[GitHub] [incubator-tvm] masahi merged pull request #4305: [RUNTIME] Proper Device Attribute Query for AMD GPU

2019-11-15 Thread GitBox
masahi merged pull request #4305: [RUNTIME] Proper Device Attribute Query for AMD GPU URL: https://github.com/apache/incubator-tvm/pull/4305 This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm] branch master updated (9e04298 -> 022b285)

2019-11-15 Thread masahi
This is an automated email from the ASF dual-hosted git repository. masahi pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 9e04298 fix install script (#4350) add 022b285 proper device query through rocm api (#4305) No new

[GitHub] [incubator-tvm] tqchen merged pull request #4350: fix install script

2019-11-15 Thread GitBox
tqchen merged pull request #4350: fix install script URL: https://github.com/apache/incubator-tvm/pull/4350 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use

[incubator-tvm] branch master updated (ccde31f -> 9e04298)

2019-11-15 Thread tqchen
This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from ccde31f AutoTVM: selecting tuning templates when extracting task (#4338) add 9e04298 fix install

[GitHub] [incubator-tvm] wweic commented on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
wweic commented on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554603605 > By aligned storage, I mean we use aligned storage to specify the unit size, and allocate an array of aligned storage, whose number of

[GitHub] [incubator-tvm] vinx13 commented on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate

2019-11-15 Thread GitBox
vinx13 commented on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-554602399 typo: enhence -> enhance This is an automated message from the Apache

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

2019-11-15 Thread GitBox
yzhliu commented on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-554602143 I updated the release notes to include recent changes, as well as some known issues as @u99127 suggested. please let me know if I missed

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

2019-11-15 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/apache/incubator-tvm/pull/2841),

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

2019-11-15 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/apache/incubator-tvm/pull/2841),

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

2019-11-15 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/apache/incubator-tvm/pull/2841),

[GitHub] [incubator-tvm] LYang-666 opened a new issue #4354: Could I change the channel numbers on ResNet18 for pynq implementation

2019-11-15 Thread GitBox
LYang-666 opened a new issue #4354: Could I change the channel numbers on ResNet18 for pynq implementation URL: https://github.com/apache/incubator-tvm/issues/4354 Hi! Could I change the channel numbers for resnet18 using the given bitstream to implement on pynq. In other

[GitHub] [incubator-tvm] tqchen commented on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554600437 By aligned storage, I mean we use aligned storage to specify the unit size, and allocate an array of aligned storage, whose number of

[GitHub] [incubator-tvm] Hzfengsy commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore

2019-11-15 Thread GitBox
Hzfengsy commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore URL: https://github.com/apache/incubator-tvm/pull/4353#discussion_r347074084 ## File path: src/runtime/contrib/cublas/cublas.cc ## @@ -36,6 +36,36 @@ inline

[GitHub] [incubator-tvm] vinx13 commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore

2019-11-15 Thread GitBox
vinx13 commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore URL: https://github.com/apache/incubator-tvm/pull/4353#discussion_r347074000 ## File path: python/tvm/contrib/cudnn.py ## @@ -341,12 +355,16 @@ def

[GitHub] [incubator-tvm] zhiics commented on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags

2019-11-15 Thread GitBox
zhiics commented on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags URL: https://github.com/apache/incubator-tvm/issues/4348#issuecomment-554597492 @gussmith23 Thanks for the proposal. I have a few thoughts/questions. - For the passes, can

[GitHub] [incubator-tvm] zhiics edited a comment on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags

2019-11-15 Thread GitBox
zhiics edited a comment on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags URL: https://github.com/apache/incubator-tvm/issues/4348#issuecomment-554597492 @gussmith23 Thanks for the proposal. I have a few thoughts/questions. - For the

[GitHub] [incubator-tvm] zhiics commented on issue #4352: [Debugger] Sorting op-time breakdown for quicker analysis.

