The motivation to do that:

1. Now, llvm would use the stock config.sub. Before that we had an
uncommitted FreeBSD-related patch. Now, it has been upstreamed and
comes back. It means that it would be easier to update these files in
the next time (less magic knowledge)

2. Fix a typo for pseudo-CPUs: 32e[lb] -> [lb]e32, 64e[lb]->[lb]64.
One of these CPUs is used for PNaCl and it was not really convenient
to have a CPU that starts with a digit.

llvm-svn: 138323

Add support for breaking 256-bit v16i16 and v32i8 VSETCC into two 128-bit ones, avoiding sclarization. Add vex form of pcmpeqq and pcmpgtq. Fixes more cases for PR10712.

llvm-svn: 138321

llvm-svn: 138319

SSE transition penalty. The pass is enabled through the "x86-use-vzeroupper"
llc command line option. This is only the first step (very naive and
conservative one) to sketch out the idea, but proper DFA is coming next
to allow smarter decisions. Comments and ideas now and in further commits
will be very appreciated.

llvm-svn: 138317

llvm-svn: 138312

llvm-svn: 138311

llvm-svn: 138308

llvm-svn: 138306

llvm-svn: 138305

llvm-svn: 138304

llvm-svn: 138303

value, we insert a load of the exception object and selector object from memory,
which is where it actually resides. If it's used by a PHI node, we follow that
to where it is being used. Eventually, all landingpad instructions should have
no uses. Any PHI nodes that were associated with those landingpads should be
removed.

llvm-svn: 138302

llvm-svn: 138301

llvm-svn: 138300

llvm-svn: 138299

llvm-svn: 138298

llvm-svn: 138297

llvm-svn: 138295

llvm-svn: 138294

llvm-svn: 138293

llvm-svn: 138292

llvm-svn: 138291

llvm-svn: 138290

Follow up to Jim's r138278. This fixes commuteInstruction so it handles two-address instructions correctly. I'll let Jim add a test case. :-)

llvm-svn: 138289

llvm-svn: 138288

llvm-svn: 138287

llvm-svn: 138286

llvm-svn: 138285

It's not playing nicely in the coalescer with the tied operand. Disable
commutability for now while we figure out the deeper fix.

llvm-svn: 138278

Some minor wording updates and cross-linking for atomic docs.  Explicitly note that we don't try to portably define what volatile in LLVM IR means.

llvm-svn: 138274

Provide operand encoding information for half-precision VCVT instructions.  Found by randomized testing.

llvm-svn: 138273

avoding scalarization of the compare. Reduces code from 59 to 6
instructions. Fix PR10712.

llvm-svn: 138271

llvm-svn: 138270

Fix decoding of VMOVSRR and VMOVRRS, which account for the overwhelming majority of decoder crashes detected by randomized testing.

llvm-svn: 138269

llvm-svn: 138260

llvm-svn: 138258

llvm-svn: 138256

llvm-svn: 138255

llvm-svn: 138252

llvm-svn: 138251