shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
96,997 Commits 1,713 Branches 298 Tags
Commit Graph

3850 Commits

Author SHA1 Message Date
Chris Lattner
116580a11c generalize the previous check to handle -1 on either side of the 
select, inserting a not to compensate.  Add a missing isZero check
that I lost somehow.

This improves codegen of:

void *func(long count) {
      return new int[count];
}

from:

__Z4funcl:                              ## @_Z4funcl
	movl	$4, %ecx                ## encoding: [0xb9,0x04,0x00,0x00,0x00]
	movq	%rdi, %rax              ## encoding: [0x48,0x89,0xf8]
	mulq	%rcx                    ## encoding: [0x48,0xf7,0xe1]
	testq	%rdx, %rdx              ## encoding: [0x48,0x85,0xd2]
	movq	$-1, %rdi               ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff]
	cmoveq	%rax, %rdi              ## encoding: [0x48,0x0f,0x44,0xf8]
	jmp	__Znam                  ## TAILCALL
                                        ## encoding: [0xeb,A]

to:

__Z4funcl:                              ## @_Z4funcl
	movl	$4, %ecx                ## encoding: [0xb9,0x04,0x00,0x00,0x00]
	movq	%rdi, %rax              ## encoding: [0x48,0x89,0xf8]
	mulq	%rcx                    ## encoding: [0x48,0xf7,0xe1]
	cmpq	$1, %rdx                ## encoding: [0x48,0x83,0xfa,0x01]
	sbbq	%rdi, %rdi              ## encoding: [0x48,0x19,0xff]
	notq	%rdi                    ## encoding: [0x48,0xf7,0xd7]
	orq	%rax, %rdi              ## encoding: [0x48,0x09,0xc7]
	jmp	__Znam                  ## TAILCALL
                                        ## encoding: [0xeb,A]

llvm-svn: 120932
 2010-12-05 02:00:51 +00:00
Chris Lattner
77a11c6174 relax this to handle linux defaulting to -static. 
llvm-svn: 120930
 2010-12-05 01:31:13 +00:00
Chris Lattner
342e6ea5f9 Improve an integer select optimization in two ways: 
1. generalize 
    (select (x == 0), -1, 0) -> (sign_bit (x - 1))
to:
    (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y

2. Handle the identical pattern that happens with !=:
   (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y

cmov is often high latency and can't fold immediates or
memory operands.  For example for (x == 0) ? -1 : 1, before 
we got:

< 	testb	%sil, %sil
< 	movl	$-1, %ecx
< 	movl	$1, %eax
< 	cmovel	%ecx, %eax

now we get:

> 	cmpb	$1, %sil
> 	sbbl	%eax, %eax
> 	orl	$1, %eax

llvm-svn: 120929
 2010-12-05 01:23:24 +00:00
Chris Lattner
0523388d60 merge some tests into select.ll and make them more specific. 
llvm-svn: 120928
 2010-12-05 01:13:58 +00:00
Chris Lattner
b89b6f17da rename test 
llvm-svn: 120927
 2010-12-05 01:02:23 +00:00
Chris Lattner
d4f8c9641a remove two tests that aren't really testing anything. 
llvm-svn: 120926
 2010-12-05 01:02:13 +00:00
Benjamin Kramer
2f489236ab Add patterns for the x86 popcnt instruction. 
- Also adds a new POPCNT subtarget feature that is currently enabled if the target
  supports SSE4.2 (nehalem) or SSE4A (barcelona).

llvm-svn: 120917
 2010-12-04 20:32:23 +00:00
Bob Wilson
ed854baad5 The Thumb tADDrSPi instruction is not valid when the destination is SP. 
Check for that and try narrowing it to tADDspi instead.  Radar 8724703.

llvm-svn: 120892
 2010-12-04 04:40:19 +00:00
Jim Grosbach
ca7eaaafda When using the 'push' mnemonic for Thumb2 stmdb, be explicit when it's the 
32-bit wide version by adding the .w suffix.

llvm-svn: 120838
 2010-12-03 20:33:01 +00:00
Devang Patel
88d794c628 Hide tests, that check .loc, .file in output assembly, from darwin9 buildbot. 
llvm-svn: 120750
 2010-12-02 23:29:58 +00:00
Devang Patel
8cabd938ed Use set directive for StartMinusEndExpr. 
This is a fix for llvm-gcc-i386-darwin9 buildbot failure.