2019-11-15 Thread GitBox
zhiics commented on issue #4352: [Debugger] Sorting op-time breakdown for quicker analysis. URL: https://github.com/apache/incubator-tvm/pull/4352#issuecomment-554596924 BTW, if I remember correctly, the correct output is sorted by the occurrence of the ops. If so, should we make this

[GitHub] [incubator-tvm] wweic commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
wweic commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#discussion_r347072383 ## File path: include/tvm/runtime/memory.h ## @@ -104,10 +124,22 @@ class SimpleObjAllocator :

[GitHub] [incubator-tvm] Laurawly commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore

2019-11-15 Thread GitBox
Laurawly commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore URL: https://github.com/apache/incubator-tvm/pull/4353#discussion_r347070174 ## File path: include/tvm/runtime/util.h ## @@ -39,6 +39,14 @@ namespace

[GitHub] [incubator-tvm] Laurawly commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore

2019-11-15 Thread GitBox
Laurawly commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore URL: https://github.com/apache/incubator-tvm/pull/4353#discussion_r347069828 ## File path: src/runtime/contrib/cublas/cublas.cc ## @@ -124,35 +175,205 @@

[GitHub] [incubator-tvm] Laurawly commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore

2019-11-15 Thread GitBox
Laurawly commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore URL: https://github.com/apache/incubator-tvm/pull/4353#discussion_r347069637 ## File path: src/runtime/contrib/cublas/cublas.cc ## @@ -36,6 +36,36 @@ inline

[GitHub] [incubator-tvm] Laurawly commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore

2019-11-15 Thread GitBox
Laurawly commented on a change in pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore URL: https://github.com/apache/incubator-tvm/pull/4353#discussion_r347069251 ## File path: src/runtime/contrib/cublas/cublas.cc ## @@ -36,6 +36,36 @@ inline

[GitHub] [incubator-tvm] optima2005 commented on issue #4300: [Relay][Frontend][Tensorflow]Add conv2d_transpose

2019-11-15 Thread GitBox
optima2005 commented on issue #4300: [Relay][Frontend][Tensorflow]Add conv2d_transpose URL: https://github.com/apache/incubator-tvm/pull/4300#issuecomment-554591424 @srkreddy1238 @yzhliu any further comments? Thanks! This is

[GitHub] [incubator-tvm] Hzfengsy opened a new pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore

2019-11-15 Thread GitBox
Hzfengsy opened a new pull request #4353: [Perf] Enhance cudnn and cublas backend and enable TensorCore URL: https://github.com/apache/incubator-tvm/pull/4353 Improvement: - Enable TensorCore at CuDNN and cublas - Add mix precision support at cublas - Choose dtype for convDesc to

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554587942 The inplace array is indeed somewhat tricky :) Here is one idea to make the effort easier for more similar cases: apology for

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554587942 The inplace array is indeed somewhat tricky :) Here is one idea to make the effort easier for more similar cases: apology for

[GitHub] [incubator-tvm] tqchen commented on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554587942 The inplace array is indeed somewhat tricky :) Here is one idea to make the effort easier for more similar cases: apology for typing in

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#discussion_r347064867 ## File path: src/runtime/container.cc ## @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#discussion_r347064899 ## File path: src/runtime/container.cc ## @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#discussion_r347065131 ## File path: src/runtime/container.cc ## @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#discussion_r347064580 ## File path: src/runtime/container.cc ## @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#discussion_r347064715 ## File path: src/runtime/container.cc ## @@ -0,0 +1,54 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] tqchen commented on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554585238 We care about alignment(otherwise it will leads to mysterious segfaults). Please use std::aligned_storage, allocate an array of

[incubator-tvm] branch master updated (0a9f7e9 -> ccde31f)

2019-11-15 Thread wuwei
This is an automated email from the ASF dual-hosted git repository. wuwei pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 0a9f7e9 Add workgroup size attribute to AMDGPU functions in codegen (#4342) add ccde31f AutoTVM:

[GitHub] [incubator-tvm] vinx13 merged pull request #4338: AutoTVM: selecting tuning templates when extracting task

2019-11-15 Thread GitBox
vinx13 merged pull request #4338: AutoTVM: selecting tuning templates when extracting task URL: https://github.com/apache/incubator-tvm/pull/4338 This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] vinx13 commented on issue #4338: AutoTVM: selecting tuning templates when extracting task

