Commit Graph

4072 Commits

Author SHA1 Message Date
Andrew Trick
67bdd42d1e misched: fix RegionBegin when DebugValues get shuffled to the top.
assert (RemainingInstrs == 0 && "Instruction count mismatch!")

rdar://12776937.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169069 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-01 01:22:38 +00:00
Nadav Rotem
90e11dc8ad When combining consecutive stores allow loads in between the stores, if the loads do not alias.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168832 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-29 00:00:08 +00:00
Andrew Trick
8b1496c922 misched: Analysis that partitions the DAG into subtrees.
This is a simple, cheap infrastructure for analyzing the shape of a
DAG. It recognizes uniform DAGs that take the shape of bottom-up
subtrees, such as the included matrix multiplication example. This is
useful for heuristics that balance register pressure with ILP. Two
canonical expressions of the heuristic are implemented in scheduling
modes: -misched-ilpmin and -misched-ilpmax.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168773 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-28 05:13:28 +00:00
Andrew Trick
8f82a08673 misched: better alias analysis.
This fixes a hole in the "cheap" alias analysis logic implemented within
the DAG builder itself, regardless of whether proper alias analysis is
enabled. It now handles this pattern produced by LSR+CodeGenPrepare.

%sunkaddr1 = ptrtoint * %obj to i64
%sunkaddr2 = add i64 %sunkaddr1, %lsr.iv
%sunkaddr3 = inttoptr i64 %sunkaddr2 to i32*
store i32 %v, i32* %sunkaddr3

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168768 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-28 03:42:49 +00:00
Manman Ren
f365d3984e X86: do not fold load instructions such as [V]MOVS[S|D] to other instructions
when the destination register is wider than the memory load.

These load instructions load from m32 or m64 and set the upper bits to zero,
while the folded instructions may accept m128.

rdar://12721174


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168710 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-27 18:09:26 +00:00
Craig Topper
020669d53f Revert accidental commit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168687 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-27 08:17:04 +00:00
Craig Topper
af87dae12c Make PrintReg constructor explicit to prevent weird implicit conversions from accidentally being triggered.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168686 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-27 08:14:24 +00:00
Craig Topper
2cf4fb4884 Add test cases for r168417.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168681 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-27 07:19:54 +00:00
NAKAMURA Takumi
cb84142195 llvm/test/CodeGen/X86/2012-07-15-broadcastfold.ll: Loosen expression corresponding to r168627. Win32 and *bsd were affected.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168651 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-27 00:48:27 +00:00
Chad Rosier
1243922fc1 Remove the X86 Maximal Stack Alignment Check pass as it is no longer necessary.
This pass was conservative in that it always reserved the FP to enable dynamic
stack realignment, which allowed the RA to use aligned spills for vector
registers.  This happens even when spills were not necessary.  The RA has 
since been improved to use unaligned spills when necessary.

The new behavior is to realign the stack if the frame pointer was already
reserved for some other reason, but don't reserve the frame pointer just
because a function contains vector virtual registers.

Part of rdar://12719844

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168627 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-26 22:55:05 +00:00
Jakub Staszak
d642baf4be Normalize splat 256bit vectors with 8 elements.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168600 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-26 19:24:31 +00:00
Elena Demikhovsky
4fe5405bdd Intel OCL built-ins calling conventions now support MacOS 32-bit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168359 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-20 09:37:57 +00:00
Jakob Stoklund Olesen
e42561ad0c Handle mixed normal and early-clobber defs on inline asm.
PR14376.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168320 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-19 19:31:10 +00:00
NAKAMURA Takumi
e0827d8880 llvm/test/CodeGen/X86/hipe-cc*.ll: Add explicit -mcpu, or they don't expect to pass on Atom.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168171 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-16 16:07:37 +00:00
Duncan Sands
dc7f174b5e Add the Erlang/HiPE calling convention, patch by Yiannis Tsiouris.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168166 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-16 12:36:39 +00:00
Craig Topper
d577552c66 Use roundps/pd for llvm.ceil, llvm.trunc, llvm.rint, and llvm.nearbyint of vector types.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168141 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-16 06:37:56 +00:00
Jakub Staszak
0e52f46e48 Make sure to not get AVX code on an AVX-capable host. Revealed in r167967.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167989 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-14 22:24:01 +00:00
NAKAMURA Takumi
9292136787 llvm/test/CodeGen/X86/memset.ll: FileCheck-ize, and add another case on +avx.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167975 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-14 21:01:40 +00:00
Benjamin Kramer
7c6e8cd7cc Force CPU in test so we don't accidentally get AVX code on an AVX-capable host.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167973 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-14 20:31:42 +00:00
Benjamin Kramer
2dbe929685 X86: Enable SSE memory intrinsics even when stack alignment is less than 16 bytes.
The stack realignment code was fixed to work when there is stack realignment and
a dynamic alloca is present so this shouldn't cause correctness issues anymore.

Note that this also enables generation of AVX instructions for memset
under the assumptions:
- Unaligned loads/stores are always fast on CPUs supporting AVX
- AVX is not slower than SSE
We may need some tweaked heuristics if one of those assumptions turns out not to
be true.

