[PATCH] RISC-V: Support LEN_FOLD_EXTRACT_LAST auto-vectorization

[Juzhe-Zhong <juzhe.zhong@rivai.ai>]

Consider this following case:
int __attribute__ ((noinline, noclone))
condition_reduction (int *a, int min_v)
{
  int last = 66; /* High start value.  */

  for (int i = 0; i < 4; i++)
    if (a[i] < min_v)
      last = i;

  return last;
}

--param=riscv-autovec-preference=fixed-vlmax --param=riscv-autovec-lmul=m8

condition_reduction:
	vsetvli	a4,zero,e32,m8,ta,ma
	li	a5,32
	vmv.v.x	v8,a1
	vl8re32.v	v0,0(a0)
	vid.v	v16
	vmslt.vv	v0,v0,v8
	vsetvli	zero,a5,e8,m2,ta,ma
	vcpop.m	a5,v0
	beq	a5,zero,.L2
	addi	a5,a5,-1
	vsetvli	a4,zero,e32,m8,ta,ma
	vcompress.vm	v8,v16,v0
	vslidedown.vx	v8,v8,a5
	vmv.x.s	a0,v8
	ret
.L2:
	li	a0,66
	ret

--param=riscv-autovec-preference=scalable

condition_reduction:
	csrr	a6,vlenb
	mv	a2,a0
	li	a3,32
	li	a0,66
	srli	a6,a6,2
	vsetvli	a4,zero,e32,m1,ta,ma
	vmv.v.x	v4,a1
	vid.v	v1
.L4:
	vsetvli	a5,a3,e8,mf4,tu,mu
	vsetvli	zero,a5,e32,m1,ta,ma    ----> redundant vsetvl
	vle32.v	v0,0(a2)
	vsetvli	a4,zero,e32,m1,ta,ma
	slli	a1,a5,2
	vmv.v.x	v2,a6
	vmslt.vv	v0,v0,v4
	sub	a3,a3,a5
	vmv1r.v	v3,v1
	vadd.vv	v1,v1,v2
	vsetvli	zero,a5,e8,mf4,ta,ma
	vcpop.m	a5,v0
	beq	a5,zero,.L3
	addi	a5,a5,-1
	vsetvli	a4,zero,e32,m1,ta,ma
	vcompress.vm	v2,v3,v0
	vslidedown.vx	v2,v2,a5
	vmv.x.s	a0,v2
.L3:
	sext.w	a0,a0
	add	a2,a2,a1
	bne	a3,zero,.L4
	ret

There is a redundant vsetvli instruction in VLA vectorized codes which is the VSETVL PASS issue.

vsetvl issue is not included in this patch but will be fixed soon.

gcc/ChangeLog:

        * config/riscv/autovec.md (len_fold_extract_last_<mode>): New pattern.
        * config/riscv/riscv-protos.h (enum insn_type): New enum.
        (expand_fold_extract_last): New function.
        * config/riscv/riscv-v.cc (emit_nonvlmax_slide_insn): Ditto.
        (emit_cpop_insn): Ditto.
        (emit_nonvlmax_compress_insn): Ditto.
        (expand_fold_extract_last): Ditto.
        * config/riscv/vector.md: Fix vcpop.m ratio demand.

gcc/testsuite/ChangeLog:

        * gcc.target/riscv/rvv/autovec/reduc/extract_last-1.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-10.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-11.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-12.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-13.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-14.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-2.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-3.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-4.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-5.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-6.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-7.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-8.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last-9.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-1.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-10.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-11.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-12.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-13.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-14.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-2.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-3.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-4.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-5.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-6.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-7.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-8.c: New test.
        * gcc.target/riscv/rvv/autovec/reduc/extract_last_run-9.c: New test.

