[2/2] forwprop: Ensure that shuffle masks are VECTOR_CSTs

Message ID 20250115191740.1172965-2-christoph.muellner@vrull.eu
State Committed
Commit b42eeef63a7e88f90e6ecab9c541b96146759b8c
Headers
Series [1/2] forwprop: Eliminate redundant calls to to_constant() |

Checks

Context Check Description
linaro-tcwg-bot/tcwg_gcc_build--master-arm success Build passed
linaro-tcwg-bot/tcwg_gcc_check--master-arm success Test passed
linaro-tcwg-bot/tcwg_gcc_build--master-aarch64 success Build passed

Commit Message

Christoph Müllner Jan. 15, 2025, 7:17 p.m. UTC
  As reported in PR118487, it is possible that the mask parameter
of a __builtin_shuffle() is not a VECTOR_CST.
If this is the case and checking is enabled then an ICE is triggered.
Let's add a check to fix this issue.

	PR tree-optimization/118487

gcc/ChangeLog:

	* tree-ssa-forwprop.cc (recognise_vec_perm_simplify_seq):
	Ensure that shuffle masks are VECTOR_CSTs.

gcc/testsuite/ChangeLog:

	* gcc.dg/tree-ssa/pr118487.c: New test.

Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
---
 gcc/testsuite/gcc.dg/tree-ssa/pr118487.c | 18 ++++++++++++++++++
 gcc/tree-ssa-forwprop.cc                 |  7 +++++--
 2 files changed, 23 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr118487.c
  

Comments

Richard Biener Jan. 16, 2025, 7:51 a.m. UTC | #1
On Wed, 15 Jan 2025, Christoph Müllner wrote:

> As reported in PR118487, it is possible that the mask parameter
> of a __builtin_shuffle() is not a VECTOR_CST.
> If this is the case and checking is enabled then an ICE is triggered.
> Let's add a check to fix this issue.

OK.

Thanks,
Richard.

> 	PR tree-optimization/118487
> 
> gcc/ChangeLog:
> 
> 	* tree-ssa-forwprop.cc (recognise_vec_perm_simplify_seq):
> 	Ensure that shuffle masks are VECTOR_CSTs.
> 
> gcc/testsuite/ChangeLog:
> 
> 	* gcc.dg/tree-ssa/pr118487.c: New test.
> 
> Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
> ---
>  gcc/testsuite/gcc.dg/tree-ssa/pr118487.c | 18 ++++++++++++++++++
>  gcc/tree-ssa-forwprop.cc                 |  7 +++++--
>  2 files changed, 23 insertions(+), 2 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr118487.c
> 
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr118487.c b/gcc/testsuite/gcc.dg/tree-ssa/pr118487.c
> new file mode 100644
> index 00000000000..aa8038a5cb9
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr118487.c
> @@ -0,0 +1,18 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O3 -fdump-tree-forwprop1-details -Wno-psabi" } */
> +/* { dg-additional-options "-msse2" { target i?86-*-* x86_64-*-* } } */
> +
> +typedef int vec __attribute__((vector_size(16)));
> +vec f1_p_v_in, f1_sel00, f1_sel11, f1_sel, f1_v_out_2;
> +void f1() {
> +  vec v_1, v_2, v_x, v_y;
> +  v_1 = __builtin_shuffle(f1_p_v_in, f1_sel00);
> +  v_2 = __builtin_shuffle(f1_p_v_in, f1_sel11);
> +  v_x = v_2 - v_1;
> +  v_y = v_1 + v_2;
> +  f1_v_out_2 = __builtin_shuffle(v_y, v_x, f1_sel);
> +}
> +
> +/* Won't blend because masks (e.g. f1_sel00) are not VECTOR_CSTs.  */
> +
> +/* { dg-final { scan-tree-dump-not "Vec perm simplify sequences have been merged" "forwprop1" } } */
> diff --git a/gcc/tree-ssa-forwprop.cc b/gcc/tree-ssa-forwprop.cc
> index 2f82f063388..9474682152a 100644
> --- a/gcc/tree-ssa-forwprop.cc
> +++ b/gcc/tree-ssa-forwprop.cc
> @@ -3541,7 +3541,8 @@ recognise_vec_perm_simplify_seq (gassign *stmt, vec_perm_simplify_seq *seq)
>    tree v_y = gimple_assign_rhs2 (stmt);
>    tree sel = gimple_assign_rhs3 (stmt);
>  
> -  if (!VECTOR_CST_NELTS (sel).is_constant (&nelts)
> +  if (TREE_CODE (sel) != VECTOR_CST
> +      || !VECTOR_CST_NELTS (sel).is_constant (&nelts)
>        || TREE_CODE (v_x) != SSA_NAME
>        || TREE_CODE (v_y) != SSA_NAME
>        || !has_single_use (v_x)
> @@ -3615,7 +3616,9 @@ recognise_vec_perm_simplify_seq (gassign *stmt, vec_perm_simplify_seq *seq)
>      return false;
>  
>    unsigned HOST_WIDE_INT v_1_nelts, v_2_nelts;
> -  if (!VECTOR_CST_NELTS (v_1_sel).is_constant (&v_1_nelts)
> +  if (TREE_CODE (v_1_sel) != VECTOR_CST
> +      || !VECTOR_CST_NELTS (v_1_sel).is_constant (&v_1_nelts)
> +      || TREE_CODE (v_2_sel) != VECTOR_CST
>        || !VECTOR_CST_NELTS (v_2_sel).is_constant (&v_2_nelts))
>      return false;
>  
>
  

