LoongArch: Fix incorrect reorder of __lsx_vldx and __lasx_xvldx [PR119084]

They could be incorrectly reordered with store instructions like st.b
because the RTL expression does not have a memory_operand or a (mem)
expression.  The incorrect reorder has been observed in openh264 LTO
build.

Expand them to a (mem) expression instead of unspec to fix the issue.
Then we need to make loongarch_address_insns return 1 for
ADDRESS_REG_REG because the constraint "R" expects this behavior, or
the vldx instruction will be considered invalid by the register
allocate pass and turned to add.d + vld.  Apply the ADDRESS_REG_REG
penalty in loongarch_address_cost instead, loongarch_rtx_costs should
also call loongarch_address_cost instead of loongarch_address_insns
then.

Closes: https://github.com/cisco/openh264/issues/3857
gcc/ChangeLog:

	PR target/119084
	* config/loongarch/lasx.md (UNSPEC_LASX_XVLDX): Remove.
	(lasx_xvldx): Remove.
	* config/loongarch/lsx.md (UNSPEC_LSX_VLDX): Remove.
	(lsx_vldx): Remove.
	* config/loongarch/simd.md (QIVEC): New define_mode_iterator.
	(<simd_isa>_<x>vldx): New define_expand.
	* config/loongarch/loongarch.cc (loongarch_address_insns_1): New
	static function with most logic factored out from ...
	(loongarch_address_insns): ... here.  Call
	loongarch_address_insns_1 with reg_reg_cost = 1.
	(loongarch_address_cost): Call loongarch_address_insns_1 with
	reg_reg_cost = la_addr_reg_reg_cost.

gcc/testsuite/ChangeLog:

	PR target/119084
	* gcc.target/loongarch/pr119084.c: New test.

diff --git a/gcc/config/loongarch/lasx.md b/gcc/config/loongarch/lasx.md
index e4505c1660d1ec64d9cebf506d5119037ded4c49..43e3ab0026abe16cff52034fc15486ec5292fc6e 100644 (file)
--- a/gcc/config/loongarch/lasx.md
+++ b/gcc/config/loongarch/lasx.md
@@ -119,7 +119,6 @@
   UNSPEC_LASX_XVSSRLRN
   UNSPEC_LASX_XVEXTL_QU_DU
   UNSPEC_LASX_XVLDI
-  UNSPEC_LASX_XVLDX
   UNSPEC_LASX_XVSTX
   UNSPEC_LASX_VECINIT_MERGE
   UNSPEC_LASX_VEC_SET_INTERNAL
@@ -3579,18 +3578,6 @@
   [(set_attr "type" "simd_load")
    (set_attr "mode" "V4DI")])
 
-(define_insn "lasx_xvldx"
-  [(set (match_operand:V32QI 0 "register_operand" "=f")
-       (unspec:V32QI [(match_operand:DI 1 "register_operand" "r")
-                      (match_operand:DI 2 "reg_or_0_operand" "rJ")]
-                     UNSPEC_LASX_XVLDX))]
-  "ISA_HAS_LASX"
-{
-  return "xvldx\t%u0,%1,%z2";
-}
-  [(set_attr "type" "simd_load")
-   (set_attr "mode" "V32QI")])
-
 (define_insn "lasx_xvstx"
   [(set (mem:V32QI (plus:DI (match_operand:DI 1 "register_operand" "r")
                            (match_operand:DI 2 "reg_or_0_operand" "rJ")))

diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
index f2177f892fba05a7a8f0f4b9b2b26b36e8e966d4..68f5d8584765b5b4ff305d1726e82c263873a579 100644 (file)
--- a/gcc/config/loongarch/loongarch.cc
+++ b/gcc/config/loongarch/loongarch.cc
@@ -2363,14 +2363,9 @@ loongarch_index_address_p (rtx addr, machine_mode mode ATTRIBUTE_UNUSED)
   return true;
 }
 
-/* Return the number of instructions needed to load or store a value
-   of mode MODE at address X.  Return 0 if X isn't valid for MODE.
-   Assume that multiword moves may need to be split into word moves
-   if MIGHT_SPLIT_P, otherwise assume that a single load or store is
-   enough.  */
-
-int
-loongarch_address_insns (rtx x, machine_mode mode, bool might_split_p)
+static int
+loongarch_address_insns_1 (rtx x, machine_mode mode, bool might_split_p,
+                          int reg_reg_cost)
 {
   struct loongarch_address_info addr;
   int factor;
@@ -2405,7 +2400,7 @@ loongarch_address_insns (rtx x, machine_mode mode, bool might_split_p)
        return factor;
 
       case ADDRESS_REG_REG:
-       return factor * la_addr_reg_reg_cost;
+       return factor * reg_reg_cost;
 
       case ADDRESS_CONST_INT:
        return lsx_p ? 0 : factor;
@@ -2420,6 +2415,18 @@ loongarch_address_insns (rtx x, machine_mode mode, bool might_split_p)
   return 0;
 }
 
+/* Return the number of instructions needed to load or store a value
+   of mode MODE at address X.  Return 0 if X isn't valid for MODE.
+   Assume that multiword moves may need to be split into word moves
+   if MIGHT_SPLIT_P, otherwise assume that a single load or store is
+   enough.  */
+
+int
+loongarch_address_insns (rtx x, machine_mode mode, bool might_split_p)
+{
+  return loongarch_address_insns_1 (x, mode, might_split_p, 1);
+}
+
 /* Return true if X fits within an unsigned field of BITS bits that is
    shifted left SHIFT bits before being used.  */
 
