[GitHub] [incubator-tvm] mbaret commented on pull request #5409: [BYOC] Don't annotate constants

2020-04-29 Thread GitBox
mbaret commented on pull request #5409: URL: https://github.com/apache/incubator-tvm/pull/5409#issuecomment-621253051 I've implemented an alternative fix in partition_graph.cc by explicitly binding constant tuples (see [5476](https://github.com/apache/incubator-tvm/pull/5476)). This means

[GitHub] [incubator-tvm] roastduck edited a comment on pull request #5465: [TIR] Convert if_then_else intrinsics to if-statements

2020-04-29 Thread GitBox
roastduck edited a comment on pull request #5465: URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-621285171 Made the pass default when lowering. So that not only generated device code, but also lowered IR in simple mode, will reflect this pass.

[GitHub] [incubator-tvm] roastduck commented on pull request #5465: [TIR] Convert if_then_else intrinsics to if-statements

2020-04-29 Thread GitBox
roastduck commented on pull request #5465: URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-621285171 Made the pass default when lowering. This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] tqchen edited a comment on pull request #5465: [TIR] Convert if_then_else intrinsics to if-statements

2020-04-29 Thread GitBox
tqchen edited a comment on pull request #5465: URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-621242357 Thanks @roastduck Given that it is a quit fundamental construct that can leads to concise generated code(e.g. ? in CUDA), I think we should keep it

[GitHub] [incubator-tvm] mbaret opened a new pull request #5476: [BYOC] Bind constant tuples in graph partitioner

2020-04-29 Thread GitBox
mbaret opened a new pull request #5476: URL: https://github.com/apache/incubator-tvm/pull/5476 Constant tuples were not being propagated into partitions making it impossible to codegen functions like concatenate. This extends the constant binding that happens in PartitionGraph to also

[GitHub] [incubator-tvm] tqchen commented on pull request #5417: [RUNTIME][uTVM] AutoTVM + uTVM for Cortex-M7

2020-04-29 Thread GitBox
tqchen commented on pull request #5417: URL: https://github.com/apache/incubator-tvm/pull/5417#issuecomment-621237313 @weberlo @tmoreau89 @liangfu @u99127 please take another look and http://tvm.apache.org/docs/contribute/code_review.html#approve-and-request-changes-explicitly

[GitHub] [incubator-tvm] tqchen commented on pull request #5465: [TIR] Convert if_then_else intrinsics to if-statements

2020-04-29 Thread GitBox
tqchen commented on pull request #5465: URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-621242357 Thanks @roastduck if the goal is mainly to utilize LoopParition, perhaps a better way would be to insert likely into the condition and enable LoopPartition to deal with

[GitHub] [incubator-tvm] mbaret commented on pull request #5473: [TFLITE] Match TFLite shape for SSD custom op

2020-04-29 Thread GitBox
mbaret commented on pull request #5473: URL: https://github.com/apache/incubator-tvm/pull/5473#issuecomment-621250794 cc @anijain2305 This is an automated message from the Apache Git Service. To respond to the message,

[incubator-tvm-vta] branch master updated: [Hardware][Xilinx] utilize uram (#6)

2020-04-29 Thread moreau
This is an automated email from the ASF dual-hosted git repository. moreau pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm-vta.git The following commit(s) were added to refs/heads/master by this push: new 22e4b88 [Hardware][Xilinx] utilize

[GitHub] [incubator-tvm] tqchen commented on issue #5464: [OpenCL] `directly 4 8 bit int in integer` causes compiling error

2020-04-29 Thread GitBox
tqchen commented on issue #5464: URL: https://github.com/apache/incubator-tvm/issues/5464#issuecomment-621240765 cc @kazum @masahi This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [incubator-tvm] tqchen commented on issue #5446: [NMS] nms operation cost too mush time

2020-04-29 Thread GitBox
tqchen commented on issue #5446: URL: https://github.com/apache/incubator-tvm/issues/5446#issuecomment-621241256 Thanks for start the discussion, Please open a new discussion thread on https://discuss.tvm.ai/ This is an

[GitHub] [incubator-tvm] mbaret commented on a change in pull request #5474: [Frontend][TFLite] ADD_N operator

