Commit Graph

17865 Commits

Author SHA1 Message Date
Nadav Rotem
f5637c3997 Improve the X86 cost model for loads and stores.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170830 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-21 01:33:59 +00:00
Reed Kotler
e30843ded9 Add test case for r170674
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170823 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-21 00:55:10 +00:00
Nadav Rotem
55306bdea5 Fix a bug in the code that checks if we can vectorize loops while using dynamic
memory bound checks.  Before the fix we were able to vectorize this loop from
the Livermore Loops benchmark:

for ( k=1 ; k<n ; k++ )
  x[k] = x[k-1] + y[k];



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170811 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-21 00:07:35 +00:00
Eric Christopher
71a9c2137b Move these files over to the debug info directory.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170810 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-21 00:03:42 +00:00
Bob Wilson
103b4a571e Revert "Adding support for llvm.arm.neon.vaddl[su].* and"
This reverts r170694.  The operations can be represented in IR without
adding any new intrinsics.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170765 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 21:09:38 +00:00
Nadav Rotem
8386acd734 LoopVectorize: Fix a bug in the scalarization of instructions.
Before if-conversion we could check if a value is loop invariant
if it was declared inside the basic block. Now that loops have
multiple blocks this check is incorrect.

This fixes External/SPEC/CINT95/099_go/099_go



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170756 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 20:24:40 +00:00
Evan Cheng
139e407d52 On some ARM cpus, flags setting movs with shifter operand, i.e. lsl, lsr, asr,
are more expensive than the non-flag setting variant. Teach thumb2 size
reduction pass to avoid generating them unless we are optimizing for size.

rdar://12892707


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170728 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 19:59:30 +00:00
Eli Bendersky
15019a8814 Change Lit error redirection to FileCheck to a more common syntax since it
can potentially cause some bots to fail.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170726 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 19:54:02 +00:00
Eli Bendersky
b17201f1b8 Add a largish auto-generated test for the aligned bundling feature, along with
the script generating it. The test should never be modified manually. If anyone
needs to change it, please change the script and re-run it.

The script is placed into utils/testgen - I couldn't think of a better place,
and after some discussion on IRC this looked like a logical location.





git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170720 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 19:16:57 +00:00
Eli Bendersky
16996c4940 Tests for the aligned bundling support added in r170718
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170719 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 19:07:30 +00:00
Rafael Espindola
ffc7d3b0ad Simplify the testcase a bit.
I checked that it would still crash llc before the corresponding fix.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170709 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 17:47:27 +00:00
James Molloy
67ae135759 Add a new attribute, 'noduplicate'. If a function contains a noduplicate call, the call cannot be duplicated - Jump threading, loop unrolling, loop unswitching, and loop rotation are inhibited if they would duplicate the call.
Similarly inlining of the function is inhibited, if that would duplicate the call (in particular inlining is still allowed when there is only one callsite and the function has internal linkage).



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170704 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 16:04:27 +00:00
Renato Golin
332bd79951 Adding support for llvm.arm.neon.vaddl[su].* and
llvm.arm.neon.vsub[su].* intrinsics.

Patch by Pete Couperus <pjcoup@gmail.com>



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170694 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 13:52:11 +00:00
Reed Kotler
cef95f702a fix most of remaining issues with large frames.
these patches are tested a lot by test-suite but
make check tests are forthcoming once the next
few patches that complete this are committed.
with the next few patches the pass rate for mips16 is
near 100%



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170656 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 04:07:42 +00:00
Akira Hatanaka
68fe665b9a [mips] Use "or $r0, $r1, $zero" instead of "addu $r0, $zero, $r1" to copy
physical register $r1 to $r0.

GNU disassembler recognizes an "or" instruction as a "move", and this change
makes the disassembled code easier to read.

Original patch by Reed Kotler.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170655 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 04:06:06 +00:00
Bob Wilson
99d8e76d44 Do not introduce vector operations in functions marked with noimplicitfloat.
<rdar://problem/12879313>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170630 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-20 01:36:20 +00:00
Eric Christopher
6eebe47060 Split out abbreviations for the skeleton info from the rest of
the abbreviations. Part of implementing split dwarf.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170589 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 22:02:53 +00:00
Evan Cheng
733c6b1db1 LLVM sdisel normalize bit extraction of the form:
((x & 0xff00) >> 8) << 2
to
 (x >> 6) & 0x3fc

This is general goodness since it folds a left shift into the mask. However,
the trailing zeros in the mask prevents the ARM backend from using the bit
extraction instructions. And worse since the mask materialization may require
an addition instruction. This comes up fairly frequently when the result of 
the bit twiddling is used as memory address. e.g.

 = ptr[(x & 0xFF0000) >> 16]

We want to generate:
  ubfx   r3, r1, #16, #8
  ldr.w  r3, [r0, r3, lsl #2]

vs.
  mov.w  r9, #1020
  and.w  r2, r9, r1, lsr #14
  ldr    r2, [r0, r2]

Add a late ARM specific isel optimization to
ARMDAGToDAGISel::PreprocessISelDAG(). It folds the left shift to the
'base + offset' address computation; change the mask to one which doesn't have
trailing zeros and enable the use of ubfx.