---
 gcc/config/riscv/autovec.md                   |  24 ++++
 gcc/config/riscv/riscv-protos.h               |   2 +
 gcc/config/riscv/riscv-v.cc                   | 115 +++++++++++++++++-
 gcc/config/riscv/vector.md                    |   2 +-
 .../riscv/rvv/autovec/reduc/extract_last-1.c  |  20 +++
 .../riscv/rvv/autovec/reduc/extract_last-10.c |   6 +
 .../riscv/rvv/autovec/reduc/extract_last-11.c |  24 ++++
 .../riscv/rvv/autovec/reduc/extract_last-12.c |   6 +
 .../riscv/rvv/autovec/reduc/extract_last-13.c |   7 ++
 .../riscv/rvv/autovec/reduc/extract_last-14.c |   6 +
 .../riscv/rvv/autovec/reduc/extract_last-2.c  |   6 +
 .../riscv/rvv/autovec/reduc/extract_last-3.c  |  26 ++++
 .../riscv/rvv/autovec/reduc/extract_last-4.c  |   6 +
 .../riscv/rvv/autovec/reduc/extract_last-5.c  |   8 ++
 .../riscv/rvv/autovec/reduc/extract_last-6.c  |   6 +
 .../riscv/rvv/autovec/reduc/extract_last-7.c  |   8 ++
 .../riscv/rvv/autovec/reduc/extract_last-8.c  |   6 +
 .../riscv/rvv/autovec/reduc/extract_last-9.c  |   8 ++
 .../rvv/autovec/reduc/extract_last_run-1.c    |  22 ++++
 .../rvv/autovec/reduc/extract_last_run-10.c   |   4 +
 .../rvv/autovec/reduc/extract_last_run-11.c   |  22 ++++
 .../rvv/autovec/reduc/extract_last_run-12.c   |   4 +
 .../rvv/autovec/reduc/extract_last_run-13.c   |  22 ++++
 .../rvv/autovec/reduc/extract_last_run-14.c   |   4 +
 .../rvv/autovec/reduc/extract_last_run-2.c    |   4 +
 .../rvv/autovec/reduc/extract_last_run-3.c    |  23 ++++
 .../rvv/autovec/reduc/extract_last_run-4.c    |   4 +
 .../rvv/autovec/reduc/extract_last_run-5.c    |  23 ++++
 .../rvv/autovec/reduc/extract_last_run-6.c    |   4 +
 .../rvv/autovec/reduc/extract_last_run-7.c    |  25 ++++
 .../rvv/autovec/reduc/extract_last_run-8.c    |   4 +
 .../rvv/autovec/reduc/extract_last_run-9.c    |  23 ++++
 32 files changed, 472 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-1.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-10.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-11.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-12.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-13.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-14.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-2.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-3.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-4.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-5.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-6.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-7.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-8.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-9.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-1.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-10.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-11.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-12.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-13.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-14.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-2.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-3.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-4.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-5.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-6.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-7.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-8.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-9.c

diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index e1addc07036..9760fa4dde0 100644
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -2126,6 +2126,30 @@
   DONE;
 })
 
+;; -------------------------------------------------------------------------
+;; ---- [INT,FP] Extract active element
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - vcompress.vm
+;; - vcpop.m
+;; - vslidedown.vx
+;; - vmv.x.s
+;; - vfmv.f.s
+;; -------------------------------------------------------------------------
+
+(define_expand "len_fold_extract_last_<mode>"
+  [(match_operand:<VEL> 0 "register_operand")
+   (match_operand:<VEL> 1 "register_operand")
+   (match_operand:<VM> 2 "register_operand")
+   (match_operand:V 3 "register_operand")
+   (match_operand 4 "autovec_length_operand")
+   (match_operand 5 "const_0_operand")]
+  "TARGET_VECTOR"
+  {
+    riscv_vector::expand_fold_extract_last (operands);
+    DONE;
+  })
+
 ;; -------------------------------------------------------------------------
 ;; ---- [INT] Average.
 ;; -------------------------------------------------------------------------
diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index 2c4405c9860..68ec1bdf62b 100644
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -207,6 +207,7 @@ enum insn_type
   RVV_SCATTER_M_OP = 4,
   RVV_REDUCTION_OP = 3,
   RVV_REDUCTION_TU_OP = RVV_REDUCTION_OP + 2,
+  RVV_CPOP = 2,
 };
 enum vlmul_type
 {
@@ -329,6 +330,7 @@ void expand_gather_scatter (rtx *, bool);
 void expand_cond_len_ternop (unsigned, rtx *);
 void prepare_ternary_operands (rtx *, bool = false);
 void expand_lanes_load_store (rtx *, bool);
+void expand_fold_extract_last (rtx *);
 
