[AArch64] Fix TBAA information when lowering NEON loads and stores to gimple

  And second (also added a test):

[AArch64] Fix TBAA information when lowering NEON loads and stores to gimple

This patch fixes the wrong TBAA information when lowering NEON loads and 
stores
to gimple that showed up when bootstrapping with UBSAN.

gcc/ChangeLog:

         * config/aarch64/aarch64-builtins.c 
(aarch64_general_gimple_fold_builtin): Change pointer alignment and alias.

gcc/testsuite/ChangeLog:

         * gcc.target/aarch64/simd/lowering_tbaa.c: New test.
  

"Andre Vieira (lists)" <andre.simoesdiasvieira@arm.com> writes:
> And second (also added a test):
>
> [AArch64] Fix TBAA information when lowering NEON loads and stores to gimple
>
> This patch fixes the wrong TBAA information when lowering NEON loads and 
> stores
> to gimple that showed up when bootstrapping with UBSAN.
>
> gcc/ChangeLog:
>
>          * config/aarch64/aarch64-builtins.c 
> (aarch64_general_gimple_fold_builtin): Change pointer alignment and alias.
>
> gcc/testsuite/ChangeLog:
>
>          * gcc.target/aarch64/simd/lowering_tbaa.c: New test.

OK, thanks.

Richard

> diff --git a/gcc/config/aarch64/aarch64-builtins.c b/gcc/config/aarch64/aarch64-builtins.c
> index a815e4cfbccab692ca688ba87c71b06c304abbfb..e06131a7c61d31c1be3278dcdccc49c3053c78cb 100644
> --- a/gcc/config/aarch64/aarch64-builtins.c
> +++ b/gcc/config/aarch64/aarch64-builtins.c
> @@ -2485,18 +2485,18 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode, gcall *stmt,
>  	      = get_mem_type_for_load_store(fcode);
>  	    aarch64_simd_type_info simd_type
>  	      = aarch64_simd_types[mem_type];
> -	    tree elt_ptr_type = build_pointer_type (simd_type.eltype);
> +	    tree elt_ptr_type = build_pointer_type_for_mode (simd_type.eltype,
> +							     VOIDmode, true);
>  	    tree zero = build_zero_cst (elt_ptr_type);
> -	    gimple_seq stmts = NULL;
> -	    tree base = gimple_convert (&stmts, elt_ptr_type,
> -					args[0]);
> -	    if (stmts)
> -	      gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
> +	    /* Use element type alignment.  */
> +	    tree access_type
> +	      = build_aligned_type (simd_type.itype,
> +				    TYPE_ALIGN (simd_type.eltype));
>  	    new_stmt
>  	      = gimple_build_assign (gimple_get_lhs (stmt),
>  				     fold_build2 (MEM_REF,
> -						  simd_type.itype,
> -						  base, zero));
> +						  access_type,
> +						  args[0], zero));
>  	  }
>  	break;
>  
> @@ -2507,18 +2507,17 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode, gcall *stmt,
>  	      = get_mem_type_for_load_store(fcode);
>  	    aarch64_simd_type_info simd_type
>  	      = aarch64_simd_types[mem_type];
> -	    tree elt_ptr_type = build_pointer_type (simd_type.eltype);
> +	    tree elt_ptr_type = build_pointer_type_for_mode (simd_type.eltype,
> +							     VOIDmode, true);
>  	    tree zero = build_zero_cst (elt_ptr_type);
> -	    gimple_seq stmts = NULL;
> -	    tree base = gimple_convert (&stmts, elt_ptr_type,
> -					args[0]);
> -	    if (stmts)
> -	      gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
> +	    /* Use element type alignment.  */
> +	    tree access_type
> +	      = build_aligned_type (simd_type.itype,
> +				    TYPE_ALIGN (simd_type.eltype));
>  	    new_stmt
> -	      = gimple_build_assign (fold_build2 (MEM_REF,
> -				     simd_type.itype,
> -				     base,
> -				     zero), args[1]);
> +	      = gimple_build_assign (fold_build2 (MEM_REF, access_type,
> +						  args[0], zero),
> +				     args[1]);
>  	  }
>  	break;
>  
> diff --git a/gcc/testsuite/gcc.target/aarch64/simd/lowering_tbaa.c b/gcc/testsuite/gcc.target/aarch64/simd/lowering_tbaa.c
> new file mode 100644
> index 0000000000000000000000000000000000000000..eaeae21f19c7d2d8d4e032f2f8b1b22bb96b7ca4
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/aarch64/simd/lowering_tbaa.c
> @@ -0,0 +1,30 @@
> +/* Tests the TBAA information of lowered AArch64 SIMD loads.  */
> +/* { dg-do run } */
> +/* { dg-options "-save-temps -O2" } */
> +
> +#include <arm_neon.h>
> +
> +void __attribute__((noipa))
> +g (float *)
> +{
> +}
> +
> +int32x4_t __attribute__((noipa))
> +f (void)
> +{
> +  float a[4] = { 1, 2, 3, 4 };
> +  g (a);
> +  a[0] = a[1] = a[2] = a[3] = 0;
> +  void *volatile ptr = a;
> +  return vld1q_s32 ((int32_t *) ptr);
> +}
> +
> +int
> +main (void)
> +{
> +  int32x4_t x = f ();
> +  int32x4_t y = vdupq_n_s32 (0);
> +  if (__builtin_memcmp (&x, &y, 16) != 0)
> +    __builtin_abort ();
> +  return 0;
> +}