RISC-V: Implement vec_set and vec_extract.

This implements the vec_set and vec_extract patterns for integer and
floating-point data types.  For vec_set we broadcast the insert value to
a vector register and then perform a vslideup with effective length 1 to
the requested index.

vec_extract is done by sliding down the requested element to index 0
and v(f)mv.[xf].s to a scalar register.

The patch does not include vector-vector extraction which
will be done at a later time.

gcc/ChangeLog:

	* config/riscv/autovec.md (vec_set<mode>): Implement.
	(vec_extract<mode><vel>): Implement.
	* config/riscv/riscv-protos.h (enum insn_type): Add slide insn.
	(emit_vlmax_slide_insn): Declare.
	(emit_nonvlmax_slide_tu_insn): Declare.
	(emit_scalar_move_insn): Export.
	(emit_nonvlmax_integer_move_insn): Export.
	* config/riscv/riscv-v.cc (emit_vlmax_slide_insn): New function.
	(emit_nonvlmax_slide_tu_insn): New function.
	(emit_vlmax_masked_mu_insn): No change.
	(emit_vlmax_integer_move_insn): Export.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-1.c: New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-2.c: New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-3.c: New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-4.c: New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-zvfh-run.c:
	New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-1.c: New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-2.c: New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-3.c: New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-4.c: New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-run.c: New test.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-zvfh-run.c:
	New test.

15 files changed, 1323 insertions, 2 deletions

diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index c23a625..9569b42 100644
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -655,3 +655,82 @@
   riscv_vector::expand_select_vl (operands);
   DONE;
 })
+
+;; -------------------------------------------------------------------------
+;; ---- [INT,FP] Insert a vector element.
+;; -------------------------------------------------------------------------
+
+(define_expand "vec_set<mode>"
+  [(match_operand:V	0 "register_operand")
+   (match_operand:<VEL> 1 "register_operand")
+   (match_operand	2 "immediate_operand")]
+  "TARGET_VECTOR"
+{
+  /* If we set the first element, emit an v(f)mv.s.[xf].  */
+  if (operands[2] == const0_rtx)
+    {
+      rtx ops[] = {operands[0], riscv_vector::gen_scalar_move_mask (<VM>mode),
+		   RVV_VUNDEF (<MODE>mode), operands[1]};
+      riscv_vector::emit_scalar_move_insn
+	  (code_for_pred_broadcast (<MODE>mode), ops);
+    }
+  else
+    {
+      /* Move the desired value into a vector register and insert
+	 it at the proper position using vslideup with an
+	 "effective length" of 1 i.e. a VL 1 past the offset.  */
+
+      /* Slide offset = element index.  */
+      int offset = INTVAL (operands[2]);
+
+      /* Only insert one element, i.e. VL = offset + 1.  */
+      rtx length = gen_reg_rtx (Pmode);
+      emit_move_insn (length, GEN_INT (offset + 1));
+
+      /* Move operands[1] into a vector register via vmv.v.x using the same
+	 VL we need for the slide.  */
+      rtx tmp = gen_reg_rtx (<MODE>mode);
+      rtx ops1[] = {tmp, operands[1]};
+      riscv_vector::emit_nonvlmax_integer_move_insn
+	(code_for_pred_broadcast (<MODE>mode), ops1, length);
+
+      /* Slide exactly one element up leaving the tail elements
+	 unchanged.  */
+      rtx ops2[] = {operands[0], operands[0], tmp, operands[2]};
+      riscv_vector::emit_nonvlmax_slide_tu_insn
+	(code_for_pred_slide (UNSPEC_VSLIDEUP, <MODE>mode), ops2, length);
+    }
+  DONE;
+})
+
+;; -------------------------------------------------------------------------
+;; ---- [INT,FP] Extract a vector element.
+;; -------------------------------------------------------------------------
+(define_expand "vec_extract<mode><vel>"
+  [(set (match_operand:<VEL>	  0 "register_operand")
+     (vec_select:<VEL>
+       (match_operand:V		  1 "register_operand")
+       (parallel
+	 [(match_operand	  2 "nonmemory_operand")])))]
+  "TARGET_VECTOR"
+{
+  /* Element extraction can be done by sliding down the requested element
+     to index 0 and then v(f)mv.[xf].s it to a scalar register.  */
+
+  /* When extracting any other than the first element we need to slide
+     it down.  */
+  rtx tmp = NULL_RTX;
+  if (operands[2] != const0_rtx)
+    {
+      /* Emit the slide down to index 0 in a new vector.  */
+      tmp = gen_reg_rtx (<MODE>mode);
+      rtx ops[] = {tmp, RVV_VUNDEF (<MODE>mode), operands[1], operands[2]};
+      riscv_vector::emit_vlmax_slide_insn
+	(code_for_pred_slide (UNSPEC_VSLIDEDOWN, <MODE>mode), ops);
+    }
+
+  /* Emit v(f)mv.[xf].s.  */
+  emit_insn (gen_pred_extract_first (<MODE>mode, operands[0],
+				     tmp ? tmp : operands[1]));
+  DONE;
+})
diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index b23a9c1..f422adf 100644
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -146,6 +146,7 @@ enum insn_type
   RVV_TERNOP = 5,
   RVV_WIDEN_TERNOP = 4,
   RVV_SCALAR_MOV_OP = 4, /* +1 for VUNDEF according to vector.md.  */
+  RVV_SLIDE_OP = 4,      /* Dest, VUNDEF, source and offset.  */
 };
 enum vlmul_type
 {
@@ -186,10 +187,14 @@ void emit_hard_vlmax_vsetvl (machine_mode, rtx);
 void emit_vlmax_insn (unsigned, int, rtx *, rtx = 0);
 void emit_vlmax_ternary_insn (unsigned, int, rtx *, rtx = 0);
 void emit_nonvlmax_insn (unsigned, int, rtx *, rtx);
+void emit_vlmax_slide_insn (unsigned, rtx *);
+void emit_nonvlmax_slide_tu_insn (unsigned, rtx *, rtx);
 void emit_vlmax_merge_insn (unsigned, int, rtx *);
 void emit_vlmax_cmp_insn (unsigned, rtx *);
 void emit_vlmax_cmp_mu_insn (unsigned, rtx *);
 void emit_vlmax_masked_mu_insn (unsigned, int, rtx *);
+void emit_scalar_move_insn (unsigned, rtx *);
+void emit_nonvlmax_integer_move_insn (unsigned, rtx *, rtx);
 enum vlmul_type get_vlmul (machine_mode);