llvm-svn: 120742
 2010-12-02 21:32:30 +00:00
Evan Cheng
5709254bd5 Fix test. 
llvm-svn: 120730
 2010-12-02 20:17:34 +00:00
Evan Cheng
419ea286ee Fix and re-enable tail call optimization of expanded libcalls. 
llvm-svn: 120622
 2010-12-01 22:59:46 +00:00
Owen Anderson
943fb60b1f Add correct encodings for STRD and LDRD, including fixup support. Additionally, update these to unified syntax. 
llvm-svn: 120589
 2010-12-01 19:18:46 +00:00
Evan Cheng
a695abde49 Speculatively disable x86 portion of r120501 to appease the x86_64 buildbot. 
llvm-svn: 120549
 2010-12-01 03:27:20 +00:00
Jason W Kim
29805961d8 ARM/MC/ELF relocation "hello world" for movw/movt. 
Lifted adjustFixupValue() from Darwin for sharing w ELF.
Test added
TODO:
  refactor ELFObjectWriter::RecordRelocation more.
  Possibly share more code with Darwin?
  Lots more relocations...

llvm-svn: 120534
 2010-12-01 02:40:06 +00:00
Evan Cheng
d4b0873c06 Enable sibling call optimization of libcalls which are expanded during 
legalization time. Since at legalization time there is no mapping from
SDNode back to the corresponding LLVM instruction and the return
SDNode is target specific, this requires a target hook to check for
eligibility. Only x86 and ARM support this form of sibcall optimization
right now.
rdar://8707777

llvm-svn: 120501
 2010-11-30 23:55:39 +00:00
Che-Liang Chiou
e9baf13657 ptx: add command-line options for gpu target and ptx version 
llvm-svn: 120423
 2010-11-30 10:14:14 +00:00
Eric Christopher
8e9fbcf0f0 Not all platforms use _<func>. Duh. 
llvm-svn: 120418
 2010-11-30 09:23:54 +00:00
Eric Christopher
fa6657cec0 Rewrite mwait and monitor support and custom lower arguments. 
Fixes PR8573.

llvm-svn: 120404
 2010-11-30 07:20:12 +00:00
Bob Wilson
431ac4ef50 Add support for NEON VLD3-dup instructions. 
The encoding for alignment in VLD4-dup instructions is still a work in progress.

llvm-svn: 120356
 2010-11-30 00:00:35 +00:00
Evan Cheng
9a133f623c Mark Darwin call instructions as using "r7" to prevent the frame-register 
assignment instructions from being moved below / above calls.
rdar://8690640

llvm-svn: 120339
 2010-11-29 22:43:27 +00:00
Benjamin Kramer
a22f0ce1a3 Add missing colon. 
llvm-svn: 120336
 2010-11-29 22:39:38 +00:00
Benjamin Kramer
e6840ef4b3 Fix some broken CHECK lines. 
llvm-svn: 120332
 2010-11-29 22:34:55 +00:00
Bob Wilson
77ab165afe Add support for NEON VLD3-dup instructions. 
llvm-svn: 120312
 2010-11-29 19:35:29 +00:00
Kalle Raiskila
1ff0bfa28f Handle lshr for i128 correctly on SPU also when 
shiftamount > 7.

llvm-svn: 120288
 2010-11-29 14:44:28 +00:00
Kalle Raiskila
dc620afd1e Enable PostRA scheduling for SPU. 
This speeds up selected test cases with up to
5% - no slowdowns observed.

llvm-svn: 120286
 2010-11-29 10:30:25 +00:00
Bob Wilson
2d790df105 Add support for NEON VLD2-dup instructions. 
llvm-svn: 120236
 2010-11-28 06:51:26 +00:00
Rafael Espindola
5d882894d8 Lower TLS_addr32 and TLS_addr64. 
llvm-svn: 120225
 2010-11-27 20:43:02 +00:00
Bob Wilson
c92eea0175 Add NEON VLD1-dup instructions (load 1 element to all lanes). 
llvm-svn: 120194
 2010-11-27 06:35:16 +00:00
Kalle Raiskila
97fc68774c Allow for 'fcmp ogt' in SPU. 
Fix by Visa Putkinen!

llvm-svn: 120090
 2010-11-24 11:42:17 +00:00
Bob Wilson
d7d2cf7842 Recognize sign/zero-extended constant BUILD_VECTORs for VMULL operations. 
We need to check if the individual vector elements are sign/zero-extended
values.  For now this only handles constants values.  Radar 8687140.

llvm-svn: 120034
 2010-11-23 19:38:38 +00:00
Kalle Raiskila
e1b6c273b8 Division by pow-of-2 is not cheap on SPU, do it with 
shifts.

