reload1.cc: rtl-optimization/116326 - Use RELOAD_ELIMINABLE_REGS.
The new macro is required because reload and LRA are using different
representations for a multi-register frame pointer. As ELIMINABLE_REGS
is used to initialize static const objects, it can't depend on -mlra.
PR rtl-optimization/116326
gcc/
* reload1.cc (reg_eliminate_1): Initialize from
RELOAD_ELIMINABLE_REGS if defined.
* config/avr/avr.h (RELOAD_ELIMINABLE_REGS): Copy from ELIMINABLE_REGS.
(ELIMINABLE_REGS): Don't mention sub-regnos of the frame pointer.
gcc/testsuite/
* gcc.target/avr/torture/lra-pr116324.c: New test.
* gcc.target/avr/torture/lra-pr116325.c: New test.
@@ -308,12 +308,19 @@ enum reg_class {
#define STATIC_CHAIN_REGNUM ((AVR_TINY) ? 18 :2)
-#define ELIMINABLE_REGS { \
+#define RELOAD_ELIMINABLE_REGS { \
{ ARG_POINTER_REGNUM, STACK_POINTER_REGNUM }, \
{ ARG_POINTER_REGNUM, FRAME_POINTER_REGNUM }, \
{ FRAME_POINTER_REGNUM, STACK_POINTER_REGNUM }, \
{ FRAME_POINTER_REGNUM + 1, STACK_POINTER_REGNUM + 1 } }
+#define ELIMINABLE_REGS \
+ { \
+ { ARG_POINTER_REGNUM, STACK_POINTER_REGNUM }, \
+ { ARG_POINTER_REGNUM, FRAME_POINTER_REGNUM }, \
+ { FRAME_POINTER_REGNUM, STACK_POINTER_REGNUM } \
+ }
+
#define INITIAL_ELIMINATION_OFFSET(FROM, TO, OFFSET) \
OFFSET = avr_initial_elimination_offset (FROM, TO)
@@ -283,7 +283,13 @@ static const struct elim_table_1
const int to;
} reg_eliminate_1[] =
+ // Reload and LRA don't agree on how a multi-register frame pointer
+ // is represented for elimination. See avr.h for a use case.
+#ifdef RELOAD_ELIMINABLE_REGS
+ RELOAD_ELIMINABLE_REGS;
+#else
ELIMINABLE_REGS;
+#endif
#define NUM_ELIMINABLE_REGS ARRAY_SIZE (reg_eliminate_1)
new file mode 100644
@@ -0,0 +1,86 @@
+/* { dg-options { -std=gnu99 } } */
+
+void f7_clr (void *cc)
+{
+ __asm ("%~call __f7_clr_asm" :: "z" (cc) : "memory");
+}
+
+void* f7_copy (void *cc, const void *aa)
+{
+ extern void __f7_copy_asm (void);
+ __asm ("%~call __f7_copy_asm" :: "z" (cc), "x" (aa) : "memory");
+ return cc;
+}
+
+typedef _Bool bool;
+typedef unsigned int uint16_t;
+typedef unsigned char uint8_t;
+typedef int int16_t;
+
+typedef struct f7_t
+{
+ union
+ {
+ struct
+ {
+ uint8_t sign :1;
+ uint8_t reserved1 :1;
+ uint8_t is_nan :1;
+ uint8_t reserved2 :4;
+ uint8_t is_inf :1;
+ };
+ uint8_t flags;
+ };
+
+ uint8_t mant[7];
+ int16_t expo;
+} f7_t;
+
+
+static inline __attribute__((__always_inline__))
+void __f7_clr (f7_t *cc)
+{
+ extern void __f7_clr_asm (void);
+ __asm ("%~call %x[f]"
+ :
+ : [f] "i" (__f7_clr_asm), "z" (cc)
+ : "memory");
+}
+
+static inline __attribute__((__always_inline__))
+bool __f7_signbit (const f7_t *aa)
+{
+ return aa->flags & (1 << 0);
+}
+
+static inline __attribute__((__always_inline__))
+int16_t sub_ssat16 (int16_t a, int16_t b)
+{
+ _Sat _Fract sa = __builtin_avr_rbits (a);
+ _Sat _Fract sb = __builtin_avr_rbits (b);
+ return __builtin_avr_bitsr (sa - sb);
+}
+