Note the optimization has to be done late since it's target specific and we
don't want to change the DAG normalization. It's also fairly restrictive
as shifter operands are not always free. It's only done for lsh 1 / 2. It's
known to be free on some cpus and they are most common for address
computation.

This is a slight win for blowfish, rijndael, etc.

rdar://12870177


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170581 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 20:16:09 +00:00
Roman Divacky
759e3fa641 Remove edis - the enhanced disassembler. Fixes PR14654.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170578 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 19:55:47 +00:00
Paul Redmond
6da2e22dff Transform (x&C)>V into (x&C)!=0 where possible
When the least bit of C is greater than V, (x&C) must be greater than V
if it is not zero, so the comparison can be simplified.

Although this was suggested in Target/X86/README.txt, it benefits any
architecture with a directly testable form of AND.

Patch by Kevin Schoedel


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170576 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 19:47:13 +00:00
Benjamin Kramer
91223a41ef PowerPC: Expand VSELECT nodes.
There's probably a better expansion for those nodes than the default for
altivec, but this is better than crashing. VSELECTs occur in loop vectorizer
output.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170551 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 15:49:14 +00:00
Benjamin Kramer
35d3462941 Make TargetLowering::getTypeConversion more resilient against odd illegal MVTs.
- An MVT can become an EVT when being split (e.g. v2i8 -> v1i8, the latter doesn't exist)
- Return the scalar value when an MVT is scalarized (v1i64 -> i64)

Fixes PR14639ff.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170546 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 14:34:28 +00:00
Evgeniy Stepanov
b8837ab8fc [msan] Heuristically instrument unknown intrinsics.
This changes adds shadow and origin propagation for unknown intrinsics
by examining the arguments and ModRef behaviour. For now, only 3 classes
of intrinsics are handled:
- those that look like simple SIMD store
- those that look like simple SIMD load
- those that don't have memory effects and look like arithmetic/logic/whatever
  operation on simple types.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170530 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 11:22:04 +00:00
Elena Demikhovsky
4b977312c7 Optimized load + SIGN_EXTEND patterns in the X86 backend.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170506 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 07:50:20 +00:00
Nadav Rotem
bf5a2c6a39 After reducing the size of an operation in the DAG we zero-extend the reduced
bitwidth op back to the original size. If we reduce ANDs then this can cause
an endless loop. This patch changes the ZEXT to ANY_EXTEND if the demanded bits
are equal or smaller than the size of the reduced operation.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170505 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 07:39:08 +00:00
Craig Topper
40b4a81ab0 Teach SimplifySetCC that comparing AssertZext i1 against a constant 1 can be rewritten as a compare against a constant 0 with the opposite condition.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170495 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-19 06:12:28 +00:00
Shuxin Yang
1a3150098c rdar://12801297
InstCombine for unsafe floating-point add/sub.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170471 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 23:10:12 +00:00
Jakub Staszak
270bfbd3d1 Reverse order of checking SSE level when calculating compare cost, so we check
AVX2 before AVX.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170464 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 22:57:56 +00:00
Quentin Colombet
b519351b87 Disable ARM partial flag dependency optimization at -Oz
To not over constrain the scheduler for ARM in thumb mode, some optimizations  for code size reduction, specific to ARM thumb, are blocked when they add a dependency (like write after read dependency).

Disables this check when code size is the priority, i.e., code is compiled with -Oz.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170462 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 22:47:16 +00:00
Andrew Trick
04f52e1300 MISched: add dependence to ExitSU to model live-out latency.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170454 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 20:53:01 +00:00
Benjamin Kramer
0ef0e2e6d0 LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops instead of scalar operations.
For example on x86 with SSE4.2 a <8 x i8> add reduction becomes
	movdqa	%xmm0, %xmm1
	movhlps	%xmm1, %xmm1            ## xmm1 = xmm1[1,1]
	paddw	%xmm0, %xmm1
	pshufd	$1, %xmm1, %xmm0        ## xmm0 = xmm1[1,0,0,0]
	paddw	%xmm1, %xmm0
	phaddw	%xmm0, %xmm0
	pextrb	$0, %xmm0, %edx

instead of
	pextrb	$2, %xmm0, %esi
	pextrb	$0, %xmm0, %edx
	addb	%sil, %dl
	pextrb	$4, %xmm0, %esi
	addb	%dl, %sil
	pextrb	$6, %xmm0, %edx
	addb	%sil, %dl
	pextrb	$8, %xmm0, %esi
	addb	%dl, %sil
	pextrb	$10, %xmm0, %edi
	pextrb	$14, %xmm0, %edx
	addb	%sil, %dil
	pextrb	$12, %xmm0, %esi
	addb	%dil, %sil
	addb	%sil, %dl

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170439 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 18:40:20 +00:00
Hal Finkel
ca2dd36c39 Check multiple register classes for inline asm tied registers
A register can be associated with several distinct register classes.
For example, on PPC, the floating point registers are each associated with
both F4RC (which holds f32) and F8RC (which holds f64). As a result, this code
would fail when provided with a floating point register and an f64 operand
because it would happen to find the register in the F4RC class first and
return that. From the F4RC class, SDAG would extract f32 as the register
type and then assert because of the invalid implied conversion between
the f64 value and the f32 register.

