[compiler-rt] Support aarch64 targets without FPU

Fall back to the old C implementation of __arm_sc_memset when
the target doesn't have an FPU.

Signed-off-by: Keith Packard <[email protected]>

Author: keith-packard

compiler-rt/lib/builtins/aarch64/sme-libc-mem-routines.S

@@ -6,8 +6,6 @@
 
 #include "../assembly.h"
 
-#ifdef __aarch64__
-
 #define L(l) .L ## l
 
 //
@@ -238,6 +236,7 @@ END_COMPILERRT_OUTLINE_FUNCTION(__arm_sc_memcpy)
 
 DEFINE_COMPILERRT_FUNCTION_ALIAS(__arm_sc_memmove, __arm_sc_memcpy)
 
+#if defined(__aarch64__) && __ARM_FP != 0
 
 //
 //  __arm_sc_memset

compiler-rt/lib/builtins/aarch64/sme-libc-routines.c

@@ -1,5 +1,20 @@
 #include <stddef.h>
 
+#if __ARM_FP == 0
+// WARNING: When building the scalar versions of these functions you need to
+// use the compiler flag "-mllvm -disable-loop-idiom-all" to prevent clang
+// from recognising a loop idiom and planting calls to memcpy!
+
+void *__arm_sc_memset(void *dest, int c, size_t n) __arm_streaming_compatible {
+  unsigned char *destp = (unsigned char *)dest;
+  unsigned char c8 = (unsigned char)c;
+  for (size_t i = 0; i < n; ++i)
+    destp[i] = c8;
+
+  return dest;
+}
+#endif
+
 const void *__arm_sc_memchr(const void *src, int c,
                             size_t n) __arm_streaming_compatible {
   const unsigned char *srcp = (const unsigned char *)src;