}
)
+;; =========================================================================
+;; == Gather Load
+;; =========================================================================
+
+(define_expand "len_mask_gather_load<VNX1_QHSD:mode><VNX1_QHSDI:mode>"
+ [(match_operand:VNX1_QHSD 0 "register_operand")
+ (match_operand 1 "pmode_reg_or_0_operand")
+ (match_operand:VNX1_QHSDI 2 "register_operand")
+ (match_operand 3 "<VNX1_QHSD:gs_extension>")
+ (match_operand 4 "<VNX1_QHSD:gs_scale>")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX1_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, true);
+ DONE;
+})
+
+(define_expand "len_mask_gather_load<VNX2_QHSD:mode><VNX2_QHSDI:mode>"
+ [(match_operand:VNX2_QHSD 0 "register_operand")
+ (match_operand 1 "pmode_reg_or_0_operand")
+ (match_operand:VNX2_QHSDI 2 "register_operand")
+ (match_operand 3 "<VNX2_QHSD:gs_extension>")
+ (match_operand 4 "<VNX2_QHSD:gs_scale>")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX2_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, true);
+ DONE;
+})
+
+(define_expand "len_mask_gather_load<VNX4_QHSD:mode><VNX4_QHSDI:mode>"
+ [(match_operand:VNX4_QHSD 0 "register_operand")
+ (match_operand 1 "pmode_reg_or_0_operand")
+ (match_operand:VNX4_QHSDI 2 "register_operand")
+ (match_operand 3 "<VNX4_QHSD:gs_extension>")
+ (match_operand 4 "<VNX4_QHSD:gs_scale>")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX4_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, true);
+ DONE;
+})
+
+(define_expand "len_mask_gather_load<VNX8_QHSD:mode><VNX8_QHSDI:mode>"
+ [(match_operand:VNX8_QHSD 0 "register_operand")
+ (match_operand 1 "pmode_reg_or_0_operand")
+ (match_operand:VNX8_QHSDI 2 "register_operand")
+ (match_operand 3 "<VNX8_QHSD:gs_extension>")
+ (match_operand 4 "<VNX8_QHSD:gs_scale>")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX8_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, true);
+ DONE;
+})
+
+(define_expand "len_mask_gather_load<VNX16_QHSD:mode><VNX16_QHSDI:mode>"
+ [(match_operand:VNX16_QHSD 0 "register_operand")
+ (match_operand 1 "pmode_reg_or_0_operand")
+ (match_operand:VNX16_QHSDI 2 "register_operand")
+ (match_operand 3 "<VNX16_QHSD:gs_extension>")
+ (match_operand 4 "<VNX16_QHSD:gs_scale>")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX16_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, true);
+ DONE;
+})
+
+(define_expand "len_mask_gather_load<VNX32_QHS:mode><VNX32_QHSI:mode>"
+ [(match_operand:VNX32_QHS 0 "register_operand")
+ (match_operand 1 "pmode_reg_or_0_operand")
+ (match_operand:VNX32_QHSI 2 "register_operand")
+ (match_operand 3 "<VNX32_QHS:gs_extension>")
+ (match_operand 4 "<VNX32_QHS:gs_scale>")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX32_QHS:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, true);
+ DONE;
+})
+
+(define_expand "len_mask_gather_load<VNX64_QH:mode><VNX64_QHI:mode>"
+ [(match_operand:VNX64_QH 0 "register_operand")
+ (match_operand 1 "pmode_reg_or_0_operand")
+ (match_operand:VNX64_QHI 2 "register_operand")
+ (match_operand 3 "<VNX64_QH:gs_extension>")
+ (match_operand 4 "<VNX64_QH:gs_scale>")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX64_QH:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, true);
+ DONE;
+})
+
+;; When SEW = 8 and LMUL = 8, we can't find any index mode with
+;; larger SEW. Since RVV indexed load/store support zero extend
+;; implicitly and not support scaling, we should only allow
+;; operands[3] and operands[4] to be const_1_operand.
