llvm-project/llvm
Zvi Rackover c1d5955684 [X86] Unsigned saturation subtraction canonicalization [the backend part]
Summary:
On behalf of julia.koval@intel.com

The patch transforms canonical version of unsigned saturation, which is sub(max(a,b),a) or sub(a,min(a,b)) to special psubus insturuction on targets, which support it(8bit and 16bit uints).
umax(a,b) - b -> subus(a,b)
a - umin(a,b) -> subus(a,b)

There is also extra case handled, when right part of sub is 32 bit and can be truncated, using UMIN(this transformation was discussed in https://reviews.llvm.org/D25987).

The example of special case code:

```
void foo(unsigned short *p, int max, int n) {

  int i;
  unsigned m;
  for (i = 0; i < n; i++) {
    m = *--p;
    *p = (unsigned short)(m >= max ? m-max : 0);
  }
}
```
Max in this example is truncated to max_short value, if it is greater than m, or just truncated to 16 bit, if it is not. It is vaid transformation, because if max > max_short, result of the expression will be zero.

Here is the table of types, I try to support, special case items are bold:

| Size | 128 | 256 | 512
| -----  | -----  | -----   | -----
| i8 | v16i8 | v32i8 | v64i8
| i16 | v8i16 | v16i16 | v32i16
| i32 | | **v8i32** | **v16i32**
| i64 | | | **v8i64**

Reviewers: zvi, spatel, DavidKreitzer, RKSimon

Reviewed By: zvi

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D37534

llvm-svn: 315237
2017-10-09 20:01:10 +00:00
..
bindings
cmake Bring r314809 back. 2017-10-04 20:27:01 +00:00
docs llvm-dwarfdump: Add an option to collect debug info quality metrics. 2017-10-06 20:24:34 +00:00
examples Fix broken links to the Itanium CXX ABI 2017-09-12 00:19:11 +00:00
include [MC] Use a unique_ptr<MCAssembler> for MCObjectStreamer's Assembler member. 2017-10-09 18:11:04 +00:00
lib [X86] Unsigned saturation subtraction canonicalization [the backend part] 2017-10-09 20:01:10 +00:00
projects
resources
runtimes [CMake][runtimes] Use the same configuration for non-target and "default" target 2017-09-08 22:26:50 +00:00
test [X86] Unsigned saturation subtraction canonicalization [the backend part] 2017-10-09 20:01:10 +00:00
tools Fix some C++ value / reference semantics issues. 2017-10-09 18:50:29 +00:00
unittests Remove unused variables. No functionality change. 2017-10-08 21:23:02 +00:00
utils [globalisel] Add support for ValueType operands in patterns. 2017-10-09 18:14:53 +00:00
.arcconfig
.clang-format
.clang-tidy
.gitignore
CMakeLists.txt Revert "[CMake] Remove `CMAKE_.*_OUTPUT_DIRECTORY` (NFCI)" 2017-09-29 19:50:41 +00:00
CODE_OWNERS.TXT [ARC] Add ARC backend. 2017-08-24 15:40:33 +00:00
CREDITS.TXT Add myself to CREDITS.txt 2017-09-18 14:33:39 +00:00
LICENSE.TXT
LLVMBuild.txt
README.txt
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.