COMPMID-1995: Update RSH GEMM assembly kernels.

-Updates u8/s8 hybrid dot product kernels to work for any N and any K >=16.
-Adds hybrid FP32 kernels with generic and A55 variants.
-Adds SVE native kernels for fp16/u8/s8.

Change-Id: Ifc0eaba9e3c8ea5bb19d334e870e1b39e4e7e728
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/863
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>

1 files changed, 77 insertions, 0 deletions

diff --git a/src/core/NEON/kernels/arm_gemm/kernels/a64_hybrid_fp32_mla_16x4.hpp b/src/core/NEON/kernels/arm_gemm/kernels/a64_hybrid_fp32_mla_16x4.hpp
new file mode 100644
index 0000000000..560593958a
--- /dev/null
+++ b/src/core/NEON/kernels/arm_gemm/kernels/a64_hybrid_fp32_mla_16x4.hpp
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) 2019 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.
+ */
+#pragma once
+
+#ifdef __aarch64__
+
+
+#include "../std_transforms_fixed.hpp"
+
+namespace arm_gemm
+{
+
+// Actual kernel implementations
+void a64_hybrid_fp32_mla_16x4(const float *, int, const float *, float *, int, float, int, int, int);
+void a64_hybrid_fp32_mla_16x4_a55(const float *, int, const float *, float *, int, float, int, int, int);
+
+class hybrid_fp32_mla_16x4
+{
+public:
+    typedef float operand_type;
+    typedef float result_type;
+
+    typedef void (*kern_type)(const float *, int, const float *, float *, int, float, int, int, int);
+
+    /* Kernel blocking parameters */
+    static unsigned int out_height()
+    {
+        return 4;
+    }
+
+    static unsigned int out_width()
+    {
+        return 16;
+    }
+
+    static unsigned int k_unroll()
+    {
+        return 1;
+    }
+
+    StdTransformsFixed<operand_type, result_type, 4, 16, 1> transforms = {};
+
+    // Default to the generic kernel
+    kern_type kernel=a64_hybrid_fp32_mla_16x4;
+
+    hybrid_fp32_mla_16x4(const CPUInfo *ci)
+    {
+        if (ci->get_cpu_model() == CPUModel::A55r1) {
+            kernel = a64_hybrid_fp32_mla_16x4_a55;
+        }
+    }
+};
+
+} // namespace arm_gemm
+
+#endif // __aarch64__