2019-11-15 Thread GitBox
vinx13 commented on issue #4338: AutoTVM: selecting tuning templates when extracting task URL: https://github.com/apache/incubator-tvm/pull/4338#issuecomment-554585331 Thanks @jackwish @comaniac @tmoreau89 this is merged

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554585238 We care about alignment(otherwise it will leads to mysterious segfaults). Please use std::aligned_storage, allocate an

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

2019-11-15 Thread GitBox
petrex commented on issue #4259: [DEV][DRAFT] TVM v0.6 Release candidate URL: https://github.com/apache/incubator-tvm/issues/4259#issuecomment-554585033 @yzhliu @ZihengJiang I can provide some input for AMD gpu backend. please tag me in your PR. thanks

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#discussion_r347062305 ## File path: include/tvm/runtime/memory.h ## @@ -104,10 +124,22 @@ class SimpleObjAllocator :

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on a change in pull request #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#discussion_r347062305 ## File path: include/tvm/runtime/memory.h ## @@ -104,10 +124,22 @@ class SimpleObjAllocator :

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule

2019-11-15 Thread GitBox
tqchen edited a comment on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-554580535 Also note that my comment about ExampleJSONModule is mainly to serve as example ways

[GitHub] [incubator-tvm] tqchen commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule

2019-11-15 Thread GitBox
tqchen commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-554580535 Also note that my comment about ExampleJSONModule is mainly to serve as example ways to

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule

2019-11-15 Thread GitBox
tqchen edited a comment on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-554580370 The current interfacing example already looks great. For the JSONModule usecase, i was

[GitHub] [incubator-tvm] tqchen commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule

2019-11-15 Thread GitBox
tqchen commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-554580370 The current interfacing example already looks great. For the JSONModule usecase, i was

[GitHub] [incubator-tvm] anijain2305 opened a new pull request #4352: [Debugger] Sorting op-time breakdown for quicker analysis.

2019-11-15 Thread GitBox
anijain2305 opened a new pull request #4352: [Debugger] Sorting op-time breakdown for quicker analysis. URL: https://github.com/apache/incubator-tvm/pull/4352 Profiler output is not sorted by time currently. So, a developer has to eyeball and find out the expensive ops. This PR sorts and

[GitHub] [incubator-tvm] petrex commented on issue #4305: [RUNTIME] Proper Device Attribute Query for AMD GPU

2019-11-15 Thread GitBox
petrex commented on issue #4305: [RUNTIME] Proper Device Attribute Query for AMD GPU URL: https://github.com/apache/incubator-tvm/pull/4305#issuecomment-554579203 Morning @masahi. That weird clang-format behavior was due to a missing `{` from a manual merging. I've pushed the fix

[GitHub] [incubator-tvm] comaniac commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule

2019-11-15 Thread GitBox
comaniac commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-554579198 > @comaniac Thanks for the update! Can you move the ExampleJSONModule into a formal module

[GitHub] [incubator-tvm] jackwish commented on issue #4338: AutoTVM: selecting tuning templates when extracting task

2019-11-15 Thread GitBox
jackwish commented on issue #4338: AutoTVM: selecting tuning templates when extracting task URL: https://github.com/apache/incubator-tvm/pull/4338#issuecomment-554571498 Thank you @comaniac ! I will update the tutorials in another PR. @tmoreau89 @vinx13 Would you like to have a look

[GitHub] [incubator-tvm] tqchen commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule

2019-11-15 Thread GitBox
tqchen commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-554569511 @comaniac Thanks for the update! Can you move the ExampleJSONModule into a formal module that

[GitHub] [incubator-tvm] anijain2305 opened a new pull request #4351: [QNN] Lowering for Depthwise Convolution.