+(define_expand "len_mask_gather_load<mode><mode>"
+ [(match_operand:VNX128_Q 0 "register_operand")
+ (match_operand 1 "pmode_reg_or_0_operand")
+ (match_operand:VNX128_Q 2 "register_operand")
+ (match_operand 3 "const_1_operand")
+ (match_operand 4 "const_1_operand")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, true);
+ DONE;
+})
+
+;; =========================================================================
+;; == Scatter Store
+;; =========================================================================
+
+(define_expand "len_mask_scatter_store<VNX1_QHSD:mode><VNX1_QHSDI:mode>"
+ [(match_operand 0 "pmode_reg_or_0_operand")
+ (match_operand:VNX1_QHSDI 1 "register_operand")
+ (match_operand 2 "<VNX1_QHSD:gs_extension>")
+ (match_operand 3 "<VNX1_QHSD:gs_scale>")
+ (match_operand:VNX1_QHSD 4 "register_operand")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX1_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, false);
+ DONE;
+})
+
+(define_expand "len_mask_scatter_store<VNX2_QHSD:mode><VNX2_QHSDI:mode>"
+ [(match_operand 0 "pmode_reg_or_0_operand")
+ (match_operand:VNX2_QHSDI 1 "register_operand")
+ (match_operand 2 "<VNX2_QHSD:gs_extension>")
+ (match_operand 3 "<VNX2_QHSD:gs_scale>")
+ (match_operand:VNX2_QHSD 4 "register_operand")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX2_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, false);
+ DONE;
+})
+
+(define_expand "len_mask_scatter_store<VNX4_QHSD:mode><VNX4_QHSDI:mode>"
+ [(match_operand 0 "pmode_reg_or_0_operand")
+ (match_operand:VNX4_QHSDI 1 "register_operand")
+ (match_operand 2 "<VNX4_QHSD:gs_extension>")
+ (match_operand 3 "<VNX4_QHSD:gs_scale>")
+ (match_operand:VNX4_QHSD 4 "register_operand")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX4_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, false);
+ DONE;
+})
+
+(define_expand "len_mask_scatter_store<VNX8_QHSD:mode><VNX8_QHSDI:mode>"
+ [(match_operand 0 "pmode_reg_or_0_operand")
+ (match_operand:VNX8_QHSDI 1 "register_operand")
+ (match_operand 2 "<VNX8_QHSD:gs_extension>")
+ (match_operand 3 "<VNX8_QHSD:gs_scale>")
+ (match_operand:VNX8_QHSD 4 "register_operand")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX8_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, false);
+ DONE;
+})
+
+(define_expand "len_mask_scatter_store<VNX16_QHSD:mode><VNX16_QHSDI:mode>"
+ [(match_operand 0 "pmode_reg_or_0_operand")
+ (match_operand:VNX16_QHSDI 1 "register_operand")
+ (match_operand 2 "<VNX16_QHSD:gs_extension>")
+ (match_operand 3 "<VNX16_QHSD:gs_scale>")
+ (match_operand:VNX16_QHSD 4 "register_operand")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX16_QHSD:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, false);
+ DONE;
+})
+
+(define_expand "len_mask_scatter_store<VNX32_QHS:mode><VNX32_QHSI:mode>"
+ [(match_operand 0 "pmode_reg_or_0_operand")
+ (match_operand:VNX32_QHSI 1 "register_operand")
+ (match_operand 2 "<VNX32_QHS:gs_extension>")
+ (match_operand 3 "<VNX32_QHS:gs_scale>")
+ (match_operand:VNX32_QHS 4 "register_operand")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX32_QHS:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, false);
+ DONE;
+})
+
+(define_expand "len_mask_scatter_store<VNX64_QH:mode><VNX64_QHI:mode>"
+ [(match_operand 0 "pmode_reg_or_0_operand")
+ (match_operand:VNX64_QHI 1 "register_operand")
+ (match_operand 2 "<VNX64_QH:gs_extension>")
+ (match_operand 3 "<VNX64_QH:gs_scale>")
+ (match_operand:VNX64_QH 4 "register_operand")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VNX64_QH:VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, false);
+ DONE;
+})
+
+;; When SEW = 8 and LMUL = 8, we can't find any index mode with
+;; larger SEW. Since RVV indexed load/store support zero extend
+;; implicitly and not support scaling, we should only allow
+;; operands[3] and operands[4] to be const_1_operand.
