RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00
Code Issues Projects Releases Wiki Activity
Mirror of https://github.com/RPCS3/llvm-mirror
115,965 Commits 4 Branches 5 Tags 704 MiB
C++ 96.9%
C 1%
Python 1%
CMake 0.6%
OCaml 0.2%
Other 0.1%
f5d182f516
Go to file
Sanjay Patel f5d182f516 [x86] Implement combineRepeatedFPDivisors 
Set the transform bar at 2 divisions because the fastest current
x86 FP divider circuit is in SandyBridge / Haswell at 10 cycle
latency (best case) relative to a 5 cycle multiplier. 
So that's the worst case for this transform (no latency win), 
but multiplies are obviously pipelined while divisions are not,
so there's still a big throughput win which we would expect to
show up in typical FP code.

These are the sequences I'm comparing:

  divss   %xmm2, %xmm0
  mulss   %xmm1, %xmm0
  divss   %xmm2, %xmm0

Becomes:

  movss   LCPI0_0(%rip), %xmm3    ## xmm3 = mem[0],zero,zero,zero
  divss   %xmm2, %xmm3
  mulss   %xmm3, %xmm0
  mulss   %xmm1, %xmm0
  mulss   %xmm3, %xmm0

[Ignore for the moment that we don't optimize the chain of 3 multiplies
into 2 independent fmuls followed by 1 dependent fmul...this is the DAG
version of: https://llvm.org/bugs/show_bug.cgi?id=21768 ...if we fix that,
then the transform becomes even more profitable on all targets.]

Differential Revision: http://reviews.llvm.org/D8941

llvm-svn: 235012
2015-04-15 15:22:55 +00:00
autoconf Try to unbreak Clang build to export LLVM_ABI_BREAKING_CHECKS, fixup for r233310. 2015-04-01 11:46:15 +00:00
bindings Go bindings: make various DIBuilder arguments optional. 2015-04-08 20:18:57 +00:00
cmake [msvc] Strip /W[0-4] before appending /W4 2015-04-14 16:57:54 +00:00
docs Correct 'teh' and other typos / repeated words. 2015-04-14 20:52:58 +00:00
examples DebugInfo: Add implicit conversion from DISubprogram to DIScope 2015-04-14 16:19:44 +00:00
include Clarify that Twine::toVector *appends* the Twine to the given SmallString. 2015-04-15 11:27:32 +00:00
lib [x86] Implement combineRepeatedFPDivisors 2015-04-15 15:22:55 +00:00
projects Reverse the order libc++ and libc++abi are added in CMake. 2015-03-04 01:16:43 +00:00
test [x86] Implement combineRepeatedFPDivisors 2015-04-15 15:22:55 +00:00
tools Change range-based for-loop to use const auto&. No functionality change. 2015-04-15 03:17:49 +00:00
unittests Only recalculate DFS Numbers if invalid. Invalidate DFS numbers on reset. Add unit test to verify recalculation 2015-04-14 19:49:26 +00:00
utils Change range-based for-loops to be -Wrange-loop-analysis clean. 2015-04-15 01:21:15 +00:00
.arcconfig Updated phabricator server. 2014-04-07 03:57:04 +00:00
.clang-format Test commit. 2014-03-02 13:08:46 +00:00
.clang-tidy Enable display of compiler diagnostics in clang-tidy by default. 2014-10-29 17:29:38 +00:00
.gitignore Ignore compile_commands.json only at the root of the tree. 2015-03-26 18:55:42 +00:00
CMakeLists.txt [CMake] Updates to llvm-shlib to support overriding exports list and added an option to export all symbols. 2015-04-13 21:29:46 +00:00
CODE_OWNERS.TXT Tom is also responsible for the 3.6 branch. 2015-03-16 18:15:27 +00:00
configure Try to unbreak Clang build to export LLVM_ABI_BREAKING_CHECKS, fixup for r233310. 2015-04-01 11:46:15 +00:00
CREDITS.TXT Rise from the dead and update personal info 2014-08-25 17:51:04 +00:00
LICENSE.TXT Update for a new year. 2015-03-12 01:25:29 +00:00
llvm.spec.in
LLVMBuild.txt
Makefile [configure/make] Propagate names of build host tools when making BuildTools 2014-03-25 21:45:41 +00:00
Makefile.common
Makefile.config.in Try to unbreak Clang build to export LLVM_ABI_BREAKING_CHECKS, fixup for r233310. 2015-04-01 11:46:15 +00:00
Makefile.rules Add support for SunOS function/data sections and associated 2015-03-03 20:54:29 +00:00
README.txt Revert test commit at revision 233535. 2015-03-30 12:39:03 +00:00

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're writing a package for LLVM, see docs/Packaging.rst for our
suggestions.