Effectively reverts r58317. Part of PR2962.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167967 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-14 20:08:40 +00:00
Rafael Espindola
8e2b8ae3b1 Handle DAG CSE adding new uses during ReplaceAllUsesWith. Fixes PR14333.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167912 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-14 05:08:56 +00:00
Eric Christopher
242343d1ab Revert "Use the 'count' attribute instead of the 'upper_bound' attribute."
temporarily as it is breaking the gdb bots.

This reverts commit r167806/e7ff4c14b157746b3e0228d2dce9f70712d1c126.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167886 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-13 23:30:43 +00:00
Manman Ren
2adc503f29 X86: when constructing VZEXT_LOAD from other loads, makes sure its output
chain is correctly setup.

As an example, if the original load must happen before later stores, we need
to make sure the constructed VZEXT_LOAD is constrained to be before the stores.

rdar://12684358


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167859 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-13 19:13:05 +00:00
Bill Wendling
e7ff4c14b1 Use the 'count' attribute instead of the 'upper_bound' attribute.
If we have a type 'int a[1]' and a type 'int b[0]', the generated DWARF is the
same for both of them because we use the 'upper_bound' attribute. Instead use
the 'count' attrbute, which gives the correct number of elements in the array.
<rdar://problem/12566646>


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167806 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-13 02:31:47 +00:00
Michael Liao
01c6de341c Fix test case added in patch fixing PR14314
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167769 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-12 22:33:18 +00:00
Michael Liao
dd3383fd09 Fix PR14314
- Fix operand order for atomic sub, where the minuend is the value
  loaded from memory and the subtrahend is the parameter specified.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167718 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-12 06:49:17 +00:00
Craig Topper
9c7ae01f39 Cleanup pcmp(e/i)str(m/i) instruction definitions and load folding support.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167652 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-10 01:23:36 +00:00
Michael Liao
be02a90de1 Add support of RTM from TSX extension
- Add RTM code generation support throught 3 X86 intrinsics:
  xbegin()/xend() to start/end a transaction region, and xabort() to abort a
  tranaction region



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167573 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-08 07:28:54 +00:00
Andrew Trick
3b87f6204f misched: Heuristics based on the machine model.
misched is disabled by default. With -enable-misched, these heuristics
balance the schedule to simultaneously avoid saturating processor
resources, expose ILP, and minimize register pressure. I've been
analyzing the performance of these heuristics on everything in the
llvm test suite in addition to a few other benchmarks. I would like
each heuristic check to be verified by a unit test, but I'm still
trying to figure out the best way to do that. The heuristics are still
in considerable flux, but as they are refined we should be rigorous
about unit testing the improvements.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167527 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-07 07:05:09 +00:00
NAKAMURA Takumi
b75111f1ef test/CodeGen/X86/fp-fast.ll: Add +avx.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167207 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-01 02:13:45 +00:00
Owen Anderson
607ebde651 Add a few more simple fast-math constant propagations and cancellations.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167200 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-01 02:00:53 +00:00
Shuxin Yang
a5526a9bff (For X86) Enhancement to add-carray/sub-borrow (adc/sbb) optimization.
The adc/sbb optimization is to able to convert following expression
into a single adc/sbb instruction:
  (ult) ... = x + 1 // where the ult is unsigned-less-than comparison
  (ult) ... = x - 1

  This change is to flip the "x >u y" (i.e. ugt comparison) in order 
to expose the adc/sbb opportunity.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167180 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-31 23:11:48 +00:00
Manman Ren
dfd0b9b460 X86 SSE: update rsqrtss and rcpss to use two source operands and
the first source operand is tied to the destination operand.

This is to accurately model the corresponding instructions where the upper
bits are unmodified.

rdar://12558838
PR14221


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167064 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-30 23:53:59 +00:00
Manman Ren
4c74a956b2 X86 MMX: optimize transfer from mmx to i32
We used to generate a store (movq) + a load.
Now we use movd.

rdar://9946746


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167056 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-30 22:15:38 +00:00
Jakub Staszak
a24262a0f5 Re-commit r166971. I reverted it to quickly, when buildbots didn't have a chance
to test it with chapni's fix (-mattr=+avx).


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166985 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-30 00:01:57 +00:00
Jakub Staszak
c1ed096b6b Revert r166971. It causes buildbot failure. To be investigated.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166979 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-29 23:13:50 +00:00
NAKAMURA Takumi
926dd447f1 llvm/test/CodeGen/X86/vec_shuffle-30.ll: Try to unbreak builds - assuming +avx.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166974 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-29 22:45:18 +00:00
Jakub Staszak
6d317824a5 Allow to fold vector load if there is more than one bitcast, so in the case:
%0 = load <8 x i16>* %dest
%1 = shufflevector <8 x i16> %0, <8 x i16> %in,
      <8 x i32> < i32 0, i32 1, i32 2, i32 3, i32 13, i32 undef, i32 14, i32 14>
store <8 x i16> %1, <8 x i16>* %dest

We get:
  vmovlpd (%eax), %xmm0, %xmm0

instead of:
  vmovaps (%eax), %xmm1
  vmovsd  %xmm1, %xmm0, %xmm0

No extra test-case is added. I just fixed the existing one
(also it uses FileCheck now).


