Commit Graph

2026 Commits

Author SHA1 Message Date
Elena Demikhovsky
8f40f7b867 Optimization of shuffle node that can fit to the register form of VBROADCAST instruction on AVX2.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159504 91177308-0d34-0410-b5e6-96231b3b80d8
2012-07-01 06:12:26 +00:00
Rafael Espindola
94e3b388e5 In the initial exec mode we always do a load to find the address of a variable.
Before this patch in pic 32 bit code we would add the global base register
and not load from that address. This is a really old bug, but before the
introduction of the tls attributes we would never select initial exec for
pic code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159409 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-29 04:22:35 +00:00
Elena Demikhovsky
fcb0946833 Removed unused variable
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159197 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-26 10:50:07 +00:00
Bill Wendling
a44489d5b5 Rename to match other X86_64* names.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159196 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-26 10:05:06 +00:00
Elena Demikhovsky
1596373671 Shuffle optimization for AVX/AVX2.
The current patch optimizes frequently used shuffle patterns and gives these instruction sequence reduction.
Before:
      vshufps $-35, %xmm1, %xmm0, %xmm2 ## xmm2 = xmm0[1,3],xmm1[1,3]
       vpermilps       $-40, %xmm2, %xmm2 ## xmm2 = xmm2[0,2,1,3]
       vextractf128    $1, %ymm1, %xmm1
       vextractf128    $1, %ymm0, %xmm0
       vshufps $-35, %xmm1, %xmm0, %xmm0 ## xmm0 = xmm0[1,3],xmm1[1,3]
       vpermilps       $-40, %xmm0, %xmm0 ## xmm0 = xmm0[0,2,1,3]
       vinsertf128     $1, %xmm0, %ymm2, %ymm0
After:
      vshufps $13, %ymm0, %ymm1, %ymm1 ## ymm1 = ymm1[1,3],ymm0[0,0],ymm1[5,7],ymm0[4,4]
      vshufps $13, %ymm0, %ymm0, %ymm0 ## ymm0 = ymm0[1,3,0,0,5,7,4,4]
      vunpcklps       %ymm1, %ymm0, %ymm0 ## ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159188 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-26 08:04:10 +00:00
Eli Friedman
52d418df5d Make some ugly hacks for inline asm operands which name a specific register a bit more thorough. PR13196.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159176 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-25 23:42:33 +00:00
Jakob Stoklund Olesen
82d58b147f %RCX is not a function live-out in eh.return functions.
The function live-out registers must be live at all function returns,
and %RCX is only used by eh.return. When a function also has a normal
return, only %RAX holds a return value.

This fixes PR13188.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159116 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-24 15:53:01 +00:00
Pete Cooper
6e2db65266 Remove code i'd been testing with but didn't mean to commit. Oops
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159094 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-24 00:08:36 +00:00
Pete Cooper
b49998d76c DAG legalisation can now handle illegal fma vector types by scalarisation
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159092 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-24 00:05:44 +00:00
Rafael Espindola
ce0a5cda8a Handle aliases to tls variables in all architectures, not just x86.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159058 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-23 00:30:03 +00:00
Craig Topper
703c38bf58 Don't insert 128-bit UNDEF into 256-bit vectors. Just keep the 256-bit vector. Original patch by Elena Demikhovsky. Tweaked by me to allow possibility of covering more cases.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158792 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-20 05:39:26 +00:00
Rafael Espindola
d6b43a317e Move the support for using .init_array from ARM to the generic
TargetLoweringObjectFileELF. Use this to support it on X86. Unlike ARM,
on X86 it is not easy to find out if .init_array should be used or not, so
the decision is made via TargetOptions and defaults to off.

