llvm-project/llvm
Craig Topper a55b483bb5 [AVX-512] Correctly preserve the passthru semantics of the FMA scalar intrinsics
Summary:
Scalar intrinsics have specific semantics about the which input's upper bits are passed through to the output. The same input is also supposed to be the input we use for the lower element when the mask bit is 0 in a masked operation. We aren't currently keeping these semantics with instruction selection.

This patch corrects this by introducing new scalar FMA ISD nodes that indicate whether operand 1(one of the multiply inputs) or operand 3(the additon/subtraction input) should pass thru its upper bits.

We use this information to select 213/132 form for the operand 1 version and the 231 form for the operand 3 version.

We also use this information to suppress combining FNEG operations on the passthru input since semantically the passthru bits aren't negated. This is stronger than the earlier check added for a user being SELECTS so we can remove that.

This fixes PR30913.

Reviewers: delena, zvi, v_klochkov

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D27144

llvm-svn: 289190
2016-12-09 06:42:28 +00:00
..
bindings Fix go binding to adapt the new attribute API 2016-11-18 10:11:02 +00:00
cmake Re-commit r289184, "Support: Use a 64-bit seek in raw_fd_ostream::seek()." with a configure-time check for lseek64. 2016-12-09 05:20:43 +00:00
docs IR, X86: Understand !absolute_symbol metadata on global variables. 2016-12-08 19:01:00 +00:00
examples Prune unused libdeps. 2016-12-08 15:28:02 +00:00
include Re-commit r289184, "Support: Use a 64-bit seek in raw_fd_ostream::seek()." with a configure-time check for lseek64. 2016-12-09 05:20:43 +00:00
lib [AVX-512] Correctly preserve the passthru semantics of the FMA scalar intrinsics 2016-12-09 06:42:28 +00:00
projects
resources
runtimes [CMake] Make the runtimes directory work with bootstrap builds 2016-10-19 21:50:25 +00:00
test [AVX-512] Correctly preserve the passthru semantics of the FMA scalar intrinsics 2016-12-09 06:42:28 +00:00
tools [ObjectYAML] Support for DWARF debug_aranges 2016-12-09 00:26:44 +00:00
unittests Fix ASAN buildbots by fixing a double free crash. 2016-12-08 16:57:04 +00:00
utils Summary: Currently there is no way to disable deprecated warning from asm like this 2016-12-05 23:55:13 +00:00
.arcconfig
.clang-format
.clang-tidy
.gitignore
CMakeLists.txt [CMake] Fixing clang standalone build 2016-12-06 17:09:29 +00:00
CODE_OWNERS.TXT CODE_OWNERS: Take ownership of IR Linker as discussed on llvm-dev 2016-12-02 14:06:53 +00:00
CREDITS.TXT Test Commit, removing a blank line in CREDITS.TXT 2016-11-24 15:40:19 +00:00
LICENSE.TXT
LLVMBuild.txt
README.txt Test commit, deleted empty line at the end of README.txt 2016-11-07 18:31:21 +00:00
RELEASE_TESTERS.TXT
configure
llvm.spec.in

README.txt

Low Level Virtual Machine (LLVM)
================================

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

LLVM is open source software. You may freely distribute it under the terms of
the license agreement found in LICENSE.txt.

Please see the documentation provided in docs/ for further
assistance with LLVM, and in particular docs/GettingStarted.rst for getting
started with LLVM and docs/README.txt for an overview of LLVM's
documentation setup.

If you are writing a package for LLVM, see docs/Packaging.rst for our
suggestions.