[GitHub] [incubator-tvm] kevinthesun commented on a change in pull request #5588: [Frontend][Tensorflow] Gather nd bug fix for one dim support in tensorflow

2020-05-18 Thread GitBox
kevinthesun commented on a change in pull request #5588: URL: https://github.com/apache/incubator-tvm/pull/5588#discussion_r427046505 ## File path: src/relay/op/tensor/transform.cc ## @@ -2248,6 +2248,9 @@ bool GatherNDRel(const Array& types, int num_inputs, const Attrs&

[GitHub] [incubator-tvm] kazum opened a new pull request #5621: [IOS] Fix build error of iOS RPC

2020-05-18 Thread GitBox
kazum opened a new pull request #5621: URL: https://github.com/apache/incubator-tvm/pull/5621 This PR fixes build error of the iOS RPC. - Update to C++14 - Use the latest RPC protocol - Resolve CoreML dependency @tqchen @ZihengJiang @FrozenGene Please help to review.

[GitHub] [incubator-tvm] littlefish0123 opened a new pull request #5620: Fix three typos

2020-05-18 Thread GitBox
littlefish0123 opened a new pull request #5620: URL: https://github.com/apache/incubator-tvm/pull/5620 Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request

[GitHub] [incubator-tvm] comaniac commented on pull request #5613: add schedule algorithm for super large batch and small inner dimension

2020-05-18 Thread GitBox
comaniac commented on pull request #5613: URL: https://github.com/apache/incubator-tvm/pull/5613#issuecomment-630521369 > @comaniac I think the `dense_large_batch` is quite complicated, therefore adjusting the `dense_large_batch` directly to handle super large batch size is error-prone.

[GitHub] [incubator-tvm] lsy643 commented on pull request #5613: add schedule algorithm for super large batch and small inner dimension

2020-05-18 Thread GitBox
lsy643 commented on pull request #5613: URL: https://github.com/apache/incubator-tvm/pull/5613#issuecomment-630518642 @comaniac I think the `dense_large_batch` is quite complicated, therefore adjusting the `dense_large_batch` directly to handle super large batch size is error-prone. In

[GitHub] [incubator-tvm] kaimast closed issue #5608: Failed to compile Rust examples on SGX

2020-05-18 Thread GitBox
kaimast closed issue #5608: URL: https://github.com/apache/incubator-tvm/issues/5608 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go

[GitHub] [incubator-tvm] kaimast commented on issue #5608: Failed to compile Rust examples on SGX

2020-05-18 Thread GitBox
kaimast commented on issue #5608: URL: https://github.com/apache/incubator-tvm/issues/5608#issuecomment-630485374 > https://github.com/apache/incubator-tvm/blob/master/apps/sgx/build.rs#L68-L73 Thanks. Not sure why but that fixes it!

[GitHub] [incubator-tvm] nhynes commented on issue #5608: Failed to compile Rust examples on SGX

2020-05-18 Thread GitBox
nhynes commented on issue #5608: URL: https://github.com/apache/incubator-tvm/issues/5608#issuecomment-630475260 https://github.com/apache/incubator-tvm/blob/master/apps/sgx/build.rs#L68-L73 This is an automated message from

[GitHub] [incubator-tvm] mbrookhart opened a new pull request #5619: Add Scatter to Topi/Relay/ONNX via hybrid script

2020-05-18 Thread GitBox
mbrookhart opened a new pull request #5619: URL: https://github.com/apache/incubator-tvm/pull/5619 cc: @jwfromm @tqchen @masahi The actual hybrid script implementation is kind of gross, I can't seem to figure out a way to clean it up without causing very opaque errors in the

[GitHub] [incubator-tvm] tqchen commented on pull request #5578: [Relay][Refactor][std::string --> String] Relay updated with String

2020-05-18 Thread GitBox
tqchen commented on pull request #5578: URL: https://github.com/apache/incubator-tvm/pull/5578#issuecomment-630462825 Thanks @ANSHUMAN87 @jroesch @zhiics This is an automated message from the Apache Git Service. To respond

[GitHub] [incubator-tvm] tqchen merged pull request #5578: [Relay][Refactor][std::string --> String] Relay updated with String

2020-05-18 Thread GitBox
tqchen merged pull request #5578: URL: https://github.com/apache/incubator-tvm/pull/5578 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to

[incubator-tvm] branch master updated: [Relay][Refactor][std::string --> String] Relay updated with String (#5578)

2020-05-18 Thread tqchen
This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/master by this push: new 538e296 [Relay][Refactor][std::string

[GitHub] [incubator-tvm] jroesch commented on pull request #5596: [TIR][REFACTOR] std::string -> String Migration in TIR nodes