+(define_expand "len_mask_scatter_store<mode><mode>"
+ [(match_operand 0 "pmode_reg_or_0_operand")
+ (match_operand:VNX128_Q 1 "register_operand")
+ (match_operand 2 "const_1_operand")
+ (match_operand 3 "const_1_operand")
+ (match_operand:VNX128_Q 4 "register_operand")
+ (match_operand 5 "autovec_length_operand")
+ (match_operand 6 "const_0_operand")
+ (match_operand:<VM> 7 "vector_mask_operand")]
+ "TARGET_VECTOR"
+{
+ riscv_vector::expand_gather_scatter (operands, false);
+ DONE;
+})
+
;; =========================================================================
;; == Vector creation
;; =========================================================================
(and (match_code "const_int,const_wide_int,const_vector")
(match_test "op == CONST0_RTX (GET_MODE (op))")))
+(define_predicate "const_1_operand"
+ (and (match_code "const_int,const_wide_int,const_vector")
+ (match_test "op == CONST1_RTX (GET_MODE (op))")))
+
(define_predicate "reg_or_0_operand"
(ior (match_operand 0 "const_0_operand")
(match_operand 0 "register_operand")))
(ior (match_operand 0 "register_operand")
(match_code "const_vector")))
+(define_predicate "vector_gs_scale_operand_16"
+ (and (match_code "const_int")
+ (match_test "INTVAL (op) == 1 || INTVAL (op) == 2")))
+
+(define_predicate "vector_gs_scale_operand_32"
+ (and (match_code "const_int")
+ (match_test "INTVAL (op) == 1 || INTVAL (op) == 4")))
+
+(define_predicate "vector_gs_scale_operand_64"
+ (and (match_code "const_int")
+ (match_test "INTVAL (op) == 1 || (INTVAL (op) == 8 && Pmode == DImode)")))
+
+(define_predicate "vector_gs_extension_operand"
+ (ior (match_operand 0 "const_1_operand")
+ (and (match_operand 0 "const_0_operand")
+ (match_test "Pmode == SImode"))))
+
+(define_predicate "vector_gs_scale_operand_16_rv32"
+ (and (match_code "const_int")
+ (match_test "INTVAL (op) == 1
+ || (INTVAL (op) == 2 && Pmode == SImode)")))
+
+(define_predicate "vector_gs_scale_operand_32_rv32"
+ (and (match_code "const_int")
+ (match_test "INTVAL (op) == 1
+ || (INTVAL (op) == 4 && Pmode == SImode)")))
+
(define_predicate "ltge_operator"
(match_code "lt,ltu,ge,geu"))
|| rtx_equal_p (op, CONST0_RTX (GET_MODE (op))))
&& maybe_gt (GET_MODE_BITSIZE (GET_MODE (op)), GET_MODE_BITSIZE (Pmode)))")
(ior (match_test "rtx_equal_p (op, CONST0_RTX (GET_MODE (op)))")
- (ior (match_operand 0 "const_int_operand")
+ (ior (match_code "const_int,const_poly_int")
(ior (match_operand 0 "register_operand")
(match_test "satisfies_constraint_Wdm (op)"))))))
RVV_SCALAR_MOV_OP = 4, /* +1 for VUNDEF according to vector.md. */
RVV_SLIDE_OP = 4, /* Dest, VUNDEF, source and offset. */
RVV_COMPRESS_OP = 4,
+ RVV_GATHER_M_OP = 5,
+ RVV_SCATTER_M_OP = 4,
};
enum vlmul_type
{
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);
/* Rounding mode bitfield for fixed point VXRM. */
enum fixed_point_rounding_mode
return true;
}
-/* Return a const_int vector of VAL.
