Audio: STFT Process: Add Xtensa HiFi function versions

This patch adds to stft_process-hifi3.c the HiFi3 versions of
higher complexity functions stft_process_apply_window() and
stft_process_overlap_add_ifft_buffer().

The functions with no clear HiFi optimization benefit are moved
from stft_process-generic.c to stft_process_common.c. Those
functions move data with practically no processing to samples.

The stft_process_setup() function is changed to allocate buffers
with mod_balloc_align() to ensure a 32-bit sample pair or complex
number is aligned for 64 bit xtensa SIMD. This patch also adds
checks to other parameters to ensure the STFT is set up in a
way that can be executed.

This change saves 17 MCPS (from 63 MCPS to 46 MCPS). The test
was done with script run:

scripts/rebuild-testbench.sh -p mtl
scripts/sof-testbench-helper.sh -x -m stft_process_1024_256_ \
  -p profile-stft_process.txt

The above STFT used FFT length 1024 with hop 256.

Signed-off-by: Seppo Ingalsuo <seppo.ingalsuo@linux.intel.com>

Author: singalsu

src/audio/stft_process/CMakeLists.txt

@@ -8,6 +8,7 @@ else()
   add_local_sources(sof stft_process_setup.c)
   add_local_sources(sof stft_process_common.c)
   add_local_sources(sof stft_process-generic.c)
+  add_local_sources(sof stft_process-hifi3.c)
 
   if(CONFIG_IPC_MAJOR_4)
     add_local_sources(sof stft_process-ipc4.c)

src/audio/stft_process/Kconfig

@@ -19,6 +19,8 @@ config COMP_STFT_PROCESS
 
 if COMP_STFT_PROCESS
 
+rsource "Kconfig.simd"
+
 config STFT_PROCESS_MAGNITUDE_PHASE
 	bool "Convert FFTs to polar magnitude and phase"
 	default n

src/audio/stft_process/Kconfig.simd

@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: BSD-3-Clause
+
+comment "STFT Process optimization level select"
+
+choice "COMP_STFT_PROCESS_SIMD_LEVEL_SELECT"
+	prompt "Choose which SIMD level is used for the STFT Process module"
+	depends on COMP_STFT_PROCESS
+	default COMP_STFT_PROCESS_HIFI_MAX
+
+	config COMP_STFT_PROCESS_HIFI_MAX
+		prompt "SIMD will be selected by toolchain pre-defined header"
+		bool
+		help
+			When this is selected, the optimization level will be
+			determined by the toolchain pre-defined macros in the
+			core isa header file.
+
+	config COMP_STFT_PROCESS_HIFI_3
+		prompt "Choose HIFI3 intrinsic optimized STFT Process module"
+		bool
+		help
+			This option is used to build HIFI3 intrinsic optimized
+			STFT Process code.
+
+	config COMP_STFT_PROCESS_HIFI_NONE
+		prompt "Choose generic C STFT Process module, no HIFI SIMD involved"
+		bool
+		help
+			This option is used to build STFT Process
+			with generic C code.
+endchoice