aarch64: Avoid out-of-range shrink-wrapped saves [PR111677]

The PR shows us ICEing due to an unrecognizable TFmode save emitted by
aarch64_process_components.  The problem is that for T{I,F,D}mode we
conservatively require mems to be in range for x-register ldp/stp.  That
is because (at least for TImode) it can be allocated to both GPRs and
FPRs, and in the GPR case that is an x-reg ldp/stp, and the FPR case is
a q-register load/store.

As Richard pointed out in the PR, aarch64_get_separate_components
already checks that the offsets are suitable for a single load, so we
just need to choose a mode in aarch64_reg_save_mode that gives the full
q-register range.  In this patch, we choose V16QImode as an alternative
16-byte "bag-of-bits" mode that doesn't have the artificial range
restrictions imposed on T{I,F,D}mode.

Unlike for GCC 14 we need additional handling in the load/store pair
code as various cases are not expecting to see V16QImode (particularly
the writeback patterns, but also aarch64_gen_load_pair).

gcc/ChangeLog:

	PR target/111677
	* config/aarch64/aarch64.c (aarch64_reg_save_mode): Use
	V16QImode for the full 16-byte FPR saves in the vector PCS case.
	(aarch64_gen_storewb_pair): Handle V16QImode.
	(aarch64_gen_loadwb_pair): Likewise.
	(aarch64_gen_load_pair): Likewise.
	* config/aarch64/aarch64.md (loadwb_pair<TX:mode>_<P:mode>):
	Rename to ...
	(loadwb_pair<TX_V16QI:mode>_<P:mode>): ... this, extending to
	V16QImode.
	(storewb_pair<TX:mode>_<P:mode>): Rename to ...
	(storewb_pair<TX_V16QI:mode>_<P:mode>): ... this, extending to
	V16QImode.
	* config/aarch64/iterators.md (TX_V16QI): New.

gcc/testsuite/ChangeLog:

	PR target/111677
	* gcc.target/aarch64/torture/pr111677.c: New test.

(cherry picked from commit fddce05d67f34174be0f306e1015d3868bbe7c31)

4 files changed, 61 insertions, 18 deletions

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 3ccfd3c30fc..9bbbc5043af 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -3466,7 +3466,7 @@ aarch64_reg_save_mode (unsigned int regno)
       case ARM_PCS_SIMD:
 	/* The vector PCS saves the low 128 bits (which is the full
 	   register on non-SVE targets).  */
-	return TFmode;
+	return V16QImode;
 
       case ARM_PCS_SVE:
 	/* Use vectors of DImode for registers that need frame
@@ -7830,6 +7830,10 @@ aarch64_gen_storewb_pair (machine_mode mode, rtx base, rtx reg, rtx reg2,
       return gen_storewb_pairtf_di (base, base, reg, reg2,
 				    GEN_INT (-adjustment),
 				    GEN_INT (UNITS_PER_VREG - adjustment));
+    case E_V16QImode:
+      return gen_storewb_pairv16qi_di (base, base, reg, reg2,
+				       GEN_INT (-adjustment),
+				       GEN_INT (UNITS_PER_VREG - adjustment));
     default:
       gcc_unreachable ();
     }
@@ -7875,6 +7879,10 @@ aarch64_gen_loadwb_pair (machine_mode mode, rtx base, rtx reg, rtx reg2,
     case E_TFmode:
       return gen_loadwb_pairtf_di (base, base, reg, reg2, GEN_INT (adjustment),
 				   GEN_INT (UNITS_PER_VREG));
+    case E_V16QImode:
+      return gen_loadwb_pairv16qi_di (base, base, reg, reg2,
+				      GEN_INT (adjustment),
+				      GEN_INT (UNITS_PER_VREG));
     default:
       gcc_unreachable ();
     }
@@ -7958,6 +7966,9 @@ aarch64_gen_load_pair (machine_mode mode, rtx reg1, rtx mem1, rtx reg2,
     case E_V4SImode:
       return gen_load_pairv4siv4si (reg1, mem1, reg2, mem2);
 
+    case E_V16QImode:
+      return gen_load_pairv16qiv16qi (reg1, mem1, reg2, mem2);
+
     default:
       gcc_unreachable ();
     }
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 1cca0f5c79f..002112d5eea 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -1737,17 +1737,18 @@
   [(set_attr "type" "neon_load1_2reg")]
 )
 
