[Commit,QUEUE,V3] RISC-V: Support strided load/store

Message ID 20231114032837.1687779-1-juzhe.zhong@rivai.ai
State Unresolved
Headers
Series [Commit,QUEUE,V3] RISC-V: Support strided load/store |

Checks

Context Check Description
snail/gcc-patch-check warning Git am fail log

Commit Message

juzhe.zhong@rivai.ai Nov. 14, 2023, 3:28 a.m. UTC
  Strided load/store has been approved.

Rebase on V3 and adapt for middle-end IR change.

Will commit after middle-end patche is approved.

gcc/ChangeLog:

	* config/riscv/autovec.md (mask_len_strided_load_<mode>): New pattern.
	(mask_len_strided_store_<mode>): Ditto.
	* config/riscv/riscv-protos.h (expand_strided_load_store): New function.
	* config/riscv/riscv-v.cc (expand_strided_load_store): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-1.c: Adapt test.
	* gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-2.c: Ditto.
	* gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-1.c: Ditto.
	* gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-2.c: Ditto.
	* gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load-1.c: New test.
	* gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load_run-1.c: New test.
	* gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store-1.c: New test.
	* gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store_run-1.c: New test.
	* gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-3.c: New test.
	* gcc.target/riscv/rvv/autovec/gather-scatter/strided_load_run-3.c: New test.
	* gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-3.c: New test.
	* gcc.target/riscv/rvv/autovec/gather-scatter/strided_store_run-3.c: New test.

---
 gcc/config/riscv/autovec.md                   | 30 ++++++
 gcc/config/riscv/riscv-protos.h               |  1 +
 gcc/config/riscv/riscv-v.cc                   | 56 +++++++++++
 .../gather-scatter/mask_strided_load-1.c      | 47 +++++++++
 .../gather-scatter/mask_strided_load_run-1.c  | 97 +++++++++++++++++++
 .../gather-scatter/mask_strided_store-1.c     | 48 +++++++++
 .../gather-scatter/mask_strided_store_run-1.c | 89 +++++++++++++++++
 .../autovec/gather-scatter/strided_load-1.c   |  2 +-
 .../autovec/gather-scatter/strided_load-2.c   |  2 +-
 .../autovec/gather-scatter/strided_load-3.c   | 45 +++++++++
 .../gather-scatter/strided_load_run-3.c       | 84 ++++++++++++++++
 .../autovec/gather-scatter/strided_store-1.c  |  2 +-
 .../autovec/gather-scatter/strided_store-2.c  |  2 +-
 .../autovec/gather-scatter/strided_store-3.c  | 45 +++++++++
 .../gather-scatter/strided_store_run-3.c      | 82 ++++++++++++++++
 15 files changed, 628 insertions(+), 4 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load-1.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load_run-1.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store-1.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store_run-1.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-3.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load_run-3.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-3.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store_run-3.c
  

Patch

diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index 80e41af6334..e0c294ffd10 100644
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -272,6 +272,36 @@ 
   DONE;
 })
 
+;; =========================================================================
+;; == Strided Load/Store
+;; =========================================================================
+
+(define_expand "mask_len_strided_load_<mode>"
+  [(match_operand:V 0 "register_operand")
+   (match_operand 1 "pmode_reg_or_0_operand")
+   (match_operand 2 "pmode_reg_or_0_operand")
+   (match_operand:<VM> 3 "vector_mask_operand")
+   (match_operand 4 "autovec_length_operand")
+   (match_operand 5 "const_0_operand")]
+  "TARGET_VECTOR"
+{
+  riscv_vector::expand_strided_load_store (<MODE>mode, operands, true);
+  DONE;
+})
+
+(define_expand "mask_len_strided_store_<mode>"
+  [(match_operand 0 "pmode_reg_or_0_operand")
+   (match_operand 1 "pmode_reg_or_0_operand")
+   (match_operand:V 2 "register_operand")
+   (match_operand:<VM> 3 "vector_mask_operand")
+   (match_operand 4 "autovec_length_operand")
+   (match_operand 5 "const_0_operand")]
+  "TARGET_VECTOR"
+{
+  riscv_vector::expand_strided_load_store (<MODE>mode, operands, false);
+  DONE;
+})
+
 ;; =========================================================================
 ;; == Array Load/Store
 ;; =========================================================================
diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index 8cdfadbcf10..3ef5740cf5b 100644
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -546,6 +546,7 @@  void expand_vec_perm (rtx, rtx, rtx, rtx);
 void expand_select_vl (rtx *);
 void expand_load_store (rtx *, bool);
 void expand_gather_scatter (rtx *, bool);
+void expand_strided_load_store (machine_mode, rtx *, bool);
 void expand_cond_len_ternop (unsigned, rtx *);
 void prepare_ternary_operands (rtx *);
 void expand_lanes_load_store (rtx *, bool);
diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index 265a298f447..6e9bb08aee7 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -3608,6 +3608,62 @@  expand_gather_scatter (rtx *ops, bool is_load)
     }
 }
 
