RISC-V: Use vmv1r.v instead of vmv.v.v for fma output reloads [PR114200].

Three-operand instructions like vmacc are modeled with an implicit
output reload when the output does not match one of the operands.  For
this we use vmv.v.v which is subject to length masking.

In a situation where the current vl is less than the full vlenb
and the fma's result value is used as input for a vector reduction
(which is never length masked) we effectively only reduce vl
elements.  The masked-out elements are relevant for the
reduction, though, leading to a wrong result.

This patch replaces the vmv reloads by full-register reloads.

gcc/ChangeLog:

	PR target/114200
	PR target/114202

	* config/riscv/vector.md: Use vmv[1248]r.v instead of vmv.v.v.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/pr114200.c: New test.
	* gcc.target/riscv/rvv/autovec/pr114202.c: New test.

3 files changed, 86 insertions, 48 deletions

diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md
index f89f9c2..8b1c24c 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -5351,10 +5351,10 @@
   "@
    vmadd.vv\t%0,%4,%5%p1
    vmacc.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%4\;vmacc.vv\t%0,%3,%4%p1
+   vmv%m4r.v\t%0,%4\;vmacc.vv\t%0,%3,%4%p1
    vmadd.vv\t%0,%4,%5%p1
    vmacc.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%5\;vmacc.vv\t%0,%3,%4%p1"
+   vmv%m5r.v\t%0,%5\;vmacc.vv\t%0,%3,%4%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")])
 
@@ -5378,9 +5378,9 @@
   "TARGET_VECTOR"
   "@
    vmadd.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%2\;vmadd.vv\t%0,%3,%4%p1
+   vmv%m2r.v\t%0,%2\;vmadd.vv\t%0,%3,%4%p1
    vmadd.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%2\;vmadd.vv\t%0,%3,%4%p1"
+   vmv%m2r.v\t%0,%2\;vmadd.vv\t%0,%3,%4%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "2")
@@ -5409,9 +5409,9 @@
   "TARGET_VECTOR"
   "@
    vmacc.vv\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vmacc.vv\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4;vmacc.vv\t%0,%2,%3%p1
    vmacc.vv\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vmacc.vv\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vmacc.vv\t%0,%2,%3%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
@@ -5462,9 +5462,9 @@
   "TARGET_VECTOR"
   "@
    vmadd.vx\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vmadd.vx\t%0,%2,%4%p1
+   vmv%m3r.v\t%0,%3\;vmadd.vx\t%0,%2,%4%p1
    vmadd.vx\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vmadd.vx\t%0,%2,%4%p1"
+   vmv%m3r.v\t%0,%3\;vmadd.vx\t%0,%2,%4%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "3")
@@ -5494,9 +5494,9 @@
   "TARGET_VECTOR"
   "@
    vmacc.vx\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vmacc.vx\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4\;vmacc.vx\t%0,%2,%3%p1
    vmacc.vx\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vmacc.vx\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vmacc.vx\t%0,%2,%3%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
@@ -5562,9 +5562,9 @@
   "TARGET_VECTOR && !TARGET_64BIT"
   "@
    vmadd.vx\t%0,%2,%4%p1
-   vmv.v.v\t%0,%2\;vmadd.vx\t%0,%2,%4%p1
+   vmv%m2r.v\t%0,%2\;vmadd.vx\t%0,%2,%4%p1
    vmadd.vx\t%0,%2,%4%p1
-   vmv.v.v\t%0,%2\;vmadd.vx\t%0,%2,%4%p1"
+   vmv%m2r.v\t%0,%2\;vmadd.vx\t%0,%2,%4%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "3")
@@ -5595,9 +5595,9 @@
   "TARGET_VECTOR && !TARGET_64BIT"
   "@
    vmacc.vx\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vmacc.vx\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4\;vmacc.vx\t%0,%2,%3%p1
    vmacc.vx\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vmacc.vx\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vmacc.vx\t%0,%2,%3%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
@@ -5649,10 +5649,10 @@
   "@
    vnmsub.vv\t%0,%4,%5%p1
    vnmsac.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%3\;vnmsub.vv\t%0,%4,%5%p1
+   vmv%m3r.v\t%0,%3\;vnmsub.vv\t%0,%4,%5%p1
    vnmsub.vv\t%0,%4,%5%p1
    vnmsac.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%3\;vnmsub.vv\t%0,%4,%5%p1"
+   vmv%m3r.v\t%0,%3\;vnmsub.vv\t%0,%4,%5%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")])
 
