llvm-svn: 125025

llvm-svn: 125023

The vld1-lane, vld1-dup and vst1-lane instructions do not yet support using
post-increment versions, but all the rest of the NEON load/store instructions
should be handled now.

llvm-svn: 125014

These operations are expanded to pairs of loads or stores, and the first one
uses the address register update to produce the address for the second one.
So far, the second load/store has also updated the address register, just
for convenience, since that output has never been used.  In anticipation of
actually supporting post-increment updates for these operations, this changes
the non-updating operations to use a non-updating load/store for the second
instruction.

llvm-svn: 125013

llvm-svn: 125012

llvm-svn: 125011

until the instructions are emitted or printed.

llvm-svn: 125010

llvm-svn: 125009

Unified EmitTextAttribute for both Asm and Obj emission (.cpu only)
Added necessary cortex-A8 related attrs for codegen compat tests.

llvm-svn: 124995

llvm-svn: 124989

Target/X86: Tweak allocating shadow area (aka home) on Win64. It must be enough for caller to allocate one.

llvm-svn: 124949

llvm-svn: 124948

llvm-svn: 124947

llvm-svn: 124946

[AVX] Revert 124910 until clients are ready.

llvm-svn: 124912

[AVX] Add some utilities to insert and extract 128-bit subvectors.
This allows us to easily support 256-bit operations that don't have
native 256-bit support.  This applies to integer operations, certain
types of shuffles and various othher things.

llvm-svn: 124910

Teach ARM/MC/ELF to handle R_ARM_JUMP24 relocation type for conditional jumps.
(yes, this is different from R_ARM_CALL)

- Adds a new method getARMBranchTargetOpValue() which handles the
  necessary distinction between the conditional and unconditional br/bl
  needed for ARM/ELF

At least for ARM mode, the needed fixup for conditional versus unconditional
br/bl is identical, but the ARM docs and existing ARM tools expect this
reloc type...

Added a few FIXME's for future naming fixups in ARMInstrInfo.td

llvm-svn: 124895

custom conversion functions).

llvm-svn: 124872

[AVX] Support VSINSERTF128 with more patterns and appropriate
infrastructure.  This makes lowering 256-bit vectors to 128-bit
vectors simple when 256-bit vector support is not available.

llvm-svn: 124868

llvm-svn: 124819

[AVX] VEXTRACTF128 support.  This commit includes patterns for
matching EXTRACT_SUBVECTOR to VEXTRACTF128 along with support routines
to examine and translate index values.  VINSERTF128 comes next.  With
these two in place we can begin supporting more AVX operations as
INSERT/EXTRACT can be used as a fallback when 256-bit support is not
available.

llvm-svn: 124797

llvm-svn: 124794

Reversing the operands allows us to fold, but doesn't force us to. Also, at
this point the DAG is still being optimized, so the check for hasOneUse is not
very precise.

llvm-svn: 124773

llvm-svn: 124725

This makes the job of the later optzn passes easier, allowing the vast amount of
icmp transforms to chew on it.

We transform 840 switches in gcc.c, leading to a 16k byte shrink of the resulting
binary on i386-linux.

The testcase from README.txt now compiles into
  decl  %edi
  cmpl  $3, %edi
  sbbl  %eax, %eax
  andl  $1, %eax
  ret

llvm-svn: 124724

llvm-svn: 124722

prefix would be misinterpreted in some cases on 32-bit
x86 platforms.  Thanks to Olivier Meurant for identifying
the bug.

llvm-svn: 124709

the load, then it may be legal to transform the load and store to integer
load and store of the same width.

This is done if the target specified the transformation as profitable. e.g.
On arm, this can transform:
vldr.32 s0, []
vstr.32 s0, []

to

ldr r12, []
str r12, []

rdar://8944252

llvm-svn: 124708

This is completely untested but pretty straightforward, so hopefully I
got it right.

llvm-svn: 124694

Patch by Brian G. Lucas!

llvm-svn: 124679

llvm-svn: 124652

llvm-svn: 124639

llvm-svn: 124611

Fix vector sign extend to put the source and destination types in the
correct places.

llvm-svn: 124601

llvm-svn: 124599

llvm-svn: 124570

Teach DAGCombine to fold fold (sra (trunc (sr x, c1)), c2) -> (trunc (sra x, c1+c2) when c1 equals the amount of bits that are truncated off.

This happens all the time when a smul is promoted to a larger type.

On x86-64 we now compile "int test(int x) { return x/10; }" into
  movslq  %edi, %rax
  imulq $1717986919, %rax, %rax
  movq  %rax, %rcx
  shrq  $63, %rcx
  sarq  $34, %rax <- used to be "shrq $32, %rax; sarl $2, %eax"
  addl  %ecx, %eax

This fires 96 times in gcc.c on x86-64.

llvm-svn: 124559

Patch by Jyun-Yan You.

llvm-svn: 124492

llvm-svn: 124458

only .syntax unified is supported.

llvm-svn: 124454