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166971 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-29 21:56:35 +00:00
Chad Rosier
53e216b304 Remove redundant test case from r166949, per Eli's suggestion.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166953 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-29 18:18:26 +00:00
Chad Rosier
2fbc239e4f [ms-inline asm] Add support for the [] operator. Essentially, [expr1][expr2] is
equivalent to [expr1 + expr2].  See test cases for more examples.
rdar://12470392

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166949 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-29 18:01:54 +00:00
Michael Liao
2a2263e744 Fix PR14204
- Add missing pattern on X86ISD::VZEXT from VR256 to VR256 when AVX2 is enabled.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166947 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-29 17:57:12 +00:00
Preston Gurd
a836563e32 This patch addresses a problem with the Post RA scheduler generating an
incorrect instruction sequence due to it not being aware that an
inline assembly instruction may reference memory.

This patch fixes the problem by causing the scheduler to always assume that any
inline assembly code instruction could access memory. This is necessary because
the internal representation of the inline instruction does not include
any information about memory accesses.
 
This should fix PR13504.




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166929 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-29 15:01:23 +00:00
Jakob Stoklund Olesen
163f67f4d9 Never attempt to join an early-clobber def with a regular kill.
This fixes PR14194.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166880 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-27 17:41:27 +00:00
Michael Liao
8d7cd1d8fc Add test for ATOM ISA SSSE3
- Remove SSE4.1 feature in other ATOM-based test cases



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166699 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-25 17:50:05 +00:00
Elena Demikhovsky
c0cd72204d The test avx-intel-ocl.ll failed. I can't reproduce on any of my machines. I added -mcpu flag, may be it will fix the problem
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166669 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-25 08:38:42 +00:00
Chad Rosier
b3009eec47 [ms-inline asm] Add back-end test case for r166632. Make sure we emit the
correct .s output as well as get the correct encoding by the integrated
assembler.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166638 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24 23:10:28 +00:00
Elena Demikhovsky
3575222175 Special calling conventions for Intel OpenCL built-in library.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166566 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24 14:46:16 +00:00
Michael Liao
1a5cc710ee Teach DAG combine to fold (buildvec (Xint2fp x)) to (Xint2fp (buildvec x))
- If more than 1 elemennts are defined and target supports the vectorized
  conversion, use the vectorized one instead to reduce the strength on
  conversion operation.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166546 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24 04:14:18 +00:00
Michael Liao
991b6a22b6 Add custom conversion from v2u32 to v2f32 in 32-bit mode
- As there's no 64-bit GPRs in 32-bit mode, a custom conversion from v2u32 to
  v2f32 is added to improve the efficiency of the code generated.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166545 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24 04:09:32 +00:00
Rafael Espindola
847a9c6d77 Change x86_fastcallcc to require inreg markers. This allows it to known
the difference from "int x" (which should go in registers and
"struct y {int x;}" (which should not).

Clang will be updated in the next patches.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166536 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-24 01:58:48 +00:00
Michael Liao
0787274b70 Fix PR14161
- Check index being extracted to be constant 0 before simplfiying.
  Otherwise, retain the original sequence.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166504 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-23 21:40:15 +00:00
Michael Liao
d9d09600ee Enable lowering ZERO_EXTEND/ANY_EXTEND to PMOVZX from SSE4.1
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166486 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-23 17:34:00 +00:00
Michael Liao
facace808c Lower BUILD_VECTOR to SHUFFLE + INSERT_VECTOR_ELT for X86
- If INSERT_VECTOR_ELT is supported (above SSE2, either by custom
  sequence of legal insn), transform BUILD_VECTOR into SHUFFLE +
  INSERT_VECTOR_ELT if most of elements could be built from SHUFFLE with few
  (so far 1) elements being inserted.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166288 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-19 17:15:18 +00:00
Sebastian Pop
83ba06afa8 Clear unknown mem ops when merging stack slots (pr14090)
When merging stack slots, if StackColoring::remapInstructions gets a
value back from GetUnderlyingObject that it does not know about or is
not itself a stack slot, clear the memory operand in case it aliases
the merged slot. This prevents the introduction of incorrect aliasing
information.

Author:    Matthew Curtis <mcurtis@codeaurora.org>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166216 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-18 19:53:48 +00:00
Nadav Rotem
1c5bf3f429 In SimplifySelectOps we pulled two loads through a select node despite the fact that one was dependent on the other.
rdar://12513091



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166196 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-18 18:06:48 +00:00
Michael Liao
07edaf3801 Revert part of r166049 back and enable test case in r166125.
- Folding (trunc (concat ... X )) to (concat ... (trunc X) ...) is valid
  when '...' are all 'undef's.
- r166125 relies on this transformation.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166155 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-17 23:45:54 +00:00
Michael Liao
6e0c2b36d6 Disable extract-concat test case temporarily
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166141 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-17 23:08:19 +00:00
Michael Liao
4031e9018b Revert r166049
- In general, it's unsafe for this transformation.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166135 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-17 22:41:15 +00:00
Michael Liao
13429e224c Teach DAG combine to fold (extract_subvec (concat v1, ..) i) to v_i
- If the extracted vector has the same type of all vectored being concatenated
  together, it should be simplified directly into v_i, where i is the index of
  the element being extracted.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166125 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-17 20:48:33 +00:00
Michael Liao
281ae5abf5 Fix setjmp on models with non-Small code model nor non-Static relocation model
- MBB address is only valid as an immediate value in Small & Static
  code/relocation models. On other models, LEA is needed to load IP address of
  the restore MBB.
- A minor fix of MBB in MC lowering is added as well to enable target
  relocation flag being propagated into MC.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166084 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-17 02:22:27 +00:00
Jakob Stoklund Olesen
320db3f805 Avoid rematerializing a redef immediately after the old def.
PR14098 contains an example where we would rematerialize a MOV8ri
immediately after the original instruction:

  %vreg7:sub_8bit<def> = MOV8ri 9; GR32_ABCD:%vreg7
  %vreg22:sub_8bit<def> = MOV8ri 9; GR32_ABCD:%vreg7

Besides being pointless, it is also wrong since the original instruction
only redefines part of the register, and the value read by the new
instruction is wrong.

