aarch64: Fix up *add<mode>3_poly_1 [PR99813]

As mentioned in the PR, Uai constraint stands for
aarch64_sve_scalar_inc_dec_immediate
while Uav for
aarch64_sve_addvl_addpl_immediate.
Both *add<mode>3_aarch64 and *add<mode>3_poly_1 patterns use
  * return aarch64_output_sve_scalar_inc_dec (operands[2]);
  * return aarch64_output_sve_addvl_addpl (operands[2]);
in that order, but the former with Uai,Uav order, while the
latter with Uav,Uai instead.  This patch swaps the constraints
so that they match the output.

Co-authored-by: Richard Sandiford <richard.sandiford@arm.com>
2021-03-31  Jakub Jelinek  <jakub@redhat.com>
	    Richard Sandiford  <richard.sandiford@arm.com>

	PR target/99813
	* config/aarch64/aarch64.md (*add<mode>3_poly_1): Swap Uai and Uav
	constraints on operands[2] and similarly 0 and rk constraints
	on operands[1] corresponding to that.

	* g++.target/aarch64/sve/pr99813.C: New test.

diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index b139c08..15bbc10 100644 (file)
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -2059,8 +2059,8 @@
   [(set
     (match_operand:GPI 0 "register_operand" "=r,r,r,r,r,r,&r")
     (plus:GPI
-     (match_operand:GPI 1 "register_operand" "%rk,rk,rk,rk,rk,0,rk")
-     (match_operand:GPI 2 "aarch64_pluslong_or_poly_operand" "I,r,J,Uaa,Uav,Uai,Uat")))]
+     (match_operand:GPI 1 "register_operand" "%rk,rk,rk,rk,0,rk,rk")
+     (match_operand:GPI 2 "aarch64_pluslong_or_poly_operand" "I,r,J,Uaa,Uai,Uav,Uat")))]
   "TARGET_SVE && operands[0] != stack_pointer_rtx"
   "@
   add\\t%<w>0, %<w>1, %2

diff --git a/gcc/testsuite/g++.target/aarch64/sve/pr99813.C b/gcc/testsuite/g++.target/aarch64/sve/pr99813.C
new file mode 100644 (file)
index 0000000..f98b17c
--- /dev/null
+++ b/gcc/testsuite/g++.target/aarch64/sve/pr99813.C
@@ -0,0 +1,27 @@
+// PR target/99813
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O3 -march=armv8.2-a+sve -fvect-cost-model=unlimited -fno-tree-dominator-opts -mtune=cortex-a72" } */
+
+long a, b;
+bool c[2][14][2][16], f[2][14][2][16];
+bool d;
+char e[2][4][2][6];
+void g() {
+  a = 0;
+  for (int h = 0; h < 2; ++h)
+    for (int i = 0; i < 14; ++i)
+      for (int j = 0; j < 2; ++j)
+        for (int k = 0; k < 16; ++k)
+          c[h][i][j][k] = 0;
+  d = 0;
+  for (int h; h < 2; ++h)
+    for (int i = 0; i < 4; ++i)
+      for (int j = 0; j < 2; ++j)
+        for (int k = 0; k < 6; ++k)
+          e[h][i][j][k] = 6;
+  for (int h = 0; h < 2; ++h)
+    for (int i = 0; i < 14; ++i)
+      for (int j = 0; j < 2; ++j)
+        for (int k = 0; k < 16; ++k)
+          f[h][i][j][k] = b = 9;
+}