common/idpf: fix AVX-512 pointer copy on 32-bit

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: 5bf87b4 ("net/idpf: add AVX512 data path for single queue model")
Cc: [email protected]

Signed-off-by: Bruce Richardson <[email protected]>
Acked-by: Ian Stokes <[email protected]>

Author: bruce-richardson

drivers/common/idpf/idpf_common_rxtx_avx512.c

@@ -1043,6 +1043,7 @@ idpf_tx_singleq_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]);
@@ -1052,6 +1053,12 @@ idpf_tx_singleq_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;