The problem was the LiveRangeEdit::allUsesAvailableAt() didn't
special-case OrigIdx == UseIdx and found the wrong SSA value.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166068 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-16 22:51:58 +00:00
Jakob Stoklund Olesen
cdcdfd2cab Revert r166046 "Switch back to the old coalescer for now to fix the 32 bit bit"
A fix for PR14098, including the test case is in the next commit.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166067 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-16 22:51:55 +00:00
Michael Liao
272ea03239 Teach DAG combine to fold (trunc (fptoXi x)) to (fptoXi x)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166049 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-16 19:38:35 +00:00
Rafael Espindola
6f7cccd2e2 Switch back to the old coalescer for now to fix the 32 bit bit
llvm+clang+compiler-rt bootstrap.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166046 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-16 19:34:06 +00:00
NAKAMURA Takumi
e26874556b Reapply r165661, Patch by Shuxin Yang <shuxin.llvm@gmail.com>.
Original message:

The attached is the fix to radar://11663049. The optimization can be outlined by following rules:

   (select (x != c), e, c) -> select (x != c), e, x),
   (select (x == c), c, e) -> select (x == c), x, e)
where the <c> is an integer constant.

 The reason for this change is that : on x86, conditional-move-from-constant needs two instructions;
however, conditional-move-from-register need only one instruction.

  While the LowerSELECT() sounds to be the most convenient place for this optimization, it turns out to be a bad place. The reason is that by replacing the constant <c> with a symbolic value, it obscure some instruction-combining opportunities which would otherwise be very easy to spot. For that reason, I have to postpone the change to last instruction-combining phase.

  The change passes the test of "make check-all -C <build-root/test" and "make -C project/test-suite/SingleSource".

Original message since r165661:

My previous change has a bug: I negated the condition code of a CMOV, and go ahead creating a new CMOV using the *ORIGINAL* condition code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166017 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-16 06:28:34 +00:00
Rafael Espindola
0cead1cfef Fix the cpu name and add -verify-machineinstrs.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166003 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-16 01:13:06 +00:00
Andrew Trick
27c28cef11 misched: Added handleMove support for updating all kill flags, not just for allocatable regs.
This is a medium term workaround until we have a more robust solution
in the form of a register liveness utility for postRA passes.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166001 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-16 00:22:51 +00:00
Michael Liao
6c0e04c823 Add __builtin_setjmp/_longjmp supprt in X86 backend
- Besides used in SjLj exception handling, __builtin_setjmp/__longjmp is also
  used as a light-weight replacement of setjmp/longjmp which are used to
  implementation continuation, user-level threading, and etc. The support added
  in this patch ONLY addresses this usage and is NOT intended to support SjLj
  exception handling as zero-cost DWARF exception handling is used by default
  in X86.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165989 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-15 22:39:43 +00:00
Andrew Trick
874c0a6ec7 Check output of the misched unit tests
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165959 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-15 20:33:14 +00:00
Rafael Espindola
32522201a8 Add a cpu to try to fix the atom builder.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165956 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-15 19:25:43 +00:00
Rafael Espindola
3da6f0392a Add testcase for pr14088.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165954 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-15 19:00:10 +00:00
Andrew Trick
bb20b24224 misched tests: add a triple to speculatively fix windows builders.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165952 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-15 18:21:08 +00:00
Andrew Trick
1e94e98b0e misched: ILP scheduler for experimental heuristics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165950 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-15 18:02:27 +00:00
Benjamin Kramer
f8b65aaf39 X86: Fix accidentally swapped operands.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165871 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-13 12:50:19 +00:00
Benjamin Kramer
444dccecfc X86: Promote i8 cmov when both operands are coming from truncates of the same width.
X86 doesn't have i8 cmovs so isel would emit a branch. Emitting branches at this
level is often not a good idea because it's too late for many optimizations to
kick in. This solution doesn't add any extensions (truncs are free) and tries
to avoid introducing partial register stalls by filtering direct copyfromregs.

I'm seeing a ~10% speedup on reading a random .png file with libpng15 via
graphicsmagick on x86_64/westmere, but YMMV depending on the microarchitecture.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165868 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-13 10:39:49 +00:00
Jakob Stoklund Olesen
2bbb07d13c Fix buildbots: -misched=shuffle is only available in +Asserts builds.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165846 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-12 23:01:33 +00:00
Jakob Stoklund Olesen
ad5e969ba9 Use a transposed algorithm for handleMove().
Completely update one interval at a time instead of collecting live
range fragments to be updated. This avoids building data structures,
except for a single SmallPtrSet of updated intervals.