+/* Expand MASK_LEN_STRIDED_{LOAD,STORE}.  */
+void
+expand_strided_load_store (machine_mode mode, rtx *ops, bool is_load)
+{
+  rtx ptr, stride, vec_reg;
+  rtx mask = ops[3];
+  rtx len = ops[4];
+  poly_int64 value;
+  if (is_load)
+    {
+      vec_reg = ops[0];
+      ptr = ops[1];
+      stride = ops[2];
+    }
+  else
+    {
+      vec_reg = ops[2];
+      ptr = ops[0];
+      stride = ops[1];
+    }
+
+  if (poly_int_rtx_p (len, &value) && known_eq (value, GET_MODE_NUNITS (mode)))
+    {
+      /* If the length operand is equal to VF, it is VLMAX load/store.  */
+      if (is_load)
+	{
+	  rtx m_ops[] = {vec_reg, mask, gen_rtx_MEM (mode, ptr), stride};
+	  emit_vlmax_insn (code_for_pred_strided_load (mode), BINARY_OP_TAMA,
+			   m_ops);
+	}
+      else
+	{
+	  len = gen_reg_rtx (Pmode);
+	  emit_vlmax_vsetvl (mode, len);
+	  emit_insn (gen_pred_strided_store (mode, gen_rtx_MEM (mode, ptr),
+					     mask, stride, vec_reg, len,
+					     get_avl_type_rtx (VLMAX)));
+	}
+    }
+  else
+    {
+      if (!satisfies_constraint_K (len))
+	len = force_reg (Pmode, len);
+      if (is_load)
+	{
+	  rtx m_ops[] = {vec_reg, mask, gen_rtx_MEM (mode, ptr), stride};
+	  emit_nonvlmax_insn (code_for_pred_strided_load (mode), BINARY_OP_TAMA,
+			      m_ops, len);
+	}
+      else
+	emit_insn (gen_pred_strided_store (mode, gen_rtx_MEM (mode, ptr), mask,
+					   stride, vec_reg, len,
+					   get_avl_type_rtx (NONVLMAX)));
+    }
+}
+
 /* Expand COND_LEN_*.  */
 void
 expand_cond_len_ternop (unsigned icode, rtx *ops)
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load-1.c
new file mode 100644
index 00000000000..b2b6a03189d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load-1.c
@@ -0,0 +1,47 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh -mabi=lp64d -O3 --param riscv-autovec-preference=scalable -fno-vect-cost-model -ffast-math -fdump-tree-optimized-details" } */
+
+#include <stdint-gcc.h>
+
+#ifndef INDEX8
+#define INDEX8 int8_t
+#define INDEX16 int16_t
+#define INDEX32 int32_t
+#define INDEX64 int64_t
+#endif
+
+#define TEST_LOOP(DATA_TYPE, BITS)                                             \
+  void __attribute__ ((noinline, noclone))                                     \
+  f_##DATA_TYPE##_##BITS (DATA_TYPE *restrict dest, DATA_TYPE *restrict src,   \
+			  INDEX##BITS stride, DATA_TYPE *restrict cond,        \
+			  INDEX##BITS n)                                       \
+  {                                                                            \
+    for (INDEX##BITS i = 0; i < n; ++i)                                        \
+      if (cond[i * stride])                                                    \
+	dest[i] += src[i * stride];                                            \
+  }
+
+#define TEST_TYPE(T, DATA_TYPE)                                                \
+  T (DATA_TYPE, 8)                                                             \
+  T (DATA_TYPE, 16)                                                            \
+  T (DATA_TYPE, 32)                                                            \
+  T (DATA_TYPE, 64)
+
+#define TEST_ALL(T)                                                            \
+  TEST_TYPE (T, int8_t)                                                        \
+  TEST_TYPE (T, uint8_t)                                                       \
+  TEST_TYPE (T, int16_t)                                                       \
+  TEST_TYPE (T, uint16_t)                                                      \
+  TEST_TYPE (T, _Float16)                                                      \
+  TEST_TYPE (T, int32_t)                                                       \
+  TEST_TYPE (T, uint32_t)                                                      \
+  TEST_TYPE (T, float)                                                         \