2020-04-29 Thread GitBox
mbaret commented on a change in pull request #5474: URL: https://github.com/apache/incubator-tvm/pull/5474#discussion_r417383328 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -1896,6 +1896,41 @@ def test_forward_mediapipe_hand_landmark():

[GitHub] [incubator-tvm] anijain2305 commented on pull request #5473: [TFLITE] Match TFLite shape for SSD custom op

2020-04-29 Thread GitBox
anijain2305 commented on pull request #5473: URL: https://github.com/apache/incubator-tvm/pull/5473#issuecomment-621313035 Thanks @mbaret This is merged! This is an automated message from the Apache Git Service. To respond

[incubator-tvm] branch master updated: [TFLITE] Match TFLite shape for SSD custom op (#5473)

2020-04-29 Thread anijain2305
This is an automated email from the ASF dual-hosted git repository. anijain2305 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 95a816c [TFLITE] Match TFLite

[GitHub] [incubator-tvm] roastduck commented on pull request #5465: [TIR] Convert if_then_else intrinsics to if-statements

2020-04-29 Thread GitBox
roastduck commented on pull request #5465: URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-621282600 > Given that it is a quit fundamental construct that can leads to concise generated code(e.g. ? in CUDA), I think we should keep it throughout the lowering process by

[GitHub] [incubator-tvm] tqchen commented on issue #4102: [Relay] Support for Tensorflow 2.0

2020-04-29 Thread GitBox
tqchen commented on issue #4102: URL: https://github.com/apache/incubator-tvm/issues/4102#issuecomment-621363297 NOTE: the Mainline CI now uses tensorflow 2.0 This is an automated message from the Apache Git Service. To

[incubator-tvm] branch master updated (f1e87f1 -> 4d8816c)

2020-04-29 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 f1e87f1 [CODEGEN][CUDA] Fix a bug when vectorized load was involved for… (#5428) add 4d8816c [CI]

[GitHub] [incubator-tvm] tqchen commented on pull request #5436: [TFLite Runtime] Re-enable test for remote execution via RPC

2020-04-29 Thread GitBox
tqchen commented on pull request #5436: URL: https://github.com/apache/incubator-tvm/pull/5436#issuecomment-621364933 NOTE: the ci-cpu is still blocked by https://github.com/apache/incubator-tvm/issues/5455 ci-gpu is now updated. If we can update the testcase to pre-check the env before

[GitHub] [incubator-tvm] icemelon9 commented on pull request #5357: [Relay] enable blocking format in x86 conv2d and fold scale axis

2020-04-29 Thread GitBox
icemelon9 commented on pull request #5357: URL: https://github.com/apache/incubator-tvm/pull/5357#issuecomment-621364453 @Menooker Could you share the script that can reproduce the error? It's a bit weird that `_alter_conv2d_layout` receive a conv2d op with `NCHWc` layout.

[GitHub] [incubator-tvm] mbaret commented on pull request #5360: [QNN] Support CallNode inputs in qnn.concatenate

2020-04-29 Thread GitBox
mbaret commented on pull request #5360: URL: https://github.com/apache/incubator-tvm/pull/5360#issuecomment-621346205 @anijain2305 @zhiics could you take a look at the changes I've made and see if this is now OK? This is an

[incubator-tvm] branch master updated: [CODEGEN][CUDA] Fix a bug when vectorized load was involved for… (#5428)

2020-04-29 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 f1e87f1 [CODEGEN][CUDA] Fix a bug when

[GitHub] [incubator-tvm] tqchen commented on pull request #5428: [CODEGEN][CUDA] Fix a bug when vectorized load was involved for…

2020-04-29 Thread GitBox
tqchen commented on pull request #5428: URL: https://github.com/apache/incubator-tvm/pull/5428#issuecomment-621350989 Thanks @wpan11nv @boh-inspur ! This is an automated message from the Apache Git Service. To respond to

[GitHub] [incubator-tvm-vta] huajsj commented on pull request #7: [pynq_driver] fix device early return

2020-04-29 Thread GitBox
huajsj commented on pull request #7: URL: https://github.com/apache/incubator-tvm-vta/pull/7#issuecomment-621379576 @zhanghaohit, thanks for the contribution, do we know the root cause for this early return issue? a sleep solution may not always work and would impact performance, we

