diff options
| author | Sean Silva <silvas@purdue.edu> | 2013-02-07 05:56:46 +0000 |
|---|---|---|
| committer | Sean Silva <silvas@purdue.edu> | 2013-02-07 05:56:46 +0000 |
| commit | a79535c0dd22c25ab4ae8e90f71b182b539b28b0 (patch) | |
| tree | 964eeecb258c5b468a73be3bf36dd948645cc976 /docs/ReleaseNotes.rst | |
| parent | 2119cf08802fdbbb78c2c527cb460c43fd121636 (diff) | |
| download | llvm-a79535c0dd22c25ab4ae8e90f71b182b539b28b0.tar.gz llvm-a79535c0dd22c25ab4ae8e90f71b182b539b28b0.tar.bz2 llvm-a79535c0dd22c25ab4ae8e90f71b182b539b28b0.tar.xz | |
[ReleaseNotes] tidy up organization and formatting
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174587 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'docs/ReleaseNotes.rst')
| -rw-r--r-- | docs/ReleaseNotes.rst | 43 |
1 files changed, 23 insertions, 20 deletions
diff --git a/docs/ReleaseNotes.rst b/docs/ReleaseNotes.rst index beb2014911..78ea24e53c 100644 --- a/docs/ReleaseNotes.rst +++ b/docs/ReleaseNotes.rst @@ -52,27 +52,12 @@ Non-comprehensive list of changes in this release easy-to-write reStructuredText. See `llvm/docs/README.txt` for more information. - Loop Vectorizer - --------------- - We've continued the work on the loop vectorizer. The loop vectorizer now has the following features: - # Loops with unknown trip count. - # Runtime checks of pointers - # Reductions, Inductions - # If Conversion - # Pointer induction variables - # Reverse iterators - # Vectorization of mixed types - # Vectorization of function calls - # Partial unrolling during vectorization - - We've also improved the X86 and ARM cost model. - - TargetTransformInfo - ------------------- - TargetTransformInto (TTI) is a new interface that can be used by IR-level passes - to obtain target-specific information, such as the costs of instructions. Only "Lowering" - passes such as LSR and the vectorizer are allowed to use the TTI infrastructure. +* TargetTransformInfo (TTI) is a new interface that can be used by IR-level + passes to obtain target-specific information, such as the costs of + instructions. Only "Lowering" passes such as LSR and the vectorizer are + allowed to use the TTI infrastructure. +* We've improved the X86 and ARM cost model. * ... next change ... @@ -86,6 +71,24 @@ Non-comprehensive list of changes in this release Makes programs 10x faster by doing Special New Thing. +Loop Vectorizer +--------------- + +We've continued the work on the loop vectorizer. The loop vectorizer now +has the following features: + +- Loops with unknown trip count. +- Runtime checks of pointers +- Reductions, Inductions +- If Conversion +- Pointer induction variables +- Reverse iterators +- Vectorization of mixed types +- Vectorization of function calls +- Partial unrolling during vectorization + + + Additional Information ====================== |