2019-11-15 Thread GitBox
anijain2305 opened a new pull request #4351: [QNN] Lowering for Depthwise Convolution. URL: https://github.com/apache/incubator-tvm/pull/4351 Adding the QNN lowering sequence for Depthwise conv2d. This creates depthwise conv2d with (u)int8 inputs, opening up path to write schedule using

[GitHub] [incubator-tvm] wweic commented on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
wweic commented on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554567596 cc @tqchen @zhiics @icemelon9 @junrushao1994 This is an automated

[GitHub] [incubator-tvm] masahi commented on issue #4305: [RUNTIME] Proper Device Attribute Query for AMD GPU

2019-11-15 Thread GitBox
masahi commented on issue #4305: [RUNTIME] Proper Device Attribute Query for AMD GPU URL: https://github.com/apache/incubator-tvm/pull/4305#issuecomment-554567246 @petrex can you check indentation issues? I see some weird indentation done by clang-format. It should be consistent with the

[GitHub] [incubator-tvm] masahi commented on issue #4342: Add workgroup size attribute to AMDGPU functions in codegen

2019-11-15 Thread GitBox
masahi commented on issue #4342: Add workgroup size attribute to AMDGPU functions in codegen URL: https://github.com/apache/incubator-tvm/pull/4342#issuecomment-554565709 The flaky test is a known issue #4284 . Finding a way to set the optimal work group size would be an interesting

[GitHub] [incubator-tvm] masahi merged pull request #4342: Add workgroup size attribute to AMDGPU functions in codegen

2019-11-15 Thread GitBox
masahi merged pull request #4342: Add workgroup size attribute to AMDGPU functions in codegen URL: https://github.com/apache/incubator-tvm/pull/4342 This is an automated message from the Apache Git Service. To respond to

[incubator-tvm] branch master updated (d58b733 -> 0a9f7e9)

2019-11-15 Thread masahi
This is an automated email from the ASF dual-hosted git repository. masahi pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from d58b733 [FIX] Fix for a specific case when loop partitioning with indivisble (#4243) add 0a9f7e9 Add

[GitHub] [incubator-tvm] comaniac opened a new pull request #4350: fix install script

2019-11-15 Thread GitBox
comaniac opened a new pull request #4350: fix install script URL: https://github.com/apache/incubator-tvm/pull/4350 Fix the install scripts with mismatch folder names. cc @tqchen This is an automated message from the

[GitHub] [incubator-tvm] yzhliu commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule

2019-11-15 Thread GitBox
yzhliu commented on issue #4280: [TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule URL: https://github.com/apache/incubator-tvm/pull/4280#issuecomment-554558656 @tqchen would you take a look again?

[incubator-tvm] branch master updated (2c5c4da -> d58b733)

2019-11-15 Thread ziheng
This is an automated email from the ASF dual-hosted git repository. ziheng pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 2c5c4da [Relay][VM][Interpreter] Enable first-class constructors in VM and interpreter via eta expansion

[GitHub] [incubator-tvm] ZihengJiang merged pull request #4243: Fix broken loop partitioning due to recent changes.

2019-11-15 Thread GitBox
ZihengJiang merged pull request #4243: Fix broken loop partitioning due to recent changes. URL: https://github.com/apache/incubator-tvm/pull/4243 This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm] branch master updated (3f6b3db -> 2c5c4da)

2019-11-15 Thread haichen
This is an automated email from the ASF dual-hosted git repository. haichen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 3f6b3db [COMMUNITY] Add DISCLAIMER, KEYS for ASF release (#4345) add 2c5c4da [Relay][VM][Interpreter]

[GitHub] [incubator-tvm] icemelon9 merged pull request #4218: [Relay][VM][Interpreter] Enable first-class constructors in VM and interpreter via eta expansion

2019-11-15 Thread GitBox
icemelon9 merged pull request #4218: [Relay][VM][Interpreter] Enable first-class constructors in VM and interpreter via eta expansion URL: https://github.com/apache/incubator-tvm/pull/4218 This is an automated message from

[GitHub] [incubator-tvm] icemelon9 commented on issue #4218: [Relay][VM][Interpreter] Enable first-class constructors in VM and interpreter via eta expansion

2019-11-15 Thread GitBox
icemelon9 commented on issue #4218: [Relay][VM][Interpreter] Enable first-class constructors in VM and interpreter via eta expansion URL: https://github.com/apache/incubator-tvm/pull/4218#issuecomment-554549602 Thanks @weberlo @MarisaKirisame. This is now merged.

