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.

The patch also fixes a too large allocation in setup. The window
function buffer allocation is common for all channels. It should
not be multiplied by channels count.

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