@@ -3746,6 +3753,17 @@ loongarch_set_reg_reg_cost (machine_mode mode)
     }
 }
 
+/* Implement TARGET_ADDRESS_COST.  */
+
+static int
+loongarch_address_cost (rtx addr, machine_mode mode,
+                       addr_space_t as ATTRIBUTE_UNUSED,
+                       bool speed ATTRIBUTE_UNUSED)
+{
+  return loongarch_address_insns_1 (addr, mode, false,
+                                   la_addr_reg_reg_cost);
+}
+
 /* Implement TARGET_RTX_COSTS.  */
 
 static bool
@@ -3814,7 +3832,7 @@ loongarch_rtx_costs (rtx x, machine_mode mode, int outer_code,
          *total = COSTS_N_INSNS (2);
          return true;
        }
-      cost = loongarch_address_insns (addr, mode, true);
+      cost = loongarch_address_cost (addr, mode, true, speed);
       if (cost > 0)
        {
          *total = COSTS_N_INSNS (cost + 1);
@@ -4401,16 +4419,6 @@ loongarch_vector_costs::finish_cost (const vector_costs *scalar_costs)
   vector_costs::finish_cost (scalar_costs);
 }
 
-/* Implement TARGET_ADDRESS_COST.  */
-
-static int
-loongarch_address_cost (rtx addr, machine_mode mode,
-                       addr_space_t as ATTRIBUTE_UNUSED,
-                       bool speed ATTRIBUTE_UNUSED)
-{
-  return loongarch_address_insns (addr, mode, false);
-}
-
 /* Implement TARGET_INSN_COST.  */
 
 static int

diff --git a/gcc/config/loongarch/lsx.md b/gcc/config/loongarch/lsx.md
index c35826ffc0e1ea3bf46819a1065d3f0d92e6db5f..407c86870dfc75d8bbbe566d3129d76227a9dcf4 100644 (file)
--- a/gcc/config/loongarch/lsx.md
+++ b/gcc/config/loongarch/lsx.md
@@ -87,7 +87,6 @@
   UNSPEC_LSX_VSSRLRN
   UNSPEC_LSX_VLDI
   UNSPEC_LSX_VSHUF_B
-  UNSPEC_LSX_VLDX
   UNSPEC_LSX_VSTX
   UNSPEC_LSX_VEXTL_QU_DU
   UNSPEC_LSX_VSETEQZ_V
@@ -2746,18 +2745,6 @@
   [(set_attr "type" "simd_shf")
    (set_attr "mode" "V16QI")])
 
-(define_insn "lsx_vldx"
-  [(set (match_operand:V16QI 0 "register_operand" "=f")
-       (unspec:V16QI [(match_operand:DI 1 "register_operand" "r")
-                      (match_operand:DI 2 "reg_or_0_operand" "rJ")]
-                     UNSPEC_LSX_VLDX))]
-  "ISA_HAS_LSX"
-{
-  return "vldx\t%w0,%1,%z2";
-}
-  [(set_attr "type" "simd_load")
-   (set_attr "mode" "V16QI")])
-
 (define_insn "lsx_vstx"
   [(set (mem:V16QI (plus:DI (match_operand:DI 1 "register_operand" "r")
                            (match_operand:DI 2 "reg_or_0_operand" "rJ")))

diff --git a/gcc/config/loongarch/simd.md b/gcc/config/loongarch/simd.md
index 5e7bd49eaa24794c31e6d54f4778ae9738bb1d4f..8f7e912982ebfb51f22b3beff7478dd224364c89 100644 (file)
--- a/gcc/config/loongarch/simd.md
+++ b/gcc/config/loongarch/simd.md
@@ -217,6 +217,15 @@
    (set_attr "mode" "<MODE>")])
 
 
+;; REG + REG load
+
+(define_mode_iterator QIVEC [(V16QI "ISA_HAS_LSX") (V32QI "ISA_HAS_LASX")])
+(define_expand "<simd_isa>_<x>vldx"
+  [(set (match_operand:QIVEC 0 "register_operand" "=f")
+       (mem:QIVEC (plus:DI (match_operand:DI 1 "register_operand")
+                           (match_operand:DI 2 "register_operand"))))]
+  "TARGET_64BIT")
+
 ;;
 ;; FP vector rounding instructions
 ;;

diff --git a/gcc/testsuite/gcc.target/loongarch/pr119084.c b/gcc/testsuite/gcc.target/loongarch/pr119084.c
new file mode 100644 (file)
index 0000000..b594330
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/pr119084.c
@@ -0,0 +1,24 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mlsx" } */
+/* { dg-require-effective-target loongarch_sx_hw } */
+
+typedef signed char V16QI __attribute__ ((vector_size (16)));
+static char x[128];
+
+__attribute__ ((noipa)) int
+noopt (int x)
+{
+  return x;
+}
+
+int
+main (void)
+{
+  int t = noopt (32);
+
+  x[32] = 1;
+
+  V16QI y = __builtin_lsx_vldx (x, t);
+  if (y[0] != 1)
+    __builtin_trap ();
+}