[CodeGen]Support Ahead Compilation in MLIR JIT #10182
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: daquexian <daquexian566@gmail.com> Co-authored-by: oneflow-ci-bot <ci-bot@oneflow.org> Co-authored-by: WangXingyu <1908865287@qq.com> Co-authored-by: daquexian <daquexian566@gmail.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> Co-authored-by: Peihong Liu <mosout@qq.com> Co-authored-by: zhao di <54237695+Alokia@users.noreply.github.com> Co-authored-by: Juncheng <liujuncheng1022@gmail.com> Co-authored-by: Wang Yi <53533850+marigoold@users.noreply.github.com> Co-authored-by: Xiaoyu Xu <xiaoyulink@gmail.com>
howin98
requested review from
daquexian,
jackalcooper,
hjchen2 and
BBuf
as code owners
|
Code got formatted by CI. Please request CI again if you still want to have this PR merged. If the PR is from a forked repo, please download the patch files from the GitHub Actions web page and apply them locally. |
BBuf
reviewed
Apr 24, 2023
oneflow/ir/lib/OneFlow/Passes.cpp
Outdated
| @@ -1024,8 +1024,9 @@ void AddLowerToLinalgMemRefPasses(PassManager& pm) { | |||
| tosa::createTosaMakeBroadcastablePass()); // tosa-make-broadcastable | |||
| pm.addPass(createCSEPass()); // cse | |||
| pm.addNestedPass<func::FuncOp>(tosa::createTosaToLinalg()); // tosa-to-linalg-on-tensors | |||
| pm.addNestedPass<func::FuncOp>( | |||
| createLinalgElementwiseOpFusionPass()); // linalg-fuse-elementwise-ops | |||
| // pm.addNestedPass<func::FuncOp>( | |||
There was a problem hiding this comment.
恢复了，这个是之前为了生成中间变量测试用的
Comment on lines
147
to
172
| std::string convertFuncToByte(func::FuncOp& func, const StringAttr& device_tag, | ||
| bool compile_to_llvm) { | ||
| mlir::DialectRegistry registry; | ||
| registry | ||
| .insert<mlir::oneflow::OneFlowDialect, mlir::func::FuncDialect, mlir::memref::MemRefDialect, | ||
| mlir::tosa::TosaDialect, mlir::linalg::LinalgDialect, mlir::tensor::TensorDialect>(); | ||
| mlir::MLIRContext mlir_ctx(registry); | ||
|
|
||
| std::string mlir; | ||
| llvm::raw_string_ostream os_mlir(mlir); | ||
| mlir::writeBytecodeToFile(func, os_mlir); | ||
| if (!compile_to_llvm) return mlir; | ||
|
|
||
| mlir::OwningOpRef<mlir::ModuleOp> module = | ||
| ::mlir::parseSourceString<mlir::ModuleOp>(mlir, &mlir_ctx); | ||
| mlir::registerLLVMDialectTranslation(registry); | ||
| if (::oneflow::ParseBooleanFromEnv("ONEFLOW_MLIR_STDOUT", false)) { func->print(llvm::outs()); } | ||
| getLowerFunction(device_tag)(&mlir_ctx, *module); | ||
| if (::oneflow::ParseBooleanFromEnv("ONEFLOW_MLIR_STDOUT", false)) { func->print(llvm::outs()); } | ||
| (*module)->setAttr(jit::RAW_GRAPH, StringAttr::get(&mlir_ctx, mlir)); | ||
|
|
||
| std::string byte; | ||
| llvm::raw_string_ostream os_byte(byte); | ||
| mlir::writeBytecodeToFile(*module, os_byte); | ||
| return byte; | ||
| } |
|
CI failed when running job: Build cpu. PR label automerge has been removed |
BBuf
reviewed
Apr 24, 2023
| mlir::LogicalResult matchAndRewrite(func::FuncOp op, | ||
| mlir::PatternRewriter& rewriter) const override { | ||
| auto [is_legal, list] = getAllocInfoList(op); | ||
| if (!is_legal) { return failure(); } |
There was a problem hiding this comment.
这里有点问题，需要后面用one shot buffize和一些其他的操作处理一下，我这里写一个TODO
BBuf
approved these changes
Apr 24, 2023
| std::string mlir; | ||
| llvm::raw_string_ostream os_mlir(mlir); | ||
| function->print(os_mlir); | ||
| std::string byte = convertFuncToByte(function); |
There was a problem hiding this comment.
这个pr有问题，我想把这个pr的改动移动到tmp buffer里面，但是不小心把tmp buffer移动到了这个pr里面，其实这部分代码还没写好，我才反应过来
auto-merge was automatically disabled
April 24, 2023 08:12
Pull request was closed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.