Add a command line option to llc that enables it.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158692 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-19 00:48:28 +00:00
Craig Topper
2a5dc43bd9 Use XOP vpcom intrinsics in patterns instead of a target specific SDNode type. Remove the custom lowering code that selected the SDNode type.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158279 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-09 17:02:24 +00:00
Craig Topper
c29106b36f Replace XOP vpcom intrinsics with fewer intrinsics that take the immediate as an argument.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158278 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-09 16:46:13 +00:00
Manman Ren
45d53b866e Enable optimization for integer ABS on X86 if Subtarget has CMOV.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158220 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-08 18:58:26 +00:00
Manman Ren
9236362a64 X86: optimize generated code for integer ABS
This patch will generate the following for integer ABS:
      movl    %edi, %eax
      negl    %eax
      cmovll  %edi, %eax
INSTEAD OF
      movl    %edi, %ecx
      sarl    $31, %ecx
      leal    (%rdi,%rcx), %eax
      xorl    %ecx, %eax

There exists a target-independent DAG combine for integer ABS, which converts
integer ABS to sar+add+xor. For X86, we match this pattern back to neg+cmov. 
This is implemented in PerformXorCombine.

rdar://10695237


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158175 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-07 22:39:10 +00:00
Nadav Rotem
bdcae38256 Do not optimize the used bits of the x86 vselect condition operand, when the condition operand is a vector of 1-bit predicates.
This may happen on MIC devices.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158168 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-07 20:53:48 +00:00
Manman Ren
e6fc9d40b3 PR13046: we can't replace usage of SUB with CMP in the lowering phase.
It will cause assertion failure later on.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158160 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-07 19:27:33 +00:00
Manman Ren
87253c2ebd X86: replace SUB with CMP if possible
This patch will optimize the following
    movq    %rdi, %rax
    subq    %rsi, %rax
    cmovsq  %rsi, %rdi
    movq    %rdi, %rax
to
    cmpq    %rsi, %rdi
    cmovsq  %rsi, %rdi
    movq    %rdi, %rax

Perform this optimization if the actual result of SUB is not used.

rdar: 11540023


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158126 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-07 00:42:47 +00:00
Benjamin Kramer
d9b0b02561 Fix typos found by http://github.com/lyda/misspell-check
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157885 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-02 10:20:22 +00:00
Hans Wennborg
f0234fcbc9 Implement the local-dynamic TLS model for x86 (PR3985)
This implements codegen support for accesses to thread-local variables
using the local-dynamic model, and adds a clean-up pass so that the base
address for the TLS block can be re-used between local-dynamic access on
an execution path.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157818 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-01 16:27:21 +00:00
Jakob Stoklund Olesen
ee66b417ef Add support for return value promotion in X86 calling conventions.
Patch by Yiannis Tsiouris!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157757 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-31 17:28:20 +00:00
Justin Holewinski
d2ea0e10cb Change interface for TargetLowering::LowerCallTo and TargetLowering::LowerCall
to pass around a struct instead of a large set of individual values.  This
cleans up the interface and allows more information to be added to the struct
for future targets without requiring changes to each and every target.

NV_CONTRIB

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157479 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-25 16:35:28 +00:00
Craig Topper
85b9e56bac Fix constant used for pshufb mask when lowering v16i8 shuffles. Bug introduced in r157043. Fixes PR12908.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157236 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-22 06:09:38 +00:00
Craig Topper
8ae97baef2 Allow 256-bit shuffles to still be split even if only half of the shuffle comes from two 128-bit pieces.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157175 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-21 06:40:16 +00:00
Nadav Rotem
87d35e8c71 On Haswell, perfer storing YMM registers using a single instruction.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157129 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-19 20:30:08 +00:00
Nadav Rotem
4fc8a5de44 Add support for additional in-reg vbroadcast patterns
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157127 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-19 19:57:37 +00:00
Craig Topper
be97ae9e89 Simplify code a bit. No functional change intended.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157044 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-18 07:07:36 +00:00
Craig Topper
b82b5abf78 Simplify handling of v16i8 shuffles and fix a missed optimization.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@157043 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-18 06:42:06 +00:00
Hans Wennborg
228756c744 Implement initial-exec TLS model for 32-bit PIC x86
This fixes a TODO from 2007 :) Previously, LLVM would emit the wrong
code here (see the update to test/CodeGen/X86/tls-pie.ll).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156611 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-11 10:11:01 +00:00
Nadav Rotem
b88e8dd31d Fix merge-typo and cleanup
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156541 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-10 12:50:02 +00:00
Nadav Rotem
b210651654 AVX2: Add an additional broadcast idiom.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156540 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-10 12:39:13 +00:00
Nadav Rotem
5fc2187a02 Generate AVX/AVX2 shuffles even when there is a memory op somewhere else in the program.
Starting r155461 we are able to select patterns for vbroadcast even when the load op is used by other users.