-
- This function also exists in aarch64, we may unify it in middle-end in the
- future. */
+/* Return a const vector of VAL. The VAL can be either const_int or
+ const_poly_int. */
static rtx
gen_const_vector_dup (machine_mode mode, poly_int64 val)
{
- rtx c = gen_int_mode (val, GET_MODE_INNER (mode));
- return gen_const_vec_duplicate (mode, c);
+ scalar_mode smode = GET_MODE_INNER (mode);
+ rtx c = gen_int_mode (val, smode);
+ if (!val.is_constant () && GET_MODE_SIZE (smode) > GET_MODE_SIZE (Pmode))
+ {
+ /* When VAL is const_poly_int value, we need to explicitly broadcast
+ it into a vector using RVV broadcast instruction. */
+ rtx dup = gen_reg_rtx (mode);
+ emit_insn (gen_vec_duplicate (mode, dup, c));
+ return dup;
+ }
+ return gen_const_vec_duplicate (mode, c);
}
/* Emit a vlmax vsetvl instruction. This should only be used when
e.emit_insn ((enum insn_code) icode, ops);
}
+/* This function emits a VLMAX masked store instruction. */
+static void
+emit_vlmax_masked_store_insn (unsigned icode, int op_num, 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 (/*OP_NUM*/ op_num,
+ /*HAS_DEST_P*/ false,
+ /*FULLY_UNMASKED_P*/ false,
+ /*USE_REAL_MERGE_P*/ true,
+ /*HAS_AVL_P*/ true,
+ /*VLMAX_P*/ true, dest_mode,
+ mask_mode);
+ e.emit_insn ((enum insn_code) icode, ops);
+}
+
+/* This function emits a non-VLMAX masked store instruction. */
+static void
+emit_nonvlmax_masked_store_insn (unsigned icode, int op_num, 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 (/*OP_NUM*/ op_num,
+ /*HAS_DEST_P*/ false,
+ /*FULLY_UNMASKED_P*/ false,
+ /*USE_REAL_MERGE_P*/ true,
+ /*HAS_AVL_P*/ true,
+ /*VLMAX_P*/ false, dest_mode,
+ mask_mode);
+ e.set_vl (avl);
+ e.emit_insn ((enum insn_code) icode, ops);
+}
+
/* This function emits a masked instruction. */
void
emit_vlmax_masked_mu_insn (unsigned icode, int op_num, rtx *ops)
expand_const_vector (rtx target, rtx src)
{
machine_mode mode = GET_MODE (target);
- scalar_mode elt_mode = GET_MODE_INNER (mode);
if (GET_MODE_CLASS (mode) == MODE_VECTOR_BOOL)
{
rtx elt;
}
else
{
- elt = force_reg (elt_mode, elt);
rtx ops[] = {tmp, elt};
emit_vlmax_insn (code_for_pred_broadcast (mode), RVV_UNOP, ops);
}
return false;
}
+/* Modulo all SEL indices to ensure they are all in range if [0, MAX_SEL]. */
+static rtx
+modulo_sel_indices (rtx sel, poly_uint64 max_sel)
+{
+ rtx sel_mod;
+ machine_mode sel_mode = GET_MODE (sel);
+ poly_uint64 nunits = GET_MODE_NUNITS (sel_mode);
+ /* If SEL is variable-length CONST_VECTOR, we don't need to modulo it. */
+ if (!nunits.is_constant () && CONST_VECTOR_P (sel))
+ sel_mod = sel;
+ else
+ {
+ rtx mod = gen_const_vector_dup (sel_mode, max_sel);
+ sel_mod
+ = expand_simple_binop (sel_mode, AND, sel, mod, NULL, 0, OPTAB_DIRECT);
+ }
+ return sel_mod;
+}
+
/* Implement vec_perm<mode>. */
void
index is in range of [0, nunits - 1]. A single vrgather instructions is
