parameters instead of raw Constants.  This prevents the constants from
being selected by the isel pass, fixing PR2735.

llvm-svn: 57385

llvm-svn: 57381

llvm-svn: 57380

the same pattern as roundpd/roundps, the Intel compiler 
builtins do not:  rounds* has an extra operand.  Fixes
gcc.target/i386/sse4_1-rounds[sd]-[1234].c

llvm-svn: 57370

llvm-svn: 57368

Extend set of return registers on sparc until someone will implement MRV support there. At least, this will allow libgcc compile, however we are not ABI-compatible with stuff compiled with native gcc.

llvm-svn: 57364

llvm-svn: 57363

llvm-svn: 57362

llvm-svn: 57359

llvm-svn: 57358

llvm-svn: 57346

Add dummy 'm' inline asm constraint handler for Sparc. I'm not sure, whether it is correct, however :)

llvm-svn: 57345

llvm-svn: 57344

and APFloat::convertToInteger.  Restore return value to
IEEE754.  Adjust all users accordingly.

llvm-svn: 57329

make it clearer what the function does.  No functional
change.

llvm-svn: 57325

llvm-svn: 57318

g++dg/abi/key2.C

llvm-svn: 57309

llvm-svn: 57295

GCC 4.4.0 gives an error on the "int" declaration for example
saying that it has already been declared (using the "short"
one). Using templates here allow the compiler to distinguish
between the function to choose.

Also, "llvm/Support/DataTypes.h" was not included, leading to
error messages about not knowing "uint32_t" for example.

Patch by Samuel Tardieu.

llvm-svn: 57292

Patch by Samuel Tardieu.

llvm-svn: 57291

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

llvm-svn: 57266

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

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

llvm-svn: 57252

llvm-svn: 57251

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

llvm-svn: 57246

llvm-svn: 57226

llvm-svn: 57210

optimized for size. Set OptForSize for each function separately.

llvm-svn: 57182

llvm-svn: 57179

Patch by Robert G. Jakabosky!

llvm-svn: 57110

llvm-svn: 57106

llvm-svn: 57096

llvm-svn: 57048

Make it all work in non-pic mode.

llvm-svn: 57034

incidentally making the case where the memop is a
pointer deref work.  Fix cmp-and-swap regression.

llvm-svn: 57027