aboutsummaryrefslogtreecommitdiff
path: root/src/core/NEON/wrapper/intrinsics/erf.h
diff options
context:
space:
mode:
authorMurray Kornelsen <murray.kornelsen@mail.mcgill.ca>2022-07-13 21:22:39 -0400
committerPablo Marquez Tello <pablo.tello@arm.com>2022-09-14 09:15:03 +0000
commit926f502ca731fa49bcdf949408ce25728616e5f2 (patch)
tree7e221103a9c0c5c0e4c054abc07cbdf11c7c7b4e /src/core/NEON/wrapper/intrinsics/erf.h
parent6e09e1404c635d948cf20eb6b4b5747dfb6656f2 (diff)
downloadComputeLibrary-926f502ca731fa49bcdf949408ce25728616e5f2.tar.gz
Adding GELU activation
OpenCL implementation uses built in erf. NEON implementation requires new vectorized erf. Uses the following approximation: erf(x) = 1 - 1 / (1 + a1x + a2x^2 + a3x^3 + a4x^4)^4 a1 = 0.278393, a2 = 0.230389, a3 = 0.000972, a4 = 0.078108 From https://en.wikipedia.org/wiki/Error_function#Numerical_approximations Signed-off-by: Murray Kornelsen <murray.kornelsen@mail.mcgill.ca> Change-Id: I2d3964b2c26a4334166b17135f9104bc6324fad2 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7921 Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Pablo Marquez Tello <pablo.tello@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/wrapper/intrinsics/erf.h')
-rw-r--r--src/core/NEON/wrapper/intrinsics/erf.h51
1 files changed, 51 insertions, 0 deletions
diff --git a/src/core/NEON/wrapper/intrinsics/erf.h b/src/core/NEON/wrapper/intrinsics/erf.h
new file mode 100644
index 0000000000..e2207648e5
--- /dev/null
+++ b/src/core/NEON/wrapper/intrinsics/erf.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright (c) 2022 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_ERF_H
+#define ARM_COMPUTE_WRAPPER_ERF_H
+
+#include "src/core/NEON/NEMath.h"
+#include <arm_neon.h>
+
+namespace arm_compute
+{
+namespace wrapper
+{
+#define VERF_IMPL(vtype, prefix, postfix) \
+ inline vtype verf(const vtype &a) \
+ { \
+ return prefix##_##postfix(a); \
+ }
+
+VERF_IMPL(float32x4_t, verfq, f32)
+#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
+VERF_IMPL(float16x8_t, verfq, f16)
+#endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
+
+#undef VERF_IMPL
+
+} // namespace wrapper
+} // namespace arm_compute
+
+#endif /* ARM_COMPUTE_WRAPPER_ERF_H */