This patch adds a bare-bones TARGET_INSN_COST. See the comment
in the patch for the rationale.
This change is needed to avoid a regression with a later change.
Tested on aarch64-linux-gnu & pushed.
Richard
gcc/
* config/aarch64/aarch64.cc (aarch64_insn_cost): New function.
(TARGET_INSN_COST): Define.
---
gcc/config/aarch64/aarch64.cc | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index a28b66acf6a..4cbfa42cb3c 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -15541,6 +15541,28 @@ aarch64_memory_move_cost (machine_mode mode,
reg_class_t rclass_i, bool in)
: aarch64_tune_params.memmov_cost.store_int);
}
+/* Implement TARGET_INSN_COST. We have the opportunity to do something
+ much more productive here, such as using insn attributes to cost things.
+ But we don't, not yet.
+
+ The main point of this current definition is to make calling insn_cost
+ on one instruction equivalent to calling seq_cost on a sequence that
+ contains only that instruction. The default definition would instead
+ only look at SET_SRCs, ignoring SET_DESTs.
+
+ This ensures that, for example, storing a 128-bit zero vector is more
+ expensive than storing a 128-bit vector register. A move of zero
+ into a 128-bit vector register followed by multiple stores of that
+ register is then cheaper than multiple stores of zero (which would
+ use STP of XZR). This in turn allows STPs to be formed. */
+static int
+aarch64_insn_cost (rtx_insn *insn, bool speed)
+{
+ if (rtx set = single_set (insn))
+ return set_rtx_cost (set, speed);
+ return pattern_cost (PATTERN (insn), speed);
+}
+
/* Implement TARGET_INIT_BUILTINS. */
static void
aarch64_init_builtins ()
@@ -28399,6 +28421,9 @@ aarch64_libgcc_floating_mode_supported_p
#undef TARGET_RTX_COSTS
#define TARGET_RTX_COSTS aarch64_rtx_costs_wrapper
+#undef TARGET_INSN_COST
+#define TARGET_INSN_COST aarch64_insn_cost
+
#undef TARGET_SCALAR_MODE_SUPPORTED_P
#define TARGET_SCALAR_MODE_SUPPORTED_P aarch64_scalar_mode_supported_p
--
2.25.1