+  TEST_TYPE (T, int64_t)                                                       \
+  TEST_TYPE (T, uint64_t)                                                      \
+  TEST_TYPE (T, double)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times " \.MASK_LEN_STRIDED_LOAD" 132 "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load_run-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load_run-1.c
new file mode 100644
index 00000000000..08e70ad4e44
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_load_run-1.c
@@ -0,0 +1,97 @@ 
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-mcmodel=medany" } */
+
+#include "mask_strided_load-1.c"
+#include <assert.h>
+
+int
+main (void)
+{
+  /* FIXME: The purpose of this assembly is to ensure that the vtype register is
+     initialized befor instructions such as vmv1r.v are executed. Otherwise you
+     will get illegal instruction errors when running with spike+pk. This is an
+     interim solution for reduce unnecessary failures and a unified solution
+     will come later. */
+  asm volatile("vsetivli x0, 0, e8, m1, ta, ma");
+#define RUN_LOOP(DATA_TYPE, BITS)                                              \
+  DATA_TYPE dest_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];               \
+  DATA_TYPE dest2_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];              \
+  DATA_TYPE src_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];                \
+  DATA_TYPE cond_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];               \
+  INDEX##BITS stride_##DATA_TYPE##_##BITS = (BITS - 3);                        \
+  INDEX##BITS n_##DATA_TYPE##_##BITS = (BITS + 13);                            \
+  for (INDEX##BITS i = 0;                                                      \
+       i < stride_##DATA_TYPE##_##BITS * n_##DATA_TYPE##_##BITS; i++)          \
+    {                                                                          \
+      dest_##DATA_TYPE##_##BITS[i]                                             \
+	= (DATA_TYPE) ((i * 81 + 735) & (BITS - 1));                           \
+      dest2_##DATA_TYPE##_##BITS[i]                                            \
+	= (DATA_TYPE) ((i * 81 + 735) & (BITS - 1));                           \
+      src_##DATA_TYPE##_##BITS[i]                                              \
+	= (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1));                          \
+      cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) (i & 1);                      \
+    }                                                                          \
+  f_##DATA_TYPE##_##BITS (dest_##DATA_TYPE##_##BITS, src_##DATA_TYPE##_##BITS, \
+			  stride_##DATA_TYPE##_##BITS,                         \
+			  cond_##DATA_TYPE##_##BITS, n_##DATA_TYPE##_##BITS);  \
+  for (int i = 0; i < n_##DATA_TYPE##_##BITS; i++)                             \
+    {                                                                          \
+      if (cond_##DATA_TYPE##_##BITS[i * stride_##DATA_TYPE##_##BITS])          \
+	assert (                                                               \
+	  dest_##DATA_TYPE##_##BITS[i]                                         \
+	  == (dest2_##DATA_TYPE##_##BITS[i]                                    \
+	      + src_##DATA_TYPE##_##BITS[i * stride_##DATA_TYPE##_##BITS]));   \
+      else                                                                     \
+	assert (dest_##DATA_TYPE##_##BITS[i]                                   \
+		== dest2_##DATA_TYPE##_##BITS[i]);                             \
+    }
+
+  RUN_LOOP (int8_t, 8)
+  RUN_LOOP (uint8_t, 8)
+  RUN_LOOP (int16_t, 8)
+  RUN_LOOP (uint16_t, 8)
+  RUN_LOOP (_Float16, 8)
+  RUN_LOOP (int32_t, 8)
+  RUN_LOOP (uint32_t, 8)
+  RUN_LOOP (float, 8)
+  RUN_LOOP (int64_t, 8)
+  RUN_LOOP (uint64_t, 8)
+  RUN_LOOP (double, 8)