[GitHub] [incubator-tvm] tqchen edited a comment on pull request #5436: [TFLite Runtime] Re-enable test for remote execution via RPC

2020-04-29 Thread GitBox
tqchen edited a comment on pull request #5436: URL: https://github.com/apache/incubator-tvm/pull/5436#issuecomment-621364933 NOTE: - the ci-cpu is still blocked by https://github.com/apache/incubator-tvm/issues/5455 - but ci-gpu is now updated to sync with the latest state. If we

[incubator-tvm] branch master updated: [BYOC] Bind constant tuples in graph partitioner (#5476)

2020-04-29 Thread zhic
This is an automated email from the ASF dual-hosted git repository. zhic 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 046b0d9 [BYOC] Bind constant tuples in

[GitHub] [incubator-tvm] icemelon9 commented on a change in pull request #5357: [Relay] enable blocking format in x86 conv2d and fold scale axis

2020-04-29 Thread GitBox
icemelon9 commented on a change in pull request #5357: URL: https://github.com/apache/incubator-tvm/pull/5357#discussion_r417472667 ## File path: python/tvm/relay/op/strategy/x86.py ## @@ -84,8 +88,13 @@ def conv2d_strategy_cpu(attrs, inputs, out_type, target): raise

[GitHub] [incubator-tvm] tqchen commented on pull request #5392: [CI] Migrate Tensorflow and Tensorflow lite in CI to 2.1.0

2020-04-29 Thread GitBox
tqchen commented on pull request #5392: URL: https://github.com/apache/incubator-tvm/pull/5392#issuecomment-621363701 NOTE: the mainline ci-gpu now takes in effect This is an automated message from the Apache Git Service. To

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

2020-04-29 Thread GitBox
kevinthesun commented on a change in pull request #4312: URL: https://github.com/apache/incubator-tvm/pull/4312#discussion_r417499071 ## File path: python/tvm/relay/frontend/tensorflow.py ## @@ -612,6 +615,51 @@ def _impl(inputs, attr, params, mod): out =

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5439: TFlite e2e FP32 Object detection model

2020-04-29 Thread GitBox
anijain2305 commented on a change in pull request #5439: URL: https://github.com/apache/incubator-tvm/pull/5439#discussion_r417583390 ## File path: tests/python/frontend/tflite/test_forward.py ## @@ -1933,21 +1937,41 @@ def test_forward_qnn_mobilenet_v3_net(): # SSD Mobilenet

[GitHub] [incubator-tvm] zhiics edited a comment on pull request #5457: [Fix] Add ConstantNode to IsAtomic

2020-04-29 Thread GitBox
zhiics edited a comment on pull request #5457: URL: https://github.com/apache/incubator-tvm/pull/5457#issuecomment-621515297 @MarisaKirisame Sorry for the late response. Yeah, transforming it to ANF should work as well and seems like better fix. Let me try it. BTW, this would also

[GitHub] [incubator-tvm] kevinthesun commented on a change in pull request #5429: [RELAY][TF] Support symbolic newshape for Reshape

2020-04-29 Thread GitBox
kevinthesun commented on a change in pull request #5429: URL: https://github.com/apache/incubator-tvm/pull/5429#discussion_r417650019 ## File path: python/tvm/relay/_parser.py ## @@ -114,7 +114,10 @@ def convert(self, v): def __call__(self, args, attrs, type_args):

[GitHub] [incubator-tvm] kevinthesun commented on pull request #5457: [Fix] Add ConstantNode to IsAtomic

2020-04-29 Thread GitBox
kevinthesun commented on pull request #5457: URL: https://github.com/apache/incubator-tvm/pull/5457#issuecomment-621505667 @MarisaKirisame The current use cases which can trigger is this issue are mainly from TensorFlow OD models. For those models, constant tensors which can be feed into

[GitHub] [incubator-tvm] yongwww commented on a change in pull request #5429: [RELAY][TF] Support symbolic newshape for Reshape