 unsigned int get_ratio (machine_mode);
 unsigned int get_nf (machine_mode);
diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index 6421e93..c6aa710 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -695,6 +695,52 @@ emit_nonvlmax_insn (unsigned icode, int op_num, rtx *ops, rtx avl)
   e.emit_insn ((enum insn_code) icode, ops);
 }
 
+/* This function emits a {NONVLMAX, TAIL_UNDISTURBED, MASK_ANY} vsetvli
+   followed by a vslide insn (with real merge operand).  */
+void
+emit_vlmax_slide_insn (unsigned icode, rtx *ops)
+{
+  machine_mode dest_mode = GET_MODE (ops[0]);
+  machine_mode mask_mode = get_mask_mode (dest_mode).require ();
+  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.emit_insn ((enum insn_code) icode, ops);
+}
+
+/* This function emits a {NONVLMAX, TAIL_UNDISTURBED, MASK_ANY} vsetvli
+   followed by a vslide insn (with real merge operand).  */
+void
+emit_nonvlmax_slide_tu_insn (unsigned icode, rtx *ops, rtx avl)
+{
+  machine_mode dest_mode = GET_MODE (ops[0]);
+  machine_mode mask_mode = get_mask_mode (dest_mode).require ();
+  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 */ false,
+					  dest_mode,
+					  mask_mode);
+
+  e.set_policy (TAIL_UNDISTURBED);
+  e.set_policy (MASK_ANY);
+  e.set_vl (avl);
+
+  e.emit_insn ((enum insn_code) icode, ops);
+}
+
+
 /* This function emits merge instruction.  */
 void
 emit_vlmax_merge_insn (unsigned icode, int op_num, rtx *ops)
@@ -768,7 +814,7 @@ emit_vlmax_masked_mu_insn (unsigned icode, int op_num, rtx *ops)
 
 /* Emit vmv.s.x instruction.  */
 
-static void
+void
 emit_scalar_move_insn (unsigned icode, rtx *ops)
 {
   machine_mode dest_mode = GET_MODE (ops[0]);
@@ -798,7 +844,7 @@ emit_vlmax_integer_move_insn (unsigned icode, rtx *ops, rtx vl)
 
 /* Emit vmv.v.x instruction with nonvlmax.  */
 
-static void
+void
 emit_nonvlmax_integer_move_insn (unsigned icode, rtx *ops, rtx avl)
 {
   emit_nonvlmax_insn (icode, riscv_vector::RVV_UNOP, ops, avl);
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-1.c
new file mode 100644
index 0000000..bda5843
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-1.c
@@ -0,0 +1,57 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <stdint-gcc.h>
+
+typedef int64_t vnx2di __attribute__((vector_size (16)));
+typedef int32_t vnx4si __attribute__((vector_size (16)));
+typedef int16_t vnx8hi __attribute__((vector_size (16)));
+typedef int8_t vnx16qi __attribute__((vector_size (16)));
+typedef _Float16 vnx8hf __attribute__((vector_size (16)));
+typedef float vnx4sf __attribute__((vector_size (16)));
+typedef double vnx2df __attribute__((vector_size (16)));
+
+
+#define VEC_EXTRACT(S,V,IDX)			\
+  S						\
+  __attribute__((noipa))			\
+  vec_extract_##V##_##IDX (V v)			\
+  {						\
+    return v[IDX];				\
+  }
+
+#define TEST_ALL1(T)				\
+  T (_Float16, vnx8hf, 0)			\
+  T (_Float16, vnx8hf, 3)			\
+  T (_Float16, vnx8hf, 7)			\
+  T (float, vnx4sf, 0)				\
+  T (float, vnx4sf, 1)				\
+  T (float, vnx4sf, 3)				\
+  T (double, vnx2df, 0)				\
+  T (double, vnx2df, 1)				\
+  T (int64_t, vnx2di, 0)			\
+  T (int64_t, vnx2di, 1)			\
+  T (int32_t, vnx4si, 0)			\
+  T (int32_t, vnx4si, 1)			\
+  T (int32_t, vnx4si, 3)			\
+  T (int16_t, vnx8hi, 0)			\
+  T (int16_t, vnx8hi, 2)			\
+  T (int16_t, vnx8hi, 6)			\
+  T (int8_t, vnx16qi, 0)			\
+  T (int8_t, vnx16qi, 1)			\
+  T (int8_t, vnx16qi, 7)			\
+  T (int8_t, vnx16qi, 11)			\
+  T (int8_t, vnx16qi, 15)			\
+
+TEST_ALL1 (VEC_EXTRACT)
+
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m1,\s*ta,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m1,\s*ta,\s*ma} 6 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m1,\s*ta,\s*ma} 6 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m1,\s*ta,\s*ma} 4 } } */
+
+/* { dg-final { scan-assembler-times {\tvslidedown.vi} 14 } } */
+/* { dg-final { scan-assembler-times {\tvslidedown.vx} 0 } } */
+
+/* { dg-final { scan-assembler-times {\tvfmv.f.s} 8 } } */
+/* { dg-final { scan-assembler-times {\tvmv.x.s} 13 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-2.c
new file mode 100644
index 0000000..43aa15c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-2.c
@@ -0,0 +1,68 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <stdint-gcc.h>
+
+typedef int64_t vnx4di __attribute__((vector_size (32)));
+typedef int32_t vnx8si __attribute__((vector_size (32)));
+typedef int16_t vnx16hi __attribute__((vector_size (32)));
+typedef int8_t vnx32qi __attribute__((vector_size (32)));
+typedef _Float16 vnx16hf __attribute__((vector_size (32)));
+typedef float vnx8sf __attribute__((vector_size (32)));
+typedef double vnx4df __attribute__((vector_size (32)));
+
+#define VEC_EXTRACT(S,V,IDX)			\
+  S						\
+  __attribute__((noipa))			\
+  vec_extract_##V##_##IDX (V v)			\
+  {						\
+    return v[IDX];				\
+  }
+
+#define TEST_ALL2(T)				\
+  T (_Float16, vnx16hf, 0)			\
+  T (_Float16, vnx16hf, 3)			\
+  T (_Float16, vnx16hf, 7)			\
+  T (_Float16, vnx16hf, 8)			\
+  T (_Float16, vnx16hf, 15)			\
+  T (float, vnx8sf, 0)				\
+  T (float, vnx8sf, 1)				\
+  T (float, vnx8sf, 3)				\
+  T (float, vnx8sf, 4)				\
+  T (float, vnx8sf, 7)				\
+  T (double, vnx4df, 0)				\
+  T (double, vnx4df, 1)				\
+  T (double, vnx4df, 2)				\
+  T (double, vnx4df, 3)				\
+  T (int64_t, vnx4di, 0)			\
+  T (int64_t, vnx4di, 1)			\
+  T (int64_t, vnx4di, 2)			\
+  T (int64_t, vnx4di, 3)			\
+  T (int32_t, vnx8si, 0)			\
+  T (int32_t, vnx8si, 1)			\
+  T (int32_t, vnx8si, 3)			\
+  T (int32_t, vnx8si, 4)			\
+  T (int32_t, vnx8si, 7)			\
+  T (int16_t, vnx16hi, 0)			\
+  T (int16_t, vnx16hi, 1)			\
+  T (int16_t, vnx16hi, 7)			\
+  T (int16_t, vnx16hi, 8)			\
+  T (int16_t, vnx16hi, 15)			\
+  T (int8_t, vnx32qi, 0)			\
+  T (int8_t, vnx32qi, 1)			\
+  T (int8_t, vnx32qi, 15)			\
+  T (int8_t, vnx32qi, 16)			\
+  T (int8_t, vnx32qi, 31)			\
+
+TEST_ALL2 (VEC_EXTRACT)
+
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m2,\s*ta,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m2,\s*ta,\s*ma} 10 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m2,\s*ta,\s*ma} 10 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m2,\s*ta,\s*ma} 8 } } */