Fix PR11900.




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156539 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-10 12:22:05 +00:00
Chad Rosier
42726835e3 Fix a regression from r147481. This combine should only happen if there is a
single use.
rdar://11360370


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156316 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-07 18:47:44 +00:00
Manman Ren
ed57984483 X86: optimization for -(x != 0)
This patch will optimize -(x != 0) on X86
FROM 
cmpl	$0x01,%edi
sbbl	%eax,%eax
notl	%eax
TO
negl %edi
sbbl %eax %eax

In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td:
def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>;

rdar: 10961709


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156312 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-07 18:06:23 +00:00
Craig Topper
d978c54e60 Use MVT instead of EVT as the argument to all the shuffle decode functions. Simplify some of the decode functions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156268 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-06 19:46:21 +00:00
Craig Topper
bdcbcb3ae7 Add VPERMQ/VPERMPD to the list of target specific shuffles that can be looked through for DAG combine purposes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156266 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-06 18:54:26 +00:00
Benjamin Kramer
aaf723dd2b Add a new target hook "predictableSelectIsExpensive".
This will be used to determine whether it's profitable to turn a select into a
branch when the branch is likely to be predicted.

Currently enabled for everything but Atom on X86 and Cortex-A9 devices on ARM.

I'm not entirely happy with the name of this flag, suggestions welcome ;)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156233 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-05 12:49:14 +00:00
Craig Topper
31a207a3b7 Fix some loops to match coding standards. No functional change intended.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156159 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-04 06:39:13 +00:00
Craig Topper
6643d9c180 Fix up some spacing. No functional change.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156158 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-04 06:18:33 +00:00
Craig Topper
5da8a80377 Simplify broadcast lowering code. No functional change intended.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156157 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-04 05:49:51 +00:00
Craig Topper
f3640d7ec1 Allow v16i16 and v32i8 shuffles to be rewritten as narrower shuffles.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156156 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-04 04:44:49 +00:00
Craig Topper
11ac1f81a8 Simplify shuffle narrowing code a bit. No functional change intended.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156154 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-04 04:08:44 +00:00
Craig Topper
b607264550 Use 'unsigned' instead of 'int' in a few places dealing with counts of vector elements.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156060 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-03 07:26:59 +00:00
Craig Topper
6b28d356c5 Fix 256-bit vpshuflw and vpshufhw immediate encoding to handle undefs in the lower half correctly. Missed in r155982.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156059 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-03 07:12:59 +00:00
Preston Gurd
c0f0a93936 For Intel Atom, use ILP scheduling always, instead of ILP for 64 bit
and Hybrid for 32 bit, since benchmarks show ILP scheduling is better
most of the time.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156028 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-02 22:02:02 +00:00
Manman Ren
e2849851b2 Revert r155853
The commit is intended to fix rdar://10961709.
But it is the root cause of PR12720.
Revert it for now.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155992 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-02 15:24:32 +00:00
Craig Topper
a9a568a79d Add support for selecting AVX2 vpshuflw and vpshufhw. Add decoding support for AsmPrinter.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155982 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-02 08:03:44 +00:00
Manman Ren
769ea2f93f X86: optimization for max-like struct
This patch will optimize the following cases on X86
(a > b) ? (a-b) : 0
(a >= b) ? (a-b) : 0
(b < a) ? (a-b) : 0
(b <= a) ? (a-b) : 0

FROM
movl    %edi, %ecx
subl    %esi, %ecx
cmpl    %edi, %esi
movl    $0, %eax
cmovll  %ecx, %eax
TO
xorl    %eax, %eax
subl    %esi, %edi
cmovll  %eax, %edi
movl    %edi, %eax

rdar: 10734411


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155919 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-01 17:16:15 +00:00
Manman Ren
16a76519a5 X86: optimization for -(x != 0)
This patch will optimize -(x != 0) on X86
FROM 
cmpl	$0x01,%edi
sbbl	%eax,%eax
notl	%eax
TO
negl %edi
sbbl %eax %eax


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155853 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-30 22:51:25 +00:00