Commit Graph

61167 Commits

Author SHA1 Message Date
Nate Begeman fe123268a9 ARM NEON:
fix vcvt naming
handle vdup, vcombine with generic vector code

llvm-svn: 105588
2010-06-08 00:14:42 +00:00
Bob Wilson 846bd7992c Further changes for Neon vector shuffles:
- change isShuffleMaskLegal to show that all shuffles with 32-bit and 64-bit
  elements are legal
- the Neon shuffle instructions do not support 64-bit elements, but we were
  not checking for that before lowering shuffles to use them
- remove some 64-bit element vduplane patterns that are no longer needed

llvm-svn: 105586
2010-06-07 23:53:38 +00:00
Bob Wilson 7149cfcda3 Fix a mistake in my previous change r105437: don't access operand 2 and assume
that it is an immediate before checking that the instruction is an
EXTRACT_SUBREG.

llvm-svn: 105585
2010-06-07 23:48:46 +00:00
Dan Gohman 7398758719 Add some basic debug output.
llvm-svn: 105561
2010-06-07 22:32:10 +00:00
Stuart Hastings 8612940357 Tweak test for debug/metadata change, update to FileCheck. Radar 7424645.
llvm-svn: 105559
2010-06-07 21:50:54 +00:00
Jim Grosbach 723d242a95 Handle dbg_value instructions (i.e., skip them) when generating IT blocks.
rdar://7797940

llvm-svn: 105557
2010-06-07 21:48:47 +00:00
Nick Lewycky 4ecf2cc5ea Plug a leak in the non-error case by removing one level of indirection.
llvm-svn: 105556
2010-06-07 21:42:19 +00:00
Jim Grosbach 6201b991a2 Cleanup. Process the dbg_values separately
llvm-svn: 105554
2010-06-07 21:28:55 +00:00
Dan Gohman 22e1adbb11 Fix this test to work under lit.
llvm-svn: 105553
2010-06-07 20:58:11 +00:00
Dan Gohman fa9ad13002 Run dead type elimination after dead argument elimination.
llvm-svn: 105552
2010-06-07 20:28:37 +00:00
Dan Gohman fb8ed43349 Make bugpoint dead-argument-hacking actually work, and actually test it.
llvm-svn: 105551
2010-06-07 20:20:33 +00:00
Dan Gohman 34a2249fde Use ->isVoidTy().
llvm-svn: 105550
2010-06-07 20:19:26 +00:00
Dan Gohman ebf2e977cf The FoldingSet hash data includes pointer values, so it isn't
determinstic. Instead, give SCEV objects an arbitrary sequence
number.

llvm-svn: 105548
2010-06-07 19:36:14 +00:00
Dan Gohman 3553feed79 Optimize this code somewhat by taking advantage of the fact
that the operands are sorted.

llvm-svn: 105546
2010-06-07 19:20:57 +00:00
Bill Wendling cfcd0e12cf Another place where the code wanted to access the argument list and not all of
the operands.

llvm-svn: 105545
2010-06-07 19:18:58 +00:00
Dan Gohman a2effb6452 Micro-optimize this, to speed up this hotspot in debug builds a little.
llvm-svn: 105544
2010-06-07 19:16:37 +00:00
Dan Gohman 18a4b46404 Micro-optimize this.
llvm-svn: 105542
2010-06-07 19:12:54 +00:00
Jim Grosbach 0f445f328e Move exit check where it really belongs.
llvm-svn: 105541
2010-06-07 19:12:21 +00:00
Dan Gohman 70910a6ab6 Optimize ScalarEvolution's SCEVComplexityCompare predicate: don't go
scrounging through SCEVUnknown contents and SCEVNAryExpr operands;
instead just do a simple deterministic comparison of the precomputed
hash data.

Also, since this is more precise, it eliminates the need for the slow
N^2 duplicate detection code.

llvm-svn: 105540
2010-06-07 19:06:13 +00:00
Bill Wendling a3bba3371a Create new accessors to get arguments for call/invoke instructions. It breaks
encapsulation to force the users of these classes to know about the internal
data structure of the Operands structure. It also can lead to errors, like in
the MSIL writer.

llvm-svn: 105539
2010-06-07 19:05:06 +00:00
Rafael Espindola c4dca3aeb6 Misc cleanups to the gold plugin.
llvm-svn: 105534
2010-06-07 16:45:22 +00:00
Nate Begeman 12d1f62f6c clang codegen support
llvm-svn: 105531
2010-06-07 16:00:37 +00:00
Kenneth Uildriks 1850444000 Partial specialization was not checking the callsite to make sure it was using the same constants as the specialization, leading to calls to the wrong specialization. Patch by Takumi Nakamura\!
llvm-svn: 105528
2010-06-05 14:50:21 +00:00
Duncan Sands e4f45cc88f This bug is also present in MSVC10. Requested by Elrood on IRC.
llvm-svn: 105527
2010-06-05 12:40:43 +00:00
Chris Lattner fdd2614330 revert r105521, which is breaking the buildbots with stuff like this:
In file included from X86InstrInfo.cpp:16:
X86GenInstrInfo.inc:2789: error: integer constant is too large for 'long' type
X86GenInstrInfo.inc:2790: error: integer constant is too large for 'long' type
X86GenInstrInfo.inc:2792: error: integer constant is too large for 'long' type
X86GenInstrInfo.inc:2793: error: integer constant is too large for 'long' type
X86GenInstrInfo.inc:2808: error: integer constant is too large for 'long' type
X86GenInstrInfo.inc:2809: error: integer constant is too large for 'long' type
X86GenInstrInfo.inc:2816: error: integer constant is too large for 'long' type
X86GenInstrInfo.inc:2817: error: integer constant is too large for 'long' type

llvm-svn: 105524
2010-06-05 04:17:30 +00:00
Bruno Cardoso Lopes 594fa26317 Initial AVX support for some instructions. No patterns matched
yet, only assembly encoding support.