+
+/* { dg-final { scan-assembler-times {\tvslidedown.vi} 26 } } */
+/* { dg-final { scan-assembler-times {\tvslidedown.vx} 0 } } */
+
+/* { dg-final { scan-assembler-times {\tvfmv.f.s} 14 } } */
+/* { dg-final { scan-assembler-times {\tvmv.x.s} 19 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-3.c
new file mode 100644
index 0000000..da26ed9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-3.c
@@ -0,0 +1,69 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <stdint-gcc.h>
+
+typedef int64_t vnx8di __attribute__((vector_size (64)));
+typedef int32_t vnx16si __attribute__((vector_size (64)));
+typedef int16_t vnx32hi __attribute__((vector_size (64)));
+typedef int8_t vnx64qi __attribute__((vector_size (64)));
+typedef _Float16 vnx32hf __attribute__((vector_size (64)));
+typedef float vnx16sf __attribute__((vector_size (64)));
+typedef double vnx8df __attribute__((vector_size (64)));
+
+#define VEC_EXTRACT(S,V,IDX)			\
+  S						\
+  __attribute__((noipa))			\
+  vec_extract_##V##_##IDX (V v)			\
+  {						\
+    return v[IDX];				\
+  }
+
+#define TEST_ALL3(T)				\
+  T (_Float16, vnx32hf, 0)			\
+  T (_Float16, vnx32hf, 3)			\
+  T (_Float16, vnx32hf, 7)			\
+  T (_Float16, vnx32hf, 8)			\
+  T (_Float16, vnx32hf, 16)			\
+  T (_Float16, vnx32hf, 31)			\
+  T (float, vnx16sf, 0)				\
+  T (float, vnx16sf, 2)				\
+  T (float, vnx16sf, 6)				\
+  T (float, vnx16sf, 8)				\
+  T (float, vnx16sf, 14)			\
+  T (double, vnx8df, 0)				\
+  T (double, vnx8df, 2)				\
+  T (double, vnx8df, 4)				\
+  T (double, vnx8df, 6)				\
+  T (int64_t, vnx8di, 0)			\
+  T (int64_t, vnx8di, 2)			\
+  T (int64_t, vnx8di, 4)			\
+  T (int64_t, vnx8di, 6)			\
+  T (int32_t, vnx16si, 0)			\
+  T (int32_t, vnx16si, 2)			\
+  T (int32_t, vnx16si, 6)			\
+  T (int32_t, vnx16si, 8)			\
+  T (int32_t, vnx16si, 14)			\
+  T (int16_t, vnx32hi, 0)			\
+  T (int16_t, vnx32hi, 2)			\
+  T (int16_t, vnx32hi, 14)			\
+  T (int16_t, vnx32hi, 16)			\
+  T (int16_t, vnx32hi, 30)			\
+  T (int8_t, vnx64qi, 0)			\
+  T (int8_t, vnx64qi, 2)			\
+  T (int8_t, vnx64qi, 30)			\
+  T (int8_t, vnx64qi, 32)			\
+  T (int8_t, vnx64qi, 63)			\
+
+TEST_ALL3 (VEC_EXTRACT)
+
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m4,\s*ta,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m4,\s*ta,\s*ma} 11 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m4,\s*ta,\s*ma} 10 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m4,\s*ta,\s*ma} 8 } } */
+
+/* { dg-final { scan-assembler-times {\tvslidedown.vi} 25 } } */
+/* { dg-final { scan-assembler-times {\tvslidedown.vx} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tvfmv.f.s} 15 } } */
+/* { dg-final { scan-assembler-times {\tvmv.x.s} 19 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-4.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-4.c
new file mode 100644
index 0000000..0d7c0e1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-4.c
@@ -0,0 +1,72 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <stdint-gcc.h>
+
+typedef int64_t vnx16di __attribute__((vector_size (128)));
+typedef int32_t vnx32si __attribute__((vector_size (128)));
+typedef int16_t vnx64hi __attribute__((vector_size (128)));
+typedef int8_t vnx128qi __attribute__((vector_size (128)));
+typedef _Float16 vnx64hf __attribute__((vector_size (128)));
+typedef float vnx32sf __attribute__((vector_size (128)));
+typedef double vnx16df __attribute__((vector_size (128)));
+
+#define VEC_EXTRACT(S,V,IDX)			\
+  S						\
+  __attribute__((noipa))			\
+  vec_extract_##V##_##IDX (V v)			\
+  {						\
+    return v[IDX];				\
+  }
+
+#define TEST_ALL4(T)				\
+  T (_Float16, vnx64hf, 0)			\
+  T (_Float16, vnx64hf, 3)			\
+  T (_Float16, vnx64hf, 7)			\
+  T (_Float16, vnx64hf, 8)			\
+  T (_Float16, vnx64hf, 16)			\
+  T (_Float16, vnx64hf, 31)			\
+  T (_Float16, vnx64hf, 42)			\
+  T (_Float16, vnx64hf, 63)			\
+  T (float, vnx32sf, 0)				\
+  T (float, vnx32sf, 3)				\
+  T (float, vnx32sf, 12)			\
+  T (float, vnx32sf, 17)			\
+  T (float, vnx32sf, 14)			\
+  T (double, vnx16df, 0)			\
+  T (double, vnx16df, 4)			\
+  T (double, vnx16df, 8)			\
+  T (double, vnx16df, 12)			\
+  T (int64_t, vnx16di, 0)			\
+  T (int64_t, vnx16di, 4)			\
+  T (int64_t, vnx16di, 8)			\
+  T (int64_t, vnx16di, 12)			\
+  T (int32_t, vnx32si, 0)			\
+  T (int32_t, vnx32si, 4)			\
+  T (int32_t, vnx32si, 12)			\
+  T (int32_t, vnx32si, 16)			\
+  T (int32_t, vnx32si, 28)			\
+  T (int16_t, vnx64hi, 0)			\
+  T (int16_t, vnx64hi, 4)			\
+  T (int16_t, vnx64hi, 28)			\
+  T (int16_t, vnx64hi, 32)			\
+  T (int16_t, vnx64hi, 60)			\
+  T (int8_t, vnx128qi, 0)			\
+  T (int8_t, vnx128qi, 4)			\
+  T (int8_t, vnx128qi, 30)			\
+  T (int8_t, vnx128qi, 60)			\
+  T (int8_t, vnx128qi, 64)			\
+  T (int8_t, vnx128qi, 127)			\
+
+TEST_ALL4 (VEC_EXTRACT)
+
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m8,\s*ta,\s*ma} 6 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m8,\s*ta,\s*ma} 13 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m8,\s*ta,\s*ma} 10 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m8,\s*ta,\s*ma} 8 } } */
+
+/* { dg-final { scan-assembler-times {\tvslidedown.vi} 23 } } */
+/* { dg-final { scan-assembler-times {\tvslidedown.vx} 7 } } */
+
+/* { dg-final { scan-assembler-times {\tvfmv.f.s} 17 } } */
+/* { dg-final { scan-assembler-times {\tvmv.x.s} 20 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-run.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-run.c
new file mode 100644
index 0000000..82bf6d6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-run.c
@@ -0,0 +1,239 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-std=c99 -march=rv64gcv -Wno-pedantic" } */
+
+#include <assert.h>
+
+#include "vec_extract-1.c"
+#include "vec_extract-2.c"
+#include "vec_extract-3.c"
+#include "vec_extract-4.c"
+
+#define CHECK(S, V, IDX)				\
+void check_##V##_##IDX ()				\
