ref: bc30e6e39c8bde9a31e1c314e6d1003ff47f2f7f
parent: bc7c99e7eca8d30d005e7d5db8b0aada2459fb15
author: Raphael Kubo da Costa <raphael.kubo.da.costa@intel.com>
date: Fri Jul 13 10:29:09 EDT 2018
vpx_sum_squares_2d_i16_neon(): Make |s2| a uint64x1_t.
This fixes the build with at least GCC 7.3, where it was previously failing
with:
sum_squares_neon.c: In function 'vpx_sum_squares_2d_i16_neon':
sum_squares_neon.c: note: use -flax-vector-conversions to permit conversions between vectors with differing element types or numbers of subparts
s2 = vpaddl_u32(s1);
^~
sum_squares_neon.c: incompatible types when assigning to type 'int64x1_t' from type 'uint64x1_t'
s2 = vpaddl_u32(s1);
^
sum_squares_neon.c: incompatible types when assigning to type 'int64x1_t' from type 'uint64x1_t'
s2 = vadd_u64(vget_low_u64(s1), vget_high_u64(s1));
^
sum_squares_neon.c: incompatible type for argument 1 of 'vget_lane_u64'
return vget_lane_u64(s2, 0);
^~
The generated assembly was verified to remain identical with both GCC and
LLVM.
Bug: chromium:819249
Change-Id: I2778428ee1fee0a674d0d4910347c2a717de21ac
--- a/vpx_dsp/arm/sum_squares_neon.c
+++ b/vpx_dsp/arm/sum_squares_neon.c
@@ -14,7 +14,7 @@
#include "./vpx_dsp_rtcd.h"
uint64_t vpx_sum_squares_2d_i16_neon(const int16_t *src, int stride, int size) {- int64x1_t s2;
+ uint64x1_t s2;
if (size == 4) {int16x4_t s[4];
--
⑨