aboutsummaryrefslogtreecommitdiff
path: root/src/cpu/kernels/softmax/generic/sve2/qasymm8.cpp
diff options
context:
space:
mode:
authorGunes Bayir <gunes.bayir@arm.com>2023-11-07 05:43:07 +0000
committerGunes Bayir <gunes.bayir@arm.com>2023-12-05 13:52:17 +0000
commitfadc9b1e0bba90d6a91beb65466b2a0895b3a5e4 (patch)
tree7d095fefe3634b4ca86dc9088bb2990d64d3a7c8 /src/cpu/kernels/softmax/generic/sve2/qasymm8.cpp
parent23158b0a69b85c9c6e5a7f2457bfe10be04d6132 (diff)
downloadComputeLibrary-fadc9b1e0bba90d6a91beb65466b2a0895b3a5e4.tar.gz
Optimize CpuSoftmaxKernel for axis=0
Implement a single kernel instead of having two consecutive ones. In the previous setup, one kernel was calculating the maximum value in the axis, and this maximum was being subtracted from each data while calculating the softmax, i.e. softmax(x_i) = exp(x_i - max) / sum_i( exp(x_i - max) ) This patch integrates these two stages into a single kernel for Neon™ for all data types. This will save some memory because we don't need to hold the max values in a separate auxiliary tensor. It also introduces some other optimizations that will ease memory pressure when the data type is float/half, by using the dst tensor as temporary storage for already exponentiated inputs. It removes the references to SVE and SVE2 implementations, and most of the associated files; but, it leaves the implementations as these may be used in the future. Resolves: COMPMID-6500 Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Change-Id: Icff9976d1214c4c6cbe15a62ca60b8a77d3784cc Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10688 Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/cpu/kernels/softmax/generic/sve2/qasymm8.cpp')
-rw-r--r--src/cpu/kernels/softmax/generic/sve2/qasymm8.cpp44
1 files changed, 0 insertions, 44 deletions
diff --git a/src/cpu/kernels/softmax/generic/sve2/qasymm8.cpp b/src/cpu/kernels/softmax/generic/sve2/qasymm8.cpp
deleted file mode 100644
index 95623786b3..0000000000
--- a/src/cpu/kernels/softmax/generic/sve2/qasymm8.cpp
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * Copyright (c) 2021-2022 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.
- */
-
-#include "arm_compute/core/Helpers.h"
-
-#include "src/cpu/kernels/softmax/generic/sve2/impl.h"
-
-namespace arm_compute
-{
-namespace cpu
-{
-void sve2_qasymm8_softmax(const ITensor *in,
- const ITensor *max,
- void *const tmp,
- ITensor *out,
- const float beta,
- bool is_log,
- const Window &window)
-{
- return sve2_softmax_logits_1d_quantized<qasymm8_t>(in, max, tmp, out, beta, is_log, window);
-}
-} // namespace cpu
-} // namespace arm_compute