PR on armv8 and don't find any problems. But just like my reply above, this cpp_rpc depends on

[GitHub] [incubator-tvm] FrozenGene edited a comment on issue #1756: [RUNTIME][RPC]C++ RPC Server

2019-11-05 Thread GitBox
FrozenGene edited a comment on issue #1756: [RUNTIME][RPC]C++ RPC Server URL: https://github.com/apache/incubator-tvm/pull/1756#issuecomment-550119753 > We should keep cpp_rpc's dependences in a limited region, then fix these cpp file using

[GitHub] [incubator-tvm] jwfromm commented on issue #4242: [AutoTVM] Add batch_matmul to tunable operations

2019-11-05 Thread GitBox
jwfromm commented on issue #4242: [AutoTVM] Add batch_matmul to tunable operations URL: https://github.com/apache/incubator-tvm/pull/4242#issuecomment-550086640 @icemelon9, autotuning seems to yield speedups of around 20% improvement over the base configuration on a 32 core CPU. Again,

[GitHub] [incubator-tvm] jwfromm commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations

2019-11-05 Thread GitBox
jwfromm commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations URL: https://github.com/apache/incubator-tvm/pull/4242#discussion_r342866103 ## File path: topi/python/topi/x86/batch_matmul.py ## @@ -18,43 +18,70 @@ """x86

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations

2019-11-05 Thread GitBox
comaniac commented on a change in pull request #4242: [AutoTVM] Add batch_matmul to tunable operations URL: https://github.com/apache/incubator-tvm/pull/4242#discussion_r342869421 ## File path: topi/python/topi/x86/batch_matmul.py ## @@ -18,43 +18,70 @@ """x86

[GitHub] [incubator-tvm] cchung100m edited a comment on issue #4235: [CMake] Imporve parameter 'ANTLR4' to avoid cmake will ignore the 'space'

2019-11-05 Thread GitBox
cchung100m edited a comment on issue #4235: [CMake] Imporve parameter 'ANTLR4' to avoid cmake will ignore the 'space' URL: https://github.com/apache/incubator-tvm/pull/4235#issuecomment-550097774 Hi This PR cannot pass the CI build process due to following issue, but I am not sure

[GitHub] [incubator-tvm] kevinthesun commented on issue #4260: [TOPI] Fix bug in Winograd on CUDA

2019-11-05 Thread GitBox
kevinthesun commented on issue #4260: [TOPI] Fix bug in Winograd on CUDA URL: https://github.com/apache/incubator-tvm/pull/4260#issuecomment-550068734 @cbalint13 This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] tqchen closed issue #4256: Install from Source doc still says to clone dmlc/tvm

2019-11-05 Thread GitBox
tqchen closed issue #4256: Install from Source doc still says to clone dmlc/tvm URL: https://github.com/apache/incubator-tvm/issues/4256 This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [incubator-tvm] tqchen merged pull request #4257: [DOCS] Link to new repo loc

2019-11-05 Thread GitBox
tqchen merged pull request #4257: [DOCS] Link to new repo loc URL: https://github.com/apache/incubator-tvm/pull/4257 This is an automated message from the Apache Git Service. To respond to the message, please log on to

  1   2   3   4   5   6   7   8   9   10   >