[AArch64]: Do not allow SIMD clones with simdlen 1 [PR113552]

This is a backport of g:306713c953d509720dc394c43c0890548bb0ae07.

The AArch64 vector PCS does not allow simd calls with simdlen 1,
however due to a bug we currently do allow it for num == 0.

This causes us to emit a symbol that doesn't exist and we fail to link.

gcc/ChangeLog:

	PR tree-optimization/113552
	* config/aarch64/aarch64.c
	(aarch64_simd_clone_compute_vecsize_and_simdlen): Block simdlen 1.

gcc/testsuite/ChangeLog:

	PR tree-optimization/113552
	* gcc.target/aarch64/pr113552.c: New test.
	* gcc.target/aarch64/simd_pcs_attribute-3.c: Remove bogus check.

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 9bbbc5043af25146234f0efc5c4b5b0327622840..4df72339952027f804c84694399921332d5cfc20 100644 (file)
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -25556,7 +25556,7 @@ aarch64_simd_clone_compute_vecsize_and_simdlen (struct cgraph_node *node,
                                        tree base_type, int num)
 {
   tree t, ret_type;
-  unsigned int elt_bits, count;
+  unsigned int elt_bits, count = 0;
   unsigned HOST_WIDE_INT const_simdlen;
   poly_uint64 vec_bits;
 
@@ -25624,11 +25624,20 @@ aarch64_simd_clone_compute_vecsize_and_simdlen (struct cgraph_node *node,
   elt_bits = GET_MODE_BITSIZE (SCALAR_TYPE_MODE (base_type));
   if (known_eq (clonei->simdlen, 0U))
     {
-      count = 2;
-      vec_bits = (num == 0 ? 64 : 128);
+      /* We don't support simdlen == 1.  */
+      if (known_eq (elt_bits, 64))
+       {
+         count = 1;
+         vec_bits = 128;
+       }
+      else
+       {
+         count = 2;
+         vec_bits = (num == 0 ? 64 : 128);
+       }
       clonei->simdlen = exact_div (vec_bits, elt_bits);
     }
-  else
+  else if (maybe_ne (clonei->simdlen, 1U))
     {
       count = 1;
       vec_bits = clonei->simdlen * elt_bits;
@@ -25643,6 +25652,7 @@ aarch64_simd_clone_compute_vecsize_and_simdlen (struct cgraph_node *node,
          return 0;
        }
     }
+
   clonei->vecsize_int = vec_bits;
   clonei->vecsize_float = vec_bits;
   return count;

diff --git a/gcc/testsuite/gcc.target/aarch64/pr113552.c b/gcc/testsuite/gcc.target/aarch64/pr113552.c
new file mode 100644 (file)
index 0000000..9c96b06
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr113552.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -march=armv8-a" } */
+
+__attribute__ ((__simd__ ("notinbranch"), const))
+double cos (double);
+
+void foo (float *a, double *b)
+{
+    for (int i = 0; i < 12; i+=3)
+      {
+        b[i] = cos (5.0 * a[i]);
+        b[i+1] = cos (5.0 * a[i+1]);
+        b[i+2] = cos (5.0 * a[i+2]);
+      }
+}
+
+/* { dg-final { scan-assembler-times {bl\t_ZGVnN2v_cos} 6 } } */

diff --git a/gcc/testsuite/gcc.target/aarch64/simd_pcs_attribute-3.c b/gcc/testsuite/gcc.target/aarch64/simd_pcs_attribute-3.c
index 95f6a6803e889c02177ef10972962ed62d2095eb..c6dac6b104c94c9de89ed88dc5a73e185d2be125 100644 (file)
--- a/gcc/testsuite/gcc.target/aarch64/simd_pcs_attribute-3.c
+++ b/gcc/testsuite/gcc.target/aarch64/simd_pcs_attribute-3.c
@@ -18,7 +18,7 @@ double foo(double x)
 }
 
 /* { dg-final { scan-assembler-not {\.variant_pcs\tfoo} } } */
-/* { dg-final { scan-assembler-times {\.variant_pcs\t_ZGVnM1v_foo} 1 } } */
+/* { dg-final { scan-assembler-not {\.variant_pcs\t_ZGVnM1v_foo} } } */
 /* { dg-final { scan-assembler-times {\.variant_pcs\t_ZGVnM2v_foo} 1 } } */
-/* { dg-final { scan-assembler-times {\.variant_pcs\t_ZGVnN1v_foo} 1 } } */
+/* { dg-final { scan-assembler-not {\.variant_pcs\t_ZGVnN1v_foo} } } */
 /* { dg-final { scan-assembler-times {\.variant_pcs\t_ZGVnN2v_foo} 1 } } */