maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
304,439 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
Nicolai Haehnle a9cc92c247 AMDGPU: Fix various issues around the VirtReg2Value mapping 
Summary:
The VirtReg2Value mapping is crucial for getting consistently
reliable divergence information into the SelectionDAG. This
patch fixes a bunch of issues that lead to incorrect divergence
info and introduces tight assertions to ensure we don't regress:

1. VirtReg2Value is generated lazily; there were some cases where
   a lookup was performed before all relevant virtual registers were
   created, leading to an out-of-sync mapping. Those cases were:

  - Complex code to lower formal arguments that generated CopyFromReg
    nodes from live-in registers (fixed by never querying the mapping
    for live-in registers).

  - Code that generates CopyToReg for formal arguments that are used
    outside the entry basic block (fixed by never querying the
    mapping for Register nodes, which don't need the divergence info
    anyway).

2. For complex values that are lowered to a sequence of registers,
   all registers must be reflected in the VirtReg2Value mapping.

I am not adding any new tests, since I'm not actually aware of any
bugs that these problems are causing with trunk as-is. However,
I recently added a test case (in r346423) which fails when D53283 is
applied without this change. Also, the new assertions should provide
most of the effective test coverage.

There is one test change in sdwa-peephole.ll. The underlying issue
is that since the divergence info is now correct, the DAGISel will
select V_OR_B32 directly instead of S_OR_B32. This leads to an extra
COPY which affects the behavior of MachineLICM in a way that ends up
with the S_MOV_B32 with the constant in a different basic block than
the V_OR_B32, which is presumably what defeats the peephole.

Reviewers: alex-t, arsenm, rampitec

Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D54340

llvm-svn: 348049
 		2018-11-30 22:55:29 +00:00
clang [analyzer] Deleting unnecessary test file 2018-11-30 22:32:17 +00:00
clang-tools-extra [clangd] Populate include graph during static indexing action. 2018-11-30 16:59:00 +00:00
compiler-rt Add a new interceptor for getvfsstat(2) from NetBSD 2018-11-30 19:43:53 +00:00
debuginfo-tests Set config.lit_tools_dir, which is needed by lit.llvm.initialize. 2018-11-06 21:54:27 +00:00
libclc travis: Add cmake build 2018-11-27 16:07:21 +00:00
libcxx First part of P0482 - Establish that char8_t is an integral type, and that numeric_limits<char8_t> is valid and sane. (second try) 2018-11-29 23:21:18 +00:00
libcxxabi [libcxx] Remove bad_array_length 2018-11-29 19:44:57 +00:00
libunwind [CMake] Passthrough CFLAGS when checking the compiler-rt path 2018-11-14 00:09:26 +00:00
lld Inline a function template that is used only once. NFC. 2018-11-30 18:19:15 +00:00
lldb Add a test to verify that lldb can load a kext binary. 2018-11-30 21:33:00 +00:00
llgo Update copyright year to 2018. 2018-06-18 12:22:17 +00:00
llvm AMDGPU: Fix various issues around the VirtReg2Value mapping 2018-11-30 22:55:29 +00:00
openmp [OPENMP][NVPTX]Make runtime compatible with the original runtime. 2018-11-30 16:52:38 +00:00
parallel-libs Update copyright year to 2018. 2018-06-18 12:22:17 +00:00
polly [CMake] Fix generation of exported targets in build directory 2018-11-06 15:18:17 +00:00
README.md Update the project name in README.md 2018-10-19 00:03:01 +00:00

README.md

The LLVM Compiler Infrastructure

This directory and its subdirectories contain source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and runtime environments.