aarch64: fix handling of reversed mem ops in ldp/stp policy model

The current ldp/stp policy framework implementation would miss cases,
where the memory operands were reversed. To address this, the call to
the framework function is moved after the lower mem check with the
suitable parameters.

This change removes the mode of aarch64_operands_ok_for_ldpstp, which
becomes unused.

gcc/ChangeLog:

	* config/aarch64/aarch64-ldpstp.md: Remove unused mode.
	* config/aarch64/aarch64-protos.h (aarch64_operands_ok_for_ldpstp):
	Likewise.
	* config/aarch64/aarch64.cc (aarch64_operands_ok_for_ldpstp):
	Call on framework moved later.

Signed-off-by: Manos Anagnostakis <manos.anagnostakis@vrull.eu>
Co-Authored-by: Manolis Tsamis <manolis.tsamis@vrull.eu>
Co-Authored-by: Philipp Tomsich <philipp.tomsich@vrull.eu>

3 files changed, 21 insertions, 21 deletions

diff --git a/gcc/config/aarch64/aarch64-ldpstp.md b/gcc/config/aarch64/aarch64-ldpstp.md
index b668fa8..b7c0bf0 100644
--- a/gcc/config/aarch64/aarch64-ldpstp.md
+++ b/gcc/config/aarch64/aarch64-ldpstp.md
@@ -23,7 +23,7 @@
 	(match_operand:GPI 1 "memory_operand" ""))
    (set (match_operand:GPI 2 "register_operand" "")
 	(match_operand:GPI 3 "memory_operand" ""))]
-  "aarch64_operands_ok_for_ldpstp (operands, true, <MODE>mode)"
+  "aarch64_operands_ok_for_ldpstp (operands, true)"
   [(const_int 0)]
 {
   aarch64_finish_ldpstp_peephole (operands, true);
@@ -35,7 +35,7 @@
 	(match_operand:GPI 1 "aarch64_reg_or_zero" ""))
    (set (match_operand:GPI 2 "memory_operand" "")
 	(match_operand:GPI 3 "aarch64_reg_or_zero" ""))]
-  "aarch64_operands_ok_for_ldpstp (operands, false, <MODE>mode)"
+  "aarch64_operands_ok_for_ldpstp (operands, false)"
   [(const_int 0)]
 {
   aarch64_finish_ldpstp_peephole (operands, false);
@@ -47,7 +47,7 @@
 	(match_operand:GPF 1 "memory_operand" ""))
    (set (match_operand:GPF 2 "register_operand" "")
 	(match_operand:GPF 3 "memory_operand" ""))]
-  "aarch64_operands_ok_for_ldpstp (operands, true, <MODE>mode)"
+  "aarch64_operands_ok_for_ldpstp (operands, true)"
   [(const_int 0)]
 {
   aarch64_finish_ldpstp_peephole (operands, true);
@@ -59,7 +59,7 @@
 	(match_operand:GPF 1 "aarch64_reg_or_fp_zero" ""))
    (set (match_operand:GPF 2 "memory_operand" "")
 	(match_operand:GPF 3 "aarch64_reg_or_fp_zero" ""))]
-  "aarch64_operands_ok_for_ldpstp (operands, false, <MODE>mode)"
+  "aarch64_operands_ok_for_ldpstp (operands, false)"
   [(const_int 0)]
 {
   aarch64_finish_ldpstp_peephole (operands, false);
@@ -71,7 +71,7 @@
 	(match_operand:DREG 1 "memory_operand" ""))
    (set (match_operand:DREG2 2 "register_operand" "")
 	(match_operand:DREG2 3 "memory_operand" ""))]
-  "aarch64_operands_ok_for_ldpstp (operands, true, <DREG:MODE>mode)"
+  "aarch64_operands_ok_for_ldpstp (operands, true)"
   [(const_int 0)]
 {
   aarch64_finish_ldpstp_peephole (operands, true);
@@ -83,7 +83,7 @@
 	(match_operand:DREG 1 "register_operand" ""))
    (set (match_operand:DREG2 2 "memory_operand" "")
 	(match_operand:DREG2 3 "register_operand" ""))]
-  "aarch64_operands_ok_for_ldpstp (operands, false, <DREG:MODE>mode)"
+  "aarch64_operands_ok_for_ldpstp (operands, false)"
   [(const_int 0)]
 {
   aarch64_finish_ldpstp_peephole (operands, false);
@@ -96,7 +96,7 @@
    (set (match_operand:VQ2 2 "register_operand" "")
 	(match_operand:VQ2 3 "memory_operand" ""))]
   "TARGET_FLOAT
-   && aarch64_operands_ok_for_ldpstp (operands, true, <VQ:MODE>mode)
+   && aarch64_operands_ok_for_ldpstp (operands, true)
    && (aarch64_tune_params.extra_tuning_flags
 	& AARCH64_EXTRA_TUNE_NO_LDP_STP_QREGS) == 0"
   [(const_int 0)]
@@ -111,7 +111,7 @@
    (set (match_operand:VQ2 2 "memory_operand" "")
 	(match_operand:VQ2 3 "register_operand" ""))]
   "TARGET_FLOAT
-   && aarch64_operands_ok_for_ldpstp (operands, false, <VQ:MODE>mode)
+   && aarch64_operands_ok_for_ldpstp (operands, false)
    && (aarch64_tune_params.extra_tuning_flags
 	& AARCH64_EXTRA_TUNE_NO_LDP_STP_QREGS) == 0"
   [(const_int 0)]
@@ -128,7 +128,7 @@
 	(sign_extend:DI (match_operand:SI 1 "memory_operand" "")))
    (set (match_operand:DI 2 "register_operand" "")
 	(sign_extend:DI (match_operand:SI 3 "memory_operand" "")))]
-  "aarch64_operands_ok_for_ldpstp (operands, true, SImode)"
+  "aarch64_operands_ok_for_ldpstp (operands, true)"
   [(const_int 0)]
 {
   aarch64_finish_ldpstp_peephole (operands, true, SIGN_EXTEND);
@@ -140,7 +140,7 @@
 	(zero_extend:DI (match_operand:SI 1 "memory_operand" "")))
    (set (match_operand:DI 2 "register_operand" "")
 	(zero_extend:DI (match_operand:SI 3 "memory_operand" "")))]
-  "aarch64_operands_ok_for_ldpstp (operands, true, SImode)"
+  "aarch64_operands_ok_for_ldpstp (operands, true)"
   [(const_int 0)]
 {
   aarch64_finish_ldpstp_peephole (operands, true, ZERO_EXTEND);
@@ -162,7 +162,7 @@
 	(match_operand:DSX 1 "aarch64_reg_zero_or_fp_zero" ""))
    (set (match_operand:<FCVT_TARGET> 2 "memory_operand" "")
 	(match_operand:<FCVT_TARGET> 3 "aarch64_reg_zero_or_fp_zero" ""))]
-  "aarch64_operands_ok_for_ldpstp (operands, false, <V_INT_EQUIV>mode)"
+  "aarch64_operands_ok_for_ldpstp (operands, false)"
   [(const_int 0)]
 {
   aarch64_finish_ldpstp_peephole (operands, false);
diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index 4c70e8a..a0b142e 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -1043,7 +1043,7 @@ int aarch64_ccmp_mode_to_code (machine_mode mode);
 