Also share code between handleMove() and handleMoveIntoBundle().

Add support for moving dead defs across other live values in the
interval. The MI scheduler can do that.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165824 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-12 21:31:57 +00:00
Jakob Stoklund Olesen
795f951c6d Fix coalescing with IMPLICIT_DEF values.
PHIElimination inserts IMPLICIT_DEF instructions to guarantee that all
PHI predecessors have a live-out value. These IMPLICIT_DEF values are
not considered to be real interference when coalescing virtual
registers:

  %vreg1 = IMPLICIT_DEF
  %vreg2 = MOV32r0

When joining %vreg1 and %vreg2, the IMPLICIT_DEF instruction and its
value number should simply be erased since the %vreg2 value number now
provides a live-out value for the PHI predecesor block.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165813 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-12 18:03:04 +00:00
Jakob Stoklund Olesen
ebba49395c Pass an explicit operand number to addLiveIns.
Not all instructions define a virtual register in their first operand.
Specifically, INLINEASM has a different format.

<rdar://problem/12472811>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165721 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-11 16:46:07 +00:00
NAKAMURA Takumi
e0297196ed Revert r165661, "Patch by Shuxin Yang <shuxin.llvm@gmail.com>."
It broke stage2 clang and test-suite/MultiSource/Benchmarks/mediabench/g721/g721encode.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165692 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-11 02:02:05 +00:00
Nadav Rotem
87255a431b Patch by Shuxin Yang <shuxin.llvm@gmail.com>.
Original message:

The attached is the fix to radar://11663049. The optimization can be outlined by following rules:

   (select (x != c), e, c) -> select (x != c), e, x),
   (select (x == c), c, e) -> select (x == c), x, e)
where the <c> is an integer constant.

 The reason for this change is that : on x86, conditional-move-from-constant needs two instructions;
however, conditional-move-from-register need only one instruction.

  While the LowerSELECT() sounds to be the most convenient place for this optimization, it turns out to be a bad place. The reason is that by replacing the constant <c> with a symbolic value, it obscure some instruction-combining opportunities which would otherwise be very easy to spot. For that reason, I have to postpone the change to last instruction-combining phase.

  The change passes the test of "make check-all -C <build-root/test" and "make -C project/test-suite/SingleSource".



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165661 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-10 21:31:55 +00:00
Michael Liao
4e2c56bdcb Specify CPU model to avoid breaking ATOM builds
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165638 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-10 18:04:52 +00:00
Michael Liao
44c2d61b67 Add support for FP_ROUND from v2f64 to v2f32
- Due to the current matching vector elements constraints in
  ISD::FP_ROUND, rounding from v2f64 to v4f32 (after legalization from
  v2f32) is scalarized. Add a customized v2f32 widening to convert it
  into a target-specific X86ISD::VFPROUND to work around this
  constraints.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165631 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-10 16:53:28 +00:00
Evan Cheng
e61e516a51 When expanding atomic load arith instructions, do not lose target flags. rdar://12453106
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165568 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-09 23:48:33 +00:00
Jakob Stoklund Olesen
6be75ae196 Don't crash on extra evil irreducible control flow.
When the CFG contains a loop with multiple entry blocks, the traces
computed by MachineTraceMetrics don't always have the same nice
properties. Loop back-edges are normally excluded from traces, but
MachineLoopInfo doesn't recognize loops with multiple entry blocks, so
those back-edges may be included.

Avoid asserting when that happens by adding an isEarlierInSameTrace()
function that accurately determines if a dominating block is part of the
same trace AND is above the currrent block in the trace.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165434 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-08 22:06:44 +00:00
Benjamin Kramer
dcf2420b07 X86: fcmov doesn't handle all possible EFLAGS, fall back to a branch for the others.
Otherwise it will try to use SSE patterns and fail horribly if sse is disabled.
Fixes PR14035.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165377 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-07 15:34:27 +00:00
Evan Cheng
2a2947885a Follow up to r165072. Try a different approach: only move the load when it's going to be folded into the call. rdar://12437604
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165287 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-05 01:48:22 +00:00
Nadav Rotem
ea2c50c041 When merging connsecutive stores, use vectors to store the constant zero.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165267 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-04 22:35:15 +00:00
Chad Rosier
34448ae393 [ms-inline asm] Add support in the X86AsmPrinter for printing memory references
in the Intel syntax.

The MC layer supports emitting in the Intel syntax, but this would require the
inline assembly MachineInstr to be lowered to an MCInst before emission.  This
is potential future work, but for now emitting directly from the MachineInstr
suffices.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165173 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-03 22:06:44 +00:00
Nadav Rotem
2e7d38192d Fix a cycle in the DAG. In this code we replace multiple loads with a single load and
multiple stores with a single load. We create the wide loads and stores (and their chains)
before we remove the scalar loads and stores and fix the DAG chain. We attempted to merge
loads with a different chain. When that happened, the assumption that it is safe to RAUW
broke and a cycle was introduced.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165148 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-03 19:30:31 +00:00
Nadav Rotem
c653de6c0f A DAGCombine optimization for mergeing consecutive stores to memory. The optimization
is not profitable in many cases because modern processors perform multiple stores
in parallel and merging stores prior to merging requires extra work. We handle two main cases:

1. Store of multiple consecutive constants:
  q->a = 3;
  q->4 = 5;
In this case we store a single legal wide integer.

2. Store of multiple consecutive loads:
  int a = p->a;
  int b = p->b;
  q->a = a;
  q->b = b;
In this case we load/store either ilegal vector registers or legal wide integer registers.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165125 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-03 16:11:15 +00:00
Jakob Stoklund Olesen
0d141f867d The early if conversion pass is ready to be used as an opt-in.
Enable the pass by default for targets that request it, and change the
-enable-early-ifcvt to the opposite -disable-early-ifcvt.

