llvm-svn: 159105

llvm-svn: 159090

Make CVTDQ2PS instruction use SSE2 predicate instead of SSE1. No functional change because there are no patterns in the instructions. Also fix a typo in a comment.

llvm-svn: 159087

Move CVTPD2DQ to use SSE2 predicate instead of SSE3. Move DQ2PD and PD2DQ to the SSE2 section of the file.

llvm-svn: 159086

llvm-svn: 159075

Remove intrinsic specific instructions for 128-bit (V)CVTDQ2PD. Replace with intrinsic patterns. Mem forms omitted because the load size is only 64-bits.

llvm-svn: 159070

llvm-svn: 158797

llvm-svn: 158795

llvm-svn: 158603

llvm-svn: 158049

It was renamed in gcc/gas a while ago and causes all kinds of
confusion because it was named differently in llvm and clang.

llvm-svn: 157745

llvm-svn: 157731

Add intrinsics, code gen, assembler and disassembler support for the SSE4a extrq and insertq instructions.

This required light surgery on the assembler and disassembler
because the instructions use an uncommon encoding. They are
the only two instructions in x86 that use register operands
and two immediates.

llvm-svn: 157634

llvm-svn: 156375

llvm-svn: 156287

llvm-svn: 156281

Remove the v2f64 patterns because it does not match any vbroadcast
instruction.

llvm-svn: 155461

using the pattern (vbroadcast (i32load src)). In some cases, after we generate
this pattern new users are added to the load node, which prevent the selection
of the blend pattern. This commit provides fallback patterns which perform
in-vector broadcast (using in-vector vbroadcast in AVX2 and pshufd on AVX1).

llvm-svn: 155437

llvm-svn: 155309

llvm-svn: 154801

Flip the arguments when converting vpermd/vpermps intrinsics into instructions. The intrinsic has the mask as the last operand, but the instruction has it as the second.

llvm-svn: 154797

llvm-svn: 154782

llvm-svn: 154778

Use non-vex instructions for SSE4.

llvm-svn: 154770

llvm-svn: 154761

llvm-svn: 154580

Original message:
Modify the code that lowers shuffles to blends from using blendvXX to vblendXX.
blendV uses a register for the selection while Vblend uses an immediate.
On sandybridge they still have the same latency and execute on the same execution ports.

llvm-svn: 154483

llvm-svn: 154425

blendv uses a register for the selection while vblend uses an immediate.
On sandybridge they still have the same latency and execute on the same execution ports.

llvm-svn: 154396

Turn avx2 vinserti128 intrinsic calls into INSERT_SUBVECTOR DAG nodes and remove patterns for selecting the intrinsic. Similar was already done for avx1.

llvm-svn: 154272

Move vinsertf128 patterns near the instruction definitions. Add AddedComplexity to AVX2 vextracti128 patterns to give them priority over the integer versions of vextractf128 patterns.

llvm-svn: 154268

llvm-svn: 153935

vextractf128 with 128-bit mem dest.

Combines

	vextractf128 $0, %ymm0, %xmm0
	vmovaps %xmm0, (%rdi)

to

    vextractf128 $0, %ymm0, (%rdi)

rdar://11082570

llvm-svn: 153139

precedence over the VINSERTF128 avx1 patterns.

llvm-svn: 153114

llvm-svn: 153105

whitespace from test case.  No functional change intended.

llvm-svn: 153103

This results in things such as

	vmovups	16(%rdi), %xmm0
	vinsertf128	$1, %xmm0, %ymm0, %ymm0

to be combined to

    vinsertf128	$1, 16(%rdi), %ymm0, %ymm0

rdar://11076953

llvm-svn: 153092

This results in things such as

	vmovaps	-96(%rbx), %xmm1
	vinsertf128	$1, %xmm1, %ymm0, %ymm0

to be combined to
         
	vinsertf128	$1, -96(%rbx), %ymm0, %ymm0

rdar://10643481

llvm-svn: 152762

llvm-svn: 152507

Original commit message from r147481:
DAGCombine for transforming 128->256 casts into a vmovaps, rather
then a vxorps + vinsertf128 pair if the original vector came from a load.

Fix:
Unaligned loads need to generate a vmovups.
rdar://10974078

llvm-svn: 152366