 bool extract_base_offset_in_addr (rtx mem, rtx *base, rtx *offset);
 bool aarch64_mergeable_load_pair_p (machine_mode, rtx, rtx);
-bool aarch64_operands_ok_for_ldpstp (rtx *, bool, machine_mode);
+bool aarch64_operands_ok_for_ldpstp (rtx *, bool);
 bool aarch64_operands_adjust_ok_for_ldpstp (rtx *, bool, machine_mode);
 bool aarch64_mem_ok_with_ldpstp_policy_model (rtx, bool, machine_mode);
 bool aarch64_ldpstp_operand_mode_p (machine_mode);
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 19c608b..a37d47b 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -27666,12 +27666,10 @@ aarch64_mem_ok_with_ldpstp_policy_model (rtx mem, bool load, machine_mode mode)
 }
 
 /* Given OPERANDS of consecutive load/store, check if we can merge
-   them into ldp/stp.  LOAD is true if they are load instructions.
-   MODE is the mode of memory operands.  */
+   them into ldp/stp.  LOAD is true if they are load instructions.  */
 
 bool
-aarch64_operands_ok_for_ldpstp (rtx *operands, bool load,
-				machine_mode mode)
+aarch64_operands_ok_for_ldpstp (rtx *operands, bool load)
 {
   enum reg_class rclass_1, rclass_2;
   rtx mem_1, mem_2, reg_1, reg_2;
@@ -27700,10 +27698,6 @@ aarch64_operands_ok_for_ldpstp (rtx *operands, bool load,
   if (MEM_VOLATILE_P (mem_1) || MEM_VOLATILE_P (mem_2))
     return false;
 
-  /* Check if mem_1 is ok with the ldp-stp policy model.  */
-  if (!aarch64_mem_ok_with_ldpstp_policy_model (mem_1, load, mode))
-    return false;
-
   /* Check if the addresses are in the form of [base+offset].  */
   bool reversed = false;
   if (!aarch64_check_consecutive_mems (&mem_1, &mem_2, &reversed))
@@ -27715,7 +27709,13 @@ aarch64_operands_ok_for_ldpstp (rtx *operands, bool load,
 
   /* The lower memory access must be a mem-pair operand.  */
   rtx lower_mem = reversed ? mem_2 : mem_1;
-  if (!aarch64_mem_pair_operand (lower_mem, GET_MODE (lower_mem)))
+  machine_mode lower_mem_mode = GET_MODE (lower_mem);
+  if (!aarch64_mem_pair_operand (lower_mem, lower_mem_mode))
+    return false;
+
+  /* Check if lower_mem is ok with the ldp-stp policy model.  */
+  if (!aarch64_mem_ok_with_ldpstp_policy_model (lower_mem, load,
+						lower_mem_mode))
     return false;
 
   if (REG_P (reg_1) && FP_REGNUM_P (REGNO (reg_1)))