llvm-svn: 61556

Use movaps / movd to extract vector element 0 even with sse4.1. It's still cheaper than pextrw especially if the value is in memory.

llvm-svn: 61555

promote from i1 all the way up to the canonical SetCC type.
In order to discover an appropriate type to use, pass
MVT::Other to getSetCCResultType.  In order to be able to
do this, change getSetCCResultType to take a type as an
argument, not a value (this is also more logical).

llvm-svn: 61542

llvm-svn: 61513

  instruction sequence and cannot ordinarily be simplified by DAGcombine
  into the various target description files or SPUDAGToDAGISel.cpp.

  This makes some 64-bit operations legal.

- Eliminate target-dependent ISD enums.

- Update tests.

llvm-svn: 61508

Darwin doesn't. Make this optional for platforms.

llvm-svn: 61484

llvm-svn: 61477

- Move v4i32, i32 mul into SPUInstrInfo.td, with a few more instruction
  cleanups there as well.
- Make SMUL_LOHI, UMUL_LOHI competely illegal for Cell SPU, to better
  assist Chris to see the problem in bug 3101.

llvm-svn: 61464

  DAGcombine's ability to find reasons to remove truncates when they were not
  needed. Consequently, the CellSPU backend would produce correct, but _really
  slow and horrible_, code.

  Replaced with instruction sequences that do the equivalent truncation in
  SPUInstrInfo.td.

- Re-examine how unaligned loads and stores work. Generated unaligned
  load code has been tested on the CellSPU hardware; see the i32operations.c
  and i64operations.c in CodeGen/CellSPU/useful-harnesses.  (While they may be
  toy test code, it does prove that some real world code does compile
  correctly.)

- Fix truncating stores in bug 3193 (note: unpack_df.ll will still make llc
  fault because i64 ult is not yet implemented.)

- Added i64 eq and neq for setcc and select/setcc; started new instruction
  information file for them in SPU64InstrInfo.td. Additional i64 operations
  should be added to this file and not to SPUInstrInfo.td.

llvm-svn: 61447

llvm-svn: 61426

llvm-svn: 61425

llvm-svn: 61424

llvm-svn: 61423

llvm-svn: 61420

about other platforms.

llvm-svn: 61415

a symbolic constant. This is unlikely to be intentional, but it
shouldn't crash the compiler.

llvm-svn: 61408

llvm-svn: 61407

llvm-svn: 61404

llvm-svn: 61400

llvm-svn: 61392

This removes all the _8, _16, _32, and _64 opcodes and replaces each
group with an unsuffixed opcode. The MemoryVT field of the AtomicSDNode
is now used to carry the size information. In tablegen, the size-specific
opcodes are replaced by size-independent opcodes that utilize the
ability to compose them with predicates.

This shrinks the per-opcode tables and makes the code that handles
atomics much more concise.

llvm-svn: 61389

llvm-svn: 61385

Fixed lowering of v8i16 shuffles for v8i16 when we fall back to extract/insert.

llvm-svn: 61365

llvm-svn: 61356

constant shift count that doesn't fit in the shift instruction's
immediate field. This fixes PR3242.

llvm-svn: 61281

that have i32 immediates so that they get selected first. This
currently only matters in the JIT, as assemblers will
automatically use the smallest encoding.

llvm-svn: 61250

llvm-svn: 61244

The EH_frame and .eh symbols are now private, except for darwin9 and earlier.
The patch also fixes the definition of PrivateGlobalPrefix on pcc linux.

llvm-svn: 61242

used, mark the defs as dead.

llvm-svn: 61215

non-entry blocks, so that it doesn't appear use-before-def anywhere.

llvm-svn: 61214

llvm-svn: 61211

and the RegisterScavenger not to expect traditional liveness 
techniques are applicable to these registers, since we don't fully
modify the effects of push and pop after stackification.

llvm-svn: 61179

especially in the case of addresses computed from loop induction
variables.

llvm-svn: 61075

llvm-svn: 61033

comments about why we're not getting other cases.

llvm-svn: 61032

llvm-svn: 61028

llvm-svn: 61014

llvm-svn: 61013

  which are identical to the original patterns.

- Change the multiply with overflow so that we distinguish between signed and
  unsigned multiplication. Currently, unsigned multiplication with overflow
  isn't working!

llvm-svn: 60963

lowering f64 function arguments.

llvm-svn: 60944