 /* Rounding mode bitfield for fixed point VXRM.  */
 enum fixed_point_rounding_mode
diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index 14eda581d00..7c9b9a4f50a 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -213,7 +213,7 @@ public:
 	      {
 		/* Optimize VLS-VLMAX code gen, we can use vsetivli instead of
 		   the vsetvli to obtain the value of vlmax.  */
-		poly_uint64 nunits = GET_MODE_NUNITS (m_dest_mode);
+		poly_uint64 nunits = GET_MODE_NUNITS (m_mask_mode);
 		len = gen_int_mode (nunits, Pmode);
 		m_vlmax_p = false; /* It has became NONVLMAX now.  */
 	      }
@@ -848,6 +848,28 @@ emit_nonvlmax_slide_tu_insn (unsigned icode, rtx *ops, rtx avl)
   e.emit_insn ((enum insn_code) icode, ops);
 }
 
+/* This function emits a {NONVLMAX, TAIL_ANY, MASK_ANY} vsetvli
+   followed by a vslide insn (with real merge operand).  */
+void
+emit_nonvlmax_slide_insn (unsigned icode, rtx *ops, rtx avl)
+{
+  machine_mode dest_mode = GET_MODE (ops[0]);
+  machine_mode mask_mode = get_mask_mode (dest_mode);
+  insn_expander<RVV_INSN_OPERANDS_MAX> e (RVV_SLIDE_OP,
+					  /* HAS_DEST_P */ true,
+					  /* FULLY_UNMASKED_P */ true,
+					  /* USE_REAL_MERGE_P */ true,
+					  /* HAS_AVL_P */ true,
+					  /* VLMAX_P */ true,
+					  dest_mode,
+					  mask_mode);
+
+  e.set_policy (TAIL_ANY);
+  e.set_policy (MASK_ANY);
+  e.set_vl (avl);
+
+  e.emit_insn ((enum insn_code) icode, ops);
+}
 
 /* This function emits merge instruction.  */
 void
@@ -1111,6 +1133,25 @@ emit_scalar_move_insn (unsigned icode, rtx *ops, rtx len)
   e.emit_insn ((enum insn_code) icode, ops);
 }
 
+/* Emit vcpop.m instruction.  */
+
+static void
+emit_cpop_insn (unsigned icode, rtx *ops, rtx len)
+{
+  machine_mode dest_mode = GET_MODE (ops[0]);
+  machine_mode mask_mode = GET_MODE (ops[1]);
+  insn_expander<RVV_INSN_OPERANDS_MAX> e (RVV_CPOP,
+					  /* HAS_DEST_P */ true,
+					  /* FULLY_UNMASKED_P */ true,
+					  /* USE_REAL_MERGE_P */ true,
+					  /* HAS_AVL_P */ true,
+					  /* VLMAX_P */ len ? false : true,
+					  dest_mode, mask_mode);
+
+  e.set_vl (len);
+  e.emit_insn ((enum insn_code) icode, ops);
+}
+
 /* Emit vmv.v.x instruction with vlmax.  */
 
 static void
@@ -1228,6 +1269,25 @@ emit_vlmax_compress_insn (unsigned icode, rtx *ops)
   e.emit_insn ((enum insn_code) icode, ops);
 }
 
+/* Emit compress instruction.  */
+static void
+emit_nonvlmax_compress_insn (unsigned icode, rtx *ops, rtx avl)
+{
+  machine_mode dest_mode = GET_MODE (ops[0]);
+  machine_mode mask_mode = get_mask_mode (dest_mode);
+  insn_expander<RVV_INSN_OPERANDS_MAX> e (RVV_COMPRESS_OP,
+					  /* HAS_DEST_P */ true,
+					  /* FULLY_UNMASKED_P */ false,
+					  /* USE_REAL_MERGE_P */ true,
+					  /* HAS_AVL_P */ true,
+					  /* VLMAX_P */ true, dest_mode,
+					  mask_mode);
+
+  e.set_policy (TAIL_ANY);
+  e.set_vl (avl);
+  e.emit_insn ((enum insn_code) icode, ops);
+}
+
 /* Emit reduction instruction.  */
 static void
 emit_vlmax_reduction_insn (unsigned icode, int op_num, rtx *ops)
@@ -3816,4 +3876,57 @@ expand_lanes_load_store (rtx *ops, bool is_load)
     }
 }
 
