[Bug rtl-optimization/65371] arm loop with volatile variable

[gcc-bugzilla at enginuities dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65371

--- Comment #2 from Stuart <gcc-bugzilla at enginuities dot com> ---
I compiled it for x86_64 and thought it was fine, however, after your comment I
tried compiling it with clang/llvm and can see the difference (I'm not
particularly familiar with the full instruction set)...

I've found another case which could also be improved:

func.c:

#include <stdint.h>

#define PERIPH_BASE        0x40000000
#define PERIPH             ((PERIPH_TypeDef *) PERIPH_BASE)

typedef struct
{
    volatile uint32_t REG1;
} PERIPH_TypeDef;

void func(uint16_t a)
{
    uint32_t t = PERIPH->REG1;

    while ((uint16_t) (PERIPH->REG1 - t) < a) { }
}

gives:

00000000 <func>:
   0:   f04f 4380       mov.w   r3, #1073741824 ; 0x40000000
   4:   461a            mov     r2, r3
   6:   6819            ldr     r1, [r3, #0]
   8:   6813            ldr     r3, [r2, #0]
   a:   1a5b            subs    r3, r3, r1
   c:   b29b            uxth    r3, r3
   e:   4283            cmp     r3, r0
  10:   d3fa            bcc.n   8 <func+0x8>
  12:   4770            bx      lr

For some reason r3 is moved in to r2 and then value at the address in r2 is
loaded in to r3 for the loop!

I would expect the following:

00000000 <func>:
   0:   f04f 4180       mov.w   r1, #1073741824 ; 0x40000000
   4:   680a            ldr     r2, [r1, #0]
   6:   680b            ldr     r3, [r1, #0]
   8:   1a9b            subs    r3, r3, r2
   a:   b29b            uxth    r3, r3
   c:   4283            cmp     r3, r0
   e:   d3fa            bcc.n   6 <func+0x6>
  10:   4770            bx      lr