vppinfra: correct intrinsic called by u16x16_from_u8x16
u16x16_from_u8x16() and i16x16_from_i8x16() call intrisics
_mm256_cvtepu8_epi64 and _mm256_cvtepi8_epi64. But they are not seems
doing the right data conversion from the name of the wrappers.
The correct intrinsics been called should be _mm256_cvtepu8_epi16
and _mm256_cvtepi8_epi16.
Type: fix
Change-Id: Id71de6ae1a266a370f11c33a46684202be766c43
Signed-off-by: Lijian Zhang <Lijian.Zhang@arm.com>
diff --git a/src/vppinfra/vector_avx2.h b/src/vppinfra/vector_avx2.h
index 4cd2dc1..6975227 100644
--- a/src/vppinfra/vector_avx2.h
+++ b/src/vppinfra/vector_avx2.h
@@ -120,13 +120,13 @@
_(u16x8, u32x8, epu16_epi32)
_(u16x8, u64x4, epu16_epi64)
_(u32x4, u64x4, epu32_epi64)
-_(u8x16, u16x16, epu8_epi64)
+_ (u8x16, u16x16, epu8_epi16)
_(u8x16, u32x8, epu8_epi32)
_(u8x16, u64x4, epu8_epi64)
_(i16x8, i32x8, epi16_epi32)
_(i16x8, i64x4, epi16_epi64)
_(i32x4, i64x4, epi32_epi64)
-_(i8x16, i16x16, epi8_epi64)
+_ (i8x16, i16x16, epi8_epi16)
_(i8x16, i32x8, epi8_epi32)
_(i8x16, i64x4, epi8_epi64)
#undef _