2020-05-18 Thread GitBox
jroesch commented on pull request #5596: URL: https://github.com/apache/incubator-tvm/pull/5596#issuecomment-630390679 Let me know when its ready for review. This is an automated message from the Apache Git Service. To

[incubator-tvm] branch master updated (3be9576 -> 09792ec)

2020-05-18 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 3be9576 [BYOC] Remove kCompiler attr from external functions (#5615) add 09792ec [Relay]Improve Shape

[GitHub] [incubator-tvm] jroesch merged pull request #5467: [Relay]Improve Shape Func handling for Tuple inputs

2020-05-18 Thread GitBox
jroesch merged pull request #5467: URL: https://github.com/apache/incubator-tvm/pull/5467 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to

[GitHub] [incubator-tvm] yzhliu opened a new pull request #5618: [Arith] Inequalities solver

2020-05-18 Thread GitBox
yzhliu opened a new pull request #5618: URL: https://github.com/apache/incubator-tvm/pull/5618 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL

[GitHub] [incubator-tvm] ANSHUMAN87 commented on pull request #5588: [Frontend][Tensorflow] Gather nd bug fix for one dim support in tensorflow

2020-05-18 Thread GitBox
ANSHUMAN87 commented on pull request #5588: URL: https://github.com/apache/incubator-tvm/pull/5588#issuecomment-630361991 @kevinthesun : Your comment is handled now. Please check. Thanks! This is an automated message from

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #5616: [RELAY][BYOC] Fix the creation of tuple of tuples in PartitionGraph

2020-05-18 Thread GitBox
comaniac commented on a change in pull request #5616: URL: https://github.com/apache/incubator-tvm/pull/5616#discussion_r426802467 ## File path: src/relay/transforms/partition_graph.cc ## @@ -404,18 +404,85 @@ IRModule RemoveDefaultAnnotations(IRModule module) { return

[GitHub] [incubator-tvm] zhiics commented on pull request #5615: [BYOC] Remove kCompiler attr from external functions

2020-05-18 Thread GitBox
zhiics commented on pull request #5615: URL: https://github.com/apache/incubator-tvm/pull/5615#issuecomment-630338767 Thanks @lhutton1 @comaniac This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm] branch master updated (2594f17 -> 3be9576)

2020-05-18 Thread zhic
This is an automated email from the ASF dual-hosted git repository. zhic pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 2594f17 fix pattern topological order (#5612) add 3be9576 [BYOC] Remove kCompiler attr from external

[GitHub] [incubator-tvm] zhiics merged pull request #5615: [BYOC] Remove kCompiler attr from external functions

2020-05-18 Thread GitBox
zhiics merged pull request #5615: URL: https://github.com/apache/incubator-tvm/pull/5615 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to

[GitHub] [incubator-tvm] deepakbabel23 commented on pull request #5617: [TENSORFLOW]StatefulPartitionedCall/PartitionedCall Ops support added

2020-05-18 Thread GitBox
deepakbabel23 commented on pull request #5617: URL: https://github.com/apache/incubator-tvm/pull/5617#issuecomment-630334497 @kevinthesun , @yongwww Hi Kevin, Please review these changes. This is an automated

[GitHub] [incubator-tvm] ANSHUMAN87 commented on pull request #5578: [Relay][Refactor][std::string --> String] Relay updated with String

2020-05-18 Thread GitBox
ANSHUMAN87 commented on pull request #5578: URL: https://github.com/apache/incubator-tvm/pull/5578#issuecomment-630326224 @tqchen : Your comment is handled now, added test case as well. Please check. Thanks! This is an

[GitHub] [incubator-tvm] kevinthesun commented on pull request #4312: [TOPI][Relay][OP] Dynamic NMS and strided_slice

2020-05-18 Thread GitBox
kevinthesun commented on pull request #4312: URL: https://github.com/apache/incubator-tvm/pull/4312#issuecomment-630322373 @heliqi The code should be OK. This is an automated message from the Apache Git Service. To respond

[incubator-tvm] branch master updated (f1fe9b0 -> 2594f17)

2020-05-18 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 f1fe9b0 Fix a typo. (#5611) add 2594f17 fix pattern topological order (#5612) No new revisions were

[GitHub] [incubator-tvm] tqchen merged pull request #5612: Fix Topological Order calculation for DFPattern Language

2020-05-18 Thread GitBox
tqchen merged pull request #5612: URL: https://github.com/apache/incubator-tvm/pull/5612 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to

[GitHub] [incubator-tvm] tqchen commented on pull request #5612: Fix Topological Order calculation for DFPattern Language

2020-05-18 Thread GitBox
tqchen commented on pull request #5612: URL: https://github.com/apache/incubator-tvm/pull/5612#issuecomment-630320123 THanks@mbrookhart @comaniac This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] comaniac commented on pull request #5613: add schedule algorithm for super large batch and small inner dimension

2020-05-18 Thread GitBox
comaniac commented on pull request #5613: URL: https://github.com/apache/incubator-tvm/pull/5613#issuecomment-630306466 Is there any obstacles that prevent you from improving `dense_large_batch` to support the batch size larger than 65535?

