X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Fhash%2Frte_thash_x86_gfni.h;h=657b1862c37f17baedd0c47f0b9106d5d0b12294;hb=6de0ea50e9b9d0129079689be1e335d1ffbf17d3;hp=53486b67348b05e697b68ddcd32e31fe9855cd25;hpb=4fd8c4cb0de198b405d6af4a31742d0982250bde;p=dpdk.git

diff --git a/lib/hash/rte_thash_x86_gfni.h b/lib/hash/rte_thash_x86_gfni.h
index 53486b6734..657b1862c3 100644
--- a/lib/hash/rte_thash_x86_gfni.h
+++ b/lib/hash/rte_thash_x86_gfni.h
@@ -18,7 +18,7 @@
 extern "C" {
 #endif
 
-#ifdef __GFNI__
+#if defined(__GFNI__) && defined(__AVX512F__)
 #define RTE_THASH_GFNI_DEFINED
 
 #define RTE_THASH_FIRST_ITER_MSK	0x0f0f0f0f0f0e0c08
@@ -33,7 +33,6 @@ __rte_thash_xor_reduce(__m512i xor_acc, uint32_t *val_1, uint32_t *val_2)
 {
 	__m256i tmp_256_1, tmp_256_2;
 	__m128i tmp128_1, tmp128_2;
-	uint64_t tmp_1, tmp_2;
 
 	tmp_256_1 = _mm512_castsi512_si256(xor_acc);
 	tmp_256_2 = _mm512_extracti32x8_epi32(xor_acc, 1);
@@ -43,12 +42,24 @@ __rte_thash_xor_reduce(__m512i xor_acc, uint32_t *val_1, uint32_t *val_2)
 	tmp128_2 = _mm256_extracti32x4_epi32(tmp_256_1, 1);
 	tmp128_1 = _mm_xor_si128(tmp128_1, tmp128_2);
 
+#ifdef RTE_ARCH_X86_64
+	uint64_t tmp_1, tmp_2;
 	tmp_1 = _mm_extract_epi64(tmp128_1, 0);
 	tmp_2 = _mm_extract_epi64(tmp128_1, 1);
 	tmp_1 ^= tmp_2;
 
 	*val_1 = (uint32_t)tmp_1;
 	*val_2 = (uint32_t)(tmp_1 >> 32);
+#else
+	uint32_t tmp_1, tmp_2;
+	tmp_1 = _mm_extract_epi32(tmp128_1, 0);
+	tmp_2 = _mm_extract_epi32(tmp128_1, 1);
+	tmp_1 ^= _mm_extract_epi32(tmp128_1, 2);
+	tmp_2 ^= _mm_extract_epi32(tmp128_1, 3);
+
+	*val_1 = tmp_1;
+	*val_2 = tmp_2;
+#endif
 }
 
 __rte_internal
@@ -56,23 +67,22 @@ static inline __m512i
 __rte_thash_gfni(const uint64_t *mtrx, const uint8_t *tuple,
 	const uint8_t *secondary_tuple, int len)
 {
-	__m512i permute_idx = _mm512_set_epi8(7, 6, 5, 4, 7, 6, 5, 4,
-						6, 5, 4, 3, 6, 5, 4, 3,
-						5, 4, 3, 2, 5, 4, 3, 2,
-						4, 3, 2, 1, 4, 3, 2, 1,
-						3, 2, 1, 0, 3, 2, 1, 0,
-						2, 1, 0, -1, 2, 1, 0, -1,
-						1, 0, -1, -2, 1, 0, -1, -2,
-						0, -1, -2, -3, 0, -1, -2, -3);
-
-	const __m512i rewind_idx = _mm512_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
-						0, 0, 0, 0, 0, 0, 0, 0,
-						0, 0, 0, 0, 0, 0, 0, 0,
-						0, 0, 0, 0, 0, 0, 0, 0,
-						0, 0, 0, 0, 0, 0, 0, 0,
-						0, 0, 0, 59, 0, 0, 0, 59,
-						0, 0, 59, 58, 0, 0, 59, 58,
-						0, 59, 58, 57, 0, 59, 58, 57);
+	__m512i permute_idx = _mm512_set_epi32(0x07060504, 0x07060504,
+		0x06050403, 0x06050403,
+		0x05040302, 0x05040302,
+		0x04030201, 0x04030201,
+		0x03020100, 0x03020100,
+		0x020100FF, 0x020100FF,
+		0x0100FFFE, 0x0100FFFE,
+		0x00FFFEFD, 0x00FFFEFD);
+	const __m512i rewind_idx = _mm512_set_epi32(0x00000000, 0x00000000,
+		0x00000000, 0x00000000,
+		0x00000000, 0x00000000,
+		0x00000000, 0x00000000,
+		0x00000000, 0x00000000,
+		0x0000003B, 0x0000003B,
+		0x00003B3A, 0x00003B3A,
+		0x003B3A39, 0x003B3A39);
 	const __mmask64 rewind_mask = RTE_THASH_REWIND_MSK;
 	const __m512i shift_8 = _mm512_set1_epi8(8);
 	__m512i xor_acc = _mm512_setzero_si512();
@@ -174,7 +184,47 @@ rte_thash_gfni(const uint64_t *m, const uint8_t *tuple, int len)
 	return val;
 }
 
-#endif /* _GFNI_ */
+/**
+ * Bulk implementation for Toeplitz hash.
+ *
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * @param m
+ *  Pointer to the matrices generated from the corresponding
+ *  RSS hash key using rte_thash_complete_matrix().
+ *  Note that @p len should not exceed the length of the rss_key minus 4.
+ * @param len
+ *  Length of the largest data buffer to be hashed.
+ * @param tuple
+ *  Array of the pointers on data to be hashed.
+ *  Data must be in network byte order.
+ * @param val
+ *  Array of uint32_t where to put calculated Toeplitz hash values
+ * @param num
+ *  Number of tuples to hash.
+ */
+__rte_experimental
+static inline void
+rte_thash_gfni_bulk(const uint64_t *mtrx, int len, uint8_t *tuple[],
+	uint32_t val[], uint32_t num)
+{
+	uint32_t i;
+	uint32_t val_zero;
+	__m512i xor_acc;
+
+	for (i = 0; i != (num & ~1); i += 2) {
+		xor_acc = __rte_thash_gfni(mtrx, tuple[i], tuple[i + 1], len);
+		__rte_thash_xor_reduce(xor_acc, val + i, val + i + 1);
+	}
+
+	if (num & 1) {
+		xor_acc = __rte_thash_gfni(mtrx, tuple[i], NULL, len);
+		__rte_thash_xor_reduce(xor_acc, val + i, &val_zero);
+	}
+}
+
+#endif /* __GFNI__ && __AVX512F__ */
 
 #ifdef __cplusplus
 }