[AArch64] Support float->int conversions in vector registers.
James Greenhalgh
james.greenhalgh@arm.com
Wed May 1 15:09:00 GMT 2013
Hi,
The fcvt instructions also have forms which leave their integer
result as a scalar in the SIMD register set.
This patch adds those alternatives for the lceil family
of standard patterns.
Regression tested on aarch64-none-elf with no regressions.
Thanks,
James
---
2013-05-01 James Greenhalgh <james.greenhalgh@arm.com>
gcc/
* config/aarch64/aarch64.md
(l<fcvt_pattern><su_optab><GPF:mode><GPI:mode>2): Add vector
register to vector register alternative.
(fix_trunc<GPF:mode><GPI:mode>2): Likewise.
(fixuns_trunc<GPF:mode><GPI:mode>2): Likewise.
gcc/testsuite/
* gcc.target/aarch64/scalar-fcvt.c: New.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0001-AArch64-Support-float-int-conversions-in-vector-regi.patch
Type: text/x-patch
Size: 7375 bytes
Desc: not available
URL: <http://gcc.gnu.org/pipermail/gcc-patches/attachments/20130501/37c8ac1c/attachment.bin>
More information about the Gcc-patches
mailing list