On 9/2/22 2:18 AM, pbhagavat...@marvell.com wrote:
From: Pavan Nikhilesh <pbhagavat...@marvell.com>
Fix port group mask generation in altivec, vec_any_eq returns
0 or 1 while port_groupx4 expects comparison mask result.
Fixes: 2193b7467f7a ("examples/l3fwd: optimize packet processing on powerpc")
Cc: sta...@dpdk.org
Signed-off-by: Pavan Nikhilesh <pbhagavat...@marvell.com>
---
v2 Changes:
- Fix PPC, RISC-V, aarch32 compilation.
examples/common/altivec/port_group.h | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/examples/common/altivec/port_group.h
b/examples/common/altivec/port_group.h
index 5e209b02fa..592ef80b7f 100644
--- a/examples/common/altivec/port_group.h
+++ b/examples/common/altivec/port_group.h
@@ -26,12 +26,19 @@ port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp,
uint16_t u16[FWDSTEP + 1];
uint64_t u64;
} *pnum = (void *)pn;
+ union u_vec {
+ __vector unsigned short v_us;
+ unsigned short s[8];
+ };
+ union u_vec res;
int32_t v;
- v = vec_any_eq(dp1, dp2);
-
+ dp1 = (__vector unsigned short)vec_cmpeq(dp1, dp2);
Altivec vec_cmpeq() is similar to Intel _mm_cmpeq_*(), so this looks
right to me.
+ res.v_us = dp1;
+ v = (res.s[0] & 0x1) | (res.s[1] & 0x2) | (res.s[2] & 0x4) |
+ (res.s[3] & 0x8);
This can be vectorized too. The Intel _mm_unpacklo_epi16() intrinsic
can be replaced with the following Altivec code:
extern __inline __m128i __attribute__((__gnu_inline__,
__always_inline__, __artificial__))
_mm_unpacklo_epi16 (__m128i __A, __m128i __B)
{
return (__m128i) vec_mergeh ((__v8hi)__A, (__v8hi)__B);
}
The Intel _mm_movemask_ps() intrinsic can be replaced with the following
Altivec implementation:
/* Creates a 4-bit mask from the most significant bits of the SPFP
values. */
extern __inline int __attribute__((__gnu_inline__, __always_inline__,
__artificial__))
_mm_movemask_ps (__m128 __A)
{
__vector unsigned long long result;
static const __vector unsigned int perm_mask =
{
#ifdef __LITTLE_ENDIAN__
0x00204060, 0x80808080, 0x80808080, 0x80808080
#else
0x80808080, 0x80808080, 0x80808080, 0x00204060
#endif
};
result = ((__vector unsigned long long)
vec_vbpermq ((__vector unsigned char) __A,
(__vector unsigned char) perm_mask));
#ifdef __LITTLE_ENDIAN__
return result[1];
#else
return result[0];
#endif
}
Dave