@@ -5676,9 +5676,9 @@
   "TARGET_VECTOR"
   "@
    vnmsub.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%2\;vnmsub.vv\t%0,%3,%4%p1
+   vmv%m2r.v\t%0,%2\;vnmsub.vv\t%0,%3,%4%p1
    vnmsub.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%2\;vnmsub.vv\t%0,%3,%4%p1"
+   vmv%m2r.v\t%0,%2\;vnmsub.vv\t%0,%3,%4%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "2")
@@ -5707,9 +5707,9 @@
   "TARGET_VECTOR"
   "@
    vnmsac.vv\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vnmsac.vv\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4\;vnmsac.vv\t%0,%2,%3%p1
    vnmsac.vv\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vnmsac.vv\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vnmsac.vv\t%0,%2,%3%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
@@ -5760,9 +5760,9 @@
   "TARGET_VECTOR"
   "@
    vnmsub.vx\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vnmsub.vx\t%0,%2,%4%p1
+   vmv%m3r.v\t%0,%3\;vnmsub.vx\t%0,%2,%4%p1
    vnmsub.vx\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vnmsub.vx\t%0,%2,%4%p1"
+   vmv%m3r.v\t%0,%3\;vnmsub.vx\t%0,%2,%4%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "3")
@@ -5792,9 +5792,9 @@
   "TARGET_VECTOR"
   "@
    vnmsac.vx\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vnmsac.vx\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4\;vnmsac.vx\t%0,%2,%3%p1
    vnmsac.vx\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vnmsac.vx\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vnmsac.vx\t%0,%2,%3%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
@@ -5860,9 +5860,9 @@
   "TARGET_VECTOR && !TARGET_64BIT"
   "@
    vnmsub.vx\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vnmsub.vx\t%0,%2,%4%p1
+   vmv%m3r.v\t%0,%3\;vnmsub.vx\t%0,%2,%4%p1
    vnmsub.vx\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vnmsub.vx\t%0,%2,%4%p1"
+   vmv%m3r.v\t%0,%3\;vnmsub.vx\t%0,%2,%4%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "3")
@@ -5893,9 +5893,9 @@
   "TARGET_VECTOR && !TARGET_64BIT"
   "@
    vnmsac.vx\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vnmsac.vx\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4\;vnmsac.vx\t%0,%2,%3%p1
    vnmsac.vx\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vnmsac.vx\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vnmsac.vx\t%0,%2,%3%p1"
   [(set_attr "type" "vimuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
@@ -6555,10 +6555,10 @@
   "@
    vf<madd_msub>.vv\t%0,%4,%5%p1
    vf<macc_msac>.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%3\;vf<madd_msub>.vv\t%0,%4,%5%p1
+   vmv%m3r.v\t%0,%3\;vf<madd_msub>.vv\t%0,%4,%5%p1
    vf<madd_msub>.vv\t%0,%4,%5%p1
    vf<macc_msac>.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%3\;vf<madd_msub>.vv\t%0,%4,%5%p1"
+   vmv%m3r.v\t%0,%3\;vf<madd_msub>.vv\t%0,%4,%5%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set (attr "frm_mode")
@@ -6586,9 +6586,9 @@
   "TARGET_VECTOR"
   "@
    vf<madd_msub>.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%2\;vf<madd_msub>.vv\t%0,%3,%4%p1
+   vmv%m2r.v\t%0,%2\;vf<madd_msub>.vv\t%0,%3,%4%p1
    vf<madd_msub>.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%2\;vf<madd_msub>.vv\t%0,%3,%4%p1"
+   vmv%m2r.v\t%0,%2\;vf<madd_msub>.vv\t%0,%3,%4%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "2")
@@ -6621,9 +6621,9 @@
   "TARGET_VECTOR"
   "@
    vf<macc_msac>.vv\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vf<macc_msac>.vv\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4\;vf<macc_msac>.vv\t%0,%2,%3%p1
    vf<macc_msac>.vv\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vf<macc_msac>.vv\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vf<macc_msac>.vv\t%0,%2,%3%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
@@ -6680,9 +6680,9 @@
   "TARGET_VECTOR"
   "@
    vf<madd_msub>.vf\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vf<madd_msub>.vf\t%0,%2,%4%p1
+   vmv%m3r.v\t%0,%3\;vf<madd_msub>.vf\t%0,%2,%4%p1
    vf<madd_msub>.vf\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vf<madd_msub>.vf\t%0,%2,%4%p1"
