[PATCH 22.11] net/idpf: fix AVX-512 pointer copy on 32-bit
Bruce Richardson
bruce.richardson at intel.com
Thu Oct 24 11:48:33 CEST 2024
[ upstream commit d16364e3bdbfd9e07a487bf776a829c565337e3c ]
The size of a pointer on 32-bit is only 4 rather than 8 bytes, so
copying 32 pointers only requires half the number of AVX-512 load store
operations.
Fixes: 5bf87b45b2c8 ("net/idpf: add AVX512 data path for single queue model")
Signed-off-by: Bruce Richardson <bruce.richardson at intel.com>
Acked-by: Ian Stokes <ian.stokes at intel.com>
---
drivers/net/idpf/idpf_rxtx_vec_avx512.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/net/idpf/idpf_rxtx_vec_avx512.c b/drivers/net/idpf/idpf_rxtx_vec_avx512.c
index f31582f5fd..29f9624a9d 100644
--- a/drivers/net/idpf/idpf_rxtx_vec_avx512.c
+++ b/drivers/net/idpf/idpf_rxtx_vec_avx512.c
@@ -587,6 +587,7 @@ idpf_tx_free_bufs_avx512(struct idpf_tx_queue *txq)
uint32_t copied = 0;
/* n is multiple of 32 */
while (copied < n) {
+#ifdef RTE_ARCH_64
const __m512i a = _mm512_loadu_si512(&txep[copied]);
const __m512i b = _mm512_loadu_si512(&txep[copied + 8]);
const __m512i c = _mm512_loadu_si512(&txep[copied + 16]);
@@ -596,6 +597,12 @@ idpf_tx_free_bufs_avx512(struct idpf_tx_queue *txq)
_mm512_storeu_si512(&cache_objs[copied + 8], b);
_mm512_storeu_si512(&cache_objs[copied + 16], c);
_mm512_storeu_si512(&cache_objs[copied + 24], d);
+#else
+ const __m512i a = _mm512_loadu_si512(&txep[copied]);
+ const __m512i b = _mm512_loadu_si512(&txep[copied + 16]);
+ _mm512_storeu_si512(&cache_objs[copied], a);
+ _mm512_storeu_si512(&cache_objs[copied + 16], b);
+#endif
copied += 32;
}
cache->len += n;
--
2.43.0
More information about the stable
mailing list