2020-04-29 Thread GitBox
yongwww commented on a change in pull request #5429: URL: https://github.com/apache/incubator-tvm/pull/5429#discussion_r417638357 ## File path: python/tvm/relay/_parser.py ## @@ -114,7 +114,10 @@ def convert(self, v): def __call__(self, args, attrs, type_args):

[GitHub] [incubator-tvm] anijain2305 opened a new pull request #5477: Removing older Object detection TFlite test

2020-04-29 Thread GitBox
anijain2305 opened a new pull request #5477: URL: https://github.com/apache/incubator-tvm/pull/5477 New test will follow up This is an automated message from the Apache Git Service. To respond to the message, please log on

[GitHub] [incubator-tvm] zhiics commented on pull request #5457: [Fix] Add ConstantNode to IsAtomic

2020-04-29 Thread GitBox
zhiics commented on pull request #5457: URL: https://github.com/apache/incubator-tvm/pull/5457#issuecomment-621515297 @MarisaKirisame Sorry for the late response. Yeah, transforming it to ANF should work as well and seems like better fix. Let me try it.

[GitHub] [incubator-tvm] tqchen opened a new pull request #5478: [RUNTIME] Improved Packed FFI for optional.

2020-04-29 Thread GitBox
tqchen opened a new pull request #5478: URL: https://github.com/apache/incubator-tvm/pull/5478 Allows Optional and module to be passed with the right type code. This is an automated message from the Apache Git

[GitHub] [incubator-tvm] tqchen commented on pull request #5478: [RUNTIME] Improved Packed FFI for optional.

2020-04-29 Thread GitBox
tqchen commented on pull request #5478: URL: https://github.com/apache/incubator-tvm/pull/5478#issuecomment-621527940 cc @zhiics @ZihengJiang @yzhliu @jroesch @junrushao1994 This is an automated message from the Apache Git

[GitHub] [incubator-tvm] anijain2305 opened a new pull request #5479: [Relay-TFLite] Quantized activations

2020-04-29 Thread GitBox
anijain2305 opened a new pull request #5479: URL: https://github.com/apache/incubator-tvm/pull/5479 TBD This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use

[GitHub] [incubator-tvm-vta] remotego commented on pull request #7: [pynq_driver] fix device early return

2020-04-29 Thread GitBox
remotego commented on pull request #7: URL: https://github.com/apache/incubator-tvm-vta/pull/7#issuecomment-621581807 Thanks @huajsj @tmoreau89 for pointing out the potential performance issue for this fix. The root cause of the issue is because on line 124, we instruct the VTA to

[GitHub] [incubator-tvm-vta] tmoreau89 commented on a change in pull request #7: [pynq_driver] fix device early return

2020-04-29 Thread GitBox
tmoreau89 commented on a change in pull request #7: URL: https://github.com/apache/incubator-tvm-vta/pull/7#discussion_r417732849 ## File path: src/pynq/pynq_driver.cc ## @@ -126,6 +127,10 @@ class VTADevice { VTAWriteMappedReg(vta_compute_handle_, 0x0, VTA_AUTORESTART);

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #7: [pynq_driver] fix device early return

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #7: URL: https://github.com/apache/incubator-tvm-vta/pull/7#issuecomment-621590481 Thank you @remotego for this logical explanation. The fix makes sense, and is highly likely not to affect performance negatively.

[GitHub] [incubator-tvm] spectrometerHBH opened a new pull request #5483: [TIR][Printer] text format printer considering future parsing use

2020-04-29 Thread GitBox
spectrometerHBH opened a new pull request #5483: URL: https://github.com/apache/incubator-tvm/pull/5483 ## Several Points 1. Rename vars/size_vars/buffers to use name hints to identify them 2. A node is either in META or not. If ref A is put in META, ref B is contained in A, then

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621597493 Thank you for the explanation. Do you mind breaking down what happens in the 32x32 configuration that causes correctness to fail (since the dependence analysis waive is

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621599822 I'll think some more about this problem overnight, thanks for bringing attention to this issue @zhanghaohit @remotego

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621599637 Perhaps one way to look at this is to start with DISTANCE=3 by default. And if the II>1 for the GEMM, we issue a warning telling the user to increase the distance to 4.