enough. Since we will use vrgatherei16.vv for variable-length vector,
it is never out of range and we don't need to modulo the index. */
- if (!nunits.is_constant () || const_vec_all_in_range_p (sel, 0, nunits - 1))
+ if (nunits.is_constant () && const_vec_all_in_range_p (sel, 0, nunits - 1))
{
emit_vlmax_gather_insn (target, op0, sel);
return;
}
+ /* Check if all the indices are same. */
+ rtx elt;
+ if (const_vec_duplicate_p (sel, &elt))
+ {
+ poly_uint64 value = rtx_to_poly_int64 (elt);
+ rtx op = op0;
+ if (maybe_gt (value, nunits - 1))
+ {
+ sel = gen_const_vector_dup (sel_mode, value - nunits);
+ op = op1;
+ }
+ emit_vlmax_gather_insn (target, op, sel);
+ }
+
+ /* Note: vec_perm indices are supposed to wrap when they go beyond the
+ size of the two value vectors, i.e. the upper bits of the indices
+ are effectively ignored. RVV vrgather instead produces 0 for any
+ out-of-range indices, so we need to modulo all the vec_perm indices
+ to ensure they are all in range of [0, nunits - 1] when op0 == op1
+ or all in range of [0, 2 * nunits - 1] when op0 != op1. */
+ rtx sel_mod
+ = modulo_sel_indices (sel,
+ rtx_equal_p (op0, op1) ? nunits - 1 : 2 * nunits - 1);
+
/* Check if the two values vectors are the same. */
- if (rtx_equal_p (op0, op1) || const_vec_duplicate_p (sel))
- {
- /* Note: vec_perm indices are supposed to wrap when they go beyond the
- size of the two value vectors, i.e. the upper bits of the indices
- are effectively ignored. RVV vrgather instead produces 0 for any
- out-of-range indices, so we need to modulo all the vec_perm indices
- to ensure they are all in range of [0, nunits - 1]. */
- rtx max_sel = gen_const_vector_dup (sel_mode, nunits - 1);
- rtx sel_mod = expand_simple_binop (sel_mode, AND, sel, max_sel, NULL, 0,
- OPTAB_DIRECT);
- emit_vlmax_gather_insn (target, op1, sel_mod);
+ if (rtx_equal_p (op0, op1))
+ {
+ emit_vlmax_gather_insn (target, op0, sel_mod);
return;
}
- rtx sel_mod = sel;
rtx max_sel = gen_const_vector_dup (sel_mode, 2 * nunits - 1);
- /* We don't need to modulo indices for VLA vector.
- Since we should gurantee they aren't out of range before. */
- if (nunits.is_constant ())
- {
- /* Note: vec_perm indices are supposed to wrap when they go beyond the
- size of the two value vectors, i.e. the upper bits of the indices
- are effectively ignored. RVV vrgather instead produces 0 for any
- out-of-range indices, so we need to modulo all the vec_perm indices
- to ensure they are all in range of [0, 2 * nunits - 1]. */
- sel_mod = expand_simple_binop (sel_mode, AND, sel, max_sel, NULL, 0,
- OPTAB_DIRECT);
- }
/* This following sequence is handling the case that:
__builtin_shufflevector (vec1, vec2, index...), the index can be any
}
}
+
/* Return true if the operation is the floating-point operation need FRM. */
static bool
needs_fp_rounding (rtx_code code, machine_mode mode)
gcc_unreachable ();
}
+/* Prepare insn_code for gather_load/scatter_store according to