[GitHub] [incubator-tvm] jroesch merged pull request #4345: [COMMUNITY] Add DISCLAIMER, KEYS for ASF release

2019-11-15 Thread GitBox
jroesch merged pull request #4345: [COMMUNITY] Add DISCLAIMER, KEYS for ASF release URL: https://github.com/apache/incubator-tvm/pull/4345 This is an automated message from the Apache Git Service. To respond to the message,

[incubator-tvm] branch master updated (da23619 -> 3f6b3db)

2019-11-15 Thread jroesch
This is an automated email from the ASF dual-hosted git repository. jroesch pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from da23619 Add check to ensure input file was successfully opened in NNVM deploy code demo (#4315) add

[GitHub] [incubator-tvm] slyubomirsky edited a comment on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags

2019-11-15 Thread GitBox
slyubomirsky edited a comment on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags URL: https://github.com/apache/incubator-tvm/issues/4348#issuecomment-554540987 I think you can iterate through the passes by looking at the defined members of

[GitHub] [incubator-tvm] slyubomirsky commented on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags

2019-11-15 Thread GitBox
slyubomirsky commented on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags URL: https://github.com/apache/incubator-tvm/issues/4348#issuecomment-554540987 I think you can iterate through the passes by looking at the defined members of

[GitHub] [incubator-tvm] t-vi commented on issue #4342: Add workgroup size attribute to AMDGPU functions in codegen

2019-11-15 Thread GitBox
t-vi commented on issue #4342: Add workgroup size attribute to AMDGPU functions in codegen URL: https://github.com/apache/incubator-tvm/pull/4342#issuecomment-554533046 So for me it says "All checks have passed 1 successful check".

[GitHub] [incubator-tvm] anijain2305 commented on issue #4335: [Relay][WIP] ConvertLayout pass.

2019-11-15 Thread GitBox
anijain2305 commented on issue #4335: [Relay][WIP] ConvertLayout pass. URL: https://github.com/apache/incubator-tvm/pull/4335#issuecomment-554532864 Ok, let me spend some more time thinking about this :) This is an automated

[GitHub] [incubator-tvm] gussmith23 commented on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags

2019-11-15 Thread GitBox
gussmith23 commented on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags URL: https://github.com/apache/incubator-tvm/issues/4348#issuecomment-554509200 Talking with Steven and Marisa: - Tests should be automatically run over all passes, so that

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4339: Added tflite frontend support for quantized mean

2019-11-15 Thread GitBox
anijain2305 commented on a change in pull request #4339: Added tflite frontend support for quantized mean URL: https://github.com/apache/incubator-tvm/pull/4339#discussion_r346978076 ## File path: python/tvm/relay/frontend/tflite.py ## @@ -659,7 +659,23 @@ def

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4339: Added tflite frontend support for quantized mean

2019-11-15 Thread GitBox
anijain2305 commented on a change in pull request #4339: Added tflite frontend support for quantized mean URL: https://github.com/apache/incubator-tvm/pull/4339#discussion_r346978076 ## File path: python/tvm/relay/frontend/tflite.py ## @@ -659,7 +659,23 @@ def

[GitHub] [incubator-tvm] wweic commented on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
wweic commented on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554491747 > NOTE: You will likely need to change memory.h::Allocator interface to allow > > ``` >

[GitHub] [incubator-tvm] gussmith23 commented on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags

2019-11-15 Thread GitBox
gussmith23 commented on issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags URL: https://github.com/apache/incubator-tvm/issues/4348#issuecomment-554491870 For the record, we want to test against real models -- not just generating adversarial

[GitHub] [incubator-tvm] tqchen merged pull request #4315: Add check to ensure input file was successfully opened in NNVM deploy…

2019-11-15 Thread GitBox
tqchen merged pull request #4315: Add check to ensure input file was successfully opened in NNVM deploy… URL: https://github.com/apache/incubator-tvm/pull/4315 This is an automated message from the Apache Git Service. To

[incubator-tvm] branch master updated (888a3c3 -> da23619)

2019-11-15 Thread tqchen
This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 888a3c3 Bump up CUDA log version in tophub.py (#4347) add da23619 Add check to ensure input file was

[GitHub] [incubator-tvm] hcho3 opened a new pull request #4349: Fix docstring in topi.nn.fifo_buffer

2019-11-15 Thread GitBox
hcho3 opened a new pull request #4349: Fix docstring in topi.nn.fifo_buffer URL: https://github.com/apache/incubator-tvm/pull/4349 Rendered output: ![Screen Shot 2019-11-15 at 11 14 18