[GitHub] [incubator-tvm] tqchen commented on pull request #5483: [TIR][Printer] text format printer considering future parsing use

2020-04-29 Thread GitBox
tqchen commented on pull request #5483: URL: https://github.com/apache/incubator-tvm/pull/5483#issuecomment-621600022 cc @jroesch @antinucleon @junrushao1994 @Hzfengsy @mbrookhart This is an automated message from the

[GitHub] [incubator-tvm-vta] huajsj commented on pull request #7: [pynq_driver] fix device early return

2020-04-29 Thread GitBox
huajsj commented on pull request #7: URL: https://github.com/apache/incubator-tvm-vta/pull/7#issuecomment-621612870 @remotego, Thanks for the detailed explain, but for this problem I think you may have a glance on related pynq driver logic, actually there is no "racing condition" between

[GitHub] [incubator-tvm] anijain2305 commented on pull request #5477: Removing older Object detection TFlite test

2020-04-29 Thread GitBox
anijain2305 commented on pull request #5477: URL: https://github.com/apache/incubator-tvm/pull/5477#issuecomment-621543411 @tqchen This PR is for the web-data PR - https://github.com/dmlc/web-data/pull/247 This is an

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #5: [WIP]Add c++ and python local deploy example

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #5: URL: https://github.com/apache/incubator-tvm-vta/pull/5#issuecomment-621552938 Very exciting development @huajsj ! I'm looking forward to the C++ example! This is an automated message

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #7: [pynq_driver] fix device early return

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #7: URL: https://github.com/apache/incubator-tvm-vta/pull/7#issuecomment-621552736 Thanks @zhanghaohit for the fix. I'm curious when the early completion occurs as @huajsj pointed out. Ideally the driver shouldn't rely on polling and instead use

[GitHub] [incubator-tvm-vta] zhanghaohit commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
zhanghaohit commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621567733 > Thanks @zhanghaohit, for catching this error. I agree with the fact that the dependence should not be hardcoded. However in order to not to add too many parameters in

[GitHub] [incubator-tvm] yzhliu opened a new pull request #5482: [team] add reviewer kparzysz-quic

2020-04-29 Thread GitBox
yzhliu opened a new pull request #5482: URL: https://github.com/apache/incubator-tvm/pull/5482 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-vta] tmoreau89 commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621598201 @remotego I just read your comment that must have been posted as I wrote my reply. Your explanation makes sense, ultimately the critical path in the accumulation is READ

[incubator-tvm] branch master updated (046b0d9 -> 684f2d7)

2020-04-29 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 046b0d9 [BYOC] Bind constant tuples in graph partitioner (#5476) add 684f2d7 [VTA][Runtime] clear sram

[GitHub] [incubator-tvm] zhanghaohit commented on pull request #5471: [VTA][Runtime] fix hardcoded VerifyDep step

2020-04-29 Thread GitBox
zhanghaohit commented on pull request #5471: URL: https://github.com/apache/incubator-tvm/pull/5471#issuecomment-621572608 > Thanks @zhanghaohit for the proposed change, moving away from a hardcoded value is the right move! > > I find the `ACC_DEP_DISTANCE` to be confusing however.

[GitHub] [incubator-tvm-vta] remotego edited a comment on pull request #7: [pynq_driver] fix device early return

2020-04-29 Thread GitBox
remotego edited a comment on pull request #7: URL: https://github.com/apache/incubator-tvm-vta/pull/7#issuecomment-621581807 Thanks @huajsj @tmoreau89 for pointing out the potential performance issue for this fix. The root cause of the issue is because on line 124, we instruct the

[GitHub] [incubator-tvm-vta] remotego commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
remotego commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621593259 > Thanks @zhanghaohit, for catching this error. I agree with the fact that the dependence should not be hardcoded. However in order to not to add too many parameters in

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621598572 I assume that if you have an FPGA that needs to be clocked at a high frequency, you'll likely end up with more cycles.

[GitHub] [incubator-tvm-vta] remotego commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
remotego commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621601302 > Perhaps one way to look at this is to start with DISTANCE=3 by default. And if the II>1 for the GEMM, we issue a warning telling the user to increase the distance to 4.