+  {							\
+    V v;						\
+    for (int i = 0; i < sizeof (V) / sizeof (S); i++)	\
+      v[i] = i;						\
+    S res = vec_extract_##V##_##IDX (v);		\
+    assert (res == v[IDX]);				\
+  }
+
+#define CHECK_ALL(T)					\
+  T (float, vnx4sf, 0)					\
+  T (float, vnx4sf, 1)					\
+  T (float, vnx4sf, 3)					\
+  T (double, vnx2df, 0)					\
+  T (double, vnx2df, 1)					\
+  T (int64_t, vnx2di, 0)				\
+  T (int64_t, vnx2di, 1)				\
+  T (int32_t, vnx4si, 0)				\
+  T (int32_t, vnx4si, 1)				\
+  T (int32_t, vnx4si, 3)				\
+  T (int16_t, vnx8hi, 0)				\
+  T (int16_t, vnx8hi, 2)				\
+  T (int16_t, vnx8hi, 6)				\
+  T (int8_t, vnx16qi, 0)				\
+  T (int8_t, vnx16qi, 1)				\
+  T (int8_t, vnx16qi, 7)				\
+  T (int8_t, vnx16qi, 11)				\
+  T (int8_t, vnx16qi, 15)				\
+  T (float, vnx8sf, 0)					\
+  T (float, vnx8sf, 1)					\
+  T (float, vnx8sf, 3)					\
+  T (float, vnx8sf, 4)					\
+  T (float, vnx8sf, 7)					\
+  T (double, vnx4df, 0)					\
+  T (double, vnx4df, 1)					\
+  T (double, vnx4df, 2)					\
+  T (double, vnx4df, 3)					\
+  T (int64_t, vnx4di, 0)				\
+  T (int64_t, vnx4di, 1)				\
+  T (int64_t, vnx4di, 2)				\
+  T (int64_t, vnx4di, 3)				\
+  T (int32_t, vnx8si, 0)				\
+  T (int32_t, vnx8si, 1)				\
+  T (int32_t, vnx8si, 3)				\
+  T (int32_t, vnx8si, 4)				\
+  T (int32_t, vnx8si, 7)				\
+  T (int16_t, vnx16hi, 0)				\
+  T (int16_t, vnx16hi, 1)				\
+  T (int16_t, vnx16hi, 7)				\
+  T (int16_t, vnx16hi, 8)				\
+  T (int16_t, vnx16hi, 15)				\
+  T (int8_t, vnx32qi, 0)				\
+  T (int8_t, vnx32qi, 1)				\
+  T (int8_t, vnx32qi, 15)				\
+  T (int8_t, vnx32qi, 16)				\
+  T (int8_t, vnx32qi, 31)				\
+  T (float, vnx16sf, 0)					\
+  T (float, vnx16sf, 2)					\
+  T (float, vnx16sf, 6)					\
+  T (float, vnx16sf, 8)					\
+  T (float, vnx16sf, 14)				\
+  T (double, vnx8df, 0)					\
+  T (double, vnx8df, 2)					\
+  T (double, vnx8df, 4)					\
+  T (double, vnx8df, 6)					\
+  T (int64_t, vnx8di, 0)				\
+  T (int64_t, vnx8di, 2)				\
+  T (int64_t, vnx8di, 4)				\
+  T (int64_t, vnx8di, 6)				\
+  T (int32_t, vnx16si, 0)				\
+  T (int32_t, vnx16si, 2)				\
+  T (int32_t, vnx16si, 6)				\
+  T (int32_t, vnx16si, 8)				\
+  T (int32_t, vnx16si, 14)				\
+  T (int16_t, vnx32hi, 0)				\
+  T (int16_t, vnx32hi, 2)				\
+  T (int16_t, vnx32hi, 14)				\
+  T (int16_t, vnx32hi, 16)				\
+  T (int16_t, vnx32hi, 30)				\
+  T (int8_t, vnx64qi, 0)				\
+  T (int8_t, vnx64qi, 2)				\
+  T (int8_t, vnx64qi, 30)				\
+  T (int8_t, vnx64qi, 32)				\
+  T (int8_t, vnx64qi, 63)				\
+  T (float, vnx32sf, 0)					\
+  T (float, vnx32sf, 3)					\
+  T (float, vnx32sf, 12)				\
+  T (float, vnx32sf, 17)				\
+  T (float, vnx32sf, 14)				\
+  T (double, vnx16df, 0)				\
+  T (double, vnx16df, 4)				\
+  T (double, vnx16df, 8)				\
+  T (double, vnx16df, 12)				\
+  T (int64_t, vnx16di, 0)				\
+  T (int64_t, vnx16di, 4)				\
+  T (int64_t, vnx16di, 8)				\
+  T (int64_t, vnx16di, 12)				\
+  T (int32_t, vnx32si, 0)				\
+  T (int32_t, vnx32si, 4)				\
+  T (int32_t, vnx32si, 12)				\
+  T (int32_t, vnx32si, 16)				\
+  T (int32_t, vnx32si, 28)				\
+  T (int16_t, vnx64hi, 0)				\
+  T (int16_t, vnx64hi, 4)				\
+  T (int16_t, vnx64hi, 28)				\
+  T (int16_t, vnx64hi, 32)				\
+  T (int16_t, vnx64hi, 60)				\
+  T (int8_t, vnx128qi, 0)				\
+  T (int8_t, vnx128qi, 4)				\
+  T (int8_t, vnx128qi, 30)				\
+  T (int8_t, vnx128qi, 60)				\
+  T (int8_t, vnx128qi, 64)				\
+  T (int8_t, vnx128qi, 127)				\
+
+CHECK_ALL (CHECK)
+
+#define RUN(S, V, IDX)						\
+  check_##V##_##IDX ();
+
+#define RUN_ALL(T)						\
+  T (float, vnx4sf, 0)					\
+  T (float, vnx4sf, 1)					\
+  T (float, vnx4sf, 3)					\
+  T (double, vnx2df, 0)					\
+  T (double, vnx2df, 1)					\
+  T (int64_t, vnx2di, 0)				\
+  T (int64_t, vnx2di, 1)				\
+  T (int32_t, vnx4si, 0)				\
+  T (int32_t, vnx4si, 1)				\
+  T (int32_t, vnx4si, 3)				\
+  T (int16_t, vnx8hi, 0)				\
+  T (int16_t, vnx8hi, 2)				\
+  T (int16_t, vnx8hi, 6)				\
+  T (int8_t, vnx16qi, 0)				\
+  T (int8_t, vnx16qi, 1)				\
+  T (int8_t, vnx16qi, 7)				\
+  T (int8_t, vnx16qi, 11)				\
+  T (int8_t, vnx16qi, 15)				\
+  T (float, vnx8sf, 0)					\
+  T (float, vnx8sf, 1)					\
+  T (float, vnx8sf, 3)					\
+  T (float, vnx8sf, 4)					\
+  T (float, vnx8sf, 7)					\
+  T (double, vnx4df, 0)					\
+  T (double, vnx4df, 1)					\
+  T (double, vnx4df, 2)					\
+  T (double, vnx4df, 3)					\
+  T (int64_t, vnx4di, 0)				\
+  T (int64_t, vnx4di, 1)				\
+  T (int64_t, vnx4di, 2)				\
+  T (int64_t, vnx4di, 3)				\
+  T (int32_t, vnx8si, 0)				\
+  T (int32_t, vnx8si, 1)				\
+  T (int32_t, vnx8si, 3)				\
+  T (int32_t, vnx8si, 4)				\
+  T (int32_t, vnx8si, 7)				\
+  T (int16_t, vnx16hi, 0)				\
+  T (int16_t, vnx16hi, 1)				\
+  T (int16_t, vnx16hi, 7)				\
+  T (int16_t, vnx16hi, 8)				\
+  T (int16_t, vnx16hi, 15)				\
+  T (int8_t, vnx32qi, 0)				\
+  T (int8_t, vnx32qi, 1)				\
+  T (int8_t, vnx32qi, 15)				\
+  T (int8_t, vnx32qi, 16)				\
+  T (int8_t, vnx32qi, 31)				\
+  T (float, vnx16sf, 0)					\
+  T (float, vnx16sf, 2)					\
+  T (float, vnx16sf, 6)					\
+  T (float, vnx16sf, 8)					\
+  T (float, vnx16sf, 14)				\
+  T (double, vnx8df, 0)					\
+  T (double, vnx8df, 2)					\
+  T (double, vnx8df, 4)					\
+  T (double, vnx8df, 6)					\
+  T (int64_t, vnx8di, 0)				\
+  T (int64_t, vnx8di, 2)				\
+  T (int64_t, vnx8di, 4)				\
+  T (int64_t, vnx8di, 6)				\
+  T (int32_t, vnx16si, 0)				\
+  T (int32_t, vnx16si, 2)				\
+  T (int32_t, vnx16si, 6)				\
+  T (int32_t, vnx16si, 8)				\
+  T (int32_t, vnx16si, 14)				\
+  T (int16_t, vnx32hi, 0)				\
+  T (int16_t, vnx32hi, 2)				\
+  T (int16_t, vnx32hi, 14)				\
+  T (int16_t, vnx32hi, 16)				\
+  T (int16_t, vnx32hi, 30)				\
+  T (int8_t, vnx64qi, 0)				\
+  T (int8_t, vnx64qi, 2)				\
+  T (int8_t, vnx64qi, 30)				\
+  T (int8_t, vnx64qi, 32)				\
+  T (int8_t, vnx64qi, 63)				\
+  T (float, vnx32sf, 0)					\
+  T (float, vnx32sf, 3)					\
+  T (float, vnx32sf, 12)				\