+extern void __f7_Iadd (f7_t*, const f7_t*);
+extern void __f7_addsub (f7_t*, const f7_t*, const f7_t*, bool neg_b);
+extern uint8_t __f7_mulx (f7_t*, const f7_t*, const f7_t*, bool);
+extern f7_t* __f7_normalize_asm (f7_t*);
+
+void __f7_madd_msub (f7_t *cc, const f7_t *aa, const f7_t *bb, const f7_t *dd,
+ bool neg_d)
+{
+ f7_t xx7, *xx = &xx7;
+ uint8_t x_lsb = __f7_mulx (xx, aa, bb, 1 );
+ uint8_t x_sign = __f7_signbit (xx);
+ int16_t x_expo = xx->expo;
+ __f7_addsub (xx, xx, dd, neg_d);
+
+
+ __f7_clr (cc);
+ cc->expo = sub_ssat16 (x_expo, (8 * 7));
+ cc->mant[7 - 1] = x_lsb;
+ cc = __f7_normalize_asm (cc);
+ cc->flags = x_sign;
+ __f7_Iadd (cc, xx);
+}
+
new file mode 100644
@@ -0,0 +1,117 @@
+typedef __SIZE_TYPE__ size_t;
+typedef __UINT8_TYPE__ uint8_t;
+
+void swapfunc (char *a, char *b, int n)
+{
+ do
+ {
+ char t = *a;
+ *a++ = *b;
+ *b++ = t;
+ } while (--n > 0);
+}
+
+
+typedef int cmp_t (const void*, const void*);
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+#define swap(a, b) \
+ swapfunc (a, b, es)
+
+#define vecswap(a, b, n) \
+ if ((n) > 0) swapfunc (a, b, n)
+
+static char*
+med3 (char *a, char *b, char *c, cmp_t *cmp)
+{
+ return cmp (a, b) < 0
+ ? (cmp (b, c) < 0 ? b : (cmp (a, c) < 0 ? c : a ))
+ : (cmp (b, c) > 0 ? b : (cmp (a, c) < 0 ? a : c ));
+}
+
+void
+qsort (void *a, size_t n, size_t es, cmp_t *cmp)
+{
+ char *pa, *pb, *pc, *pd, *pl, *pm, *pn;
+ int d, r, swap_cnt;
+
+loop:
+ swap_cnt = 0;
+ if (n < 7)
+ {
+ for (pm = (char*) a + es; pm < (char*) a + n * es; pm += es)
+ for (pl = pm; pl > (char*) a && cmp (pl - es, pl) > 0; pl -= es)
+ swap (pl, pl - es);
+ return;
+ }
+ pm = (char*) a + (n / 2) * es;
+ if (n > 7)
+ {
+ pl = a;
+ pn = (char*) a + (n - 1) * es;
+ if (n > 40)
+ {
+ d = (n / 8) * es;
+ pl = med3 (pl, pl + d, pl + 2 * d, cmp);
+ pm = med3 (pm - d, pm, pm + d, cmp);
+ pn = med3 (pn - 2 * d, pn - d, pn, cmp);
+ }
+ pm = med3 (pl, pm, pn, cmp);
+ }
+ swap (a, pm);
+ pa = pb = (char*) a + es;
+
+ pc = pd = (char*) a + (n - 1) * es;
+ for (;;)
+ {
+ while (pb <= pc && (r = cmp (pb, a)) <= 0)
+ {
+ if (r == 0)
+ {
+ swap_cnt = 1;
+ swap (pa, pb);
+ pa += es;
+ }
+ pb += es;
+ }
+ while (pb <= pc && (r = cmp (pc, a)) >= 0)
+ {
+ if (r == 0)
+ {
+ swap_cnt = 1;
+ swap (pc, pd);
+ pd -= es;
+ }
+ pc -= es;
+ }
+ if (pb > pc)
+ break;
+ swap (pb, pc);
+ swap_cnt = 1;
+ pb += es;
+ pc -= es;
+ }
+ if (swap_cnt == 0)
+ {
+ for (pm = (char*) a + es; pm < (char*) a + n * es; pm += es)
+ for (pl = pm; pl > (char*) a && cmp (pl - es, pl) > 0; pl -= es)
+ swap (pl, pl - es);
+ return;
+ }
+
+ pn = (char*) a + n * es;
+ r = min (pa - (char*) a, pb - pa);
+ vecswap (a, pb - r, r);
+ r = min (pd - pc, (int) (pn - pd - es));
+ vecswap (pb, pn - r, r);
+ if ((r = pb - pa) > (int) es)
+ qsort(a, r / es, es, cmp);
+ if ((r = pd - pc) > (int) es)
+ {
+ /* Iterate rather than recurse to save stack space */
+ a = pn - r;
+ n = r / es;
+ goto loop;
+ }
+}