[dpdk-dev] [PATCH 07/12] Add vector memcpy for IBM Power architecture

[Chao Zhu]

The SSE based memory copy in DPDK only support x86. This patch adds
altivec based memory copy functions for IBM Power architecture.

Signed-off-by: Chao Zhu <bjzhuc at cn.ibm.com>
---
 .../common/include/powerpc/arch/rte_memcpy_arch.h  |  129 ++++++++++++++++++++
 1 files changed, 129 insertions(+), 0 deletions(-)
 create mode 100644 lib/librte_eal/common/include/powerpc/arch/rte_memcpy_arch.h

diff --git a/lib/librte_eal/common/include/powerpc/arch/rte_memcpy_arch.h b/lib/librte_eal/common/include/powerpc/arch/rte_memcpy_arch.h
new file mode 100644
index 0000000..41aa483
--- /dev/null
+++ b/lib/librte_eal/common/include/powerpc/arch/rte_memcpy_arch.h
@@ -0,0 +1,129 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright (C) IBM Corporation 2014.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of IBM Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+
+#ifndef _RTE_MEMCPY_ARCH_H_
+#define _RTE_MEMCPY_ARCH_H_
+
+#include <stdint.h>
+#include <string.h>
+#include <altivec.h>
+
+/**
+ * Copy 16 bytes from one location to another using optimised Altivec
+ * functions. The locations should not overlap.
+ *
+ * @param dst
+ *   Pointer to the destination of the data.
+ * @param src
+ *   Pointer to the source data.
+ */
+static inline void
+rte_arch_mov16(uint8_t *dst, const uint8_t *src)
+{
+	vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
+}
+
+/**
+ * Copy 32 bytes from one location to another using optimised Altivec
+ * functions. The locations should not overlap.
+ *
+ * @param dst
+ *   Pointer to the destination of the data.
+ * @param src
+ *   Pointer to the source data.
+ */
+static inline void
+rte_arch_mov32(uint8_t *dst, const uint8_t *src)
+{
+	vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
+	vec_vsx_st(vec_vsx_ld(16, src), 16, dst);
+}
+
+/**
+ * Copy 48 bytes from one location to another using optimised Altivec
+ * functions. The locations should not overlap.
+ *
+ * @param dst
+ *   Pointer to the destination of the data.
+ * @param src
+ *   Pointer to the source data.
+ */
+static inline void
+rte_arch_mov48(uint8_t *dst, const uint8_t *src)
+{
+	vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
+	vec_vsx_st(vec_vsx_ld(16, src), 16, dst);
+	vec_vsx_st(vec_vsx_ld(32, src), 32, dst);
+}
+
+/**
+ * Copy 64 bytes from one location to another using optimised Altivec
+ * functions. The locations should not overlap.
+ *
+ * @param dst
+ *   Pointer to the destination of the data.
+ * @param src
+ *   Pointer to the source data.
+ */
+static inline void
+rte_arch_mov64(uint8_t *dst, const uint8_t *src)
+{
+	vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
+	vec_vsx_st(vec_vsx_ld(16, src), 16, dst);
+	vec_vsx_st(vec_vsx_ld(32, src), 32, dst);
+	vec_vsx_st(vec_vsx_ld(48, src), 48, dst);
+}
+
+/**
+ * Copy 128 bytes from one location to another using optimised Altivec
+ * functions. The locations should not overlap.
+ *
+ * @param dst
+ *   Pointer to the destination of the data.
+ * @param src
+ *   Pointer to the source data.
+ */
+static inline void
+rte_arch_mov128(uint8_t *dst, const uint8_t *src)
+{
+	vec_vsx_st(vec_vsx_ld(0, src), 0, dst);
+	vec_vsx_st(vec_vsx_ld(16, src), 16, dst);
+	vec_vsx_st(vec_vsx_ld(32, src), 32, dst);
+	vec_vsx_st(vec_vsx_ld(48, src), 48, dst);
+	vec_vsx_st(vec_vsx_ld(64, src), 64, dst);
+	vec_vsx_st(vec_vsx_ld(80, src), 80, dst);
+	vec_vsx_st(vec_vsx_ld(96, src), 96, dst);
+	vec_vsx_st(vec_vsx_ld(112, src), 112, dst);
+}
+
+#endif /* _RTE_MEMCPY_ARCH_H_ */
+
-- 
1.7.1