+  T (float, vnx32sf, 17)				\
+  T (float, vnx32sf, 14)				\
+  T (double, vnx16df, 0)				\
+  T (double, vnx16df, 4)				\
+  T (double, vnx16df, 8)				\
+  T (double, vnx16df, 12)				\
+  T (int64_t, vnx16di, 0)				\
+  T (int64_t, vnx16di, 4)				\
+  T (int64_t, vnx16di, 8)				\
+  T (int64_t, vnx16di, 12)				\
+  T (int32_t, vnx32si, 0)				\
+  T (int32_t, vnx32si, 4)				\
+  T (int32_t, vnx32si, 12)				\
+  T (int32_t, vnx32si, 16)				\
+  T (int32_t, vnx32si, 28)				\
+  T (int16_t, vnx64hi, 0)				\
+  T (int16_t, vnx64hi, 4)				\
+  T (int16_t, vnx64hi, 28)				\
+  T (int16_t, vnx64hi, 32)				\
+  T (int16_t, vnx64hi, 60)				\
+  T (int8_t, vnx128qi, 0)				\
+  T (int8_t, vnx128qi, 4)				\
+  T (int8_t, vnx128qi, 30)				\
+  T (int8_t, vnx128qi, 60)				\
+  T (int8_t, vnx128qi, 64)				\
+  T (int8_t, vnx128qi, 127)				\
+
+int main ()
+{
+  RUN_ALL (RUN);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-zvfh-run.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-zvfh-run.c
new file mode 100644
index 0000000..a0b2cf9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_extract-zvfh-run.c
@@ -0,0 +1,77 @@
+/* { dg-do run {target { riscv_zvfh_hw } } } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <assert.h>
+
+#include "vec_extract-1.c"
+#include "vec_extract-2.c"
+#include "vec_extract-3.c"
+#include "vec_extract-4.c"
+
+#define CHECK(S, V, IDX)				\
+void check_##V##_##IDX ()				\
+  {							\
+    V v;						\
+    for (int i = 0; i < sizeof (V) / sizeof (S); i++)	\
+      v[i] = i;						\
+    S res = vec_extract_##V##_##IDX (v);		\
+    assert (res == v[IDX]);				\
+  }
+
+#define CHECK_ALL(T)					\
+  T (_Float16, vnx8hf, 0)				\
+  T (_Float16, vnx8hf, 3)				\
+  T (_Float16, vnx8hf, 7)				\
+  T (_Float16, vnx16hf, 0)				\
+  T (_Float16, vnx16hf, 3)				\
+  T (_Float16, vnx16hf, 7)				\
+  T (_Float16, vnx16hf, 8)				\
+  T (_Float16, vnx16hf, 15)				\
+  T (_Float16, vnx32hf, 0)				\
+  T (_Float16, vnx32hf, 3)				\
+  T (_Float16, vnx32hf, 7)				\
+  T (_Float16, vnx32hf, 8)				\
+  T (_Float16, vnx32hf, 16)				\
+  T (_Float16, vnx32hf, 31)				\
+  T (_Float16, vnx64hf, 0)				\
+  T (_Float16, vnx64hf, 3)				\
+  T (_Float16, vnx64hf, 7)				\
+  T (_Float16, vnx64hf, 8)				\
+  T (_Float16, vnx64hf, 16)				\
+  T (_Float16, vnx64hf, 31)				\
+  T (_Float16, vnx64hf, 42)				\
+  T (_Float16, vnx64hf, 63)				\
+
+CHECK_ALL (CHECK)
+
+#define RUN(S, V, IDX)					\
+  check_##V##_##IDX ();
+
+#define RUN_ALL(T)					\
+  T (_Float16, vnx8hf, 0)				\
+  T (_Float16, vnx8hf, 3)				\
+  T (_Float16, vnx8hf, 7)				\
+  T (_Float16, vnx16hf, 0)				\
+  T (_Float16, vnx16hf, 3)				\
+  T (_Float16, vnx16hf, 7)				\
+  T (_Float16, vnx16hf, 8)				\
+  T (_Float16, vnx16hf, 15)				\
+  T (_Float16, vnx32hf, 0)				\
+  T (_Float16, vnx32hf, 3)				\
+  T (_Float16, vnx32hf, 7)				\
+  T (_Float16, vnx32hf, 8)				\
+  T (_Float16, vnx32hf, 16)				\
+  T (_Float16, vnx32hf, 31)				\
+  T (_Float16, vnx64hf, 0)				\
+  T (_Float16, vnx64hf, 3)				\
+  T (_Float16, vnx64hf, 7)				\
+  T (_Float16, vnx64hf, 8)				\
+  T (_Float16, vnx64hf, 16)				\
+  T (_Float16, vnx64hf, 31)				\
+  T (_Float16, vnx64hf, 42)				\
+  T (_Float16, vnx64hf, 63)				\
+
+int main ()
+{
+  RUN_ALL (RUN);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-1.c
new file mode 100644
index 0000000..4fb4e82
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-1.c
@@ -0,0 +1,62 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <stdint-gcc.h>
+
+typedef int64_t vnx2di __attribute__((vector_size (16)));
+typedef int32_t vnx4si __attribute__((vector_size (16)));
+typedef int16_t vnx8hi __attribute__((vector_size (16)));
+typedef int8_t vnx16qi __attribute__((vector_size (16)));
+typedef _Float16 vnx8hf __attribute__((vector_size (16)));
+typedef float vnx4sf __attribute__((vector_size (16)));
+typedef double vnx2df __attribute__((vector_size (16)));
+
+#define VEC_SET(S,V,IDX)			\
+  V						\
+  __attribute__((noipa))			\
+  vec_set_##V##_##IDX (V v, S s)		\
+  {						\
+    v[IDX] = s;					\
+    return v;					\
+  }
+
+#define TEST_ALL1(T)				\
+  T (_Float16, vnx8hf, 0)			\
+  T (_Float16, vnx8hf, 3)			\
+  T (_Float16, vnx8hf, 7)			\
+  T (float, vnx4sf, 0)				\
+  T (float, vnx4sf, 1)				\
+  T (float, vnx4sf, 3)				\
+  T (double, vnx2df, 0)				\
+  T (double, vnx2df, 1)				\
+  T (int64_t, vnx2di, 0)			\
+  T (int64_t, vnx2di, 1)			\
+  T (int32_t, vnx4si, 0)			\
+  T (int32_t, vnx4si, 1)			\
+  T (int32_t, vnx4si, 3)			\
+  T (int16_t, vnx8hi, 0)			\
+  T (int16_t, vnx8hi, 2)			\
+  T (int16_t, vnx8hi, 6)			\
+  T (int8_t, vnx16qi, 0)			\
+  T (int8_t, vnx16qi, 1)			\
+  T (int8_t, vnx16qi, 7)			\
+  T (int8_t, vnx16qi, 11)			\
+  T (int8_t, vnx16qi, 15)			\
+
+TEST_ALL1 (VEC_SET)
+
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m1,\s*ta,\s*ma} 1 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m1,\s*tu,\s*ma} 4 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m1,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m1,\s*tu,\s*ma} 4 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m1,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m1,\s*tu,\s*ma} 4 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m1,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m1,\s*tu,\s*ma} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tvmv.v.x} 9 } } */
+/* { dg-final { scan-assembler-times {\tvfmv.v.f} 5 } } */
+/* { dg-final { scan-assembler-times {\tvslideup.vi} 14 } } */
+
+/* { dg-final { scan-assembler-times {\tvfmv.s.f} 3 } } */
+/* { dg-final { scan-assembler-times {\tvmv.s.x} 4 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-2.c
new file mode 100644
index 0000000..379e92f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-2.c
@@ -0,0 +1,74 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <stdint-gcc.h>
+
+typedef int64_t vnx4di __attribute__((vector_size (32)));
+typedef int32_t vnx8si __attribute__((vector_size (32)));
+typedef int16_t vnx16hi __attribute__((vector_size (32)));
