optabs.c (expand_binop): Don't create a broadcast vector with a source element…

optabs.c (expand_binop): Don't create a broadcast vector with a source element wider than the inner mode.

[gcc]

2015-09-03  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	* optabs.c (expand_binop): Don't create a broadcast vector with a
	source element wider than the inner mode.

[gcc/testsuite]

2015-09-03  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	* gcc.target/powerpc/vec-shift.c: New test.

From-SVN: r227444

gcc/ChangeLog

+2015-09-03  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	* optabs.c (expand_binop): Don't create a broadcast vector with a
+	source element wider than the inner mode.
+
 2015-09-03  Richard Biener  <rguenther@suse.de>
 
 	* varasm.c (output_constant): Use fold_convert instead of

gcc/optabs.c

@@ -1608,6 +1608,15 @@ expand_binop (machine_mode mode, optab binoptab, rtx op0, rtx op1,
 
       if (otheroptab && optab_handler (otheroptab, mode) != CODE_FOR_nothing)
 	{
+	  /* The scalar may have been extended to be too wide.  Truncate
+	     it back to the proper size to fit in the broadcast vector.  */
+	  machine_mode inner_mode = GET_MODE_INNER (mode);
+	  if (!CONST_INT_P (op1)
+	      && (GET_MODE_BITSIZE (inner_mode)
+		  < GET_MODE_BITSIZE (GET_MODE (op1))))
+	    op1 = force_reg (inner_mode,
+			     simplify_gen_unary (TRUNCATE, inner_mode, op1,
+						 GET_MODE (op1)));
 	  rtx vop1 = expand_vector_broadcast (mode, op1);
 	  if (vop1)
 	    {

gcc/testsuite/ChangeLog

+2015-09-03  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	* gcc.target/powerpc/vec-shift.c: New test.
+
 2015-09-03  Tom de Vries  <tom@codesourcery.com>
 
 	PR tree-optimization/65637

gcc/testsuite/gcc.target/powerpc/vec-shift.c

+/* { dg-do compile { target { powerpc*-*-* } } } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+/* { dg-skip-if "" { powerpc*-*-darwin* } { "*" } { "" } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power7" } } */
+/* { dg-options "-mcpu=power7 -O2" } */
+
+/* This used to ICE.  During gimplification, "i" is widened to an unsigned
+   int.  We used to fail at expand time as we tried to cram an SImode item
+   into a QImode memory slot.  This has been fixed to properly truncate the
+   shift amount when splatting it into a vector.  */
+
+typedef unsigned char v16ui __attribute__((vector_size(16)));
+
+v16ui vslb(v16ui v, unsigned char i)
+{
+	return v << i;
+}
+
+/* { dg-final { scan-assembler "vspltb" } } */
+/* { dg-final { scan-assembler "vslb" } } */