llvm-svn: 122073

Reapply r121905 (automatic synthesis of @llvm.sadd.with.overflow) with a fix for a bug that manifested itself
on the DragonEgg self-host bot.  Unfortunately, the testcase is pretty messy and doesn't reduce well due to
interactions with other parts of InstCombine.

llvm-svn: 122072

llvm-svn: 122070

llvm-svn: 122067

llvm-svn: 122066

llvm-svn: 122065

llvm-svn: 122064

llvm-svn: 122054

llvm-svn: 122053

Patch (slightly modified) by Visa Putkinen.

llvm-svn: 122052

llvm-svn: 122050

comparisons formed by comparisons.  For example,
this:

void foo(unsigned x) {
  if (x == 0 || x == 1 || x == 3 || x == 4 || x == 6) 
    bar();
}

compiles into:

_foo:                                   ## @foo
## BB#0:                                ## %entry
	cmpl	$6, %edi
	ja	LBB0_2
## BB#1:                                ## %entry
	movl	%edi, %eax
	movl	$91, %ecx
	btq	%rax, %rcx
	jb	LBB0_3

instead of:

_foo:                                   ## @foo
## BB#0:                                ## %entry
	cmpl	$2, %edi
	jb	LBB0_4
## BB#1:                                ## %switch.early.test
	cmpl	$6, %edi
	ja	LBB0_3
## BB#2:                                ## %switch.early.test
	movl	%edi, %eax
	movl	$88, %ecx
	btq	%rax, %rcx
	jb	LBB0_4

This catches a bunch of cases in GCC, which look like this:

 %804 = load i32* @which_alternative, align 4, !tbaa !0
 %805 = icmp ult i32 %804, 2
 %806 = icmp eq i32 %804, 3
 %or.cond121 = or i1 %805, %806
 %807 = icmp eq i32 %804, 4
 %or.cond124 = or i1 %or.cond121, %807
 br i1 %or.cond124, label %.thread, label %808

turning this into a range comparison.

llvm-svn: 122045

llvm-svn: 122044

IsSymbolRefDifferenceFullyResolved(). For example, we will now fold away
something like:
--
_a:
...
L0:
...
L1:
...
.long (L1 - L0) / 2
--

llvm-svn: 122043

IsSymbolRefDifferenceFullyResolved, it turns out this does change behavior on
enough cases for x86-32 that I would rather wait a bit on it.
 - In practice, we will want to change this eventually because it only means we
   generate less relocations (it also eliminates the need for the horrible
   '.set' hack that Darwin requires in some places).

llvm-svn: 122042

 - Unlike for fixups, we always do the "reliable" thing (not just for x86_64).
 - Since Darwin 'as' would typically reject things that using this will allow,
   we don't need to worry about compatibility.

llvm-svn: 122038

 - Currently just has stub implementations for Mach-O, ELF, and COFF.

llvm-svn: 122037

This is a three-way interval list intersection between a virtual register, a
live interval union, and a loop. It will be used to identify interference-free
loops for live range splitting.

llvm-svn: 122034

-- and remove FIXME asking for the same!

llvm-svn: 122032

assembler.

llvm-svn: 122031

llvm-svn: 122026

superceded and was effectively dead.

llvm-svn: 122024

llvm-svn: 122023

llvm-svn: 122019

Radar 8776599

llvm-svn: 122018

llvm-svn: 122017

llvm-svn: 122016

llvm-svn: 122015

a null endptr argument, because they may write to errno.

This fixes a seflhost miscompile observed on Linux targets when TBAA
was enabled.

llvm-svn: 122014

llvm-svn: 122013

here?

llvm-svn: 122012

in MCAsmLayout).

llvm-svn: 122011

llvm-svn: 122010

llvm-svn: 122009

llvm-svn: 122008

llvm-svn: 122006

llvm-svn: 122005

the MemoryBuffer*, however, it doesn't seem to delete it.

llvm-svn: 122004

llvm-svn: 121995

are correctly marked as used. This removes a hack where the call instructions
marked all possible argument registers as used in the tablegen description.

llvm-svn: 121994