There are still some x86 regressions when enabling early if-conversion
because of the missing machine models. Disable the pass for x86 until
machine models are added.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165075 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-03 00:51:32 +00:00
Evan Cheng
2b87e06d26 Fix a serious X86 instruction selection bug. In
X86DAGToDAGISel::PreprocessISelDAG(), isel is moving load inside
callseq_start / callseq_end so it can be folded into a call. This can
create a cycle in the DAG when the call is glued to a copytoreg. We
have been lucky this hasn't caused too many issues because the pre-ra
scheduler has special handling of call sequences. However, it has
caused a crash in a specific tailcall case.

rdar://12393897


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165072 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-02 23:49:13 +00:00
Nick Lewycky
b09649b335 Make sure to put our sret argument into %rax on x86-64. Fixes PR13563!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165063 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-02 22:45:06 +00:00
Duncan Sands
48da0be8b5 Fix PR13991: legalizing an overflowing multiplication operation is harder than
the add/sub case since in the case of multiplication you also have to check that
the operation in the larger type did not overflow.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165017 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-02 15:03:49 +00:00
NAKAMURA Takumi
3fc42fd77c test/CodeGen/X86/red-zone2.ll: Add -mtriple=x86_64-linux, and FileCheck-ize.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164975 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-01 22:48:07 +00:00
Michael Liao
3118937305 Fix PR13899
- Update maximal stack alignment when stack arguments are prepared before a
  call.
- Test cases are enhanced to show it's not a Win32 specific issue but a generic
  one.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164946 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-01 16:44:04 +00:00
Nadav Rotem
73fab91f2c Revert r164910 because it causes failures to several phase2 builds.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164911 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-30 07:17:56 +00:00
Nadav Rotem
e5f163a3b9 A DAGCombine optimization for merging consecutive stores. This optimization is not profitable in many cases
because moden processos can store multiple values in parallel, and preparing the consecutive store requires
some work.  We only handle these cases:

1. Consecutive stores where the values and consecutive loads. For example:
 int a = p->a;
 int b = p->b;
 q->a = a;
 q->b = b;

2. Consecutive stores where the values are constants. Foe example:
 q->a = 4;
 q->b = 5;



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164910 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-30 06:24:14 +00:00
Duncan Sands
454627252b Speculatively revert commit 164885 (nadav) in the hope of ressurecting a pile of
buildbots.  Original commit message:

A DAGCombine optimization for merging consecutive stores. This optimization is not profitable in many cases
because moden processos can store multiple values in parallel, and preparing the consecutive store requires
some work.  We only handle these cases:

1. Consecutive stores where the values and consecutive loads. For example:
  int a = p->a;
  int b = p->b;
  q->a = a;
  q->b = b;

2. Consecutive stores where the values are constants. Foe example:
  q->a = 4;
  q->b = 5;



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164890 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-29 10:25:35 +00:00
Nadav Rotem
72f7b0811e A DAGCombine optimization for merging consecutive stores. This optimization is not profitable in many cases
because moden processos can store multiple values in parallel, and preparing the consecutive store requires
some work.  We only handle these cases:

1. Consecutive stores where the values and consecutive loads. For example:
  int a = p->a;
  int b = p->b;
  q->a = a;
  q->b = b;

2. Consecutive stores where the values are constants. Foe example:
  q->a = 4;
  q->b = 5;



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164885 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-29 06:33:25 +00:00
Evan Cheng
465970736b Do not delete BBs if their addresses are taken. rdar://12396696
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164866 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-28 23:58:57 +00:00
Manman Ren
284c1004f7 Testcase for r164835
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164842 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-28 20:26:33 +00:00
Jakob Stoklund Olesen
ddc26d8936 Avoid dereferencing a NULL pointer.
Fixes PR13943.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164778 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-27 16:34:19 +00:00
NAKAMURA Takumi
e6232ed86d llvm/test/CodeGen/X86/mulx*.ll: Fix copypasto.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164681 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-26 09:24:12 +00:00
Michael Liao
4fa2ddbb94 Add SARX/SHRX/SHLX code generation support
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164675 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-26 08:26:25 +00:00
Michael Liao
6bcdb5b903 Add RORX code generation support
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164674 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-26 08:24:51 +00:00
Michael Liao
0832a72a66 Add MULX code generation support
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164673 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-26 08:22:37 +00:00
Michael Liao
e5e8f7656a Add missing i64 max/min/umax/umin on 32-bit target
- Turn on atomic6432.ll and add specific test case as well



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164616 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-25 18:08:13 +00:00
Evan Cheng
b1cacc7423 Fix an illegal tailcall opt where the callee returns a double via xmm while caller returns x86_fp80 via st0. rdar://12229511
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164588 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-25 05:32:34 +00:00
Jim Grosbach
e9525d8624 Mark jump tables in code sections with DataRegion directives.
Even out-of-line jump tables can be in the code section, so mark them
as data-regions for those targets which support the directives.

