configure: aarch64: Support assembling the dotprod and i8mm arch extensions

These are available since ARMv8.4-a and ARMv8.6-a respectively,
but can also be available optionally since ARMv8.2-a.

Check if ".arch armv8.2-a" and ".arch_extension {dotprod,i8mm}" are
supported, and check if the instructions can be assembled.

Current clang versions fail to support the dotprod and i8mm
features in the .arch_extension directive, but do support them
if enabled with -march=armv8.4-a on the command line. (Curiously,
lowering the arch level with ".arch armv8.2-a" doesn't make the
extensions unavailable if they were enabled with -march; if that
changes, Clang should also learn to support these extensions via
.arch_extension for them to remain usable here.)

Signed-off-by: Martin Storsjö <martin@martin.st>

configure

@@ -454,6 +454,8 @@ Optimization options (experts only):
   --disable-armv6t2        disable armv6t2 optimizations
   --disable-vfp            disable VFP optimizations
   --disable-neon           disable NEON optimizations
+  --disable-dotprod        disable DOTPROD optimizations
+  --disable-i8mm           disable I8MM optimizations
   --disable-inline-asm     disable use of inline assembly
   --disable-x86asm         disable use of standalone x86 assembly
   --disable-mipsdsp        disable MIPS DSP ASE R1 optimizations
@@ -1154,6 +1156,43 @@ check_insn(){
     check_as ${1}_external "$2"
 }
 
+check_arch_level(){
+    log check_arch_level "$@"
+    level="$1"
+    check_as tested_arch_level ".arch $level"
+    enabled tested_arch_level && as_arch_level="$level"
+}
+
+check_archext_insn(){
+    log check_archext_insn "$@"
+    feature="$1"
+    instr="$2"
+    # Check if the assembly is accepted in inline assembly.
+    check_inline_asm ${feature}_inline "\"$instr\""
+    # We don't check if the instruction is supported out of the box by the
+    # external assembler (we don't try to set ${feature}_external) as we don't
+    # need to use these instructions in non-runtime detected codepaths.
+
+    disable $feature
+
+    enabled as_arch_directive && arch_directive=".arch $as_arch_level" || arch_directive=""
+
+    # Test if the assembler supports the .arch_extension $feature directive.
+    arch_extension_directive=".arch_extension $feature"
+    test_as <<EOF && enable as_archext_${feature}_directive || arch_extension_directive=""
+$arch_directive
+$arch_extension_directive
+EOF
+
+    # Test if we can assemble the instruction after potential .arch and
+    # .arch_extension directives.
+    test_as <<EOF && enable ${feature}
+$arch_directive
+$arch_extension_directive
+$instr
+EOF
+}
+
 check_x86asm(){
     log check_x86asm "$@"
     name=$1
@@ -2059,6 +2098,8 @@ ARCH_EXT_LIST_ARM="
     armv6
     armv6t2
     armv8
+    dotprod
+    i8mm
     neon
     vfp
     vfpv3
@@ -2322,6 +2363,8 @@ SYSTEM_LIBRARIES="
 
 TOOLCHAIN_FEATURES="
     as_arch_directive
+    as_archext_dotprod_directive
+    as_archext_i8mm_directive
     as_dn_directive
     as_fpu_directive
     as_func
@@ -2622,6 +2665,8 @@ intrinsics_neon_deps="neon"
 vfp_deps_any="aarch64 arm"
 vfpv3_deps="vfp"
 setend_deps="arm"
+dotprod_deps="aarch64 neon"
+i8mm_deps="aarch64 neon"
 
 map 'eval ${v}_inline_deps=inline_asm' $ARCH_EXT_LIST_ARM
 
@@ -5988,12 +6033,27 @@ check_inline_asm inline_asm_labels '"1:\n"'
 check_inline_asm inline_asm_nonlocal_labels '"Label:\n"'
 
 if enabled aarch64; then
+    as_arch_level="armv8-a"
+    check_as as_arch_directive ".arch $as_arch_level"
+    enabled as_arch_directive && check_arch_level armv8.2-a
+
     enabled armv8 && check_insn armv8 'prfm   pldl1strm, [x0]'
     # internal assembler in clang 3.3 does not support this instruction
     enabled neon && check_insn neon 'ext   v0.8B, v0.8B, v1.8B, #1'
     enabled vfp  && check_insn vfp  'fmadd d0,    d0,    d1,    d2'
 
