Fix PR64068 and PR64559

On 01/15/2015 06:23 PM, Martin Liška wrote:
> Hello.
> 
> This is Honsa's patch that I've just tested on x86_64-linux-pc. The patch is
> preapproved by Honza
> and is going to be installed.

backporting the fix for PR63970 introduced PR64938.  Backporting this patch as
well fixes the ICE reported in PR64938.  Honza approved the backport on IRC.

Matthias

On Thu, Feb 05, 2015 at 12:33:18AM +0100, Matthias Klose wrote:
> On 01/15/2015 06:23 PM, Martin Liška wrote:
> > Hello.
> > 
> > This is Honsa's patch that I've just tested on x86_64-linux-pc. The patch is
> > preapproved by Honza
> > and is going to be installed.
> 
> backporting the fix for PR63970 introduced PR64938.  Backporting this patch as
> well fixes the ICE reported in PR64938.  Honza approved the backport on IRC.

How can an aarch64 patch fix an arm PR64938 issue?

> # DP: Proposed fix for PR target/64893 (AArch64)
> 
> commit 455a54f36a205af281b3fe8dbc97916ede704ca8
> Author: Andrew Pinski <apinski@cavium.com>
> Date:   Mon Feb 2 18:40:08 2015 +0000
> 
>     Fix bug 64893: ICE with vget_lane_u32 with C++ front-end
>     
>     	PR target/64893
>             * config/aarch64/aarch64-builtins.c (aarch64_init_simd_builtins):
>             Change the first argument type to size_type_node and add another
>             size_type_node.
>             (aarch64_simd_expand_builtin): Handle the new argument to
>             AARCH64_SIMD_BUILTIN_LANE_CHECK and don't ICE but rather
>             print sorry out when the first two arguments are not
>             integer constants.
>             * config/aarch64/arm_neon.h (__AARCH64_LANE_CHECK):
>             Pass the sizeof directly to __builtin_aarch64_im_lane_boundsi.
>             * testsuite/c-c++-common/torture/aarch64-vect-lane-1.c: New testcase.
> 
> --- a/src/gcc/config/aarch64/aarch64-builtins.c
> +++ b/src/gcc/config/aarch64/aarch64-builtins.c
> @@ -712,7 +712,8 @@ aarch64_init_simd_builtins (void)
>    aarch64_init_simd_builtin_scalar_types ();
>   
>    tree lane_check_fpr = build_function_type_list (void_type_node,
> -						  intSI_type_node,
> +						  size_type_node,
> +						  size_type_node,
>  						  intSI_type_node,
>  						  NULL);
>    aarch64_builtin_decls[AARCH64_SIMD_BUILTIN_LANE_CHECK] =
> @@ -1001,13 +1002,18 @@ aarch64_simd_expand_builtin (int fcode, tree exp, rtx target)
>  {
>    if (fcode == AARCH64_SIMD_BUILTIN_LANE_CHECK)
>      {
> -      tree nlanes = CALL_EXPR_ARG (exp, 0);
> -      gcc_assert (TREE_CODE (nlanes) == INTEGER_CST);
> -      rtx lane_idx = expand_normal (CALL_EXPR_ARG (exp, 1));
> -      if (CONST_INT_P (lane_idx))
> -	aarch64_simd_lane_bounds (lane_idx, 0, TREE_INT_CST_LOW (nlanes), exp);
> +      rtx totalsize = expand_normal (CALL_EXPR_ARG (exp, 0));
> +      rtx elementsize = expand_normal (CALL_EXPR_ARG (exp, 1));
> +      if (CONST_INT_P (totalsize) && CONST_INT_P (elementsize))
> +	{
> +	  rtx lane_idx = expand_normal (CALL_EXPR_ARG (exp, 2));
> +          if (CONST_INT_P (lane_idx))
> +	    aarch64_simd_lane_bounds (lane_idx, 0, UINTVAL (totalsize)/UINTVAL (elementsize), exp);
> +          else
> +	    error ("%Klane index must be a constant immediate", exp);
> +	}
>        else
> -	error ("%Klane index must be a constant immediate", exp);
> +	sorry ("%Ktotal size and element size must be a constant immediate", exp);
>        /* Don't generate any RTL.  */
>        return const0_rtx;
>      }
> --- a/src/gcc/config/aarch64/arm_neon.h
> +++ b/src/gcc/config/aarch64/arm_neon.h
> @@ -541,7 +541,7 @@ typedef struct poly16x8x4_t
>  
>  #define __AARCH64_NUM_LANES(__v) (sizeof (__v) / sizeof (__v[0]))
>  #define __AARCH64_LANE_CHECK(__vec, __idx)	\
> -	__builtin_aarch64_im_lane_boundsi (__AARCH64_NUM_LANES (__vec), __idx)
> +	__builtin_aarch64_im_lane_boundsi (sizeof(__vec), sizeof(__vec[0]), __idx)
>  
>  /* For big-endian, GCC's vector indices are the opposite way around
>     to the architectural lane indices used by Neon intrinsics.  */
> --- /dev/null
> +++ b/src/gcc/testsuite/c-c++-common/torture/aarch64-vect-lane-1.c
> @@ -0,0 +1,8 @@
> +// { dg-do compile { target "aarch64*-*-*" } }
> +#include <arm_neon.h>
> +int
> +search_line_fast (uint32x2_t t)
> +{
> +  return vget_lane_u32 (t, 0);
> +}
> +


	Jakub