-(define_insn "loadwb_pair<TX:mode>_<P:mode>"
+(define_insn "loadwb_pair<TX_V16QI:mode>_<P:mode>"
   [(parallel
     [(set (match_operand:P 0 "register_operand" "=k")
-          (plus:P (match_operand:P 1 "register_operand" "0")
-                  (match_operand:P 4 "aarch64_mem_pair_offset" "n")))
-     (set (match_operand:TX 2 "register_operand" "=w")
-          (mem:TX (match_dup 1)))
-     (set (match_operand:TX 3 "register_operand" "=w")
-          (mem:TX (plus:P (match_dup 1)
+	  (plus:P (match_operand:P 1 "register_operand" "0")
+		  (match_operand:P 4 "aarch64_mem_pair_offset" "n")))
+     (set (match_operand:TX_V16QI 2 "register_operand" "=w")
+	  (mem:TX_V16QI (match_dup 1)))
+     (set (match_operand:TX_V16QI 3 "register_operand" "=w")
+	  (mem:TX_V16QI (plus:P (match_dup 1)
 			  (match_operand:P 5 "const_int_operand" "n"))))])]
-  "TARGET_SIMD && INTVAL (operands[5]) == GET_MODE_SIZE (<TX:MODE>mode)"
+  "TARGET_SIMD
+   && known_eq (INTVAL (operands[5]), GET_MODE_SIZE (<TX_V16QI:MODE>mode))"
   "ldp\\t%q2, %q3, [%1], %4"
   [(set_attr "type" "neon_ldp_q")]
 )
@@ -1786,20 +1787,20 @@
   [(set_attr "type" "neon_store1_2reg<q>")]
 )
 
-(define_insn "storewb_pair<TX:mode>_<P:mode>"
+(define_insn "storewb_pair<TX_V16QI:mode>_<P:mode>"
   [(parallel
     [(set (match_operand:P 0 "register_operand" "=&k")
-          (plus:P (match_operand:P 1 "register_operand" "0")
-                  (match_operand:P 4 "aarch64_mem_pair_offset" "n")))
-     (set (mem:TX (plus:P (match_dup 0)
+	  (plus:P (match_operand:P 1 "register_operand" "0")
+		  (match_operand:P 4 "aarch64_mem_pair_offset" "n")))
+     (set (mem:TX_V16QI (plus:P (match_dup 0)
 			  (match_dup 4)))
-          (match_operand:TX 2 "register_operand" "w"))
-     (set (mem:TX (plus:P (match_dup 0)
+	  (match_operand:TX_V16QI 2 "register_operand" "w"))
+     (set (mem:TX_V16QI (plus:P (match_dup 0)
 			  (match_operand:P 5 "const_int_operand" "n")))
-          (match_operand:TX 3 "register_operand" "w"))])]
+	  (match_operand:TX_V16QI 3 "register_operand" "w"))])]
   "TARGET_SIMD
-   && INTVAL (operands[5])
-      == INTVAL (operands[4]) + GET_MODE_SIZE (<TX:MODE>mode)"
+   && known_eq (INTVAL (operands[5]),
+		INTVAL (operands[4]) + GET_MODE_SIZE (<TX_V16QI:MODE>mode))"
   "stp\\t%q2, %q3, [%0, %4]!"
   [(set_attr "type" "neon_stp_q")]
 )
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index c9ec6265e7c..ad37741aff8 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -289,6 +289,9 @@
 
 (define_mode_iterator TX [TI TF])
 
+;; TX plus V16QImode.
+(define_mode_iterator TX_V16QI [TI TF V16QI])
+
 ;; Advanced SIMD opaque structure modes.
 (define_mode_iterator VSTRUCT [OI CI XI])
 
diff --git a/gcc/testsuite/gcc.target/aarch64/torture/pr111677.c b/gcc/testsuite/gcc.target/aarch64/torture/pr111677.c
new file mode 100644
index 00000000000..6bb640c42c0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/torture/pr111677.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target fopenmp } */
+/* { dg-options "-ffast-math -fstack-protector-strong -fopenmp" } */
+typedef struct {
+  long size_z;
+  int width;
+} dt_bilateral_t;
+typedef float dt_aligned_pixel_t[4];
+#pragma omp declare simd
+void dt_bilateral_splat(dt_bilateral_t *b) {
+  float *buf;
+  long offsets[8];
+  for (; b;) {
+    int firstrow;
+    for (int j = firstrow; j; j++)
+      for (int i; i < b->width; i++) {
+        dt_aligned_pixel_t contrib;
+        for (int k = 0; k < 4; k++)
+          buf[offsets[k]] += contrib[k];
+      }
+    float *dest;
+    for (int j = (long)b; j; j++) {
+      float *src = (float *)b->size_z;
+      for (int i = 0; i < (long)b; i++)
+        dest[i] += src[i];
+    }
+  }
+}