+ the vector mode and index mode. */
+static insn_code
+prepare_gather_scatter (machine_mode vec_mode, machine_mode idx_mode,
+ bool is_load)
+{
+ if (!is_load)
+ return code_for_pred_indexed_store (UNSPEC_UNORDERED, vec_mode, idx_mode);
+ else
+ {
+ unsigned src_eew_bitsize = GET_MODE_BITSIZE (GET_MODE_INNER (idx_mode));
+ unsigned dst_eew_bitsize = GET_MODE_BITSIZE (GET_MODE_INNER (vec_mode));
+ if (dst_eew_bitsize == src_eew_bitsize)
+ return code_for_pred_indexed_load_same_eew (UNSPEC_UNORDERED, vec_mode);
+ else if (dst_eew_bitsize > src_eew_bitsize)
+ {
+ unsigned factor = dst_eew_bitsize / src_eew_bitsize;
+ switch (factor)
+ {
+ case 2:
+ return code_for_pred_indexed_load_x2_greater_eew (
+ UNSPEC_UNORDERED, vec_mode);
+ case 4:
+ return code_for_pred_indexed_load_x4_greater_eew (
+ UNSPEC_UNORDERED, vec_mode);
+ case 8:
+ return code_for_pred_indexed_load_x8_greater_eew (
+ UNSPEC_UNORDERED, vec_mode);
+ default:
+ gcc_unreachable ();
+ }
+ }
+ else
+ {
+ unsigned factor = src_eew_bitsize / dst_eew_bitsize;
+ switch (factor)
+ {
+ case 2:
+ return code_for_pred_indexed_load_x2_smaller_eew (
+ UNSPEC_UNORDERED, vec_mode);
+ case 4:
+ return code_for_pred_indexed_load_x4_smaller_eew (
+ UNSPEC_UNORDERED, vec_mode);
+ case 8:
+ return code_for_pred_indexed_load_x8_smaller_eew (
+ UNSPEC_UNORDERED, vec_mode);
+ default:
+ gcc_unreachable ();
+ }
+ }
+ }
+}
+
+/* Expand LEN_MASK_{GATHER_LOAD,SCATTER_STORE}. */
+void
+expand_gather_scatter (rtx *ops, bool is_load)
+{
+ rtx ptr, vec_offset, vec_reg, len, mask;
+ bool zero_extend_p;
+ int scale_log2;
+ if (is_load)
+ {
+ vec_reg = ops[0];
+ ptr = ops[1];
+ vec_offset = ops[2];
+ zero_extend_p = INTVAL (ops[3]);
+ scale_log2 = exact_log2 (INTVAL (ops[4]));
+ len = ops[5];
+ mask = ops[7];
+ }
+ else
+ {
+ vec_reg = ops[4];
+ ptr = ops[0];
+ vec_offset = ops[1];
+ zero_extend_p = INTVAL (ops[2]);
+ scale_log2 = exact_log2 (INTVAL (ops[3]));
+ len = ops[5];
+ mask = ops[7];
+ }
+
+ machine_mode vec_mode = GET_MODE (vec_reg);
+ machine_mode idx_mode = GET_MODE (vec_offset);
+ scalar_mode inner_vec_mode = GET_MODE_INNER (vec_mode);
+ scalar_mode inner_idx_mode = GET_MODE_INNER (idx_mode);
+ unsigned inner_vsize = GET_MODE_BITSIZE (inner_vec_mode);
+ unsigned inner_offsize = GET_MODE_BITSIZE (inner_idx_mode);
+ poly_int64 nunits = GET_MODE_NUNITS (vec_mode);
+ poly_int64 value;
+ bool is_vlmax = poly_int_rtx_p (len, &value) && known_eq (value, nunits);
+
+ if (inner_offsize < inner_vsize)
+ {
+ /* 7.2. Vector Load/Store Addressing Modes.
+ If the vector offset elements are narrower than XLEN, they are
+ zero-extended to XLEN before adding to the ptr effective address. If
+ the vector offset elements are wider than XLEN, the least-significant
+ XLEN bits are used in the address calculation. An implementation must
+ raise an illegal instruction exception if the EEW is not supported for
+ offset elements.