llvm-svn: 120022
 2010-11-23 13:27:59 +00:00
Chris Lattner
adc29567fc filecheckize 
llvm-svn: 119987
 2010-11-23 02:26:52 +00:00
Evan Cheng
eb56dca4fd Fix epilogue codegen to avoid leaving the stack pointer in an invalid 
state. Previously Thumb2 would restore sp from fp like this:
mov sp, r7
sub, sp, #4
If an interrupt is taken after the 'mov' but before the 'sub', callee-saved
registers might be clobbered by the interrupt handler. Instead, try
restoring directly from sp:
add sp, #4
Or, if necessary (with VLA, etc.) use a scratch register to compute sp and
then restore it:
sub.w r4, r7, #8
mov sp, r7
rdar://8465407

llvm-svn: 119977
 2010-11-22 18:12:04 +00:00
Kalle Raiskila
77d11d054c Fix a bug with extractelement on SPU. 
In the attached testcase, the element was
never extracted (missing rotate).

llvm-svn: 119973
 2010-11-22 16:28:26 +00:00
Benjamin Kramer
24656c9583 Implement the "if (X == 6 || X == 4)" -> "if ((X|2) == 6)" optimization. 
This currently only catches the most basic case, a two-case switch, but can be
extended later.

llvm-svn: 119964
 2010-11-22 09:45:38 +00:00
Wesley Peck
f1d3800e65 Implement branch analysis in the MBlaze backend. 
llvm-svn: 119951
 2010-11-21 21:53:36 +00:00
Andrew Trick
cf7fefb25c Removing the useless test that I added recently. It was meant as an example, but not complicated enough to merit another test. 
llvm-svn: 119898
 2010-11-20 07:26:51 +00:00
Dale Johannesen
c9242c577e Prefetch has a MemOperand now. FileCheckize a test. 
This finishes up 8460971.

llvm-svn: 119848
 2010-11-19 21:49:38 +00:00
Mon P Wang
88ff56caa3 Make isScalarToVector to return false if the node is a scalar. This will prevent 
DAGCombine from making an illegal transformation of bitcast of a scalar to a
vector into a scalar_to_vector.

llvm-svn: 119819
 2010-11-19 19:08:12 +00:00
Tanya Lattner
cd68095650 Fix bug in DAGCombiner for ARM that was trying to do a ShiftCombine on illegal types (vector should be split first). 
Added test case.

llvm-svn: 119749
 2010-11-18 22:06:46 +00:00
Duncan Sands
12f3b3b44f The DAGCombiner was threading select over pairs of extending loads even 
if the extension types were not the same.  The result was that if you
fed a select with sext and zext loads, as in the testcase, then it
would get turned into a zext (or sext) of the select, which is wrong
in the cases when it should have been an sext (resp. zext).  Reported
and diagnosed by Sebastien Deldon.

llvm-svn: 119728
 2010-11-18 20:05:18 +00:00
Eric Christopher
b006fc9c07 Rewrite stack callee saved spills and restores to use push/pop instructions. 
Remove movePastCSLoadStoreOps and associated code for simple pointer
increments. Update routines that depended upon other opcodes for save/restore.

Adjust all testcases accordingly.

llvm-svn: 119725
 2010-11-18 19:40:05 +00:00
Rafael Espindola
67c6ab8865 Change CodeGen to use .loc directives. This produces a lot more readable output 
and testing is easier.  A good example is the unknown-location.ll test that
now can just look for ".loc 1 0 0".  We also don't use a DW_LNE_set_address for
every address change anymore.

llvm-svn: 119613
 2010-11-18 02:04:25 +00:00
Dale Johannesen
ed0d840838 Do not throw away alignment when generating the DAG for 
memset; we may need it to decide between MOVAPS and MOVUPS
later.  Adjust a test that was looking for wrong code.
PR 3866 / 8675131.

llvm-svn: 119605
 2010-11-18 01:35:23 +00:00
John Thompson
488051f1a6 Fixed to use input redirection for source - to eliminate .s output. 
llvm-svn: 119599
 2010-11-18 00:50:20 +00:00
John Thompson
ddc7ce548c Bug 8621 fix - pointer cast stripped from inline asm constraint argument. 
llvm-svn: 119590
 2010-11-17 23:58:47 +00:00
Dale Johannesen
0659c8f157 These tests are looking for library function names that 
appear to differ on Linux.  Try to make them pass on Linux.
Would be good for a Linux person to review this.

llvm-svn: 119572
 2010-11-17 21:57:32 +00:00
Bob Wilson
881b45ccdf Change ARMGlobalMerge to keep BSS globals in separate pools. 
This completes the fixes for Radar 8673120.

llvm-svn: 119566
 2010-11-17 21:25:39 +00:00