instead.

So now: -fast-isel or -fast-isel=true enable fast-isel, and
-fast-isel=false disables it. Fast-isel is also on by default
with -fast, and off by default otherwise.

llvm-svn: 57270

SDISel typically adds them in. This makes it a little easier
to compare FastISel output with SDISel output.

llvm-svn: 57266

for things like null pointers, which at this level aren't
different from regular integer constants.

llvm-svn: 57265

X86::CL that was used, emit an EXTRACT_SUBREG from the CL
super-register to CL. This more precisely describes how the
CL register is being used.

llvm-svn: 57264

Unconditional branch instruction encoding fix. Needs to use ABI, not AXI, to get the proper opcode bits.

llvm-svn: 57262

llvm-svn: 57261

llvm-svn: 57259

llvm-svn: 57258

Fixes local RA miscompilation of gcc.c-torture/execute/20020904-1.c -O0.

llvm-svn: 57257

llvm-svn: 57255

llvm-svn: 57254

Clarify naming and correct conditional so that CMP and CMN instructions get the Rn operand encoded properly

llvm-svn: 57252

llvm-svn: 57251

llvm-svn: 57249

llvm-svn: 57248

llvm-svn: 57247

Certain patterns involving the "movss" instruction were marked as requiring SSE2, when in reality movss is an SSE1 instruction.

llvm-svn: 57246

llvm-svn: 57243

llvm-svn: 57226

since -0.0 can't be represented as an int.
This prevents llvm from reducing -0.0 to a
load-and-convert of int 0.  Fixes
ieee.exp/mzero[2356].c in gcc testsuite.

llvm-svn: 57224

2006-01-23-UnionInit on x86-64 when inlining is not enabled.

llvm-svn: 57223

llvm-svn: 57221

are Inexact.  (These are not Inexact as defined
by IEEE754, but that seems like a reasonable way
to abstract what happens:  information is lost.)

llvm-svn: 57218

llvm-svn: 57210

it is too aggressive.

llvm-svn: 57203

Patch By Matthijs Kooijman.

llvm-svn: 57202

Improve description of unsupported formats.

llvm-svn: 57185

optimized for size. Set OptForSize for each function separately.

llvm-svn: 57182

ENABLE_EXPENSIVE_CHECKS for finding this.

llvm-svn: 57181

llvm-svn: 57179

This includes not marking a GEP involving a vector as unsafe, but only when it
has all zero indices. This allows scalarrepl to work in a few more cases.

llvm-svn: 57177

llvm-svn: 57148

llvm-svn: 57147

llvm-svn: 57123

and actually work.  We can now read the llvm 2.3 bc file from PR2849

llvm-svn: 57122

llvm-svn: 57114

llvm-svn: 57113

Patch by Robert G. Jakabosky!

llvm-svn: 57110

llvm-svn: 57106

llvm-svn: 57096