+   vmv%m3r.v\t%0,%3\;vf<madd_msub>.vf\t%0,%2,%4%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "3")
@@ -6716,9 +6716,9 @@
   "TARGET_VECTOR"
   "@
    vf<macc_msac>.vf\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vf<macc_msac>.vf\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4\;vf<macc_msac>.vf\t%0,%2,%3%p1
    vf<macc_msac>.vf\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vf<macc_msac>.vf\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vf<macc_msac>.vf\t%0,%2,%3%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
@@ -6778,10 +6778,10 @@
   "@
    vf<nmsub_nmadd>.vv\t%0,%4,%5%p1
    vf<nmsac_nmacc>.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%3\;vf<nmsub_nmadd>.vv\t%0,%4,%5%p1
+   vmv%m3r.v\t%0,%3\;vf<nmsub_nmadd>.vv\t%0,%4,%5%p1
    vf<nmsub_nmadd>.vv\t%0,%4,%5%p1
    vf<nmsac_nmacc>.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%3\;vf<nmsub_nmadd>.vv\t%0,%4,%5%p1"
+   vmv%m3r.v\t%0,%3\;vf<nmsub_nmadd>.vv\t%0,%4,%5%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set (attr "frm_mode")
@@ -6810,9 +6810,9 @@
   "TARGET_VECTOR"
   "@
    vf<nmsub_nmadd>.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%2\;vf<nmsub_nmadd>.vv\t%0,%3,%4%p1
+   vmv%m2r.v\t%0,%2\;vf<nmsub_nmadd>.vv\t%0,%3,%4%p1
    vf<nmsub_nmadd>.vv\t%0,%3,%4%p1
-   vmv.v.v\t%0,%2\;vf<nmsub_nmadd>.vv\t%0,%3,%4%p1"
+   vmv%m2r.v\t%0,%2\;vf<nmsub_nmadd>.vv\t%0,%3,%4%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "2")
@@ -6846,9 +6846,9 @@
   "TARGET_VECTOR"
   "@
    vf<nmsac_nmacc>.vv\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vf<nmsac_nmacc>.vv\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4\;vf<nmsac_nmacc>.vv\t%0,%2,%3%p1
    vf<nmsac_nmacc>.vv\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vf<nmsac_nmacc>.vv\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vf<nmsac_nmacc>.vv\t%0,%2,%3%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
@@ -6907,9 +6907,9 @@
   "TARGET_VECTOR"
   "@
    vf<nmsub_nmadd>.vf\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vf<nmsub_nmadd>.vf\t%0,%2,%4%p1
+   vmv%m3r.v\t%0,%3\;vf<nmsub_nmadd>.vf\t%0,%2,%4%p1
    vf<nmsub_nmadd>.vf\t%0,%2,%4%p1
-   vmv.v.v\t%0,%3\;vf<nmsub_nmadd>.vf\t%0,%2,%4%p1"
+   vmv%m3r.v\t%0,%3\;vf<nmsub_nmadd>.vf\t%0,%2,%4%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "3")
@@ -6944,9 +6944,9 @@
   "TARGET_VECTOR"
   "@
    vf<nmsac_nmacc>.vf\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vf<nmsac_nmacc>.vf\t%0,%2,%3%p1
+   vmv%m4r.v\t%0,%4\;vf<nmsac_nmacc>.vf\t%0,%2,%3%p1
    vf<nmsac_nmacc>.vf\t%0,%2,%3%p1
-   vmv.v.v\t%0,%4\;vf<nmsac_nmacc>.vf\t%0,%2,%3%p1"
+   vmv%m4r.v\t%0,%4\;vf<nmsac_nmacc>.vf\t%0,%2,%3%p1"
   [(set_attr "type" "vfmuladd")
    (set_attr "mode" "<MODE>")
    (set_attr "merge_op_idx" "4")
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr114200.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr114200.c
new file mode 100644
index 0000000..ad64a02
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr114200.c
@@ -0,0 +1,18 @@
+/* { dg-do run { target { riscv_v && rv64 } } } */
+/* { dg-options { -march=rv64gcv -mabi=lp64d -O3 -fwrapv } } */
+
+short a, e = 1;
+_Bool b, d;
+short c[300];
+
+int main() {
+  for (int f = 0; f < 19; f++) {
+    for (int g = 0; g < 14; g++)
+      for (int h = 0; h < 10; h++)
+        a += c[g] + e;
+    b += d;
+  }
+
+  if (a != 2660)
+    __builtin_abort ();
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr114202.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr114202.c
new file mode 100644
index 0000000..93a59bc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr114202.c
@@ -0,0 +1,20 @@
+/* { dg-do run { target { riscv_v && rv64 } } } */
+/* { dg-options { -march=rv64gcv -mabi=lp64d -O3 -fwrapv } } */
+
+signed char a = 0, d = 0;
+_Bool b;
+signed char c[324];
+int e;
+
+int main() {
+  c[63] = 50;
+  for (int f = 0; f < 9; f++) {
+    for (unsigned g = 0; g < 12; g++)
+      for (char h = 0; h < 8; h++)
+        e = a += c[g * 9];
+    b = e ? d : 0;
+  }
+
+  if (a != 16)
+    __builtin_abort ();
+}