llvm-svn: 105521
2010-06-05 03:53:24 +00:00
Bruno Cardoso Lopes c4f614870f Teach tablegen to support 'defm' inside multiclasses.
llvm-svn: 105519
2010-06-05 02:11:52 +00:00
Dan Gohman 0501b03242 Make MachineFunctionPass::createPrinterPass private, as no subclasses
should be calling it.

llvm-svn: 105517
2010-06-05 01:19:12 +00:00
Dale Johannesen 81ef35b3ca Improvements to tail call code. No functional effect
unless using -arm-tail-calls.

llvm-svn: 105515
2010-06-05 00:51:39 +00:00
Dan Gohman 520913cf9e getFoldedOffsetOf no longer does anything special with vector types.
llvm-svn: 105514
2010-06-05 00:47:34 +00:00
Dan Gohman 8c292adba4 No need to special-case structs here; structs are first-class now.
llvm-svn: 105513
2010-06-05 00:42:29 +00:00
Stuart Hastings 3ca391027f Revert 105492 & 105493 due to a testcase regression. Radar 7424645.
llvm-svn: 105511
2010-06-05 00:39:29 +00:00
Dan Gohman bbfb6aca92 LSR needs to remember inserted instructions even in postinc mode, because
there could be multiple subexpressions within a single expansion which
require insert point adjustment. This fixes PR7306.

llvm-svn: 105510
2010-06-05 00:33:07 +00:00
Dale Johannesen df1a7f83bf Fix some liveout handling related to tail calls, see comments.
I don't think this ever resulted in problems on x86, but it
would on ARM.

llvm-svn: 105509
2010-06-05 00:30:45 +00:00
Dan Gohman d7910a805d Implement operator== and operator!= for SetVector.
llvm-svn: 105508
2010-06-05 00:26:02 +00:00
Devang Patel 3eed2cf587 test case for r105504.
Radar 8055687.

llvm-svn: 105505
2010-06-04 23:47:41 +00:00
Evan Cheng a03e6f85fe Re-apply 105308 with fix.
llvm-svn: 105502
2010-06-04 23:28:13 +00:00
Dan Gohman 67b4403101 Don't track users of undef values; they aren't interesting for
register pressure.

llvm-svn: 105501
2010-06-04 23:16:05 +00:00
Jim Grosbach a1e08fb256 Make if-conversion ignore dbg_value instructions in its analysis. rdar://7797940
llvm-svn: 105498
2010-06-04 23:01:26 +00:00
Nate Begeman 7090e5be2b Handle multi-vector returns and args.
llvm-svn: 105496
2010-06-04 22:53:30 +00:00
Devang Patel e89b759501 Update docs to reflect new DISubprogram elements.
llvm-svn: 105495
2010-06-04 22:49:55 +00:00
Stuart Hastings 7c015988fe Support for nested functions/classes in debug output. Radar 7424645.
llvm-svn: 105492
2010-06-04 22:36:03 +00:00
Devang Patel 36da24b546 Copy location info for current function argument from dbg.declare if respective store instruction does not have any location info.
llvm-svn: 105490
2010-06-04 22:27:30 +00:00
Nate Begeman 0d081df3f2 Additional fixes to BuiltinsARM.def generator, on to clang codegen.
llvm-svn: 105488
2010-06-04 21:36:00 +00:00
Dale Johannesen 065d6fd537 More tail call removal.
llvm-svn: 105485
2010-06-04 21:14:24 +00:00
Jim Grosbach 50d229e6b3 Skip dbg_value instructions when scanning instructions in register scavenging.
llvm-svn: 105481
2010-06-04 20:18:30 +00:00
Dan Gohman 538b413ccb Fix normalization and de-normalization of non-affine SCEVs.
llvm-svn: 105480
2010-06-04 19:16:34 +00:00
Jakob Stoklund Olesen 864827afb0 Keep track of the call instructions whose clobber lists were skipped during fast
register allocation.

Process all of the clobber lists at the end of the function, marking the
registers as used in MachineRegisterInfo.

This is necessary in case the calls clobber callee-saved registers (sic).

llvm-svn: 105473
2010-06-04 18:08:29 +00:00
Dale Johannesen d1b9311afa More thoroughly disable tails calls by default.
8060143, although this doesn't fix the real problem with tail call.

llvm-svn: 105472
2010-06-04 18:04:24 +00:00
Jim Grosbach 3548803f62 Another fix to prevent debug info from affecting codegen. rdar://7797940
llvm-svn: 105470
2010-06-04 17:57:34 +00:00