[GitHub] [incubator-tvm] comaniac commented on issue #5605: [BUG] Pattern Reeriter Seg Fault

2020-05-18 Thread GitBox
comaniac commented on issue #5605: URL: https://github.com/apache/incubator-tvm/issues/5605#issuecomment-630303281 The PR fixed this issue. Thanks! This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] comaniac closed issue #5605: [BUG] Pattern Reeriter Seg Fault

2020-05-18 Thread GitBox
comaniac closed issue #5605: URL: https://github.com/apache/incubator-tvm/issues/5605 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go

[GitHub] [incubator-tvm] deepakbabel23 opened a new pull request #5617: [TENSORFLOW]StatefulPartitionedCall/PartitionedCall Ops support added

2020-05-18 Thread GitBox
deepakbabel23 opened a new pull request #5617: URL: https://github.com/apache/incubator-tvm/pull/5617 Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #5600: [TOPI] Improve CUDA softmax scheduling

2020-05-18 Thread GitBox
tqchen commented on a change in pull request #5600: URL: https://github.com/apache/incubator-tvm/pull/5600#discussion_r426737561 ## File path: src/target/llvm/codegen_llvm.cc ## @@ -736,7 +736,40 @@ llvm::Function* CodeGenLLVM::GetIntrinsicDecl(llvm::Intrinsic::ID id,

[GitHub] [incubator-tvm] tqchen commented on pull request #5600: [TOPI] Improve CUDA softmax scheduling

2020-05-18 Thread GitBox
tqchen commented on pull request #5600: URL: https://github.com/apache/incubator-tvm/pull/5600#issuecomment-630282939 @icemelon9 @Hzfengsy @Shawn-Inspur please also take a look This is an automated message from the Apache

[GitHub] [incubator-tvm] wpan11nv commented on a change in pull request #5600: [TOPI] Improve CUDA softmax scheduling

2020-05-18 Thread GitBox
wpan11nv commented on a change in pull request #5600: URL: https://github.com/apache/incubator-tvm/pull/5600#discussion_r426735612 ## File path: src/tir/transforms/lower_warp_memory.cc ## @@ -213,9 +213,13 @@ class WarpAccessRewriter : protected StmtExprMutator {

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #5578: [Relay][Refactor][std::string --> String] Relay updated with String

2020-05-18 Thread GitBox
tqchen commented on a change in pull request #5578: URL: https://github.com/apache/incubator-tvm/pull/5578#discussion_r426677508 ## File path: include/tvm/relay/base.h ## @@ -93,7 +93,7 @@ class IdNode : public Object { * this only acts as a hint to the user, * and

[incubator-tvm] branch master updated (cb7bd98 -> f1fe9b0)

2020-05-18 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 cb7bd98 [CUDA] Fix codegen for warp shuffle intrinsics (#5606) add f1fe9b0 Fix a typo. (#5611) No new

[GitHub] [incubator-tvm] tqchen commented on pull request #5611: Fix a typo.

2020-05-18 Thread GitBox
tqchen commented on pull request #5611: URL: https://github.com/apache/incubator-tvm/pull/5611#issuecomment-630221296 Thanks @littlefish0123 @cchung100m This is an automated message from the Apache Git Service. To respond

[GitHub] [incubator-tvm] tqchen merged pull request #5611: Fix a typo.

2020-05-18 Thread GitBox
tqchen merged pull request #5611: URL: https://github.com/apache/incubator-tvm/pull/5611 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to

[GitHub] [incubator-tvm] manupa-arm opened a new pull request #5616: [RELAY][BYOC] Fix the creation of tuple of tuples in PartitionGraph

2020-05-18 Thread GitBox
manupa-arm opened a new pull request #5616: URL: https://github.com/apache/incubator-tvm/pull/5616 If the annotated compiler region contains multiple outputs where some of the outputs are tuple output, the current PartitionGraph will create tuple of tuples. This will not be handled by the

[GitHub] [incubator-tvm] lhutton1 commented on pull request #5615: [BYOC] Remove kCompiler attr from external functions

2020-05-18 Thread GitBox
lhutton1 commented on pull request #5615: URL: https://github.com/apache/incubator-tvm/pull/5615#issuecomment-630216977 cc @comaniac @zhiics @mbaret This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] lhutton1 opened a new pull request #5615: [BYOC] Remove kCompiler attr from external functions