rdar://12362871&12362974

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164571 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-24 23:06:27 +00:00
Michael Liao
90d9e9405e Revise test to avoid using of 'grep'
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164472 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-23 02:41:47 +00:00
Michael Liao
4d6b84028a Enhance test case of atomic16 to verify inst encoding fixed in r164453.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164465 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-22 21:07:59 +00:00
NAKAMURA Takumi
f17422181f llvm/test/CodeGen/X86/pr5145.ll: Tweak expressions to match for darwin target.
.LBB0_1: # Linux
LBB0_1:  # Darwin

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164362 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-21 05:19:19 +00:00
Michael Liao
fe87c302aa Add missing i8 max/min/umax/umin support
- Fix PR5145 and turn on test 8-bit atomic ops



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164358 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-21 03:18:52 +00:00
Benjamin Kramer
902ba576fd Fix broken check lines.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164317 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-20 19:54:13 +00:00
Michael Liao
85fb261a55 Specify CPu to prevent failure on ATOM due to different code scheduling
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164283 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-20 03:34:04 +00:00
Michael Liao
b118a073d7 Re-work X86 code generation of atomic ops with spin-loop
- Rewrite/merge pseudo-atomic instruction emitters to address the
  following issue:
  * Reduce one unnecessary load in spin-loop

    previously the spin-loop looks like

        thisMBB:
        newMBB:
          ld  t1 = [bitinstr.addr]
          op  t2 = t1, [bitinstr.val]
          not t3 = t2  (if Invert)
          mov EAX = t1
          lcs dest = [bitinstr.addr], t3  [EAX is implicit]
          bz  newMBB
          fallthrough -->nextMBB

    the 'ld' at the beginning of newMBB should be lift out of the loop
    as lcs (or CMPXCHG on x86) will load the current memory value into
    EAX. This loop is refined as:

        thisMBB:
          EAX = LOAD [MI.addr]
        mainMBB:
          t1 = OP [MI.val], EAX
          LCMPXCHG [MI.addr], t1, [EAX is implicitly used & defined]
          JNE mainMBB
        sinkMBB:

  * Remove immopc as, so far, all pseudo-atomic instructions has
    all-register form only, there is no immedidate operand.

  * Remove unnecessary attributes/modifiers in pseudo-atomic instruction
    td

  * Fix issues in PR13458

- Add comprehensive tests on atomic ops on various data types.
  NOTE: Some of them are turned off due to missing functionality.

- Revise tests due to the new spin-loop generated.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164281 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-20 03:06:15 +00:00
Michael Liao
cd9ede9fc0 Unify the logic in SelectAtomicLoadAdd and SelectAtomicLoadArith
- Merge the processing of LOAD_ADD with other atomic load-arith
  operations
- Separate the logic getting target constant for atomic-load-op and add
  an optimization for atomic-load-add on i16 with negative value
- Optimize a minor case for atomic-fetch-add i16 with negative operand. Test
  case is revised.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164243 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-19 19:36:58 +00:00
Jan Wen Voung
b024b7014a Add some cases to x86 OptimizeCompare to handle DEC and INC, too.
While we are setting the earlier def to true, also make it live.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164056 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-17 22:04:23 +00:00
Michael Liao
bb73002247 Fix PR13859
- Preserve the original NOutVT during casting from vector to integer by
  extracting vector elements.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164042 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-17 18:05:20 +00:00
Nadav Rotem
6fc671ca63 Fix the testcase to work on all platforms.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163997 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-16 07:58:47 +00:00
Nadav Rotem
638e4c13cb The PMOVZXWD family of functions had patterns extends narrow vector types to wide vector types.
It had patterns for zext-loading and extending. This commit adds patterns for loading a wide type, performing a bitcast,
and extending. This is an odd pattern, but it is commonly used when writing code with intrinsics.

rdar://11897677



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163995 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-16 07:39:07 +00:00
Benjamin Kramer
562b240fc5 X86: Emitting x87 fsin/fcos for sinf/cosf is not safe without unsafe fp math.
This was only an issue if sse is disabled.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163967 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-15 12:44:27 +00:00
Eric Christopher
ffaf69b8b1 Fix both the test for zero and what we do if we have a zero for
umulo legalization.

Fixes PR13839

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163856 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 23:24:02 +00:00
Michael Liao
f966e4e5b3 Add wider vector/integer support for PR12312
- Enhance the fix to PR12312 to support wider integer, such as 256-bit
  integer. If more than 1 fully evaluated vectors are found, POR them
  first followed by the final PTEST.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163832 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 20:24:54 +00:00
Michael Liao
092122f124 Enhance type legalization on bitcast from vector to integer
- Find a legal vector type before casting and extracting element from it.
- As the new vector type may have more than 2 elements, build the final
  hi/lo pair by BFS pairing them from bottom to top.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163830 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 19:58:21 +00:00
Jakob Stoklund Olesen
da0e8219b7 Fix test case to avoid PIC magic.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163827 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 19:47:45 +00:00
Jakob Stoklund Olesen
7bba7d0efc Fix the TCRETURNmi64 bug differently.
Add a PatFrag to match X86tcret using 6 fixed registers or less. This
avoids folding loads into TCRETURNmi64 using 7 or more volatile
registers.

