[dpdk-dev] [PATCH 1/3] eal: introduce rte_vect_* abstractions

[Jerin Jacob <jerin.jacob@caviumnetworks.com>]

introduce rte_vect_* abstractions to remove SSE/AVX specific
code in the common code(i.e the test applications)

The patch does not provide any functional change for IA, the goal is to
have infrastructure to reuse the common vector-based test code across
all the architectures.

Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
---
 lib/librte_eal/common/include/arch/arm/rte_vect.h | 17 ++++++++++++++++-
 lib/librte_eal/common/include/arch/x86/rte_vect.h |  8 ++++++++
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/lib/librte_eal/common/include/arch/arm/rte_vect.h b/lib/librte_eal/common/include/arch/arm/rte_vect.h
index 21cdb4d..d300951 100644
--- a/lib/librte_eal/common/include/arch/arm/rte_vect.h
+++ b/lib/librte_eal/common/include/arch/arm/rte_vect.h
@@ -33,13 +33,14 @@
 #ifndef _RTE_VECT_ARM_H_
 #define _RTE_VECT_ARM_H_
 
-#include "arm_neon.h"
+#include <arm_neon.h>
 
 #ifdef __cplusplus
 extern "C" {
 #endif
 
 typedef int32x4_t xmm_t;
+typedef int32x4_t __m128i;
 
 #define	XMM_SIZE	(sizeof(xmm_t))
 #define	XMM_MASK	(XMM_SIZE - 1)
@@ -53,6 +54,20 @@ typedef union rte_xmm {
 	double   pd[XMM_SIZE / sizeof(double)];
 } __attribute__((aligned(16))) rte_xmm_t;
 
+/* rte_vect_* abstraction implementation using NEON */
+
+/* loads the __m128i value from address p(does not need to be 16-byte aligned)*/
+#define rte_vect_loadu_sil128(p) vld1q_s32((const int32_t *)p)
+
+/* sets the 4 signed 32-bit integer values and returns the __m128i variable */
+static inline __m128i  __attribute__((always_inline))
+rte_vect_set_epi32(int i3, int i2, int i1, int i0)
+{
+	int32_t data[4] = {i0, i1, i2, i3};
+
+	return vld1q_s32(data);
+}
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/lib/librte_eal/common/include/arch/x86/rte_vect.h b/lib/librte_eal/common/include/arch/x86/rte_vect.h
index b698797..91c6523 100644
--- a/lib/librte_eal/common/include/arch/x86/rte_vect.h
+++ b/lib/librte_eal/common/include/arch/x86/rte_vect.h
@@ -125,6 +125,14 @@ typedef union rte_ymm {
 })
 #endif /* (defined(__ICC) && __ICC < 1210) */
 
+/* rte_vect_* abstraction implementation using SSE */
+
+/* loads the __m128i value from address p(does not need to be 16-byte aligned)*/
+#define rte_vect_loadu_sil128(p) _mm_loadu_si128(p)
+
+/* sets the 4 signed 32-bit integer values and returns the __m128i variable */
+#define rte_vect_set_epi32(i3, i2, i1, i0) _mm_set_epi32(i3, i2, i1, i0)
+
 #ifdef __cplusplus
 }
 #endif
-- 
2.1.0