[GitHub] [incubator-tvm] Menooker commented on pull request #5357: [Relay] enable blocking format in x86 conv2d and fold scale axis

2020-04-29 Thread GitBox
Menooker commented on pull request #5357: URL: https://github.com/apache/incubator-tvm/pull/5357#issuecomment-621567041 > @Menooker Could you share the script that can reproduce the error? It's a bit weird that `_alter_conv2d_layout` receive a conv2d op with `NCHWc` layout. My

[GitHub] [incubator-tvm] huajsj opened a new pull request #5481: [VTA] Fix VTA compile issue

2020-04-29 Thread GitBox
huajsj opened a new pull request #5481: URL: https://github.com/apache/incubator-tvm/pull/5481 Issue1: When doing vta compile in xilinx FPGA, the pynqdriver.cc report can not find Issue2: Run vta on pynq board , libvta.so load failed. solution: fixed VTA.make

[GitHub] [incubator-tvm] tobegit3hub commented on issue #4464: [RFC] Add TVMDSOOp to integrate any TVM operator with TensorFlow

2020-04-29 Thread GitBox
tobegit3hub commented on issue #4464: URL: https://github.com/apache/incubator-tvm/issues/4464#issuecomment-621593883 The PR has been merged and we will close this issue. This is an automated message from the Apache Git

[GitHub] [incubator-tvm] tqchen opened a new pull request #5484: [REFACTOR][RPC][PROCOTOL-CHANGE] Modularize the RPC infra

2020-04-29 Thread GitBox
tqchen opened a new pull request #5484: URL: https://github.com/apache/incubator-tvm/pull/5484 This PR refactors the RPC protocol to make it more modularized. - RPCSession: represent a set of features that need to be implemented - RPCEndPont: End point that forwards the RPCSession

[GitHub] [incubator-tvm] tqchen commented on pull request #5484: [REFACTOR][RPC][PROCOTOL-CHANGE] Modularize the RPC infra

2020-04-29 Thread GitBox
tqchen commented on pull request #5484: URL: https://github.com/apache/incubator-tvm/pull/5484#issuecomment-621598079 cc @FrozenGene @merrymercy @eqy @ZihengJiang @areusch @ajtulloch @antinucleon @junrushao1994 @jroesch @kazum @yzhliu

[GitHub] [incubator-tvm] tqchen commented on pull request #5484: [REFACTOR][RPC][PROCOTOL-CHANGE] Modularize the RPC infra

2020-04-29 Thread GitBox
tqchen commented on pull request #5484: URL: https://github.com/apache/incubator-tvm/pull/5484#issuecomment-621597882 RFC https://discuss.tvm.ai/t/modularize-rpc-infra/6544 This is an automated message from the Apache Git

[incubator-tvm] branch master updated (684f2d7 -> 90b08f5)

2020-04-29 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 684f2d7 [VTA][Runtime] clear sram index in reset (#5470) add 90b08f5 [intrin] a few more math

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621551928 Thanks @zhanghaohit, for catching this error. I agree with the fact that the dependence should not be hardcoded. However in order to not to add too many parameters in the

[GitHub] [incubator-tvm] siju-samuel opened a new pull request #5480: [TFLITE]Argmin & Argmax op support

2020-04-29 Thread GitBox
siju-samuel opened a new pull request #5480: URL: https://github.com/apache/incubator-tvm/pull/5480 @anijain2305 @masahi please help to review this PR. Thanks. This is an automated message from the Apache Git Service.

[GitHub] [incubator-tvm] srkreddy1238 commented on issue #4102: [Relay] Support for Tensorflow 2.0

2020-04-29 Thread GitBox
srkreddy1238 commented on issue #4102: URL: https://github.com/apache/incubator-tvm/issues/4102#issuecomment-621595847 Good to see CI moving to 2.0. On this context. - I have upgraded TF test cases to use pure 2.0 API (with out compat v1, tf.graph, tf.session ...etc.). -

[GitHub] [incubator-tvm-vta] tmoreau89 commented on pull request #8: [Hardware][Xilinx] explicitly specify acc dep distance to avoid hidden pitfall

2020-04-29 Thread GitBox
tmoreau89 commented on pull request #8: URL: https://github.com/apache/incubator-tvm-vta/pull/8#issuecomment-621599402 So to conclude, I agree with you that we may want this parameter to be larger than 2 cycles if the hardware pipeline becomes more complicated. So the big question