-    map 'enabled_any ${v}_external ${v}_inline || disable $v' $ARCH_EXT_LIST_ARM
+    archext_list="dotprod i8mm"
+    enabled dotprod && check_archext_insn dotprod 'udot v0.4s, v0.16b, v0.16b'
+    enabled i8mm    && check_archext_insn i8mm    'usdot v0.4s, v0.16b, v0.16b'
+
+    # Disable the main feature (e.g. HAVE_NEON) if neither inline nor external
+    # assembly support the feature out of the box. Skip this for the features
+    # checked with check_archext_insn above, as that function takes care of
+    # updating all the variables as necessary.
+    for v in $ARCH_EXT_LIST_ARM; do
+        is_in $v $archext_list && continue
+        enabled_any ${v}_external ${v}_inline || disable $v
+    done
 
 elif enabled alpha; then
 
@@ -6022,6 +6082,12 @@ EOF
         warn "Compiler does not indicate floating-point ABI, guessing $fpabi."
     fi
 
+    # Test for various instruction sets, testing support both in inline and
+    # external assembly. This sets the ${v}_inline or ${v}_external flags
+    # if the instruction can be used unconditionally in either inline or
+    # external assembly. This means that if the ${v}_external feature is set,
+    # that feature can be used unconditionally in various support macros
+    # anywhere in external assembly, in any function.
     enabled armv5te && check_insn armv5te 'qadd r0, r0, r0'
     enabled armv6   && check_insn armv6   'sadd16 r0, r0, r0'
     enabled armv6t2 && check_insn armv6t2 'movt r0, #0'
@@ -6030,6 +6096,14 @@ EOF
     enabled vfpv3   && check_insn vfpv3   'vmov.f32 s0, #1.0'
     enabled setend  && check_insn setend  'setend be'
 
+    # If neither inline nor external assembly can use the feature by default,
+    # disable the main unsuffixed feature (e.g. HAVE_NEON).
+    #
+    # For targets that support runtime CPU feature detection, don't disable
+    # the main feature flag - there we assume that all supported toolchains
+    # can assemble code for all instruction set features (e.g. NEON) with
+    # suitable assembly flags (such as ".fpu neon"); we don't check
+    # specifically that they really do.
     [ $target_os = linux ] || [ $target_os = android ] ||
         map 'enabled_any ${v}_external ${v}_inline || disable $v' \
             $ARCH_EXT_LIST_ARM
@@ -7610,6 +7684,8 @@ fi
 if enabled aarch64; then
     echo "NEON enabled              ${neon-no}"
     echo "VFP enabled               ${vfp-no}"
+    echo "DOTPROD enabled           ${dotprod-no}"
+    echo "I8MM enabled              ${i8mm-no}"
 fi
 if enabled arm; then
     echo "ARMv5TE enabled           ${armv5te-no}"
@@ -7900,6 +7976,9 @@ test -n "$assert_level" &&
 test -n "$malloc_prefix" &&
     echo "#define MALLOC_PREFIX $malloc_prefix" >>$TMPH
 
+enabled aarch64 &&
+    echo "#define AS_ARCH_LEVEL $as_arch_level" >>$TMPH
+
 if enabled x86asm; then
     append config_files $TMPASM
     cat > $TMPASM <<EOF

libavutil/aarch64/asm.S

@@ -36,6 +36,17 @@
 #   define __has_feature(x) 0
 #endif
 
+#if HAVE_AS_ARCH_DIRECTIVE
+        .arch           AS_ARCH_LEVEL
+#endif
+
+#if HAVE_AS_ARCHEXT_DOTPROD_DIRECTIVE
+        .arch_extension dotprod
+#endif
+#if HAVE_AS_ARCHEXT_I8MM_DIRECTIVE
+        .arch_extension i8mm
+#endif
+
 
 /* Support macros for
  *   - Armv8.3-A Pointer Authentication and