+
+  RUN_LOOP (int8_t, 16)
+  RUN_LOOP (uint8_t, 16)
+  RUN_LOOP (int16_t, 16)
+  RUN_LOOP (uint16_t, 16)
+  RUN_LOOP (_Float16, 16)
+  RUN_LOOP (int32_t, 16)
+  RUN_LOOP (uint32_t, 16)
+  RUN_LOOP (float, 16)
+  RUN_LOOP (int64_t, 16)
+  RUN_LOOP (uint64_t, 16)
+  RUN_LOOP (double, 16)
+
+  RUN_LOOP (int8_t, 32)
+  RUN_LOOP (uint8_t, 32)
+  RUN_LOOP (int16_t, 32)
+  RUN_LOOP (uint16_t, 32)
+  RUN_LOOP (_Float16, 32)
+  RUN_LOOP (int32_t, 32)
+  RUN_LOOP (uint32_t, 32)
+  RUN_LOOP (float, 32)
+  RUN_LOOP (int64_t, 32)
+  RUN_LOOP (uint64_t, 32)
+  RUN_LOOP (double, 32)
+
+  RUN_LOOP (int8_t, 64)
+  RUN_LOOP (uint8_t, 64)
+  RUN_LOOP (int16_t, 64)
+  RUN_LOOP (uint16_t, 64)
+  RUN_LOOP (_Float16, 64)
+  RUN_LOOP (int32_t, 64)
+  RUN_LOOP (uint32_t, 64)
+  RUN_LOOP (float, 64)
+  RUN_LOOP (int64_t, 64)
+  RUN_LOOP (uint64_t, 64)
+  RUN_LOOP (double, 64)
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store-1.c
new file mode 100644
index 00000000000..a832af2ba57
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store-1.c
@@ -0,0 +1,48 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh -mabi=lp64d -O3 --param riscv-autovec-preference=scalable -fno-vect-cost-model -ffast-math -fdump-tree-optimized-details" } */
+
+#include <stdint-gcc.h>
+
+#ifndef INDEX8
+#define INDEX8 int8_t
+#define INDEX16 int16_t
+#define INDEX32 int32_t
+#define INDEX64 int64_t
+#endif
+
+#define TEST_LOOP(DATA_TYPE, BITS)                                             \
+  void __attribute__ ((noinline, noclone))                                     \
+  f_##DATA_TYPE##_##BITS (DATA_TYPE *restrict dest, DATA_TYPE *restrict src,   \
+			  INDEX##BITS stride, DATA_TYPE *restrict cond,        \
+			  INDEX##BITS n)                                       \
+  {                                                                            \
+    for (INDEX##BITS i = 0; i < n; ++i)                                        \
+      if (cond[i * stride])                                                    \
+	dest[i * stride] = src[i] + BITS;                                      \
+  }
+
+#define TEST_TYPE(T, DATA_TYPE)                                                \
+  T (DATA_TYPE, 8)                                                             \
+  T (DATA_TYPE, 16)                                                            \
+  T (DATA_TYPE, 32)                                                            \
+  T (DATA_TYPE, 64)
+
+#define TEST_ALL(T)                                                            \
+  TEST_TYPE (T, int8_t)                                                        \
+  TEST_TYPE (T, uint8_t)                                                       \
+  TEST_TYPE (T, int16_t)                                                       \
+  TEST_TYPE (T, uint16_t)                                                      \
+  TEST_TYPE (T, _Float16)                                                      \
+  TEST_TYPE (T, int32_t)                                                       \
+  TEST_TYPE (T, uint32_t)                                                      \
+  TEST_TYPE (T, float)                                                         \
+  TEST_TYPE (T, int64_t)                                                       \
+  TEST_TYPE (T, uint64_t)                                                      \
+  TEST_TYPE (T, double)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times " \.MASK_LEN_STRIDED_STORE" 66 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " \.MASK_LEN_STRIDED_LOAD" 66 "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store_run-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store_run-1.c
new file mode 100644
index 00000000000..58956bd6925
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/mask_strided_store_run-1.c
@@ -0,0 +1,89 @@ 
+/* { dg-do run { target { riscv_v } } } */
