<feed xmlns='http://www.w3.org/2005/Atom'>
<title>llvm/lib/Target/X86, branch stable</title>
<subtitle>http://llvm.org</subtitle>
<id>https://git.amat.us/llvm/atom/lib/Target/X86?h=stable</id>
<link rel='self' href='https://git.amat.us/llvm/atom/lib/Target/X86?h=stable'/>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/'/>
<updated>2013-04-01T10:23:49Z</updated>
<entry>
<title>X86TTI: Add accurate costs for itofp operations, based on the actual instruction counts.</title>
<updated>2013-04-01T10:23:49Z</updated>
<author>
<name>Benjamin Kramer</name>
<email>benny.kra@googlemail.com</email>
</author>
<published>2013-04-01T10:23:49Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=13497b3aa7589fc4f9e924f850a7e5151e9ddd2f'/>
<id>urn:sha1:13497b3aa7589fc4f9e924f850a7e5151e9ddd2f</id>
<content type='text'>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178459 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
<entry>
<title>X86: Promote sitofp &lt;8 x i16&gt; to &lt;8 x i32&gt; when AVX is available.</title>
<updated>2013-03-31T12:49:15Z</updated>
<author>
<name>Benjamin Kramer</name>
<email>benny.kra@googlemail.com</email>
</author>
<published>2013-03-31T12:49:15Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=b8f0d89d0584e37e205c04ed5753f57a23365403'/>
<id>urn:sha1:b8f0d89d0584e37e205c04ed5753f57a23365403</id>
<content type='text'>
A vector sext + sitofp is a lot cheaper than 8 scalar conversions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178448 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
<entry>
<title>Change '@SECREL' suffix to GAS-compatible '@SECREL32'.</title>
<updated>2013-03-30T16:21:50Z</updated>
<author>
<name>Benjamin Kramer</name>
<email>benny.kra@googlemail.com</email>
</author>
<published>2013-03-30T16:21:50Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=42734cfb4140287d59d3b35718d62b5f90737499'/>
<id>urn:sha1:42734cfb4140287d59d3b35718d62b5f90737499</id>
<content type='text'>
'@SECREL' is what is used by the Microsoft assembler, but GNU as expects '@SECREL32'.
With the patch, the MC-generated code works fine in combination with a recent GNU as (2.23.51.20120920 here).

Patch by David Nadlinger!
Differential Revision: http://llvm-reviews.chandlerc.com/D429

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178427 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
<entry>
<title>Remove the old CodePlacementOpt pass.</title>
<updated>2013-03-29T17:14:24Z</updated>
<author>
<name>Benjamin Kramer</name>
<email>benny.kra@googlemail.com</email>
</author>
<published>2013-03-29T17:14:24Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=74a4533a4290b7c6f1fe04a30ca13ec25c529e0a'/>
<id>urn:sha1:74a4533a4290b7c6f1fe04a30ca13ec25c529e0a</id>
<content type='text'>
It was superseded by MachineBlockPlacement and disabled by default since LLVM 3.1.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178349 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
<entry>
<title>Add support of RDSEED defined in AVX2 extension</title>
<updated>2013-03-28T23:41:26Z</updated>
<author>
<name>Michael Liao</name>
<email>michael.liao@intel.com</email>
</author>
<published>2013-03-28T23:41:26Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=c26392aa5d9c2dbca2909d6874d181455f8aeb8f'/>
<id>urn:sha1:c26392aa5d9c2dbca2909d6874d181455f8aeb8f</id>
<content type='text'>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178314 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
<entry>
<title>Enhance boolean simplification to handle 16-/64-bit RDRAND</title>
<updated>2013-03-28T23:38:52Z</updated>
<author>
<name>Michael Liao</name>
<email>michael.liao@intel.com</email>
</author>
<published>2013-03-28T23:38:52Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=258d9b7bc021ebc78f5a3aef3907e225e632edfa'/>
<id>urn:sha1:258d9b7bc021ebc78f5a3aef3907e225e632edfa</id>
<content type='text'>
- RDRAND always clears the destination value when a random value is not
  available (i.e. CF == 0). This value is truncated or zero-extended as
  the false boolean value to be returned. Boolean simplification needs
  to skip this 'zext' or 'trunc' node.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178312 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
<entry>
<title>Skip moving call address loading into callseq when targets prefer register indirect call.</title>
<updated>2013-03-28T23:13:21Z</updated>
<author>
<name>Michael Liao</name>
<email>michael.liao@intel.com</email>
</author>
<published>2013-03-28T23:13:21Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=816f6d0ac76c0ffb2ea9ecb72349d5d7d0fa8d1a'/>
<id>urn:sha1:816f6d0ac76c0ffb2ea9ecb72349d5d7d0fa8d1a</id>
<content type='text'>
To enable a load of a call address to be folded with that call, this
load is moved from outside of callseq into callseq. Such a moving
adds a non-glued node (that load) into a glued sequence. This non-glue
load is only removed when DAG selection folds them into a memory form
call instruction. When such instruction selection is disabled, it breaks
DAG schedule.

To prevent that, such moving is disabled when target favors register
indirect call.

Previous workaround disabling CALL32m/CALL64m insn selection is removed.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178308 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
<entry>
<title>Add the X86 FMAs to the scheduling model.</title>
<updated>2013-03-28T22:54:45Z</updated>
<author>
<name>Nadav Rotem</name>
<email>nrotem@apple.com</email>
</author>
<published>2013-03-28T22:54:45Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=bad24f757d430ed9ef5348da58aa20d03409d6a0'/>
<id>urn:sha1:bad24f757d430ed9ef5348da58aa20d03409d6a0</id>
<content type='text'>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178303 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
<entry>
<title>Add the Haswell machine model.</title>
<updated>2013-03-28T22:34:46Z</updated>
<author>
<name>Nadav Rotem</name>
<email>nrotem@apple.com</email>
</author>
<published>2013-03-28T22:34:46Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=59af9d0bf4601276d03c52cc22865bbeba03e375'/>
<id>urn:sha1:59af9d0bf4601276d03c52cc22865bbeba03e375</id>
<content type='text'>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178301 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
<entry>
<title>Remove the unused port from the SandyBridge machine model</title>
<updated>2013-03-28T22:32:41Z</updated>
<author>
<name>Nadav Rotem</name>
<email>nrotem@apple.com</email>
</author>
<published>2013-03-28T22:32:41Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/llvm/commit/?id=0b6a69d4a191b40923deceffc0bfff94be851569'/>
<id>urn:sha1:0b6a69d4a191b40923deceffc0bfff94be851569</id>
<content type='text'>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178300 91177308-0d34-0410-b5e6-96231b3b80d8
</content>
</entry>
</feed>