+typedef int8_t vnx32qi __attribute__((vector_size (32)));
+typedef _Float16 vnx16hf __attribute__((vector_size (32)));
+typedef float vnx8sf __attribute__((vector_size (32)));
+typedef double vnx4df __attribute__((vector_size (32)));
+
+#define VEC_SET(S,V,IDX)			\
+  V						\
+  __attribute__((noipa))			\
+  vec_set_##V##_##IDX (V v, S s)		\
+  {						\
+    v[IDX] = s;					\
+    return v;					\
+  }
+
+#define TEST_ALL2(T)				\
+  T (_Float16, vnx16hf, 0)			\
+  T (_Float16, vnx16hf, 3)			\
+  T (_Float16, vnx16hf, 7)			\
+  T (_Float16, vnx16hf, 8)			\
+  T (_Float16, vnx16hf, 15)			\
+  T (float, vnx8sf, 0)				\
+  T (float, vnx8sf, 1)				\
+  T (float, vnx8sf, 3)				\
+  T (float, vnx8sf, 4)				\
+  T (float, vnx8sf, 7)				\
+  T (double, vnx4df, 0)				\
+  T (double, vnx4df, 1)				\
+  T (double, vnx4df, 2)				\
+  T (double, vnx4df, 3)				\
+  T (int64_t, vnx4di, 0)			\
+  T (int64_t, vnx4di, 1)			\
+  T (int64_t, vnx4di, 2)			\
+  T (int64_t, vnx4di, 3)			\
+  T (int32_t, vnx8si, 0)			\
+  T (int32_t, vnx8si, 1)			\
+  T (int32_t, vnx8si, 3)			\
+  T (int32_t, vnx8si, 4)			\
+  T (int32_t, vnx8si, 7)			\
+  T (int16_t, vnx16hi, 0)			\
+  T (int16_t, vnx16hi, 1)			\
+  T (int16_t, vnx16hi, 7)			\
+  T (int16_t, vnx16hi, 8)			\
+  T (int16_t, vnx16hi, 15)			\
+  T (int8_t, vnx32qi, 0)			\
+  T (int8_t, vnx32qi, 1)			\
+  T (int8_t, vnx32qi, 15)			\
+  T (int8_t, vnx32qi, 16)			\
+  T (int8_t, vnx32qi, 31)			\
+
+TEST_ALL2 (VEC_SET)
+
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m2,\s*ta,\s*ma} 1 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m2,\s*tu,\s*ma} 4 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m2,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m2,\s*tu,\s*ma} 8 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m2,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m2,\s*tu,\s*ma} 8 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m2,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m2,\s*tu,\s*ma} 6 } } */
+
+/* { dg-final { scan-assembler-times {\tvmv.v.x} 15 } } */
+/* { dg-final { scan-assembler-times {\tvfmv.v.f} 11 } } */
+/* { dg-final { scan-assembler-times {\tvslideup.vi} 26 } } */
+
+/* { dg-final { scan-assembler-times {\tvfmv.s.f} 3 } } */
+/* { dg-final { scan-assembler-times {\tvmv.s.x} 4 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-3.c
new file mode 100644
index 0000000..b1e7815
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-3.c
@@ -0,0 +1,76 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <stdint-gcc.h>
+
+typedef int64_t vnx8di __attribute__((vector_size (64)));
+typedef int32_t vnx16si __attribute__((vector_size (64)));
+typedef int16_t vnx32hi __attribute__((vector_size (64)));
+typedef int8_t vnx64qi __attribute__((vector_size (64)));
+typedef _Float16 vnx32hf __attribute__((vector_size (64)));
+typedef float vnx16sf __attribute__((vector_size (64)));
+typedef double vnx8df __attribute__((vector_size (64)));
+
+#define VEC_SET(S,V,IDX)			\
+  V						\
+  __attribute__((noipa))			\
+  vec_set_##V##_##IDX (V v, S s)		\
+  {						\
+    v[IDX] = s;					\
+    return v;					\
+  }
+
+#define TEST_ALL3(T)				\
+  T (_Float16, vnx32hf, 0)			\
+  T (_Float16, vnx32hf, 3)			\
+  T (_Float16, vnx32hf, 7)			\
+  T (_Float16, vnx32hf, 8)			\
+  T (_Float16, vnx32hf, 16)			\
+  T (_Float16, vnx32hf, 31)			\
+  T (float, vnx16sf, 0)				\
+  T (float, vnx16sf, 2)				\
+  T (float, vnx16sf, 6)				\
+  T (float, vnx16sf, 8)				\
+  T (float, vnx16sf, 14)			\
+  T (double, vnx8df, 0)				\
+  T (double, vnx8df, 2)				\
+  T (double, vnx8df, 4)				\
+  T (double, vnx8df, 6)				\
+  T (int64_t, vnx8di, 0)			\
+  T (int64_t, vnx8di, 2)			\
+  T (int64_t, vnx8di, 4)			\
+  T (int64_t, vnx8di, 6)			\
+  T (int32_t, vnx16si, 0)			\
+  T (int32_t, vnx16si, 2)			\
+  T (int32_t, vnx16si, 6)			\
+  T (int32_t, vnx16si, 8)			\
+  T (int32_t, vnx16si, 14)			\
+  T (int16_t, vnx32hi, 0)			\
+  T (int16_t, vnx32hi, 2)			\
+  T (int16_t, vnx32hi, 14)			\
+  T (int16_t, vnx32hi, 16)			\
+  T (int16_t, vnx32hi, 30)			\
+  T (int8_t, vnx64qi, 0)			\
+  T (int8_t, vnx64qi, 2)			\
+  T (int8_t, vnx64qi, 30)			\
+  T (int8_t, vnx64qi, 32)			\
+  T (int8_t, vnx64qi, 63)			\
+
+TEST_ALL3 (VEC_SET)
+
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m4,\s*ta,\s*ma} 1 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m4,\s*tu,\s*ma} 4 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m4,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m4,\s*tu,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m4,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m4,\s*tu,\s*ma} 8 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m4,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m4,\s*tu,\s*ma} 6 } } */
+
+/* { dg-final { scan-assembler-times {\tvmv.v.x} 15 } } */
+/* { dg-final { scan-assembler-times {\tvfmv.v.f} 12 } } */
+/* { dg-final { scan-assembler-times {\tvslideup.vi} 25 } } */
+/* { dg-final { scan-assembler-times {\tvslideup.vx} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tvfmv.s.f} 3 } } */
+/* { dg-final { scan-assembler-times {\tvmv.s.x} 4 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-4.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-4.c
new file mode 100644
index 0000000..0b7f53d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-4.c
@@ -0,0 +1,79 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <stdint-gcc.h>
+
+typedef int64_t vnx16di __attribute__((vector_size (128)));
+typedef int32_t vnx32si __attribute__((vector_size (128)));
+typedef int16_t vnx64hi __attribute__((vector_size (128)));
+typedef int8_t vnx128qi __attribute__((vector_size (128)));
+typedef _Float16 vnx64hf __attribute__((vector_size (128)));
+typedef float vnx32sf __attribute__((vector_size (128)));
+typedef double vnx16df __attribute__((vector_size (128)));
+
+#define VEC_SET(S,V,IDX)			\
+  V						\
+  __attribute__((noipa))			\
+  vec_set_##V##_##IDX (V v, S s)		\
+  {						\
+    v[IDX] = s;					\
+    return v;					\
+  }
+