+
+#include "mask_strided_store-1.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS)                                              \
+  DATA_TYPE dest_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];               \
+  DATA_TYPE dest2_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];              \
+  DATA_TYPE src_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];                \
+  DATA_TYPE cond_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];               \
+  INDEX##BITS stride_##DATA_TYPE##_##BITS = (BITS - 3);                        \
+  INDEX##BITS n_##DATA_TYPE##_##BITS = (BITS + 13);                            \
+  for (INDEX##BITS i = 0;                                                      \
+       i < stride_##DATA_TYPE##_##BITS * n_##DATA_TYPE##_##BITS; i++)          \
+    {                                                                          \
+      dest_##DATA_TYPE##_##BITS[i]                                             \
+	= (DATA_TYPE) ((i * 81 + 735) & (BITS - 1));                           \
+      dest2_##DATA_TYPE##_##BITS[i]                                            \
+	= (DATA_TYPE) ((i * 81 + 735) & (BITS - 1));                           \
+      src_##DATA_TYPE##_##BITS[i]                                              \
+	= (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1));                          \
+      cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) (i & 1);                      \
+    }                                                                          \
+  f_##DATA_TYPE##_##BITS (dest_##DATA_TYPE##_##BITS, src_##DATA_TYPE##_##BITS, \
+			  stride_##DATA_TYPE##_##BITS,                         \
+			  cond_##DATA_TYPE##_##BITS, n_##DATA_TYPE##_##BITS);  \
+  for (int i = 0; i < n_##DATA_TYPE##_##BITS; i++)                             \
+    {                                                                          \
+      if (cond_##DATA_TYPE##_##BITS[i * stride_##DATA_TYPE##_##BITS])          \
+	assert (dest_##DATA_TYPE##_##BITS[i * stride_##DATA_TYPE##_##BITS]     \
+		== (src_##DATA_TYPE##_##BITS[i] + BITS));                      \
+      else                                                                     \
+	assert (                                                               \
+	  dest_##DATA_TYPE##_##BITS[i * stride_##DATA_TYPE##_##BITS]           \
+	  == dest2_##DATA_TYPE##_##BITS[i * stride_##DATA_TYPE##_##BITS]);     \
+    }
+
+  RUN_LOOP (int8_t, 8)
+  RUN_LOOP (uint8_t, 8)
+  RUN_LOOP (int16_t, 8)
+  RUN_LOOP (uint16_t, 8)
+  RUN_LOOP (_Float16, 8)
+  RUN_LOOP (int32_t, 8)
+  RUN_LOOP (uint32_t, 8)
+  RUN_LOOP (float, 8)
+  RUN_LOOP (int64_t, 8)
+  RUN_LOOP (uint64_t, 8)
+  RUN_LOOP (double, 8)
+
+  RUN_LOOP (int8_t, 16)
+  RUN_LOOP (uint8_t, 16)
+  RUN_LOOP (int16_t, 16)
+  RUN_LOOP (uint16_t, 16)
+  RUN_LOOP (_Float16, 16)
+  RUN_LOOP (int32_t, 16)
+  RUN_LOOP (uint32_t, 16)
+  RUN_LOOP (float, 16)
+  RUN_LOOP (int64_t, 16)
+  RUN_LOOP (uint64_t, 16)
+  RUN_LOOP (double, 16)
+
+  RUN_LOOP (int8_t, 32)
+  RUN_LOOP (uint8_t, 32)
+  RUN_LOOP (int16_t, 32)
+  RUN_LOOP (uint16_t, 32)
+  RUN_LOOP (_Float16, 32)
+  RUN_LOOP (int32_t, 32)
+  RUN_LOOP (uint32_t, 32)
+  RUN_LOOP (float, 32)
+  RUN_LOOP (int64_t, 32)
+  RUN_LOOP (uint64_t, 32)
+  RUN_LOOP (double, 32)
+
+  RUN_LOOP (int8_t, 64)
+  RUN_LOOP (uint8_t, 64)
+  RUN_LOOP (int16_t, 64)
+  RUN_LOOP (uint16_t, 64)
+  RUN_LOOP (_Float16, 64)
+  RUN_LOOP (int32_t, 64)
+  RUN_LOOP (uint32_t, 64)
+  RUN_LOOP (float, 64)
+  RUN_LOOP (int64_t, 64)
+  RUN_LOOP (uint64_t, 64)
+  RUN_LOOP (double, 64)
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-1.c
index b1e6a17543f..8f383069b0e 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-1.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-1.c
@@ -40,6 +40,6 @@ 
 
