Go to file
Diego Caballero 7dd198852b [mlir][Affine] Add support for multi-store producer fusion
This patch adds support for producer-consumer fusion scenarios with
multiple producer stores to the AffineLoopFusion pass. The patch
introduces some changes to the producer-consumer algorithm, including:

* For a given consumer loop, producer-consumer fusion iterates over its
producer candidates until a fixed point is reached.

* Producer candidates are gathered beforehand for each iteration of the
consumer loop and visited in reverse program order (not strictly guaranteed)
to maximize the number of loops fused per iteration.

In general, these changes were needed to simplify the multi-store producer
support and remove some of the workarounds that were introduced in the past
to support more fusion cases under the single-store producer limitation.

This patch also preserves the existing functionality of AffineLoopFusion with
one minor change in behavior. Producer-consumer fusion didn't fuse scenarios
with escaping memrefs and multiple outgoing edges (from a single store).
Multi-store producer scenarios will usually (always?) have multiple outgoing
edges so we couldn't fuse any with escaping memrefs, which would greatly limit
the applicability of this new feature. Therefore, the patch enables fusion for
these scenarios. Please, see modified tests for specific details.

Reviewed By: andydavis1, bondhugula

Differential Revision: https://reviews.llvm.org/D92876
2021-01-20 19:03:07 +02:00
.github [github] Move repo lockdown config into llvm-project repo 2021-01-11 16:20:08 -08:00
clang Implement dynamic mapAnyOf in terms of ASTNodeKinds 2021-01-20 15:53:05 +00:00
clang-tools-extra Revert "Following up on PR48517, fix handling of template arguments that refer" 2021-01-20 15:55:35 +01:00
compiler-rt [CMake] Remove dead code setting policies to NEW 2021-01-19 17:19:36 +02:00
debuginfo-tests [DebugInfo][dexter] Tweak dexter test for merged values 2021-01-19 12:45:31 +00:00
flang [flang] Refine WhyNotModifiable() 2021-01-19 11:44:51 -08:00
libc [libc] Extend the current fenv functions to aarch64. 2021-01-19 12:47:54 -08:00
libclc libclc: Use find_package to find Python 3 and require it 2020-10-01 22:31:33 +02:00
libcxx [libc++] Split re.alg tests into locale-dependent and independent tests 2021-01-20 15:48:50 +00:00
libcxxabi [CMake] Remove dead code setting policies to NEW 2021-01-19 17:19:36 +02:00
libunwind [CMake] Remove dead code setting policies to NEW 2021-01-19 17:19:36 +02:00
lld [LLD][ELF] Correct test temporary file paths 2021-01-20 11:46:11 +00:00
lldb Revert "Following up on PR48517, fix handling of template arguments that refer" 2021-01-20 15:55:35 +01:00
llvm [AMDGPU] pin lit test divergent-unswitch.ll to the old pass manager 2021-01-20 22:02:09 +05:30
mlir [mlir][Affine] Add support for multi-store producer fusion 2021-01-20 19:03:07 +02:00
openmp [OpenMP][NVPTX] Replaced CUDA builtin vars with LLVM intrinsics 2021-01-20 12:02:06 -05:00
parallel-libs Reapply "Try enabling -Wsuggest-override again, using add_compile_options instead of add_compile_definitions for disabling it in unittests/ directories." 2020-07-22 17:50:19 -07:00
polly [polly][NewPM][test] Fix polly tests under -enable-new-pm 2021-01-19 12:38:58 -08:00
pstl [pstl] Replace direct use of assert() with _PSTL_ASSERT 2020-11-02 18:35:54 -05:00
runtimes [MSVC] Don't add -nostdinc++ -isystem to runtimes builds 2021-01-15 13:22:07 -08:00
utils/arcanist Fix arc lint's clang-format rule: only format the file we were asked to format. 2020-10-11 14:24:23 -07:00
.arcconfig Set the target branch for `arc land` to main 2020-12-07 21:57:32 +00:00
.arclint PR46997: don't run clang-format on clang's testcases. 2020-08-04 17:53:25 -07:00
.clang-format
.clang-tidy - Update .clang-tidy to ignore parameters of main like functions for naming violations in clang and llvm directory 2020-01-31 16:49:45 +00:00
.git-blame-ignore-revs NFC: Add whitespace-changing revisions to .git-blame-ignore-revs 2020-09-21 20:17:24 -04:00
.gitignore Reland [lldb][docs] Use sphinx instead of epydoc to generate LLDB's Python reference 2021-01-17 12:13:01 +01:00
CONTRIBUTING.md
README.md Revert "This is a test commit" 2020-10-21 09:34:15 +08:00

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.