[PATCH] AArch64: Implement big endian bit-conversion for NEON types

[Christian Pirker]

Hi All,

This is the first patch (others to follow) based on Tim Northovers suggestion (see D3305, Tim's comment from April 13, 2014: item 2) to allow correct conversion between integer and vector data in big endian mode (data format differs wrt. endian mode).
It's an alternative approach to D2284 and enables llvm utilizing both LDR/STR and LDn/STn instructions in big endian mode.
The patch covers the conversion between floating point and vector types, and the function argument passing of vector types providing compatibility to the ARM ABI.
Big endian bit-conversions are implemented using REV64 and EXT instructions.
In addition this patch is a substitute for D3306.

Thanks,
Christian


http://reviews.llvm.org/D3424

Files:
  lib/Target/AArch64/AArch64InstrNEON.td
  test/CodeGen/AArch64/neon-bitconv.ll
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D3424.1.patch
Type: text/x-patch
Size: 24926 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20140418/45b125f3/attachment.bin>