 TEST_ALL (TEST_LOOP)
 
-/* { dg-final { scan-tree-dump-times " \.MASK_LEN_GATHER_LOAD" 66 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " \.MASK_LEN_STRIDED_LOAD" 66 "optimized" } } */
 /* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "optimized" } } */
 /* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-2.c
index 2c9e7dd14a8..3b497e69088 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-2.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-2.c
@@ -40,6 +40,6 @@ 
 
 TEST_ALL (TEST_LOOP)
 
-/* { dg-final { scan-tree-dump-times " \.MASK_LEN_GATHER_LOAD" 33 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " \.MASK_LEN_STRIDED_LOAD" 33 "optimized" } } */
 /* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "optimized" } } */
 /* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-3.c
new file mode 100644
index 00000000000..77e34a85575
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load-3.c
@@ -0,0 +1,45 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh -mabi=lp64d -O3 --param riscv-autovec-preference=scalable -fno-vect-cost-model -ffast-math -fdump-tree-optimized-details" } */
+
+#include <stdint-gcc.h>
+
+#ifndef INDEX8
+#define INDEX8 uint8_t
+#define INDEX16 uint16_t
+#define INDEX32 uint32_t
+#define INDEX64 uint64_t
+#endif
+
+#define TEST_LOOP(DATA_TYPE, BITS)                                             \
+  void __attribute__ ((noinline, noclone))                                     \
+  f_##DATA_TYPE##_##BITS (DATA_TYPE *restrict dest, DATA_TYPE *restrict src,   \
+			  INDEX##BITS stride, INDEX##BITS n)                   \
+  {                                                                            \
+    for (INDEX##BITS i = 0; i < n; ++i)                                        \
+      dest[i] += src[i * stride];                                              \
+  }
+
+#define TEST_TYPE(T, DATA_TYPE)                                                \
+  T (DATA_TYPE, 8)                                                             \
+  T (DATA_TYPE, 16)                                                            \
+  T (DATA_TYPE, 32)                                                            \
+  T (DATA_TYPE, 64)
+
+#define TEST_ALL(T)                                                            \
+  TEST_TYPE (T, int8_t)                                                        \
+  TEST_TYPE (T, uint8_t)                                                       \
+  TEST_TYPE (T, int16_t)                                                       \
+  TEST_TYPE (T, uint16_t)                                                      \
+  TEST_TYPE (T, _Float16)                                                      \
+  TEST_TYPE (T, int32_t)                                                       \
+  TEST_TYPE (T, uint32_t)                                                      \
+  TEST_TYPE (T, float)                                                         \
+  TEST_TYPE (T, int64_t)                                                       \
+  TEST_TYPE (T, uint64_t)                                                      \
+  TEST_TYPE (T, double)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times " \.MASK_LEN_STRIDED_LOAD" 55 "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load_run-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load_run-3.c
new file mode 100644
index 00000000000..2835e502cfa
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_load_run-3.c
@@ -0,0 +1,84 @@ 