+#define TEST_ALL4(T)				\
+  T (_Float16, vnx64hf, 0)			\
+  T (_Float16, vnx64hf, 3)			\
+  T (_Float16, vnx64hf, 7)			\
+  T (_Float16, vnx64hf, 8)			\
+  T (_Float16, vnx64hf, 16)			\
+  T (_Float16, vnx64hf, 31)			\
+  T (_Float16, vnx64hf, 42)			\
+  T (_Float16, vnx64hf, 63)			\
+  T (float, vnx32sf, 0)				\
+  T (float, vnx32sf, 3)				\
+  T (float, vnx32sf, 12)			\
+  T (float, vnx32sf, 17)			\
+  T (float, vnx32sf, 14)			\
+  T (double, vnx16df, 0)			\
+  T (double, vnx16df, 4)			\
+  T (double, vnx16df, 8)			\
+  T (double, vnx16df, 12)			\
+  T (int64_t, vnx16di, 0)			\
+  T (int64_t, vnx16di, 4)			\
+  T (int64_t, vnx16di, 8)			\
+  T (int64_t, vnx16di, 12)			\
+  T (int32_t, vnx32si, 0)			\
+  T (int32_t, vnx32si, 4)			\
+  T (int32_t, vnx32si, 12)			\
+  T (int32_t, vnx32si, 16)			\
+  T (int32_t, vnx32si, 28)			\
+  T (int16_t, vnx64hi, 0)			\
+  T (int16_t, vnx64hi, 4)			\
+  T (int16_t, vnx64hi, 28)			\
+  T (int16_t, vnx64hi, 32)			\
+  T (int16_t, vnx64hi, 60)			\
+  T (int8_t, vnx128qi, 0)			\
+  T (int8_t, vnx128qi, 4)			\
+  T (int8_t, vnx128qi, 30)			\
+  T (int8_t, vnx128qi, 60)			\
+  T (int8_t, vnx128qi, 64)			\
+  T (int8_t, vnx128qi, 127)			\
+
+TEST_ALL4 (VEC_SET)
+
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m8,\s*ta,\s*ma} 1 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m8,\s*tu,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m8,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m8,\s*tu,\s*ma} 11 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m8,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m8,\s*tu,\s*ma} 8 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m8,\s*ta,\s*ma} 2 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m8,\s*tu,\s*ma} 6 } } */
+
+/* { dg-final { scan-assembler-times {\tvmv.v.x} 16 } } */
+/* { dg-final { scan-assembler-times {\tvfmv.v.f} 14 } } */
+/* { dg-final { scan-assembler-times {\tvslideup.vi} 23 } } */
+/* { dg-final { scan-assembler-times {\tvslideup.vx} 7 } } */
+
+/* { dg-final { scan-assembler-times {\tvfmv.s.f} 3 } } */
+/* { dg-final { scan-assembler-times {\tvmv.s.x} 4 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-run.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-run.c
new file mode 100644
index 0000000..7e5e0e6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-run.c
@@ -0,0 +1,240 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-std=c99 -march=rv64gcv -Wno-pedantic" } */
+
+#include <assert.h>
+
+#include "vec_set-1.c"
+#include "vec_set-2.c"
+#include "vec_set-3.c"
+#include "vec_set-4.c"
+
+#define CHECK(S, V, IDX)				\
+void check_##V##_##IDX ()				\
+  {							\
+    V v;						\
+    for (int i = 0; i < sizeof (V) / sizeof (S); i++)	\
+      v[i] = i;						\
+    V res = vec_set_##V##_##IDX (v, 77);		\
+    for (int i = 0; i < sizeof (V) / sizeof (S); i++)	\
+      assert (res[i] == (i == IDX ? 77 : i));		\
+  }
+
+#define CHECK_ALL(T)					\
+  T (float, vnx4sf, 0)					\
+  T (float, vnx4sf, 1)					\
+  T (float, vnx4sf, 3)					\
+  T (double, vnx2df, 0)					\
+  T (double, vnx2df, 1)					\
+  T (int64_t, vnx2di, 0)				\
+  T (int64_t, vnx2di, 1)				\
+  T (int32_t, vnx4si, 0)				\
+  T (int32_t, vnx4si, 1)				\
+  T (int32_t, vnx4si, 3)				\
+  T (int16_t, vnx8hi, 0)				\
+  T (int16_t, vnx8hi, 2)				\
+  T (int16_t, vnx8hi, 6)				\
+  T (int8_t, vnx16qi, 0)				\
+  T (int8_t, vnx16qi, 1)				\
+  T (int8_t, vnx16qi, 7)				\
+  T (int8_t, vnx16qi, 11)				\
+  T (int8_t, vnx16qi, 15)				\
+  T (float, vnx8sf, 0)					\
+  T (float, vnx8sf, 1)					\
+  T (float, vnx8sf, 3)					\
+  T (float, vnx8sf, 4)					\
+  T (float, vnx8sf, 7)					\
+  T (double, vnx4df, 0)					\
+  T (double, vnx4df, 1)					\
+  T (double, vnx4df, 2)					\
+  T (double, vnx4df, 3)					\
+  T (int64_t, vnx4di, 0)				\
+  T (int64_t, vnx4di, 1)				\
+  T (int64_t, vnx4di, 2)				\
+  T (int64_t, vnx4di, 3)				\
+  T (int32_t, vnx8si, 0)				\
+  T (int32_t, vnx8si, 1)				\
+  T (int32_t, vnx8si, 3)				\
+  T (int32_t, vnx8si, 4)				\
+  T (int32_t, vnx8si, 7)				\
+  T (int16_t, vnx16hi, 0)				\
+  T (int16_t, vnx16hi, 1)				\
+  T (int16_t, vnx16hi, 7)				\
+  T (int16_t, vnx16hi, 8)				\
+  T (int16_t, vnx16hi, 15)				\
+  T (int8_t, vnx32qi, 0)				\
+  T (int8_t, vnx32qi, 1)				\
+  T (int8_t, vnx32qi, 15)				\
+  T (int8_t, vnx32qi, 16)				\
+  T (int8_t, vnx32qi, 31)				\
+  T (float, vnx16sf, 0)					\
+  T (float, vnx16sf, 2)					\
+  T (float, vnx16sf, 6)					\
+  T (float, vnx16sf, 8)					\
+  T (float, vnx16sf, 14)				\
+  T (double, vnx8df, 0)					\
+  T (double, vnx8df, 2)					\
+  T (double, vnx8df, 4)					\
+  T (double, vnx8df, 6)					\
+  T (int64_t, vnx8di, 0)				\
+  T (int64_t, vnx8di, 2)				\
+  T (int64_t, vnx8di, 4)				\
+  T (int64_t, vnx8di, 6)				\
+  T (int32_t, vnx16si, 0)				\
+  T (int32_t, vnx16si, 2)				\
+  T (int32_t, vnx16si, 6)				\
+  T (int32_t, vnx16si, 8)				\
+  T (int32_t, vnx16si, 14)				\
+  T (int16_t, vnx32hi, 0)				\
+  T (int16_t, vnx32hi, 2)				\
+  T (int16_t, vnx32hi, 14)				\
+  T (int16_t, vnx32hi, 16)				\
+  T (int16_t, vnx32hi, 30)				\
+  T (int8_t, vnx64qi, 0)				\
+  T (int8_t, vnx64qi, 2)				\
+  T (int8_t, vnx64qi, 30)				\
+  T (int8_t, vnx64qi, 32)				\
+  T (int8_t, vnx64qi, 63)				\
+  T (float, vnx32sf, 0)					\
+  T (float, vnx32sf, 3)					\
+  T (float, vnx32sf, 12)				\
+  T (float, vnx32sf, 17)				\
+  T (float, vnx32sf, 14)				\
+  T (double, vnx16df, 0)				\
+  T (double, vnx16df, 4)				\
+  T (double, vnx16df, 8)				\
+  T (double, vnx16df, 12)				\
+  T (int64_t, vnx16di, 0)				\
+  T (int64_t, vnx16di, 4)				\
+  T (int64_t, vnx16di, 8)				\
+  T (int64_t, vnx16di, 12)				\
+  T (int32_t, vnx32si, 0)				\
+  T (int32_t, vnx32si, 4)				\
+  T (int32_t, vnx32si, 12)				\
+  T (int32_t, vnx32si, 16)				\
+  T (int32_t, vnx32si, 28)				\
+  T (int16_t, vnx64hi, 0)				\
+  T (int16_t, vnx64hi, 4)				\
+  T (int16_t, vnx64hi, 28)				\
+  T (int16_t, vnx64hi, 32)				\
+  T (int16_t, vnx64hi, 60)				\
+  T (int8_t, vnx128qi, 0)				\
