[AArch64] Implement vcopy intrinsics.

[James Greenhalgh]

Hi,

This patch adds intrinsics for vcopy<q>_lane<q>_<pfsu><8,16,32,64>.

These are implemented in an optimal way using the vget_lane and vset_lane
intrinsics and a combine pattern.

I've added a testcase and run a full regression run for aarch64-none-elf.

OK?

Thanks,
James

---
gcc/

2013-09-13  James Greenhalgh  <james.greenhalgh@arm.com>

	* config/aarch64/aarch64-simd.md
	(*aarch64_simd_vec_copy_lane<mode>): New.
	(*aarch64_simd_vec_copy_lane_<vswap_width_name><mode>): Likewise.
	* config/aarch64/arm_neon.h
	(vcopy<q>_lane_<pfsu><8,16,32,64>): Remove asm implementations.
	(vcopy<q>_lane<q>_<pfsu><8,16,32,64>): Implement optimally.

gcc/testsuite

2013-09-13  James Greenhalgh  <james.greenhalgh@arm.com>

	* gcc.target/aarch64/vect_copy_lane_1.c: New.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0001-AArch64-Implement-vcopy-intrinsics.patch
Type: text/x-patch
Size: 30734 bytes
Desc: not available
URL: <http://gcc.gnu.org/pipermail/gcc-patches/attachments/20130913/19e0d36d/attachment.bin>