+/* Expand LEN_FOLD_EXTRACT_LAST.  */
+void
+expand_fold_extract_last (rtx *ops)
+{
+  rtx dst = ops[0];
+  rtx default_value = ops[1];
+  rtx mask = ops[2];
+  rtx anchor = gen_reg_rtx (Pmode);
+  rtx index = gen_reg_rtx (Pmode);
+  rtx vect = ops[3];
+  rtx else_label = gen_label_rtx ();
+  rtx end_label = gen_label_rtx ();
+  rtx len = ops[4];
+  poly_int64 value;
+  machine_mode mode = GET_MODE (vect);
+  machine_mode mask_mode = GET_MODE (mask);
+  rtx compress_vect = gen_reg_rtx (mode);
+  rtx slide_vect = gen_reg_rtx (mode);
+  insn_code icode;
+
+  if (poly_int_rtx_p (len, &value) && known_eq (value, GET_MODE_NUNITS (mode)))
+    len = NULL_RTX;
+
+  /* Calculate the number of 1-bit in mask. */
+  rtx cpop_ops[] = {anchor, mask};
+  emit_cpop_insn (code_for_pred_popcount (mask_mode, Pmode), cpop_ops, len);
+
+  riscv_expand_conditional_branch (else_label, EQ, anchor, const0_rtx);
+  emit_insn (gen_rtx_SET (index, gen_rtx_PLUS (Pmode, anchor, constm1_rtx)));
+  /* Compress the vector.  */
+  icode = code_for_pred_compress (mode);
+  rtx compress_ops[] = {compress_vect, RVV_VUNDEF (mode), vect, mask};
+  if (len)
+    emit_nonvlmax_compress_insn (icode, compress_ops, len);
+  else
+    emit_vlmax_compress_insn (icode, compress_ops);
+  /* Emit the slide down to index 0 in a new vector.  */
+  rtx slide_ops[] = {slide_vect, RVV_VUNDEF (mode), compress_vect, index};
+  icode = code_for_pred_slide (UNSPEC_VSLIDEDOWN, mode);
+  if (len)
+    emit_nonvlmax_slide_insn (icode, slide_ops, len);
+  else
+    emit_vlmax_slide_insn (icode, slide_ops);
+  /* Emit v(f)mv.[xf].s.  */
+  emit_insn (gen_pred_extract_first (mode, dst, slide_vect));
+
+  emit_jump_insn (gen_jump (end_label));
+  emit_barrier ();
+  emit_label (else_label);
+  emit_move_insn (dst, default_value);
+  emit_label (end_label);
+}
+
 } // namespace riscv_vector
diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md
index 6ceae25dbed..a442e0fdd3c 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -417,7 +417,7 @@
 			  vialu,vshift,vicmp,vimul,vidiv,vsalu,\
 			  vext,viwalu,viwmul,vicalu,vnshift,\
 			  vimuladd,vimerge,vaalu,vsmul,vsshift,\
-			  vnclip,viminmax,viwmuladd,vmpop,vmffs,vmsfs,\
+			  vnclip,viminmax,viwmuladd,vmffs,vmsfs,\
 			  vmiota,vmidx,vfalu,vfmul,vfminmax,vfdiv,\
 			  vfwalu,vfwmul,vfsqrt,vfrecp,vfsgnj,vfcmp,\
 			  vfmerge,vfcvtitof,vfcvtftoi,vfwcvtitof,\
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-1.c
new file mode 100644
index 00000000000..6c86f29e7d4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-1.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#define N 32
+
+/* Simple condition reduction.  */
+
+int __attribute__ ((noinline, noclone))
+condition_reduction (int *a, int min_v)
+{
+  int last = 66; /* High start value.  */
+
+  for (int i = 0; i < N; i++)
+    if (a[i] < min_v)
+      last = i;
+
+  return last;
+}
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-10.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-10.c
new file mode 100644
index 00000000000..c5fe5204763
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-10.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#include "extract_last-9.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-11.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-11.c
new file mode 100644
index 00000000000..85547c8bd76
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-11.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#define N 32
+
+#ifndef TYPE
+#define TYPE float
+#endif
+
+/* Non-integer data types.  */
+
+TYPE __attribute__ ((noinline, noclone))
+condition_reduction (TYPE *a, TYPE min_v)
+{
+  TYPE last = 0;
+
+  for (int i = 0; i < N; i++)
+    if (a[i] < min_v)
+      last = a[i];
+
+  return last;
+}
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-12.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-12.c
new file mode 100644
index 00000000000..c165cb33ce4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-12.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#include "extract_last-11.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-13.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-13.c
new file mode 100644
index 00000000000..9a04af6c266
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-13.c
@@ -0,0 +1,7 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#define TYPE double
+#include "extract_last-11.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-14.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-14.c
new file mode 100644
index 00000000000..88f8a4c056a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-14.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#include "extract_last-13.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-2.c
new file mode 100644