Patch

diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr118487.c b/gcc/testsuite/gcc.dg/tree-ssa/pr118487.c
new file mode 100644
index 00000000000..aa8038a5cb9
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr118487.c
@@ -0,0 +1,18 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-tree-forwprop1-details -Wno-psabi" } */
+/* { dg-additional-options "-msse2" { target i?86-*-* x86_64-*-* } } */
+
+typedef int vec __attribute__((vector_size(16)));
+vec f1_p_v_in, f1_sel00, f1_sel11, f1_sel, f1_v_out_2;
+void f1() {
+  vec v_1, v_2, v_x, v_y;
+  v_1 = __builtin_shuffle(f1_p_v_in, f1_sel00);
+  v_2 = __builtin_shuffle(f1_p_v_in, f1_sel11);
+  v_x = v_2 - v_1;
+  v_y = v_1 + v_2;
+  f1_v_out_2 = __builtin_shuffle(v_y, v_x, f1_sel);
+}
+
+/* Won't blend because masks (e.g. f1_sel00) are not VECTOR_CSTs.  */
+
+/* { dg-final { scan-tree-dump-not "Vec perm simplify sequences have been merged" "forwprop1" } } */
diff --git a/gcc/tree-ssa-forwprop.cc b/gcc/tree-ssa-forwprop.cc
index 2f82f063388..9474682152a 100644
--- a/gcc/tree-ssa-forwprop.cc
+++ b/gcc/tree-ssa-forwprop.cc
@@ -3541,7 +3541,8 @@  recognise_vec_perm_simplify_seq (gassign *stmt, vec_perm_simplify_seq *seq)
   tree v_y = gimple_assign_rhs2 (stmt);
   tree sel = gimple_assign_rhs3 (stmt);
 
-  if (!VECTOR_CST_NELTS (sel).is_constant (&nelts)
+  if (TREE_CODE (sel) != VECTOR_CST
+      || !VECTOR_CST_NELTS (sel).is_constant (&nelts)
       || TREE_CODE (v_x) != SSA_NAME
       || TREE_CODE (v_y) != SSA_NAME
       || !has_single_use (v_x)
@@ -3615,7 +3616,9 @@  recognise_vec_perm_simplify_seq (gassign *stmt, vec_perm_simplify_seq *seq)
     return false;
 
   unsigned HOST_WIDE_INT v_1_nelts, v_2_nelts;
-  if (!VECTOR_CST_NELTS (v_1_sel).is_constant (&v_1_nelts)
+  if (TREE_CODE (v_1_sel) != VECTOR_CST
+      || !VECTOR_CST_NELTS (v_1_sel).is_constant (&v_1_nelts)
+      || TREE_CODE (v_2_sel) != VECTOR_CST
       || !VECTOR_CST_NELTS (v_2_sel).is_constant (&v_2_nelts))
     return false;