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554488600 NOTE: You will likely need to change memory.h::Allocator interface to allow

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen edited a comment on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554488600 NOTE: You will likely need to change memory.h::Allocator interface to allow ```

[GitHub] [incubator-tvm] yidawang commented on a change in pull request #4344: [ThreadPool] Solve thread transitions issue

2019-11-15 Thread GitBox
yidawang commented on a change in pull request #4344: [ThreadPool] Solve thread transitions issue URL: https://github.com/apache/incubator-tvm/pull/4344#discussion_r346968947 ## File path: src/runtime/thread_pool.cc ## @@ -370,11 +374,7 @@ class ThreadPool { // number

[GitHub] [incubator-tvm] tqchen commented on issue #4346: [Runtime] Make ADTObject POD container type

2019-11-15 Thread GitBox
tqchen commented on issue #4346: [Runtime] Make ADTObject POD container type URL: https://github.com/apache/incubator-tvm/pull/4346#issuecomment-554488600 NOTE: You will likely need to change memory.h::Allocator interface to allow Allocator::make_with_extra_space(size *

[incubator-tvm] branch master updated (b0b16a0 -> 888a3c3)

2019-11-15 Thread tqchen
This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from b0b16a0 [CodeGen] Add build config option disable_assert to control whether to generate assert (#4340)

[GitHub] [incubator-tvm] tqchen merged pull request #4347: Bump up CUDA log version in tophub.py

2019-11-15 Thread GitBox
tqchen merged pull request #4347: Bump up CUDA log version in tophub.py URL: https://github.com/apache/incubator-tvm/pull/4347 This is an automated message from the Apache Git Service. To respond to the message, please log

[GitHub] [incubator-tvm] weberlo commented on issue #4218: [Relay][VM][Interpreter] Enable first-class constructors in VM and interpreter via eta expansion

2019-11-15 Thread GitBox
weberlo commented on issue #4218: [Relay][VM][Interpreter] Enable first-class constructors in VM and interpreter via eta expansion URL: https://github.com/apache/incubator-tvm/pull/4218#issuecomment-554483679 @icemelon9 CI is green again

[GitHub] [incubator-tvm] gussmith23 opened a new issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags

2019-11-15 Thread GitBox
gussmith23 opened a new issue #4348: [Relay] Add tests in CI which run tests based on specific Relay feature flags URL: https://github.com/apache/incubator-tvm/issues/4348 A persistent problem in Relay is what @MarisaKirisame calls the "split-brain" problem: the developers of Relay and

[GitHub] [incubator-tvm] tqchen merged pull request #4340: [CodeGen] Add build config option disable_assert to control whether to generate assert

2019-11-15 Thread GitBox
tqchen merged pull request #4340: [CodeGen] Add build config option disable_assert to control whether to generate assert URL: https://github.com/apache/incubator-tvm/pull/4340 This is an automated message from the Apache

[GitHub] [incubator-tvm] tqchen commented on issue #4340: [CodeGen] Add build config option disable_assert to control whether to generate assert

2019-11-15 Thread GitBox
tqchen commented on issue #4340: [CodeGen] Add build config option disable_assert to control whether to generate assert URL: https://github.com/apache/incubator-tvm/pull/4340#issuecomment-554466791 Thanks @FrozenGene ! This

[incubator-tvm] branch master updated (a8e6ee9 -> b0b16a0)

2019-11-15 Thread tqchen
This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from a8e6ee9 fix inconsistent tag name (#4134) add b0b16a0 [CodeGen] Add build config option disable_assert

[incubator-tvm] branch master updated (5b1ca85 -> a8e6ee9)

2019-11-15 Thread kevinthesun
This is an automated email from the ASF dual-hosted git repository. kevinthesun pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 5b1ca85 [VTA] Bug fix for padded load with large inputs (#4293) add a8e6ee9 fix inconsistent tag

[GitHub] [incubator-tvm] kevinthesun merged pull request #4134: [TOPI] fix inconsistent tag name

2019-11-15 Thread GitBox
kevinthesun merged pull request #4134: [TOPI] fix inconsistent tag name URL: https://github.com/apache/incubator-tvm/pull/4134 This is an automated message from the Apache Git Service. To respond to the message, please log

