/* OP is a memref of CONST_VECTOR, return scalar constant mem
if CONST_VECTOR is a vec_duplicate, else return NULL. */
-static rtx
+rtx
ix86_broadcast_from_constant (machine_mode mode, rtx op)
{
int nunits = GET_MODE_NUNITS (mode);
extern void ix86_expand_move (machine_mode, rtx[]);
extern void ix86_expand_vector_move (machine_mode, rtx[]);
extern void ix86_expand_vector_move_misalign (machine_mode, rtx[]);
+extern rtx ix86_broadcast_from_constant (machine_mode, rtx);
extern rtx ix86_fixup_binary_operands (enum rtx_code, machine_mode,
rtx[], bool = false);
extern void ix86_fixup_binary_operands_no_copy (enum rtx_code, machine_mode,
return true;
case MEM:
+ /* CONST_VECTOR_DUPLICATE_P in constant_pool is just broadcast.
+ or variants in ix86_vector_duplicate_simode_const. */
+
+ if (GET_MODE_SIZE (mode) >= 16
+ && VECTOR_MODE_P (mode)
+ && SYMBOL_REF_P (XEXP (x, 0))
+ && CONSTANT_POOL_ADDRESS_P (XEXP (x, 0))
+ && ix86_broadcast_from_constant (mode, x))
+ {
+ *total = COSTS_N_INSNS (2) + speed;
+ return true;
+ }
+
/* An insn that accesses memory is slightly more expensive
than one that does not. */
if (speed)
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=x86-64-v3 -mno-avx512f -O2" } */
+/* { dg-final { scan-assembler-not "vpsra[dw]" } } */
+
+void
+foo2 (char* __restrict a, short* b)
+{
+ for (int i = 0; i != 32; i++)
+ a[i] = b[i] >> (short)8;
+}
+
+void
+foo3 (char* __restrict a, short* b)
+{
+ for (int i = 0; i != 16; i++)
+ a[i] = b[i] >> (short)8;
+}
+