maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
350,946 Commits 23 Branches 0 Tags 2.2 GiB
C++ 39.1%
LLVM 35.7%
C 12.1%
Assembly 8.9%
Python 1.1%
Other 2.7%
Go to file
Nicolas Vasilache 882ba48474 [mlir][Linalg] Create a tool to generate named Linalg ops from a Tensor Comprehensions-like specification. 
Summary:

This revision adds a tool that generates the ODS and C++ implementation for "named" Linalg ops according to the [RFC discussion](https://llvm.discourse.group/t/rfc-declarative-named-ops-in-the-linalg-dialect/745).

While the mechanisms and language aspects are by no means set in stone, this revision allows connecting the pieces end-to-end from a mathematical-like specification.

Some implementation details and short-term decisions taken for the purpose of bootstrapping and that are not set in stone include:

    1. using a "[Tensor Comprehension](https://arxiv.org/abs/1802.04730)-inspired" syntax
    2. implicit and eager discovery of dims and symbols when parsing
    3. using EDSC ops to specify the computation (e.g. std_addf, std_mul_f, ...)

A followup revision will connect this tool to tablegen mechanisms and allow the emission of named Linalg ops that automatically lower to various loop forms and run end to end.

For the following "Tensor Comprehension-inspired" string:

```
    def batch_matmul(A: f32(Batch, M, K), B: f32(K, N)) -> (C: f32(Batch, M, N)) {
      C(b, m, n) = std_addf<k>(std_mulf(A(b, m, k), B(k, n)));
    }
```

With -gen-ods-decl=1, this emits (modulo formatting):

```
      def batch_matmulOp : LinalgNamedStructured_Op<"batch_matmul", [
        NInputs<2>,
        NOutputs<1>,
        NamedStructuredOpTraits]> {
          let arguments = (ins Variadic<LinalgOperand>:$views);
          let results = (outs Variadic<AnyRankedTensor>:$output_tensors);
          let extraClassDeclaration = [{
            llvm::Optional<SmallVector<StringRef, 8>> referenceIterators();
            llvm::Optional<SmallVector<AffineMap, 8>> referenceIndexingMaps();
            void regionBuilder(ArrayRef<BlockArgument> args);
          }];
          let hasFolder = 1;
      }
```

With -gen-ods-impl, this emits (modulo formatting):

```
      llvm::Optional<SmallVector<StringRef, 8>> batch_matmul::referenceIterators() {
          return SmallVector<StringRef, 8>{ getParallelIteratorTypeName(),
                                            getParallelIteratorTypeName(),
                                            getParallelIteratorTypeName(),
                                            getReductionIteratorTypeName() };
      }
      llvm::Optional<SmallVector<AffineMap, 8>> batch_matmul::referenceIndexingMaps()
      {
        MLIRContext *context = getContext();
        AffineExpr d0, d1, d2, d3;
        bindDims(context, d0, d1, d2, d3);
        return SmallVector<AffineMap, 8>{
            AffineMap::get(4, 0, {d0, d1, d3}),
            AffineMap::get(4, 0, {d3, d2}),
            AffineMap::get(4, 0, {d0, d1, d2}) };
      }
      void batch_matmul::regionBuilder(ArrayRef<BlockArgument> args) {
        using namespace edsc;
        using namespace intrinsics;
        ValueHandle _0(args[0]), _1(args[1]), _2(args[2]);

        ValueHandle _4 = std_mulf(_0, _1);
        ValueHandle _5 = std_addf(_2, _4);
        (linalg_yield(ValueRange{ _5 }));
      }
```