<rdar://problem/12282281>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163819 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 18:31:27 +00:00
Jakob Stoklund Olesen
0767dc546e Revert r163761 "Don't fold indexed loads into TCRETURNmi64."
The patch caused "Wrong topological sorting" assertions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163810 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 16:52:17 +00:00
Nadav Rotem
91a7e0184a Fix a dagcombine optimization. The optimization attempts to optimize a bitcast of fneg to integers
by xoring the high-bit. This fails if the source operand is a vector because we need to negate
each of the elements in the vector.

Fix rdar://12281066 PR13813.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163802 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 14:54:28 +00:00
Nadav Rotem
0cd19b9301 Stack Coloring: We have code that checks that all of the uses of allocas
are within the lifetime zone. Sometime legitimate usages of allocas are
hoisted outside of the lifetime zone. For example, GEPS may calculate the
address of a member of an allocated struct. This commit makes sure that
we only check (abort regions or assert) for instructions that read and write
memory using stack frames directly. Notice that by allowing legitimate
usages outside the lifetime zone we also stop checking for instructions
which use derivatives of allocas. We will catch less bugs in user code
and in the compiler itself.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163791 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 12:38:37 +00:00
Jakob Stoklund Olesen
aa0cfea9a4 Don't fold indexed loads into TCRETURNmi64.
We don't have enough GR64_TC registers when calling a varargs function
with 6 arguments. Since %al holds the number of vector registers used,
only %r11 is available as a scratch register.

This means that addressing modes using both base and index registers
can't be folded into TCRETURNmi64.

<rdar://problem/12282281>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163761 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-13 00:25:00 +00:00
Michael Liao
6c7ccaa3fd Fix PR11985
- BlockAddress has no support of BA + offset form and there is no way to
  propagate that offset into machine operand;
- Add BA + offset support and a new interface 'getTargetBlockAddress' to
  simplify target block address forming;
- All targets are modified to use new interface and X86 backend is enhanced to
  support BA + offset addressing.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163743 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-12 21:43:09 +00:00
Nadav Rotem
0a16da4457 Stack coloring: remove lifetime intervals which contain escaped allocas.
The input program may contain intructions which are not inside lifetime
markers. This can happen due to a bug in the compiler or due to a bug in
user code (for example, returning a reference to a local variable).
This commit adds checks that all of the instructions in the function and
invalidates lifetime ranges which do not contain all of the instructions.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163678 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-12 04:57:37 +00:00
Chad Rosier
a7b159ccdd [ms-inline asm] Split the parsing of IR asm strings into GCC and MS variants.
Add support in the EmitMSInlineAsmStr() function for handling integer consts.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163645 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-11 19:09:56 +00:00
Chad Rosier
ef68cfa8b8 Formatting. No functional change intended.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163627 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-11 16:33:10 +00:00
Nadav Rotem
8754bbbe67 Stack Coloring: Dont crash on dbg values which use stack frames.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163616 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-11 12:34:27 +00:00
NAKAMURA Takumi
985dcfc351 test/CodeGen/X86/ms-inline-asm.ll: Relax for non-darwin x86 targets. '##InlineAsm' could not be seen in other hosts.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163554 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 22:04:54 +00:00
Chad Rosier
24f5fddbdf [ms-inline asm] Properly emit the asm directives when the AsmPrinterVariant
and InlineAsmVariant don't match.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163550 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 21:36:05 +00:00
Chad Rosier
5c3dcb7bc0 Update test case for Release builds.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163549 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 21:31:43 +00:00
Chad Rosier
3b132fab0b [ms-inline asm] Pass the correct AsmVariant to the PrintAsmOperand() function
and update the printOperand() function accordingly.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163544 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 21:10:49 +00:00
Nadav Rotem
6165dba25f Stack Coloring: Handle the case where END markers come before BEGIN markers properly.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163530 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 18:51:09 +00:00
Michael Liao
b8150d8523 Enhance PR11334 fix to support extload from v2f32/v4f32
- Fix an remaining issue of PR11674 as well



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163528 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 18:33:51 +00:00
Michael Liao
7fdc66bf73 Add boolean simplification support from CMOV
- If a boolean value is generated from CMOV and tested as boolean value,
  simplify the use of test result by referencing the original condition.
  RDRAND intrinisc is one of such cases.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163516 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 16:36:16 +00:00
Nadav Rotem
e47feeb823 Stack Coloring: Add support for multiple regions of the same slot, within a single basic block.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163507 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 12:39:35 +00:00
Elena Demikhovsky
8100d244ff The VPSHUFB 256-bit instruction may be generated when one of input vector is undefined or zeroinitializer.
I've added the "zeroinitializer" case in this patch.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163506 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 12:13:11 +00:00
Nadav Rotem
9a2ae00c85 Teach the DAGBuilder about lifetime markers which are generated from PHINodes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163494 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-10 08:43:23 +00:00
Craig Topper
956342b210 Teach DAG combiner to constant fold fneg of a BUILD_VECTOR of constants.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163483 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-09 22:58:45 +00:00
Craig Topper
12fb5c667f Add instruction selection for ffloor of vectors when SSE4.1 or AVX is enabled.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163473 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-08 17:42:27 +00:00