index 00000000000..b1eea0db0cd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-2.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#include "extract_last-1.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-3.c
new file mode 100644
index 00000000000..2c94ef58a47
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-3.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#include <stdint-gcc.h>
+
+#if !defined(TYPE)
+#define TYPE uint32_t
+#endif
+
+#define N 254
+
+/* Non-simple condition reduction.  */
+
+TYPE __attribute__ ((noinline, noclone))
+condition_reduction (TYPE *a, TYPE min_v)
+{
+  TYPE last = 65;
+
+  for (TYPE i = 0; i < N; i++)
+    if (a[i] < min_v)
+      last = a[i];
+
+  return last;
+}
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-4.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-4.c
new file mode 100644
index 00000000000..a9ac667edd3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-4.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#include "extract_last-3.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-5.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-5.c
new file mode 100644
index 00000000000..dc7fa639786
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-5.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#define TYPE uint8_t
+
+#include "extract_last-3.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-6.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-6.c
new file mode 100644
index 00000000000..4e434a1813d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-6.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#include "extract_last-5.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-7.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-7.c
new file mode 100644
index 00000000000..e75e9b21ed3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-7.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#define TYPE int16_t
+
+#include "extract_last-3.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-8.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-8.c
new file mode 100644
index 00000000000..a37eb26f5a4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-8.c
@@ -0,0 +1,6 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=scalable -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#include "extract_last-7.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-9.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-9.c
new file mode 100644
index 00000000000..c7ae0d747cc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last-9.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d --param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model -fdump-tree-optimized" } */
+
+#define TYPE uint64_t
+
+#include "extract_last-3.c"
+
+/* { dg-final { scan-tree-dump "\.LEN_FOLD_EXTRACT_LAST" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-1.c
new file mode 100644
index 00000000000..c2083455cde
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-1.c
@@ -0,0 +1,22 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model" } */
+
+#include "extract_last-1.c"
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+  int a[N] = {
+    11, -12, 13, 14, 15, 16, 17, 18, 19, 20,
+    1, 2, -3, 4, 5, 6, 7, -8, 9, 10,
+    21, 22, 23, 24, 25, 26, 27, 28, 29, 30,
+    31, 32
+  };
+
+  int ret = condition_reduction (a, 1);
+
+  if (ret != 17)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-10.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-10.c
new file mode 100644
index 00000000000..7ff435df4f1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-10.c
@@ -0,0 +1,4 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "extract_last_run-9.c"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-11.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-11.c
new file mode 100644
index 00000000000..99af6b3287e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-11.c
@@ -0,0 +1,22 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model" } */
+
+#include "extract_last-11.c"
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+  float a[N] = {
+    11.5, 12.2, 13.22, 14.1, 15.2, 16.3, 17, 18.7, 19, 20,
+    1, 2, 3.3, 4.3333, 5.5, 6.23, 7, 8.63, 9, 10.6,
+    21, 22.12, 23.55, 24.76, 25, 26, 27.34, 28.765, 29, 30,
+    31.111, 32.322
+  };
+
+  float ret = condition_reduction (a, 16.7);
+
+  if (ret != (float) 10.6)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-12.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-12.c
new file mode 100644
index 00000000000..43d1c765bb5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-12.c
@@ -0,0 +1,4 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "extract_last_run-11.c"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-13.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-13.c
new file mode 100644
index 00000000000..1e418964d68
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-13.c
@@ -0,0 +1,22 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model" } */