+  T (int8_t, vnx128qi, 4)				\
+  T (int8_t, vnx128qi, 30)				\
+  T (int8_t, vnx128qi, 60)				\
+  T (int8_t, vnx128qi, 64)				\
+  T (int8_t, vnx128qi, 127)				\
+
+CHECK_ALL (CHECK)
+
+#define RUN(S, V, IDX)					\
+  check_##V##_##IDX ();
+
+#define RUN_ALL(T)					\
+  T (float, vnx4sf, 0)					\
+  T (float, vnx4sf, 1)					\
+  T (float, vnx4sf, 3)					\
+  T (double, vnx2df, 0)					\
+  T (double, vnx2df, 1)					\
+  T (int64_t, vnx2di, 0)				\
+  T (int64_t, vnx2di, 1)				\
+  T (int32_t, vnx4si, 0)				\
+  T (int32_t, vnx4si, 1)				\
+  T (int32_t, vnx4si, 3)				\
+  T (int16_t, vnx8hi, 0)				\
+  T (int16_t, vnx8hi, 2)				\
+  T (int16_t, vnx8hi, 6)				\
+  T (int8_t, vnx16qi, 0)				\
+  T (int8_t, vnx16qi, 1)				\
+  T (int8_t, vnx16qi, 7)				\
+  T (int8_t, vnx16qi, 11)				\
+  T (int8_t, vnx16qi, 15)				\
+  T (float, vnx8sf, 0)					\
+  T (float, vnx8sf, 1)					\
+  T (float, vnx8sf, 3)					\
+  T (float, vnx8sf, 4)					\
+  T (float, vnx8sf, 7)					\
+  T (double, vnx4df, 0)					\
+  T (double, vnx4df, 1)					\
+  T (double, vnx4df, 2)					\
+  T (double, vnx4df, 3)					\
+  T (int64_t, vnx4di, 0)				\
+  T (int64_t, vnx4di, 1)				\
+  T (int64_t, vnx4di, 2)				\
+  T (int64_t, vnx4di, 3)				\
+  T (int32_t, vnx8si, 0)				\
+  T (int32_t, vnx8si, 1)				\
+  T (int32_t, vnx8si, 3)				\
+  T (int32_t, vnx8si, 4)				\
+  T (int32_t, vnx8si, 7)				\
+  T (int16_t, vnx16hi, 0)				\
+  T (int16_t, vnx16hi, 1)				\
+  T (int16_t, vnx16hi, 7)				\
+  T (int16_t, vnx16hi, 8)				\
+  T (int16_t, vnx16hi, 15)				\
+  T (int8_t, vnx32qi, 0)				\
+  T (int8_t, vnx32qi, 1)				\
+  T (int8_t, vnx32qi, 15)				\
+  T (int8_t, vnx32qi, 16)				\
+  T (int8_t, vnx32qi, 31)				\
+  T (float, vnx16sf, 0)					\
+  T (float, vnx16sf, 2)					\
+  T (float, vnx16sf, 6)					\
+  T (float, vnx16sf, 8)					\
+  T (float, vnx16sf, 14)				\
+  T (double, vnx8df, 0)					\
+  T (double, vnx8df, 2)					\
+  T (double, vnx8df, 4)					\
+  T (double, vnx8df, 6)					\
+  T (int64_t, vnx8di, 0)				\
+  T (int64_t, vnx8di, 2)				\
+  T (int64_t, vnx8di, 4)				\
+  T (int64_t, vnx8di, 6)				\
+  T (int32_t, vnx16si, 0)				\
+  T (int32_t, vnx16si, 2)				\
+  T (int32_t, vnx16si, 6)				\
+  T (int32_t, vnx16si, 8)				\
+  T (int32_t, vnx16si, 14)				\
+  T (int16_t, vnx32hi, 0)				\
+  T (int16_t, vnx32hi, 2)				\
+  T (int16_t, vnx32hi, 14)				\
+  T (int16_t, vnx32hi, 16)				\
+  T (int16_t, vnx32hi, 30)				\
+  T (int8_t, vnx64qi, 0)				\
+  T (int8_t, vnx64qi, 2)				\
+  T (int8_t, vnx64qi, 30)				\
+  T (int8_t, vnx64qi, 32)				\
+  T (int8_t, vnx64qi, 63)				\
+  T (float, vnx32sf, 0)					\
+  T (float, vnx32sf, 3)					\
+  T (float, vnx32sf, 12)				\
+  T (float, vnx32sf, 17)				\
+  T (float, vnx32sf, 14)				\
+  T (double, vnx16df, 0)				\
+  T (double, vnx16df, 4)				\
+  T (double, vnx16df, 8)				\
+  T (double, vnx16df, 12)				\
+  T (int64_t, vnx16di, 0)				\
+  T (int64_t, vnx16di, 4)				\
+  T (int64_t, vnx16di, 8)				\
+  T (int64_t, vnx16di, 12)				\
+  T (int32_t, vnx32si, 0)				\
+  T (int32_t, vnx32si, 4)				\
+  T (int32_t, vnx32si, 12)				\
+  T (int32_t, vnx32si, 16)				\
+  T (int32_t, vnx32si, 28)				\
+  T (int16_t, vnx64hi, 0)				\
+  T (int16_t, vnx64hi, 4)				\
+  T (int16_t, vnx64hi, 28)				\
+  T (int16_t, vnx64hi, 32)				\
+  T (int16_t, vnx64hi, 60)				\
+  T (int8_t, vnx128qi, 0)				\
+  T (int8_t, vnx128qi, 4)				\
+  T (int8_t, vnx128qi, 30)				\
+  T (int8_t, vnx128qi, 60)				\
+  T (int8_t, vnx128qi, 64)				\
+  T (int8_t, vnx128qi, 127)				\
+
+int main ()
+{
+  RUN_ALL (RUN);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-zvfh-run.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-zvfh-run.c
new file mode 100644
index 0000000..bf514f9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-zvfh-run.c
@@ -0,0 +1,78 @@
+/* { dg-do run { target { riscv_zvfh_hw } } } */
+/* { dg-additional-options "-march=rv64gcv_zvfh -Wno-pedantic" } */
+
+#include <assert.h>
+
+#include "vec_set-1.c"
+#include "vec_set-2.c"
+#include "vec_set-3.c"
+#include "vec_set-4.c"
+
+#define CHECK(S, V, IDX)				\
+void check_##V##_##IDX ()				\
+  {							\
+    V v;						\
+    for (int i = 0; i < sizeof (V) / sizeof (S); i++)	\
+      v[i] = i;						\
+    V res = vec_set_##V##_##IDX (v, 77);		\
+    for (int i = 0; i < sizeof (V) / sizeof (S); i++)	\
+      assert (res[i] == (i == IDX ? 77 : i));		\
+  }
+
+#define CHECK_ALL(T)					\
+  T (_Float16, vnx8hf, 0)				\
+  T (_Float16, vnx8hf, 3)				\
+  T (_Float16, vnx8hf, 7)				\
+  T (_Float16, vnx16hf, 0)				\
+  T (_Float16, vnx16hf, 3)				\
+  T (_Float16, vnx16hf, 7)				\
+  T (_Float16, vnx16hf, 8)				\
+  T (_Float16, vnx16hf, 15)				\
+  T (_Float16, vnx32hf, 0)				\
+  T (_Float16, vnx32hf, 3)				\
+  T (_Float16, vnx32hf, 7)				\
+  T (_Float16, vnx32hf, 8)				\
+  T (_Float16, vnx32hf, 16)				\
+  T (_Float16, vnx32hf, 31)				\
+  T (_Float16, vnx64hf, 0)				\
+  T (_Float16, vnx64hf, 3)				\
+  T (_Float16, vnx64hf, 7)				\
+  T (_Float16, vnx64hf, 8)				\
+  T (_Float16, vnx64hf, 16)				\
+  T (_Float16, vnx64hf, 31)				\
+  T (_Float16, vnx64hf, 42)				\
+  T (_Float16, vnx64hf, 63)				\
+
+CHECK_ALL (CHECK)
+
+#define RUN(S, V, IDX)					\
+  check_##V##_##IDX ();
+
+#define RUN_ALL(T)					\
+  T (_Float16, vnx8hf, 0)				\
+  T (_Float16, vnx8hf, 3)				\
+  T (_Float16, vnx8hf, 7)				\
+  T (_Float16, vnx16hf, 0)				\
+  T (_Float16, vnx16hf, 3)				\
+  T (_Float16, vnx16hf, 7)				\
+  T (_Float16, vnx16hf, 8)				\
+  T (_Float16, vnx16hf, 15)				\
+  T (_Float16, vnx32hf, 0)				\
+  T (_Float16, vnx32hf, 3)				\
+  T (_Float16, vnx32hf, 7)				\
+  T (_Float16, vnx32hf, 8)				\
+  T (_Float16, vnx32hf, 16)				\
+  T (_Float16, vnx32hf, 31)				\
+  T (_Float16, vnx64hf, 0)				\
+  T (_Float16, vnx64hf, 3)				\
+  T (_Float16, vnx64hf, 7)				\
+  T (_Float16, vnx64hf, 8)				\
+  T (_Float16, vnx64hf, 16)				\
+  T (_Float16, vnx64hf, 31)				\
+  T (_Float16, vnx64hf, 42)				\
+  T (_Float16, vnx64hf, 63)				\
+
+int main ()
+{
+  RUN_ALL (RUN);
+}