[GitHub] [incubator-tvm] kevinthesun commented on issue #4134: [TOPI] fix inconsistent tag name

2019-11-15 Thread GitBox
kevinthesun commented on issue #4134: [TOPI] fix inconsistent tag name URL: https://github.com/apache/incubator-tvm/pull/4134#issuecomment-554464671 Thanks @ziyu-guo This is now merged. This is an automated message from the

[GitHub] [incubator-tvm] tmoreau89 merged pull request #4293: [VTA] Bug fix for padded load with large inputs

2019-11-15 Thread GitBox
tmoreau89 merged pull request #4293: [VTA] Bug fix for padded load with large inputs URL: https://github.com/apache/incubator-tvm/pull/4293 This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm] branch master updated (9e6371f -> 5b1ca85)

2019-11-15 Thread moreau
This is an automated email from the ASF dual-hosted git repository. moreau pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 9e6371f imp module is deprecated (#4275) add 5b1ca85 [VTA] Bug fix for padded load with large inputs

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #4303: [TOPI][Relay][OP] Add a strided_set operation.

2019-11-15 Thread GitBox
junrushao1994 commented on a change in pull request #4303: [TOPI][Relay][OP] Add a strided_set operation. URL: https://github.com/apache/incubator-tvm/pull/4303#discussion_r346942383 ## File path: topi/python/topi/transform.py ## @@ -155,6 +157,78 @@ def strided_slice(a,

[GitHub] [incubator-tvm] vegaluisjose commented on issue #4293: [VTA] Bug fix for padded load with large inputs

2019-11-15 Thread GitBox
vegaluisjose commented on issue #4293: [VTA] Bug fix for padded load with large inputs URL: https://github.com/apache/incubator-tvm/pull/4293#issuecomment-554463825 LGTM This is an automated message from the Apache Git

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #4303: [TOPI][Relay][OP] Add a strided_set operation.

2019-11-15 Thread GitBox
junrushao1994 commented on a change in pull request #4303: [TOPI][Relay][OP] Add a strided_set operation. URL: https://github.com/apache/incubator-tvm/pull/4303#discussion_r346942216 ## File path: python/tvm/relay/op/_transform.py ## @@ -304,6 +305,31 @@ def

[GitHub] [incubator-tvm] tmoreau89 commented on issue #4318: [Relay][TOPI]Fix meaning of conv2d_transpose output_padding parameter

2019-11-15 Thread GitBox
tmoreau89 commented on issue #4318: [Relay][TOPI]Fix meaning of conv2d_transpose output_padding parameter URL: https://github.com/apache/incubator-tvm/pull/4318#issuecomment-554462420 @abergeron ack, I'll investigate to see what causes the failure at the moment. Will report back by

[GitHub] [incubator-tvm] tmoreau89 commented on issue #4293: [VTA] Bug fix for padded load with large inputs

2019-11-15 Thread GitBox
tmoreau89 commented on issue #4293: [VTA] Bug fix for padded load with large inputs URL: https://github.com/apache/incubator-tvm/pull/4293#issuecomment-554462047 Thanks. @vegaluisjose pending your approval I'll merge the changes.

[GitHub] [incubator-tvm] comaniac commented on issue #4338: AutoTVM: selecting tuning templates when extracting task

2019-11-15 Thread GitBox
comaniac commented on issue #4338: AutoTVM: selecting tuning templates when extracting task URL: https://github.com/apache/incubator-tvm/pull/4338#issuecomment-554459503 Thanks. LGTM. btw, would you update the tutorial as well?

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #4338: AutoTVM: selecting tuning templates when extracting task

2019-11-15 Thread GitBox
comaniac commented on a change in pull request #4338: AutoTVM: selecting tuning templates when extracting task URL: https://github.com/apache/incubator-tvm/pull/4338#discussion_r346937857 ## File path: python/tvm/autotvm/task/relay_integration.py ## @@ -103,8 +104,8 @@

[incubator-tvm] branch master updated (510bd8f -> 9e6371f)

2019-11-15 Thread tqchen
This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 510bd8f [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth (#4271) add 9e6371f imp

  1   2   >