Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[CodeGen] Add build config option disable_assert to control whether to generate assert #4340

Merged
merged 6 commits into from
Nov 15, 2019

Conversation

FrozenGene
Copy link
Member

@FrozenGene FrozenGene commented Nov 14, 2019

Currently, we will generate assert stmt, which will make us see many assert stmt in LLVM IR. It will Interference our focus.

The usage is simple:

with tvm.build_config(disable_assert=True):
    tvm.build(...)

disable_assert default value is false.

Related discuss:
https://discuss.tvm.ai/t/disable-assert-in-runtime/2152/4

@tqchen

Copy link
Member

@tqchen tqchen left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actually, it would be great if we can do it at an earlier point, and add a pass to remove assert. This will allow the same pass to work for both LLVM and C backend

@FrozenGene
Copy link
Member Author

Actually, it would be great if we can do it at an earlier point, and add a pass to remove assert. This will allow the same pass to work for both LLVM and C backend

@tqchen I tried to implement one IRPass (like SkipAssert) to remove assert in BuildStmt https://github.com/apache/incubator-tvm/blob/master/src/codegen/build_module.cc#L389. However, I find that during lower https://github.com/apache/incubator-tvm/blob/master/src/codegen/build_module.cc#L444, we will still produce AssertStmt internally. Do you have any good suggestion?

For CodeGenC, one way could be like CodeGenCPU:

void CodeGenC::VisitStmt_(const AssertStmt* op) {
    if (!BuildConfig::Current()->disable_assert) {
        std::string cond = PrintExpr(op->condition);
        PrintIndent();
        if (const auto* str = op->message.as<StringImm>()) {
            // GLOG style check
           stream << "CHECK(" << cond << ") << \"" << str->value << "\";\n";
        } else {
           stream << "assert(" << cond << ");\n";
       }
       this->PrintStmt(op->body);
    }
}

@tqchen
Copy link
Member

tqchen commented Nov 15, 2019

We can do it one step before the final codegen

@FrozenGene
Copy link
Member Author

We can do it one step before the final codegen

@tqchen please review it again. I add one pass SkipAssert called on the final codegen in Build function.

@tqchen tqchen merged commit b0b16a0 into apache:master Nov 15, 2019
@tqchen
Copy link
Member

tqchen commented Nov 15, 2019

Thanks @FrozenGene !

zxy844288792 pushed a commit to zxy844288792/tvm that referenced this pull request Nov 15, 2019
zxy844288792 pushed a commit to zxy844288792/tvm that referenced this pull request Nov 15, 2019
@FrozenGene FrozenGene deleted the assert branch November 18, 2019 02:16
kevinthesun pushed a commit to neo-ai/tvm that referenced this pull request Nov 25, 2019
* [TOPI][OP] Support Faster-RCNN Proposal OP on CPU (apache#4297)

* Support Proposal operator on CPU.

* PyLint space issue

* PyLint space issue

* Pylint singleton-comparison issue

* [QNN][Legalize] Specialize for Platforms without any fast Int8 arithmetic units. (apache#4307)

* fix error when memory_id is VTA_MEM_ID_OUT (apache#4330)

* [CI][DOCKER] Add ONNX runtime dep (apache#4314)

* [DOCKER] Add ONNX runtime dep

* Improve ci script

* [QNN] Quantize - Fixing the sequence of lowering. (apache#4316)

* [QNN] Use Int16 upcast in Fallback Conv2D. Fix test names. (apache#4329)

* [doc][fix] fix sphinx parsing for pass infra tutorial (apache#4337)

* change ci image version (apache#4313)

* [Codegen] remove fp16 function override for cuda  (apache#4331)

* add volatile override back

* [codegen] remove fp16 function override for cuda

* [CI] Set workspace to be per executor (apache#4336)

* [Build][Windows] Fix Windows build by including cctype (apache#4319)

* Fix build

* dummy change to retrigger CI

* dummy change to retrigger ci

* dummy change to retrigger ci

* Enable hipModuleGetGlobal() (apache#4321)

* [Relay][Pass] Add pass to remove unused functions in relay module (apache#4334)

* [Relay][Pass] Add pass to remove unused functions in relay module

* Add tests

* Fix lint

* Fix visit order

* Add pass argument

* Fix

* Add support for quant. mul operator in tflite frontend (apache#4283)

A test for qnn_mul has to be added when the qnn elemwise tests (apache#4282) get merged.

* Add topi.nn.fifo_buffer to TVM doc (apache#4343)

* Solve custom model of prelu (apache#4326)

* Deprecate NNVM warning msg (apache#4333)

* [Contrib] Add MKL DNN option (apache#4323)

* [Contrib] Add MKL DNN

* update

* update

* [Relay][Frontend][TF] Fix transpose when axes is not a param (apache#4327)

* [Relay][Frontend][TF] Use _infer_value_simulated when axes is not a const to Transpose

* uncomment tests

* dummy change to retrigger ci

* [RUNTIME] Add device query for AMD GcnArch (apache#4341)

* add gcnArch query

* kGcnArch query for cuda is a no-op

* [Test][Relay][Pass] Add test case for lambda lift (apache#4317)

* [Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth (apache#4271)

* imp module is deprecated (apache#4275)

* [VTA] Bug fix for padded load with large inputs (apache#4293)

* bug fix for padded load with large inputs

* Update TensorLoad.scala

* Update test_vta_insn.py

* fix inconsistent tag name (apache#4134)

* [CodeGen] Add build config option disable_assert to control whether to generate assert (apache#4340)

* Bump up CUDA log version in tophub.py (apache#4347)

* Add check to ensure input file was successfully opened in NNVM deploy code demo (apache#4315)

* [COMMUNITY] Add DISCLAIMER, KEYS for ASF release (apache#4345)

* [COMMUNITY] Add DISCLAIMER, KEYS for ASF release

* Add file name spec

* [Relay][VM][Interpreter] Enable first-class constructors in VM and interpreter via eta expansion (apache#4218)

* Fix constructor pretty printing

* Make Module::HasDef name consistent with API

* Add VM constructor compilation via eta expansion

* Lint

* Fix CI

* Fix failing test

* Address comment

* Retrigger CI

* Retrigger CI

* Update dmlc_tvm_commit_id.txt
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants