RISC-V: Enable SLP un-order reduction

This patch is to enable SLP un-order reduction autao-vectorization

Consider this following case:

int __attribute__((noipa))
add_loop (int *x, int n, int res)
{
  for (int i = 0; i < n; ++i)
    {
      res += x[i * 2];
      res += x[i * 2 + 1];
    }
  return res;
}

--param riscv-autovec-preference=scalable -fopt-info-vec-missed:
<source>:4:21: missed: couldn't vectorize loop
<source>:4:21: missed: unsupported SLP instances

After this patch:

add_loop:
	ble	a1,zero,.L5
	csrr	a6,vlenb
	srli	a4,a6,2
	slli	a1,a1,1
	neg	a7,a4
	vsetvli	t1,zero,e32,m1,ta,ma
	vmv.v.i	v2,0
	vslide1up.vx	v1,v2,a2   -----------> generated by VEC_SHL_INSERT
.L4:
	mv	a3,a1
	mv	a5,a1
	bleu	a1,a4,.L3
	mv	a5,a4
.L3:
	vsetvli	zero,a5,e32,m1,tu,ma
	add	a1,a1,a7
	vle32.v	v2,0(a0)
	add	a0,a0,a6
	vadd.vv	v1,v1,v2
	bgtu	a3,a4,.L4
	vsetivli	zero,1,e32,m1,ta,ma
	vmv.v.i	v2,0
	vsetvli	t1,zero,e32,m1,ta,ma
	vredsum.vs	v1,v1,v2
	vmv.x.s	a0,v1
	ret
.L5:
	mv	a0,a2
	ret

gcc/ChangeLog:

	* config/riscv/autovec.md (vec_shl_insert_<mode>): New patterns.
	* config/riscv/riscv-v.cc (shuffle_compress_patterns): Fix bugs.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/reduc/reduc-5.c: New test.
	* gcc.target/riscv/rvv/autovec/reduc/reduc-6.c: New test.
	* gcc.target/riscv/rvv/autovec/reduc/reduc-7.c: New test.
	* gcc.target/riscv/rvv/autovec/reduc/reduc-8.c: New test.
	* gcc.target/riscv/rvv/autovec/reduc/reduc-9.c: New test.
	* gcc.target/riscv/rvv/autovec/reduc/reduc_run-5.c: New test.
	* gcc.target/riscv/rvv/autovec/reduc/reduc_run-6.c: New test.
	* gcc.target/riscv/rvv/autovec/reduc/reduc_run-7.c: New test.
	* gcc.target/riscv/rvv/autovec/reduc/reduc_run-8.c: New test.
	* gcc.target/riscv/rvv/autovec/reduc/reduc_run-9.c: New test.

12 files changed, 542 insertions, 0 deletions

diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index 8cdec75..cd5b194 100644
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -372,6 +372,31 @@
   }
 )
 
+;; Slide an RVV vector left and insert a scalar into element 0.
+(define_expand "vec_shl_insert_<mode>"
+  [(match_operand:VI 0 "register_operand")
+   (match_operand:VI 1 "register_operand")
+   (match_operand:<VEL> 2 "reg_or_0_operand")]
+  "TARGET_VECTOR"
+{
+  insn_code icode = code_for_pred_slide (UNSPEC_VSLIDE1UP, <MODE>mode);
+  rtx ops[] = {operands[0], RVV_VUNDEF (<MODE>mode), operands[1], operands[2]};
+  riscv_vector::emit_vlmax_slide_insn (icode, ops);
+  DONE;
+})
+
+(define_expand "vec_shl_insert_<mode>"
+  [(match_operand:VF 0 "register_operand")
+   (match_operand:VF 1 "register_operand")
+   (match_operand:<VEL> 2 "register_operand")]
+  "TARGET_VECTOR"
+{
+  insn_code icode = code_for_pred_slide (UNSPEC_VFSLIDE1UP, <MODE>mode);
+  rtx ops[] = {operands[0], RVV_VUNDEF (<MODE>mode), operands[1], operands[2]};
+  riscv_vector::emit_vlmax_slide_insn (icode, ops);
+  DONE;
+})
+
 ;; ========================================================================
 ;; == Vector operations
 ;; =========================================================================
diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index b4884a3..ff1e682 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -2823,6 +2823,10 @@ shuffle_compress_patterns (struct expand_vec_perm_d *d)
     if (known_le (d->perm[i], d->perm[i - 1]))
       return false;
 
+  /* Success!  */
+  if (d->testing_p)
+    return true;
+
   /* Check whether we need to slideup op1 to apply compress approach.
 
        E.g. For index = { 0, 2, 6, 7}, since d->perm[i - 1] = 7 which
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-5.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-5.c
new file mode 100644
index 0000000..e973041
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-5.c
@@ -0,0 +1,88 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=fixed-vlmax -ffast-math -fno-vect-cost-model" } */
+
+#include <stdint-gcc.h>
+
+void __attribute__((noipa))
+add_loop (unsigned int *x, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < 0x7ff; ++i)
+    {
+      res0 += x[i * 2];
+      res1 += x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+min_loop (unsigned int *x, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < 0x7ff; ++i)
+    {
+      res0 = res0 < x[i * 2] ? res0 : x[i * 2];
+      res1 = res1 < x[i * 2 + 1] ? res1 : x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+max_loop (unsigned int *x, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < 0x7ff; ++i)
+    {
+      res0 = res0 > x[i * 2] ? res0 : x[i * 2];
+      res1 = res1 > x[i * 2 + 1] ? res1 : x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+and_loop (unsigned int *x, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < 0x7ff; ++i)
+    {
+      res0 &= x[i * 2];
+      res1 &= x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+or_loop (unsigned int *x, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < 0x7ff; ++i)
+    {
+      res0 |= x[i * 2];
+      res1 |= x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+eor_loop (unsigned int *x, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < 0x7ff; ++i)
+    {
+      res0 ^= x[i * 2];
+      res1 ^= x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-6.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-6.c
new file mode 100644
index 0000000..30961f0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-6.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math -fno-vect-cost-model -fdump-tree-optimized-details" } */
+
+#include "reduc-5.c"
+
+/* { dg-final { scan-tree-dump-times "VEC_SHL_INSERT" 8 "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-7.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-7.c
new file mode 100644
index 0000000..e2e65be
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-7.c
@@ -0,0 +1,88 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math -fno-vect-cost-model -fdump-tree-optimized-details" } */
+
+void __attribute__((noipa))
+add_loop (unsigned int *x, int n, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < n; ++i)
+    {
+      res0 += x[i * 2];
+      res1 += x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+min_loop (unsigned int *x, int n, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < n; ++i)
+    {
+      res0 = res0 < x[i * 2] ? res0 : x[i * 2];
+      res1 = res1 < x[i * 2 + 1] ? res1 : x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+max_loop (unsigned int *x, int n, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < n; ++i)
+    {
+      res0 = res0 > x[i * 2] ? res0 : x[i * 2];
+      res1 = res1 > x[i * 2 + 1] ? res1 : x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+and_loop (unsigned int *x, int n, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < n; ++i)
+    {
+      res0 &= x[i * 2];
+      res1 &= x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+or_loop (unsigned int *x, int n, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < n; ++i)
+    {
+      res0 |= x[i * 2];
+      res1 |= x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+void __attribute__((noipa))
+eor_loop (unsigned int *x, int n, unsigned int *res)
+{
+  unsigned int res0 = res[0];
+  unsigned int res1 = res[1];
+  for (int i = 0; i < n; ++i)
+    {
+      res0 ^= x[i * 2];
+      res1 ^= x[i * 2 + 1];
+    }
+  res[0] = res0;
+  res[1] = res1;
+}
+
+/* { dg-final { scan-tree-dump-times "VEC_SHL_INSERT" 8 "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-8.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-8.c
new file mode 100644
index 0000000..4cbcccd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-8.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math -fno-vect-cost-model -fdump-tree-optimized-details" } */
+
+int __attribute__((noipa))
+add_loop (int *x, int n, int res)
+{
+  for (int i = 0; i < n; ++i)
+    {
+      res += x[i * 2];
+      res += x[i * 2 + 1];
+    }
+  return res;
+}
+
+/* { dg-final { scan-tree-dump-times "VEC_SHL_INSERT" 1 "optimized" } } */
+/* { dg-final { scan-assembler-times {vslide1up\.vx\s+v[0-9]+,\s*v[0-9]+,\s*[a-x0-9]+} 1 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-9.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-9.c
new file mode 100644
index 0000000..6810561
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc-9.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param=riscv-autovec-preference=scalable -ffast-math -fno-vect-cost-model -fdump-tree-optimized-details" } */
+
+float __attribute__((noipa))
+add_loop (float *x, int n, float res)
+{
+  for (int i = 0; i < n; ++i)
+    {
+      res += x[i * 2];
+      res += x[i * 2 + 1];
+    }
+  return res;
+}
+
+/* { dg-final { scan-tree-dump-times "VEC_SHL_INSERT" 1 "optimized" } } */
+/* { dg-final { scan-assembler-times {vfslide1up\.vf\s+v[0-9]+,\s*v[0-9]+,\s*[a-x0-9]+} 1 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-5.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-5.c
new file mode 100644
index 0000000..c47463d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-5.c
@@ -0,0 +1,61 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=fixed-vlmax -ffast-math -fno-vect-cost-model" } */
+
+#define N 0x1100
+
+#include "reduc-5.c"
+
+int
+main (void)
+{
+  unsigned int x[N];
+  for (int i = 0; i < N; ++i)
+    x[i] = ((i + 1) * (i + 2)) & 0xfffff;
+
+  unsigned int add_res[2] = { 42, 1111 };
+  add_loop (x, add_res);
+  if (add_res[0] != 968538154
+      || add_res[1] != 964340823)
+    __builtin_abort ();
+
+  unsigned int max_res1[2] = { 0, 0 };
+  max_loop (x, max_res1);
+  if (max_res1[0] != 1048150
+      || max_res1[1] != 1045506)
+    __builtin_abort ();
+
+  unsigned int max_res2[2] = { 1048151, 1045507 };
+  max_loop (x, max_res2);
+  if (max_res2[0] != 1048151
+      || max_res2[1] != 1045507)
+    __builtin_abort ();
+
+  unsigned int or_res[2] = { 0x1000000, 0x2000000 };
+  or_loop (x, or_res);
+  if (or_res[0] != 0x10ffffe
+      || or_res[1] != 0x20ffffe)
+    __builtin_abort ();
+
+  unsigned int eor_res[2] = { 0x1000000, 0x2000000 };
+  eor_loop (x, eor_res);
+  if (eor_res[0] != 0x1010000
+      || eor_res[1] != 0x20b5000)
+    __builtin_abort ();
+
+  for (int i = 0; i < N; ++i)
+    x[i] = ~x[i] & 0xfffff;
+
+  unsigned int min_res1[2] = { 500, 4000 };
+  min_loop (x, min_res1);
+  if (min_res1[0] != 425
+      || min_res1[1] != 3069)
+    __builtin_abort ();
+
+  unsigned int min_res2[2] = { 424, 3068 };
+  min_loop (x, min_res2);
+  if (min_res2[0] != 424
+      || min_res2[1] != 3068)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-6.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-6.c
new file mode 100644
index 0000000..540b2e7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-6.c
@@ -0,0 +1,6 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math -fno-vect-cost-model" } */
+
+#define N 0x1100
+
+#include "reduc_run-5.c"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-7.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-7.c
new file mode 100644
index 0000000..cc141dc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-7.c
@@ -0,0 +1,188 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math -fno-vect-cost-model" } */
+
+#define N 0x1100
+
+#include "reduc-7.c"
+
+
+int
+main (void)
+{
+  unsigned int x[N];
+  for (int i = 0; i < N; ++i)
+    x[i] = ((i + 1) * (i + 2)) & 0xfffff;
+
+  unsigned int add_res1[2] = { 11, 22 };
+  add_loop (x, 0, add_res1);
+  if (add_res1[0] != 11
+      || add_res1[1] != 22)
+    __builtin_abort ();
+
+  unsigned int add_res2[2] = { 10, 20 };
+  add_loop (x, 11, add_res2);
+  if (add_res2[0] != 1902
+      || add_res2[1] != 2176)
+    __builtin_abort ();
+
+  unsigned int add_res3[2] = { 15, 30 };
+  add_loop (x, 0x100, add_res3);
+  if (add_res3[0] != 22435087
+      || add_res3[1] != 22566686)
+    __builtin_abort ();
+
+  unsigned int add_res4[2] = { 100, 200 };
+  add_loop (x, 0x11f, add_res4);
+  if (add_res4[0] != 31602244
+      || add_res4[1] != 31767656)
+    __builtin_abort ();
+
+  unsigned int max_res1[2] = { 461, 500 };
+  max_loop (x, 11, max_res1);
+  if (max_res1[0] != 462
+      || max_res1[1] != 506)
+    __builtin_abort ();
+
+  unsigned int max_res2[2] = { 463, 507 };
+  max_loop (x, 11, max_res2);
+  if (max_res2[0] != 463
+      || max_res2[1] != 507)
+    __builtin_abort ();
+
+  unsigned int max_res3[2] = { 1000000, 1000000 };
+  max_loop (x, 0x200, max_res3);
+  if (max_res3[0] != 1047552
+      || max_res3[1] != 1045506)
+    __builtin_abort ();
+
+  unsigned int max_res4[2] = { 1047553, 1045507 };
+  max_loop (x, 0x200, max_res4);
+  if (max_res4[0] != 1047553
+      || max_res4[1] != 1045507)
+    __builtin_abort ();
+
+  unsigned int max_res5[2] = { 300000, 30000 };
+  max_loop (x, 0x11f, max_res5);
+  if (max_res5[0] != 328902
+      || max_res5[1] != 330050)
+    __builtin_abort ();
+
+  unsigned int max_res6[2] = { 328903, 330051 };
+  max_loop (x, 0x11f, max_res6);
+  if (max_res6[0] != 328903
+      || max_res6[1] != 330051)
+    __builtin_abort ();
+
+  unsigned int or_res1[2] = { 11, 22 };
+  or_loop (x, 0, or_res1);
+  if (or_res1[0] != 11
+      || or_res1[1] != 22)
+    __builtin_abort ();
+
+  unsigned int or_res2[2] = { 0x200000, 0xe00000 };
+  or_loop (x, 11, or_res2);
+  if (or_res2[0] != 0x2001fe
+      || or_res2[1] != 0xe001fe)
+    __builtin_abort ();
+
+  unsigned int or_res3[2] = { 0x800000, 0x700000 };
+  or_loop (x, 0x40, or_res3);
+  if (or_res3[0] != 0x803ffe
+      || or_res3[1] != 0x707ffe)
+    __builtin_abort ();
+
+  unsigned int or_res4[2] = { 0x100001, 0x300000 };
+  or_loop (x, 0x4f, or_res4);
+  if (or_res4[0] != 0x107fff
+      || or_res4[1] != 0x307ffe)
+    __builtin_abort ();
+
+  unsigned int eor_res1[2] = { 11, 22 };
+  eor_loop (x, 0, eor_res1);
+  if (eor_res1[0] != 11
+      || eor_res1[1] != 22)
+    __builtin_abort ();
+
+  unsigned int eor_res2[2] = { 0x2000ff, 0xe000ff };
+  eor_loop (x, 11, eor_res2);
+  if (eor_res2[0] != 0x2001cf
+      || eor_res2[1] != 0xe000b7)
+    __builtin_abort ();
+
+  unsigned int eor_res3[2] = { 0x805000, 0x70f000 };
+  eor_loop (x, 0x100, eor_res3);
+  if (eor_res3[0] != 0x824200
+      || eor_res3[1] != 0x77dc00)
+    __builtin_abort ();
+
+  unsigned int eor_res4[2] = { 0x101201, 0x300f00 };
+  eor_loop (x, 0x11f, eor_res4);
+  if (eor_res4[0] != 0x178801
+      || eor_res4[1] != 0x337240)
+    __builtin_abort ();
+
+  for (int i = 0; i < N; ++i)
+    x[i] = ~x[i] & 0xfffff;
+
+  unsigned int min_res1[2] = { 1048200, 1048100 };
+  min_loop (x, 11, min_res1);
+  if (min_res1[0] != 1048113
+      || min_res1[1] != 1048069)
+    __builtin_abort ();
+
+  unsigned int min_res2[2] = { 1048112, 1048068 };
+  min_loop (x, 11, min_res2);
+  if (min_res2[0] != 1048112
+      || min_res2[1] != 1048068)
+    __builtin_abort ();
+
+  unsigned int min_res3[2] = { 10000, 10000 };
+  min_loop (x, 0x200, min_res3);
+  if (min_res3[0] != 1023
+      || min_res3[1] != 3069)
+    __builtin_abort ();
+
+  unsigned int min_res4[2] = { 1022, 3068 };
+  min_loop (x, 0x200, min_res4);
+  if (min_res4[0] != 1022
+      || min_res4[1] != 3068)
+    __builtin_abort ();
+
+  unsigned int min_res5[2] = { 719680, 718530 };
+  min_loop (x, 0x11f, min_res5);
+  if (min_res5[0] != 719673
+      || min_res5[1] != 718525)
+    __builtin_abort ();
+
+  unsigned int min_res6[2] = { 719672, 718524 };
+  min_loop (x, 0x11f, min_res6);
+  if (min_res6[0] != 719672
+      || min_res6[1] != 718524)
+    __builtin_abort ();
+
+  unsigned int and_res1[2] = { 11, 22 };
+  and_loop (x, 0, and_res1);
+  if (and_res1[0] != 11
+      || and_res1[1] != 22)
+    __builtin_abort ();
+
+  unsigned int and_res2[2] = { 0xf5cff, 0xf78ff };
+  and_loop (x, 11, and_res2);
+  if (and_res2[0] != 0xf5c01
+      || and_res2[1] != 0xf7801)
+    __builtin_abort ();
+
+  unsigned int and_res3[2] = { 0x7efff, 0xecfff };
+  and_loop (x, 0x40, and_res3);
+  if (and_res3[0] != 0x7c001
+      || and_res3[1] != 0xe8001)
+    __builtin_abort ();
+
+  unsigned int and_res4[2] = { 0xffffff, 0xffffff };
+  and_loop (x, 0x4f, and_res4);
+  if (and_res4[0] != 0xf8001
+      || and_res4[1] != 0xf8001)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-8.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-8.c
new file mode 100644
index 0000000..07fa76d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-8.c
@@ -0,0 +1,22 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math -fno-vect-cost-model" } */
+
+#define N 0x1100
+
+#include "reduc-8.c"
+
+int
+main (void)
+{
+  int x[N];
+  for (int i = 0; i < N; ++i)
+    x[i] = ((i + 1) * (i + 2)) & 0xfffff;
+
+  if (add_loop (x, 0, 33) != 33
+      || add_loop (x, 11, 30) != 4078
+      || add_loop (x, 0x100, 45) != 45001773
+      || add_loop (x, 0x11f, 300) != 63369900)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-9.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-9.c
new file mode 100644
index 0000000..47f8082
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/reduc_run-9.c
@@ -0,0 +1,22 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -ffast-math -fno-vect-cost-model" } */
+
+#define N 0x1100
+
+#include "reduc-9.c"
+
+int
+main (void)
+{
+  float x[N];
+  for (int i = 0; i < N; ++i)
+    x[i] = ((i + 1) * (i + 2)) & 0xfffff;
+
+  if (add_loop (x, 0, 33) != 33
+      || add_loop (x, 11, 30) != 4078
+      || add_loop (x, 0x100, 45) != 45001773
+      || add_loop (x, 0x11f, 300) != 63369900)
+    __builtin_abort ();
+
+  return 0;
+}