Fix optimized armhf builds

Apparently gcc-6.2 with -O3 and -mfpu=neon can use ARM instructions
that requires 64bit alignment (here vst1.64) with data that
is not 64bit aligned (g->strcache) https://i.imgur.com/vYktsUn.png

So we need to be able to build "arm_neon_functions.cc" with
-mfpu=neon, while not automatically using NEON for the rest
of the codebase, unless explicitly asked for.

libs/ardour/wscript

@@ -481,10 +481,25 @@ def build(bld):
                         obj.source += [ 'sse_functions_xmm.cc' ]
                         obj.source += [ 'sse_functions_64bit_win.s',  'sse_avx_functions_64bit_win.s' ]
                         avx_sources = [ 'sse_functions_avx.cc' ]
-        elif bld.env['build_target'] == 'armhf' or bld.env['build_target'] == 'aarch64':
+        elif bld.env['build_target'] == 'aarch64':
             obj.source += ['arm_neon_functions.cc']
             obj.defines += [ 'ARM_NEON_SUPPORT' ]
 
+        elif bld.env['build_target'] == 'armhf':
+            # 32bit ARM needs -mfpu=neon
+            obj.defines += [ 'ARM_NEON_SUPPORT' ]
+            arm_neon_cxxflags = list(bld.env['CXXFLAGS'])
+            arm_neon_cxxflags.append (bld.env['compiler_flags_dict']['neon'])
+            bld(features = 'cxx cxxstlib asm',
+                source   = ['arm_neon_functions.cc'],
+                cxxflags = arm_neon_cxxflags,
+                includes = [ '.' ],
+                definfes = obj.defines,
+                use = [ 'libpbd', 'libevoral'],
+                target   = 'arm_neon_functions')
+
+            obj.use += ['arm_neon_functions' ]
+
         if avx_sources:
             # as long as we want to use AVX intrinsics in this file,
             # compile it with -mavx flag - append avx flag to the existing

wscript

@@ -86,6 +86,8 @@ compiler_flags_dictionaries= {
         'attasm': '-masm=att',
         # Flags to make AVX instructions/intrinsics available
         'avx': '-mavx',
+        # Flags to make ARM/NEON instructions/intrinsics available
+        'neon': '-mfpu=neon',
         # Flags to generate position independent code, when needed to build a shared object
         'pic': '-fPIC',
         # Flags required to compile C code with anonymous unions (only part of C11)
@@ -120,6 +122,7 @@ compiler_flags_dictionaries= {
         'c99': '/TP',
         'attasm': '',
         'avx': '',
+        'neon': '',
         'pic': '',
         'c-anonymous-union': '',
     },