+/* { dg-do run { target { riscv_v } } } */
+
+#include "strided_load-3.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS)                                              \
+  DATA_TYPE dest_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];               \
+  DATA_TYPE dest2_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];              \
+  DATA_TYPE src_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];                \
+  INDEX##BITS stride_##DATA_TYPE##_##BITS = (BITS - 3);                        \
+  INDEX##BITS n_##DATA_TYPE##_##BITS = (BITS + 13);                            \
+  for (INDEX##BITS i = 0;                                                      \
+       i < stride_##DATA_TYPE##_##BITS * n_##DATA_TYPE##_##BITS; i++)          \
+    {                                                                          \
+      dest_##DATA_TYPE##_##BITS[i]                                             \
+	= (DATA_TYPE) ((i * 81 + 735) & (BITS - 1));                           \
+      dest2_##DATA_TYPE##_##BITS[i]                                            \
+	= (DATA_TYPE) ((i * 81 + 735) & (BITS - 1));                           \
+      src_##DATA_TYPE##_##BITS[i]                                              \
+	= (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1));                          \
+    }                                                                          \
+  f_##DATA_TYPE##_##BITS (dest_##DATA_TYPE##_##BITS, src_##DATA_TYPE##_##BITS, \
+			  stride_##DATA_TYPE##_##BITS,                         \
+			  n_##DATA_TYPE##_##BITS);                             \
+  for (int i = 0; i < n_##DATA_TYPE##_##BITS; i++)                             \
+    {                                                                          \
+      assert (                                                                 \
+	dest_##DATA_TYPE##_##BITS[i]                                           \
+	== (dest2_##DATA_TYPE##_##BITS[i]                                      \
+	    + src_##DATA_TYPE##_##BITS[i * stride_##DATA_TYPE##_##BITS]));     \
+    }
+
+  RUN_LOOP (int8_t, 8)
+  RUN_LOOP (uint8_t, 8)
+  RUN_LOOP (int16_t, 8)
+  RUN_LOOP (uint16_t, 8)
+  RUN_LOOP (_Float16, 8)
+  RUN_LOOP (int32_t, 8)
+  RUN_LOOP (uint32_t, 8)
+  RUN_LOOP (float, 8)
+  RUN_LOOP (int64_t, 8)
+  RUN_LOOP (uint64_t, 8)
+  RUN_LOOP (double, 8)
+
+  RUN_LOOP (int8_t, 16)
+  RUN_LOOP (uint8_t, 16)
+  RUN_LOOP (int16_t, 16)
+  RUN_LOOP (uint16_t, 16)
+  RUN_LOOP (_Float16, 16)
+  RUN_LOOP (int32_t, 16)
+  RUN_LOOP (uint32_t, 16)
+  RUN_LOOP (float, 16)
+  RUN_LOOP (int64_t, 16)
+  RUN_LOOP (uint64_t, 16)
+  RUN_LOOP (double, 16)
+
+  RUN_LOOP (int8_t, 32)
+  RUN_LOOP (uint8_t, 32)
+  RUN_LOOP (int16_t, 32)
+  RUN_LOOP (uint16_t, 32)
+  RUN_LOOP (_Float16, 32)
+  RUN_LOOP (int32_t, 32)
+  RUN_LOOP (uint32_t, 32)
+  RUN_LOOP (float, 32)
+  RUN_LOOP (int64_t, 32)
+  RUN_LOOP (uint64_t, 32)
+  RUN_LOOP (double, 32)
+
+  RUN_LOOP (int8_t, 64)
+  RUN_LOOP (uint8_t, 64)
+  RUN_LOOP (int16_t, 64)
+  RUN_LOOP (uint16_t, 64)
+  RUN_LOOP (_Float16, 64)
+  RUN_LOOP (int32_t, 64)
+  RUN_LOOP (uint32_t, 64)
+  RUN_LOOP (float, 64)
+  RUN_LOOP (int64_t, 64)
+  RUN_LOOP (uint64_t, 64)
+  RUN_LOOP (double, 64)
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-1.c
index 3e6a34029b3..d8da51f3ac5 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-1.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-1.c
@@ -40,6 +40,6 @@ 
 