2020-05-18 Thread GitBox
lhutton1 opened a new pull request #5615: URL: https://github.com/apache/incubator-tvm/pull/5615 Functions destined for external codegen keep their kCompiler attribute which means SkipFunction returns true when running a pass over such functions during the codegen step. This makes sense

[GitHub] [incubator-tvm] siju-samuel opened a new pull request #5614: [MXNET]MaxPool3d and AvgPool3d Ops support added

2020-05-18 Thread GitBox
siju-samuel opened a new pull request #5614: URL: https://github.com/apache/incubator-tvm/pull/5614 MaxPool3D and AvgPool3D op support added in mxnet. @FrozenGene @masahi Please help to review this PR. TIA This is

[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request #5394: [TFLITE]Quantize & Dequantize op

2020-05-18 Thread GitBox
siju-samuel commented on a change in pull request #5394: URL: https://github.com/apache/incubator-tvm/pull/5394#discussion_r426560071 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -1552,6 +1552,48 @@ def test_forward_squeeze():

[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request #5394: [TFLITE]Quantize & Dequantize op

2020-05-18 Thread GitBox
siju-samuel commented on a change in pull request #5394: URL: https://github.com/apache/incubator-tvm/pull/5394#discussion_r426561425 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -1552,6 +1552,48 @@ def test_forward_squeeze():

[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request #5394: [TFLITE]Quantize & Dequantize op

2020-05-18 Thread GitBox
siju-samuel commented on a change in pull request #5394: URL: https://github.com/apache/incubator-tvm/pull/5394#discussion_r426560071 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -1552,6 +1552,48 @@ def test_forward_squeeze():

[GitHub] [incubator-tvm] inadob commented on a change in pull request #5394: [TFLITE]Quantize & Dequantize op

2020-05-18 Thread GitBox
inadob commented on a change in pull request #5394: URL: https://github.com/apache/incubator-tvm/pull/5394#discussion_r426555314 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -1552,6 +1552,48 @@ def test_forward_squeeze():

[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request #5394: [TFLITE]Quantize & Dequantize op

2020-05-18 Thread GitBox
FrozenGene commented on a change in pull request #5394: URL: https://github.com/apache/incubator-tvm/pull/5394#discussion_r426550701 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -1552,6 +1552,48 @@ def test_forward_squeeze():

[GitHub] [incubator-tvm] siju-samuel commented on pull request #5394: [TFLITE]Quantize & Dequantize op

2020-05-18 Thread GitBox
siju-samuel commented on pull request #5394: URL: https://github.com/apache/incubator-tvm/pull/5394#issuecomment-630102640 @masahi @anijain2305 @inadob Please help to review and merge this PR. TIA This is an automated

[GitHub] [incubator-tvm] siju-samuel commented on pull request #5098: [KERAS]Global MaxPool3d and AvgPool3d support

2020-05-18 Thread GitBox
siju-samuel commented on pull request #5098: URL: https://github.com/apache/incubator-tvm/pull/5098#issuecomment-630102255 @masahi Please help to review and merge. TIA. This is an automated message from the Apache Git

[GitHub] [incubator-tvm] heliqi commented on pull request #4312: [TOPI][Relay][OP] Dynamic NMS and strided_slice

2020-05-18 Thread GitBox
heliqi commented on pull request #4312: URL: https://github.com/apache/incubator-tvm/pull/4312#issuecomment-630033704 Is there anything wrong with this code? Can I use it directly now? My model has an operator "NonMaxSuppressionv4", only one more parameter "pad_to_max_output_size".

[GitHub] [incubator-tvm] Sophia0806 commented on issue #4490: Issue with running cpp test

2020-05-18 Thread GitBox
Sophia0806 commented on issue #4490: URL: https://github.com/apache/incubator-tvm/issues/4490#issuecomment-630008095 Hi have you resolved this problem? I meet the same one. This is an automated message from the Apache Git

[GitHub] [incubator-tvm] lsy643 opened a new pull request #5613: add schedule algorithm for super large batch and small inner dimension

2020-05-18 Thread GitBox
lsy643 opened a new pull request #5613: URL: https://github.com/apache/incubator-tvm/pull/5613 For dense operation such as `C = relay.op.dense(A, B), A.shape = [215296, 1], B.shape = [1, 4]`, no valid config can be found for current schedule algorithms either `dense_small_batch` nor

[GitHub] [incubator-tvm] ANSHUMAN87 commented on pull request #5578: [Relay][Refactor][std::string --> String] Relay updated with String

2020-05-18 Thread GitBox
ANSHUMAN87 commented on pull request #5578: URL: https://github.com/apache/incubator-tvm/pull/5578#issuecomment-629964510 Gentle ping @jroesch , @tqchen ! This is an automated message from the Apache Git Service. To respond