COMPMID-1540 Implement YOLOLayer on NEON

Change-Id: Ice28996959dc666fff5e8ae486c1ff8093db083f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/148367
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>

1 files changed, 58 insertions, 0 deletions

diff --git a/arm_compute/core/NEON/wrapper/intrinsics/mul.h b/arm_compute/core/NEON/wrapper/intrinsics/mul.h
new file mode 100644
index 0000000000..c1908fc7b3
--- /dev/null
+++ b/arm_compute/core/NEON/wrapper/intrinsics/mul.h
@@ -0,0 +1,58 @@
+/*
+ * Copyright (c) 2018 ARM Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __ARM_COMPUTE_WRAPPER_MUL_H__
+#define __ARM_COMPUTE_WRAPPER_MUL_H__
+
+#include <arm_neon.h>
+
+namespace arm_compute
+{
+namespace wrapper
+{
+#define VMUL_IMPL(stype, vtype, prefix, postfix)      \
+    inline vtype vmul(const vtype &a, const vtype &b) \
+    {                                                 \
+        return prefix##_##postfix(a, b);              \
+    }
+
+VMUL_IMPL(uint8x8_t, uint8x8_t, vmul, u8)
+VMUL_IMPL(int8x8_t, int8x8_t, vmul, s8)
+VMUL_IMPL(uint16x4_t, uint16x4_t, vmul, u16)
+VMUL_IMPL(int16x4_t, int16x4_t, vmul, s16)
+VMUL_IMPL(uint32x2_t, uint32x2_t, vmul, u32)
+VMUL_IMPL(int32x2_t, int32x2_t, vmul, s32)
+VMUL_IMPL(float32x2_t, float32x2_t, vmul, f32)
+
+VMUL_IMPL(uint8_t, uint8x16_t, vmulq, u8)
+VMUL_IMPL(int8_t, int8x16_t, vmulq, s8)
+VMUL_IMPL(uint16_t, uint16x8_t, vmulq, u16)
+VMUL_IMPL(int16_t, int16x8_t, vmulq, s16)
+VMUL_IMPL(uint32_t, uint32x4_t, vmulq, u32)
+VMUL_IMPL(int32_t, int32x4_t, vmulq, s32)
+VMUL_IMPL(float32x4_t, float32x4_t, vmulq, f32)
+
+#undef VMUL_IMPL
+} // namespace wrapper
+} // namespace arm_compute
+#endif /* __ARM_COMPUTE_WRAPPER_MUL_H__ */