ligang/vpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Revert "vppinfra: AVX2 blend"

Browse Source 
Causes clang validation failures. The patch did not actually pass validation; unfortunately it received a +1 from fd.io JJB - presumably due to a race condition

This reverts commit 779c865cc6c7af5bb435d8b3465d80685370edb2.

Change-Id: Ica3697f8f90e67d3eae4debc597f27d7d512004a
Signed-off-by: Dave Barach <dbarach@cisco.com>
This commit is contained in:
Dave Barach
2018-07-12 20:56:52 +00:00
parent c82b358048
commit 93c90a5c97
1 changed files with 0 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/vppinfra/vector_avx2.h
View File

@ -165,12 +165,6 @@ u16x16_mask_last (u16x16 v, u8 n_last)
return v & masks[16 - n_last];
}
static_always_inline u32x8
u32x8_blend (u32x8 v0, u32x8 v1, u8 opt)
{
return (u32x8) _mm256_blend_epi32 ((__m256i) v0, (__m256i) v1, opt);
}
#endif /* included_vector_avx2_h */
/*