Instead, search all register classes. If a register class containing the
the requested register has the requested type, then return that register
class. Otherwise, as before, return the first register class found that
contains the requested register.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170436 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 17:50:58 +00:00
Nadav Rotem
aaf3b420b7 Rename the test so that we can add additional vectors-of-pointers tests
into the same file in the future.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170414 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 05:50:54 +00:00
Nadav Rotem
e21708e4aa SROA: Replace calls to getScalarSizeInBits to DataLayout's API because
getScalarSizeInBits could not handle vectors of pointers.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170412 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 05:23:31 +00:00
NAKAMURA Takumi
f8cd4df304 llvm/test/MC/ELF/comp-dir.s: Appease MSYS Bash.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170410 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 05:08:12 +00:00
Eric Christopher
6c583141bf Add support for passing -main-file-name all the way through to
the assembler.

Part of PR14624

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170390 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-18 00:31:01 +00:00
Chandler Carruth
1b6e9b867b Add a triple to this test -- it has to be an ELF platform...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170374 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 21:44:50 +00:00
Chandler Carruth
6c31d31357 Prepare LLVM to fix PR14625, exposing a hook in MCContext to manage the
compilation directory.

This defaults to the current working directory, just as it always has,
but now an assembler can choose to override it with a custom directory.
I've taught llvm-mc about this option and added a test case.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170371 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 21:32:42 +00:00
Chandler Carruth
b0de1e31d1 Fix another SROA crasher, PR14601.
This was a silly oversight, we weren't pruning allocas which were used
by variable-length memory intrinsics from the set that could be widened
and promoted as integers. Fix that.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170353 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 18:48:07 +00:00
Tim Northover
1c2b2f9c56 Teach MachO which sections contain code
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170349 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 17:59:32 +00:00
Richard Osborne
c47793c62c Add instruction encodings / disassembly support for l2r instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170345 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 16:28:02 +00:00
Chandler Carruth
99a54942ae Teach the rewriting of memcpy calls to support subvector copies.
This also cleans up a bit of the memcpy call rewriting by sinking some
irrelevant code further down and making the call-emitting code a bit
more concrete.

Previously, memcpy of a subvector would actually miscompile (!!!) the
copy into a single vector element copy. I have no idea how this ever
worked. =/ This is the memcpy half of PR14478 which we probably weren't
noticing previously because it didn't actually assert.

The rewrite relies on the newly refactored insert- and extractVector
functions to do the heavy lifting, and those are the same as used for
loads and stores which makes the test coverage a bit more meaningful
here.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170338 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 14:51:24 +00:00
Richard Osborne
a839ffc323 Add instruction encodings for PEEK and ENDIN.
Previously these were marked with the wrong format.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170334 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 14:23:54 +00:00
Chandler Carruth
8bbff2348d Fix a secondary bug I introduced while fixing the first part of PR14478.
The first half of fixing this bug was actually in r170328, but was
entirely coincidental. It did however get me to realize the nature of
the bug, and adapt the test case to test more interesting behavior. In
turn, that uncovered the rest of the bug which I've fixed here.

This should fix two new asserts that showed up in the vectorize nightly
tester.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170333 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 14:03:01 +00:00
Richard Osborne
35150cbf41 Add instruction encodings / disassembly support for rus instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170330 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 13:50:04 +00:00
Richard Osborne
ff6114e872 Add instruction encodings for ZEXT and SEXT.
Previously these were marked with the wrong format.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170327 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 13:20:37 +00:00
Richard Osborne
1ffe48a84b Add instruction encodings / disassembly support for 2r instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170323 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 12:29:31 +00:00
Richard Osborne
dd78daa199 Add instruction encodings / disassembly support for 0r instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170322 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 12:26:29 +00:00
Craig Topper
b72ae70036 Add rest of BMI/BMI2 instructions to the folding tables as well as popcnt and lzcnt.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170304 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 05:02:29 +00:00
Chandler Carruth
17c84ea594 Fix the first part of PR14478: memset now works.
PR14478 highlights a serious problem in SROA that simply wasn't being
exercised due to a lack of vector input code mixed with C-library
function calls. Part of SROA was written carefully to handle subvector
accesses via memset and memcpy, but the rewriter never grew support for
this. Fixing it required refactoring the subvector access code in other
parts of SROA so it could be shared, and then fixing the splat formation
logic and using subvector insertion (this patch).

The PR isn't quite fixed yet, as memcpy is still broken in the same way.
I'm starting on that series of patches now.

Hopefully this will be enough to bring the bullet benchmark back to life
with the bb-vectorizer enabled, but that may require fixing memcpy as
well.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@170301 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-17 04:07:37 +00:00