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #5360: [QNN] Support CallNode inputs in qnn.concatenate

2020-04-29 Thread GitBox
zhiics commented on a change in pull request #5360: URL: https://github.com/apache/incubator-tvm/pull/5360#discussion_r417496245 ## File path: python/tvm/relay/qnn/op/qnn.py ## @@ -180,15 +180,16 @@ def concatenate(data, The concatenated quantized tensor. """ -

[GitHub] [incubator-tvm] siju-samuel opened a new pull request #5475: [FRONTEND][TFLITE]Logical not op support

2020-04-29 Thread GitBox
siju-samuel opened a new pull request #5475: URL: https://github.com/apache/incubator-tvm/pull/5475 Supported Logical Not for TFLite frontend. @FrozenGene @masahi Please help to review and merge this PR. TIA This

[GitHub] [incubator-tvm] roastduck commented on pull request #5465: [TIR] Convert if_then_else intrinsics to if-statements

2020-04-29 Thread GitBox
roastduck commented on pull request #5465: URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-621159263 Fixed the breaking `fifo_buffer` test by avoiding passing the same buffer as different arguments to a CUDA kernel.

[GitHub] [incubator-tvm] roastduck commented on a change in pull request #5345: [RELAY] Move frontend utils

2020-04-29 Thread GitBox
roastduck commented on a change in pull request #5345: URL: https://github.com/apache/incubator-tvm/pull/5345#discussion_r417265081 ## File path: python/tvm/relay/qnn/op/legalizations.py ## @@ -20,8 +20,8 @@ import tvm from tvm import relay +import numpy as np Review

[GitHub] [incubator-tvm] Menooker commented on a change in pull request #5357: [Relay] enable blocking format in x86 conv2d and fold scale axis

2020-04-29 Thread GitBox
Menooker commented on a change in pull request #5357: URL: https://github.com/apache/incubator-tvm/pull/5357#discussion_r417267279 ## File path: python/tvm/relay/op/strategy/x86.py ## @@ -84,8 +88,13 @@ def conv2d_strategy_cpu(attrs, inputs, out_type, target): raise

[GitHub] [incubator-tvm] Menooker commented on pull request #5357: [Relay] enable blocking format in x86 conv2d and fold scale axis

2020-04-29 Thread GitBox
Menooker commented on pull request #5357: URL: https://github.com/apache/incubator-tvm/pull/5357#issuecomment-621165175 @icemelon9 If you unchenge these, you will get ``` File "/home/menooker/work/mobilenet/tvm/python/tvm/relay/op/nn/_nn.py", line 97, in

[GitHub] [incubator-tvm] mbaret commented on a change in pull request #5345: [RELAY] Move frontend utils

2020-04-29 Thread GitBox
mbaret commented on a change in pull request #5345: URL: https://github.com/apache/incubator-tvm/pull/5345#discussion_r417275917 ## File path: python/tvm/relay/qnn/op/legalizations.py ## @@ -20,8 +20,8 @@ import tvm from tvm import relay +import numpy as np Review

[incubator-tvm] branch master updated: [Frontend][TFLite] support for FILL and SPLIT_V operators (#5330)

2020-04-29 Thread zhaowu
This is an automated email from the ASF dual-hosted git repository. zhaowu 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 063ba63 [Frontend][TFLite] support for

[GitHub] [incubator-tvm] maheshambule opened a new pull request #5474: [Frontend][TFLite] ADD_N operator

2020-04-29 Thread GitBox
maheshambule opened a new pull request #5474: URL: https://github.com/apache/incubator-tvm/pull/5474 - added support for ADD_N operator - refactored some of the ADD code This is an automated message from the Apache Git

[GitHub] [incubator-tvm] siju-samuel commented on pull request #5472: [TENSORFLOW]TF Addons activations support added

2020-04-29 Thread GitBox
siju-samuel commented on pull request #5472: URL: https://github.com/apache/incubator-tvm/pull/5472#issuecomment-621154395 ` Running relay Tensorflow frontend test... = test session starts == platform linux -- Python 3.6.10,