This obviously helps a lot if the division would be turned into a libcall
(think i64 udiv on i386), but div is also one of the few remaining instructions
on modern CPUs that become more expensive when the bitwidth gets bigger.

This also helps register pressure on i386 when dividing chars, divb needs
two 8-bit parts of a 16 bit register as input where divl uses two registers.

int foo(unsigned char a) { return a/10; }
int bar(unsigned char a, unsigned char b) { return a/b; }

compiles into (x86_64)
_foo:
  imull $205, %edi, %eax
  shrl  $11, %eax
  ret
_bar:
  movzbl        %dil, %eax
  divb  %sil, %al
  movzbl        %al, %eax
  ret

llvm-svn: 130615

This folds away silly stuff like (a&255)/1000 -> 0.

llvm-svn: 130614

llvm-svn: 130613

llvm-svn: 130599

llvm-svn: 130567

Make FastEmit_ri_ try a bit harder to succeed for supported operations; FastEmit_i can fail for non-Thumb2 ARM.  Makes ARMSimplifyAddress work correctly, and reduces the number of fast-isel bailouts on non-Thumb ARM.

llvm-svn: 130560

llvm-svn: 130552

llvm-svn: 130540

Fix a rather obscure crash caused by ARM fast-isel generating code which redefines a register.
rdar://problem/9338332 .

llvm-svn: 130539

for bools, but is a start.

llvm-svn: 130534

llvm-svn: 130528

llvm-svn: 130527

llvm-svn: 130526

currently used, because variables don't get reported as being "defined".

llvm-svn: 130524

MC: Change variable symbols to be recognized as defined, by assigning their sections based on FindAssociatedSection().

llvm-svn: 130523

emmits: .cfi_personality, .cfi_lsda and the moves.

llvm-svn: 130503

Generalization of Nate Begeman's patch!

llvm-svn: 130502

llvm-svn: 130498

Fixes PR9809.

llvm-svn: 130485

llvm-svn: 130462

llvm-svn: 130455

rdar://problem/9338332 .

llvm-svn: 130454

fast-isel sret calls, try 2.  We actually do need to do something on x86-32. rdar://problem/9303592 .

llvm-svn: 130429

llvm-svn: 130418

a nice and tidy:
  %x1 = load i32* %0, align 4
  %1 = icmp eq i32 %x1, 1179403647
  br i1 %1, label %if.then, label %if.end

instead of doing lots of loads and branches.  May the FreeBSD bootloader
long fit in its allocated space.

llvm-svn: 130416

llvm-svn: 130412

This happens when GVN widens loads. Part of PR6627.

llvm-svn: 130405

wider load would allow elimination of subsequent loads, and when the wider
load is still a native integer type.  This eliminates a ton of loads on 
various benchmarks involving struct fields, though it is somewhat hobbled
by clang not being very aggressive about field alignment.

This is yet another step along the way towards resolving PR6627.

llvm-svn: 130390

This fixes clang generated blocks' variables' debug info.
Radar 9279956.

llvm-svn: 130373

llvm-svn: 130360

- selection of bitwise preds (AND, OR, XOR)
- new bitwise.ll test

Patch by Dan Bailey

llvm-svn: 130353

llvm-svn: 130348

llvm-svn: 130345

Modified LinearFunctionTestReplace to push the condition on the dead
list instead of eagerly deleting it. This can cause unnecessary
IV rewrites, which should have no effect on codegen and will not be an
issue once we stop generating canonical IVs.

llvm-svn: 130340

Make the fast-isel code for literal 0.0 a bit shorter/faster, since 0.0 is common.  rdar://problem/9303592 .

llvm-svn: 130338

llvm-svn: 130327

successors) and use inverse depth first search to traverse the BBs. However
that doesn't work when the CFG has infinite loops. Simply do a linear
traversal of all BBs work just fine.

rdar://9344645

llvm-svn: 130324

only check arguments with pointer types. Update the documentation
of IntrReadArgMem reflect this.

While here, add support for TBAA tags on intrinsic calls.

llvm-svn: 130317

Simplify cfg inserts a call to trap when unreachable code is detected. Assign DebugLoc to this new trap instruction.

llvm-svn: 130315

We cannot rely on the <imp-def> operands added by LiveIntervals in all cases as
demonstrated by the test case.

llvm-svn: 130313