Differential Revision: https://reviews.llvm.org/D77067
 		2020-04-10 13:59:25 -04:00
clang Implement `-fsanitize-coverage-whitelist` and `-fsanitize-coverage-blacklist` for clang 2020-04-10 10:44:03 -07:00
clang-tools-extra [clang-tidy] Add check to find calls to NSInvocation methods under ARC that don't have proper object argument lifetimes. 2020-04-10 08:51:21 -07:00
compiler-rt Implement `-fsanitize-coverage-whitelist` and `-fsanitize-coverage-blacklist` for clang 2020-04-10 10:44:03 -07:00
debuginfo-tests [Dexter] Add support for Windows to regression test suite. 2020-03-31 10:18:12 +01:00
flang [flang] [NFC] Adjust README.md for upstreaming. 2020-04-09 21:15:48 +01:00
libc [libc] Change minimum cmake requirement. 2020-04-09 20:42:55 -07:00
libclc libclc: cmake configure should depend on file list 2020-02-25 04:43:14 -05:00
libcxx [libc++] Fix recursive instantiation in std::array. 2020-04-09 17:42:10 -04:00
libcxxabi [libc++abi] Enable the new libc++ testing format by default 2020-04-07 09:16:06 -04:00
libunwind [libunwind] add hexagon support 2020-04-10 04:24:10 -05:00
lld [AArch64InstPrinter] Change printAlignedLabel to print the target address in hexadecimal form 2020-04-10 09:21:09 -07:00
lldb Attempt to fix a compile error reported with older compilers and libstdc++ 2020-04-10 10:34:44 -07:00
llvm [Pipeliner] Fix the bug in pragma that disables the pipeliner. 2020-04-10 12:52:16 -05:00
mlir [mlir][Linalg] Create a tool to generate named Linalg ops from a Tensor Comprehensions-like specification. 2020-04-10 13:59:25 -04:00
openmp [OpenMP] Put old APIs back and added new _async series for backward compatibility 2020-04-09 22:40:58 -04:00
parallel-libs [arcconfig] Delete subproject arcconfigs 2020-02-24 16:20:36 -08:00
polly [NFC] Modernize misc. uses of Align/MaybeAlign APIs. 2020-04-06 17:53:04 -07:00
pstl [pstl] A hot fix for exclusive_scan (+ lost enable_if in declaration) 2020-03-17 16:22:24 -04:00
utils/arcanist Use in-tree clang-format-diff.py as Arcanist linter 2020-04-06 12:02:20 -04:00
.arcconfig [arcconfig] Default base to previous revision 2020-02-24 16:20:25 -08:00
.arclint Setup clang-format as an Arcanist linter 2020-03-30 15:02:33 -04:00
.clang-format
…
.clang-tidy
…
.git-blame-ignore-revs Add some libc++ revisions to .git-blame-ignore-revs 2020-03-17 17:30:20 -04:00
.gitignore
…
CONTRIBUTING.md
…
README.md Add missing hyphens 2020-04-08 08:21:53 +02:00

README.md

The LLVM Compiler Infrastructure

This directory and its sub-directories contain source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and run-time environments.

The README briefly describes how to get started with building LLVM. For more information on how to contribute to the LLVM project, please take a look at the Contributing to LLVM guide.

Getting Started with the LLVM System

Taken from https://llvm.org/docs/GettingStarted.html.

Overview

Welcome to the LLVM project!

The LLVM project has multiple components. The core of the project is itself called "LLVM". This contains all of the tools, libraries, and header files needed to process intermediate representations and converts it into object files. Tools include an assembler, disassembler, bitcode analyzer, and bitcode optimizer. It also contains basic regression tests.

C-like languages use the Clang front end. This component compiles C, C++, Objective-C, and Objective-C++ code into LLVM bitcode -- and from there into object files, using LLVM.

Other components include: the libc++ C++ standard library, the LLD linker, and more.

Getting the Source Code and Building LLVM

The LLVM Getting Started documentation may be out of date. The Clang Getting Started page might have more accurate information.

This is an example work-flow and configuration to get and build the LLVM source:

  1. Checkout LLVM (including related sub-projects like Clang):

    • git clone https://github.com/llvm/llvm-project.git

    • Or, on windows, git clone --config core.autocrlf=false https://github.com/llvm/llvm-project.git

  2. Configure and build LLVM and Clang:

    • cd llvm-project

    • mkdir build

    • cd build

    • cmake -G <generator> [options] ../llvm

      Some common build system generators are:

      • Ninja --- for generating Ninja build files. Most llvm developers use Ninja.
      • Unix Makefiles --- for generating make-compatible parallel makefiles.
      • Visual Studio --- for generating Visual Studio projects and solutions.
      • Xcode --- for generating Xcode projects.

      Some Common options:

      • -DLLVM_ENABLE_PROJECTS='...' --- semicolon-separated list of the LLVM sub-projects you'd like to additionally build. Can include any of: clang, clang-tools-extra, libcxx, libcxxabi, libunwind, lldb, compiler-rt, lld, polly, or debuginfo-tests.

        For example, to build LLVM, Clang, libcxx, and libcxxabi, use -DLLVM_ENABLE_PROJECTS="clang;libcxx;libcxxabi".

      • -DCMAKE_INSTALL_PREFIX=directory --- Specify for directory the full path name of where you want the LLVM tools and libraries to be installed (default /usr/local).

      • -DCMAKE_BUILD_TYPE=type --- Valid options for type are Debug, Release, RelWithDebInfo, and MinSizeRel. Default is Debug.

      • -DLLVM_ENABLE_ASSERTIONS=On --- Compile with assertion checks enabled (default is Yes for Debug builds, No for all other build types).

    • cmake --build . [-- [options] <target>] or your build system specified above directly.

      • The default target (i.e. ninja or make) will build all of LLVM.

      • The check-all target (i.e. ninja check-all) will run the regression tests to ensure everything is in working order.

      • CMake will generate targets for each tool and library, and most LLVM sub-projects generate their own check-<project> target.

      • Running a serial build will be slow. To improve speed, try running a parallel build. That's done by default in Ninja; for make, use the option -j NNN, where NNN is the number of parallel jobs, e.g. the number of CPUs you have.

    • For more information see CMake

Consult the Getting Started with LLVM page for detailed information on configuring and compiling LLVM. You can visit Directory Layout to learn about the layout of the source code tree.