+
+#include "extract_last-13.c"
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+  double a[N] = {
+    11.5, 12.2, 13.22, 14.1, 15.2, 16.3, 17, 18.7, 19, 20,
+    1, 2, 3.3, 4.3333, 5.5, 6.23, 7, 8.63, 9, 10.6,
+    21, 22.12, 23.55, 24.76, 25, 26, 27.34, 28.765, 29, 30,
+    31.111, 32.322
+  };
+
+  double ret = condition_reduction (a, 16.7);
+
+  if (ret != 10.6)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-14.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-14.c
new file mode 100644
index 00000000000..535b68f0f22
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-14.c
@@ -0,0 +1,4 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "extract_last_run-13.c"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-2.c
new file mode 100644
index 00000000000..ee53bf9ccab
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-2.c
@@ -0,0 +1,4 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "extract_last_run-1.c"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-3.c
new file mode 100644
index 00000000000..ff2b0258dc8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-3.c
@@ -0,0 +1,23 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model" } */
+
+#include "extract_last-3.c"
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+  TYPE a[N] = {
+    11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
+    1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
+    21, 22, 23, 24, 25, 26, 27, 28, 29, 30,
+    31, 32
+  };
+  __builtin_memset (a + 32, 43, (N - 32) * sizeof (TYPE));
+
+  TYPE ret = condition_reduction (a, 16);
+
+  if (ret != 10)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-4.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-4.c
new file mode 100644
index 00000000000..4b5b6332adf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-4.c
@@ -0,0 +1,4 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "extract_last_run-3.c"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-5.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-5.c
new file mode 100644
index 00000000000..7b66b24261f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-5.c
@@ -0,0 +1,23 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model" } */
+
+#include "extract_last-5.c"
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+  TYPE a[N] = {
+    11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
+    1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
+    21, 22, 23, 24, 25, 26, 27, 28, 29, 30,
+    31, 32
+  };
+  __builtin_memset (a + 32, 43, (N - 32) * sizeof (TYPE));
+
+  TYPE ret = condition_reduction (a, 16);
+
+  if (ret != 10)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-6.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-6.c
new file mode 100644
index 00000000000..a52eac92487
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-6.c
@@ -0,0 +1,4 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "extract_last_run-5.c"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-7.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-7.c
new file mode 100644
index 00000000000..a1ac4a5dfb7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-7.c
@@ -0,0 +1,25 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model" } */
+
+#include "extract_last-7.c"
+
+extern void abort (void) __attribute__ ((noreturn));
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+  TYPE a[N] = {
+  11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
+  1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
+  21, 22, 23, 24, 25, 26, 27, 28, 29, 30,
+  31, 32
+  };
+  __builtin_memset (a+32, 43, (N-32)*sizeof (TYPE));
+
+  TYPE ret = condition_reduction (a, 16);
+
+  if (ret != 10)
+    abort ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-8.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-8.c
new file mode 100644
index 00000000000..56858f99921
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-8.c
@@ -0,0 +1,4 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=scalable -fno-vect-cost-model" } */
+
+#include "extract_last_run-7.c"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-9.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-9.c
new file mode 100644
index 00000000000..67672bfb705
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/reduc/extract_last_run-9.c
@@ -0,0 +1,23 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param=riscv-autovec-preference=fixed-vlmax -fno-vect-cost-model" } */
+
+#include "extract_last-9.c"
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+  TYPE a[N] = {
+    11, 12, 13, 14, 15, 16, 17, 18, 19, 20,
+    1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
+    21, 22, 23, 24, 25, 26, 27, 28, 29, 30,
+    31, 32
+  };
+  __builtin_memset (a + 32, 43, (N - 32) * sizeof (TYPE));
+
+  TYPE ret = condition_reduction (a, 16);
+
+  if (ret != 10)
+    __builtin_abort ();
+
+  return 0;
+}
-- 
2.36.3