 TEST_ALL (TEST_LOOP)
 
-/* { dg-final { scan-tree-dump-times " \.MASK_LEN_SCATTER_STORE" 66 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " \.MASK_LEN_STRIDED_STORE" 66 "optimized" } } */
 /* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "optimized" } } */
 /* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-2.c
index 6906af17d84..9ffea4e0d99 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-2.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-2.c
@@ -40,6 +40,6 @@ 
 
 TEST_ALL (TEST_LOOP)
 
-/* { dg-final { scan-tree-dump-times " \.MASK_LEN_SCATTER_STORE" 44 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " \.MASK_LEN_STRIDED_STORE" 44 "optimized" } } */
 /* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "optimized" } } */
 /* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-3.c
new file mode 100644
index 00000000000..eb0bcddaade
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store-3.c
@@ -0,0 +1,45 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh -mabi=lp64d -O3 --param riscv-autovec-preference=scalable -fno-vect-cost-model -ffast-math -fdump-tree-optimized-details" } */
+
+#include <stdint-gcc.h>
+
+#ifndef INDEX8
+#define INDEX8 uint8_t
+#define INDEX16 uint16_t
+#define INDEX32 uint32_t
+#define INDEX64 uint64_t
+#endif
+
+#define TEST_LOOP(DATA_TYPE, BITS)                                             \
+  void __attribute__ ((noinline, noclone))                                     \
+  f_##DATA_TYPE##_##BITS (DATA_TYPE *restrict dest, DATA_TYPE *restrict src,   \
+			  INDEX##BITS stride, INDEX##BITS n)                   \
+  {                                                                            \
+    for (INDEX##BITS i = 0; i < n; ++i)                                        \
+      dest[i * stride] = src[i] + BITS;                                        \
+  }
+
+#define TEST_TYPE(T, DATA_TYPE)                                                \
+  T (DATA_TYPE, 8)                                                             \
+  T (DATA_TYPE, 16)                                                            \
+  T (DATA_TYPE, 32)                                                            \
+  T (DATA_TYPE, 64)
+
+#define TEST_ALL(T)                                                            \
+  TEST_TYPE (T, int8_t)                                                        \
+  TEST_TYPE (T, uint8_t)                                                       \
+  TEST_TYPE (T, int16_t)                                                       \
+  TEST_TYPE (T, uint16_t)                                                      \
+  TEST_TYPE (T, _Float16)                                                      \
+  TEST_TYPE (T, int32_t)                                                       \
+  TEST_TYPE (T, uint32_t)                                                      \
+  TEST_TYPE (T, float)                                                         \
+  TEST_TYPE (T, int64_t)                                                       \
+  TEST_TYPE (T, uint64_t)                                                      \
+  TEST_TYPE (T, double)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times " \.MASK_LEN_STRIDED_STORE" 55 "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "optimized" } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store_run-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store_run-3.c
new file mode 100644
index 00000000000..079336737bb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/strided_store_run-3.c
@@ -0,0 +1,82 @@ 
+/* { dg-do run { target { riscv_v } } } */
+
+#include "strided_store-3.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS)                                              \
+  DATA_TYPE dest_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];               \
+  DATA_TYPE dest2_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];              \
+  DATA_TYPE src_##DATA_TYPE##_##BITS[(BITS - 3) * (BITS + 13)];                \
+  INDEX##BITS stride_##DATA_TYPE##_##BITS = (BITS - 3);                        \
+  INDEX##BITS n_##DATA_TYPE##_##BITS = (BITS + 13);                            \
+  for (INDEX##BITS i = 0;                                                      \
+       i < stride_##DATA_TYPE##_##BITS * n_##DATA_TYPE##_##BITS; i++)          \
+    {                                                                          \
+      dest_##DATA_TYPE##_##BITS[i]                                             \
+	= (DATA_TYPE) ((i * 81 + 735) & (BITS - 1));                           \
+      dest2_##DATA_TYPE##_##BITS[i]                                            \
+	= (DATA_TYPE) ((i * 81 + 735) & (BITS - 1));                           \
+      src_##DATA_TYPE##_##BITS[i]                                              \
+	= (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1));                          \
+    }                                                                          \
+  f_##DATA_TYPE##_##BITS (dest_##DATA_TYPE##_##BITS, src_##DATA_TYPE##_##BITS, \
+			  stride_##DATA_TYPE##_##BITS,                         \
+			  n_##DATA_TYPE##_##BITS);                             \
+  for (int i = 0; i < n_##DATA_TYPE##_##BITS; i++)                             \
+    {                                                                          \
+      assert (dest_##DATA_TYPE##_##BITS[i * stride_##DATA_TYPE##_##BITS]       \
+	      == (src_##DATA_TYPE##_##BITS[i] + BITS));                        \
+    }
+
+  RUN_LOOP (int8_t, 8)
+  RUN_LOOP (uint8_t, 8)
+  RUN_LOOP (int16_t, 8)
+  RUN_LOOP (uint16_t, 8)
+  RUN_LOOP (_Float16, 8)
+  RUN_LOOP (int32_t, 8)
+  RUN_LOOP (uint32_t, 8)
+  RUN_LOOP (float, 8)
+  RUN_LOOP (int64_t, 8)
+  RUN_LOOP (uint64_t, 8)
+  RUN_LOOP (double, 8)
+
+  RUN_LOOP (int8_t, 16)
+  RUN_LOOP (uint8_t, 16)
+  RUN_LOOP (int16_t, 16)
+  RUN_LOOP (uint16_t, 16)
+  RUN_LOOP (_Float16, 16)
+  RUN_LOOP (int32_t, 16)
+  RUN_LOOP (uint32_t, 16)
+  RUN_LOOP (float, 16)
+  RUN_LOOP (int64_t, 16)
+  RUN_LOOP (uint64_t, 16)
+  RUN_LOOP (double, 16)
+
+  RUN_LOOP (int8_t, 32)
+  RUN_LOOP (uint8_t, 32)
+  RUN_LOOP (int16_t, 32)
+  RUN_LOOP (uint16_t, 32)
+  RUN_LOOP (_Float16, 32)
+  RUN_LOOP (int32_t, 32)
+  RUN_LOOP (uint32_t, 32)
+  RUN_LOOP (float, 32)
+  RUN_LOOP (int64_t, 32)
+  RUN_LOOP (uint64_t, 32)
+  RUN_LOOP (double, 32)
+
+  RUN_LOOP (int8_t, 64)
+  RUN_LOOP (uint8_t, 64)
+  RUN_LOOP (int16_t, 64)
+  RUN_LOOP (uint16_t, 64)
+  RUN_LOOP (_Float16, 64)
+  RUN_LOOP (int32_t, 64)
+  RUN_LOOP (uint32_t, 64)
+  RUN_LOOP (float, 64)
+  RUN_LOOP (int64_t, 64)
+  RUN_LOOP (uint64_t, 64)
+  RUN_LOOP (double, 64)
+  return 0;
+}