+
+ RVV spec only refers to the scale_log == 0 case. */
+ if (!zero_extend_p || (zero_extend_p && scale_log2 != 0))
+ {
+ if (zero_extend_p)
+ inner_idx_mode
+ = int_mode_for_size (inner_offsize * 2, 0).require ();
+ else
+ inner_idx_mode = int_mode_for_size (BITS_PER_WORD, 0).require ();
+ machine_mode new_idx_mode
+ = get_vector_mode (inner_idx_mode, nunits).require ();
+ rtx tmp = gen_reg_rtx (new_idx_mode);
+ emit_insn (gen_extend_insn (tmp, vec_offset, new_idx_mode, idx_mode,
+ zero_extend_p ? true : false));
+ vec_offset = tmp;
+ idx_mode = new_idx_mode;
+ }
+ }
+
+ if (scale_log2 != 0)
+ {
+ rtx tmp = expand_binop (idx_mode, ashl_optab, vec_offset,
+ gen_int_mode (scale_log2, Pmode), NULL_RTX, 0,
+ OPTAB_DIRECT);
+ vec_offset = tmp;
+ }
+
+ insn_code icode = prepare_gather_scatter (vec_mode, idx_mode, is_load);
+ if (is_vlmax)
+ {
+ if (is_load)
+ {
+ rtx load_ops[]
+ = {vec_reg, mask, RVV_VUNDEF (vec_mode), ptr, vec_offset};
+ emit_vlmax_masked_insn (icode, RVV_GATHER_M_OP, load_ops);
+ }
+ else
+ {
+ rtx store_ops[] = {mask, ptr, vec_offset, vec_reg};
+ emit_vlmax_masked_store_insn (icode, RVV_SCATTER_M_OP, store_ops);
+ }
+ }
+ else
+ {
+ if (is_load)
+ {
+ rtx load_ops[]
+ = {vec_reg, mask, RVV_VUNDEF (vec_mode), ptr, vec_offset};
+ emit_nonvlmax_masked_insn (icode, RVV_GATHER_M_OP, load_ops, len);
+ }
+ else
+ {
+ rtx store_ops[] = {mask, ptr, vec_offset, vec_reg};
+ emit_nonvlmax_masked_store_insn (icode, RVV_SCATTER_M_OP, store_ops,
+ len);
+ }
+ }
+}
+
} // namespace riscv_vector
(m, n) = base * magn + constant.
This calculation doesn't need div operation. */
- emit_move_insn (tmp, gen_int_mode (BYTES_PER_RISCV_VECTOR, mode));
+ if (known_le (GET_MODE_SIZE (mode), GET_MODE_SIZE (Pmode)))
+ emit_move_insn (tmp, gen_int_mode (BYTES_PER_RISCV_VECTOR, mode));
+ else
+ {
+ emit_move_insn (gen_highpart (Pmode, tmp), CONST0_RTX (Pmode));
+ emit_move_insn (gen_lowpart (Pmode, tmp),
+ gen_int_mode (BYTES_PER_RISCV_VECTOR, Pmode));
+ }
if (BYTES_PER_RISCV_VECTOR.is_constant ())
{
return false;
}
- if (satisfies_constraint_vp (src))
+ if (satisfies_constraint_vp (src) && GET_MODE (src) == Pmode)
return false;
if (GET_MODE_SIZE (mode).to_constant () < GET_MODE_SIZE (Pmode))
(define_mode_iterator VEEWEXT2 [
(VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx64HI "TARGET_MIN_VLEN >= 128")
+ (VNx1HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN < 128") (VNx2HF "TARGET_VECTOR_ELEN_FP_16") (VNx4HF "TARGET_VECTOR_ELEN_FP_16")
+ (VNx8HF "TARGET_VECTOR_ELEN_FP_16") (VNx16HF "TARGET_VECTOR_ELEN_FP_16") (VNx32HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32")
+ (VNx64HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN >= 128")
(VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128")
(VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128") (VNx2DI "TARGET_VECTOR_ELEN_64")
(VNx4DI "TARGET_VECTOR_ELEN_64") (VNx8DI "TARGET_VECTOR_ELEN_64") (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128")
(define_mode_iterator VEEWTRUNC2 [
(VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI VNx32QI (VNx64QI "TARGET_MIN_VLEN >= 128")
(VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI VNx16HI (VNx32HI "TARGET_MIN_VLEN >= 128")
+ (VNx1HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN < 128") (VNx2HF "TARGET_VECTOR_ELEN_FP_16") (VNx4HF "TARGET_VECTOR_ELEN_FP_16")
+ (VNx8HF "TARGET_VECTOR_ELEN_FP_16") (VNx16HF "TARGET_VECTOR_ELEN_FP_16") (VNx32HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN >= 128")
(VNx1SI "TARGET_MIN_VLEN < 128") VNx2SI VNx4SI VNx8SI (VNx16SI "TARGET_MIN_VLEN >= 128")
(VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128")
(VNx2SF "TARGET_VECTOR_ELEN_FP_32")
(define_mode_iterator VEEWTRUNC4 [
(VNx1QI "TARGET_MIN_VLEN < 128") VNx2QI VNx4QI VNx8QI VNx16QI (VNx32QI "TARGET_MIN_VLEN >= 128")
(VNx1HI "TARGET_MIN_VLEN < 128") VNx2HI VNx4HI VNx8HI (VNx16HI "TARGET_MIN_VLEN >= 128")
+ (VNx1HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN < 128") (VNx2HF "TARGET_VECTOR_ELEN_FP_16") (VNx4HF "TARGET_VECTOR_ELEN_FP_16")
+ (VNx8HF "TARGET_VECTOR_ELEN_FP_16") (VNx16HF "TARGET_VECTOR_ELEN_FP_16")
])
(define_mode_iterator VEEWTRUNC8 [
])
(define_mode_iterator VNX1_QHSD [
- (VNx1QI "TARGET_MIN_VLEN < 128") (VNx1HI "TARGET_MIN_VLEN < 128") (VNx1SI "TARGET_MIN_VLEN < 128")
+ (VNx1QI "TARGET_MIN_VLEN < 128")
+ (VNx1HI "TARGET_MIN_VLEN < 128")
+ (VNx1SI "TARGET_MIN_VLEN < 128")
(VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128")
+ (VNx1HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN < 128")
(VNx1SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN < 128")
(VNx1DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN < 128")
])
(define_mode_iterator VNX2_QHSD [
- VNx2QI VNx2HI VNx2SI
+ VNx2QI
+ VNx2HI
+ VNx2SI
(VNx2DI "TARGET_VECTOR_ELEN_64")
+ (VNx2HF "TARGET_VECTOR_ELEN_FP_16")
(VNx2SF "TARGET_VECTOR_ELEN_FP_32")
(VNx2DF "TARGET_VECTOR_ELEN_FP_64")
])
(define_mode_iterator VNX4_QHSD [
- VNx4QI VNx4HI VNx4SI
+ VNx4QI
+ VNx4HI
+ VNx4SI
(VNx4DI "TARGET_VECTOR_ELEN_64")
+ (VNx4HF "TARGET_VECTOR_ELEN_FP_16")
(VNx4SF "TARGET_VECTOR_ELEN_FP_32")
(VNx4DF "TARGET_VECTOR_ELEN_FP_64")
])
(define_mode_iterator VNX8_QHSD [
- VNx8QI VNx8HI VNx8SI
+ VNx8QI
+ VNx8HI
+ VNx8SI
(VNx8DI "TARGET_VECTOR_ELEN_64")
+ (VNx8HF "TARGET_VECTOR_ELEN_FP_16")
(VNx8SF "TARGET_VECTOR_ELEN_FP_32")
(VNx8DF "TARGET_VECTOR_ELEN_FP_64")
])
-(define_mode_iterator VNX16_QHS [
- VNx16QI VNx16HI (VNx16SI "TARGET_MIN_VLEN > 32")
+(define_mode_iterator VNX16_QHSD [
+ VNx16QI
+ VNx16HI
+ (VNx16SI "TARGET_MIN_VLEN > 32")
+ (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128")
+ (VNx16HF "TARGET_VECTOR_ELEN_FP_16")
(VNx16SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32")
- (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128") (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128")
+ (VNx16DF "TARGET_VECTOR_ELEN_FP_64 && TARGET_MIN_VLEN >= 128")
])
(define_mode_iterator VNX32_QHS [
- VNx32QI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128") (VNx32SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128")
+ VNx32QI
+ (VNx32HI "TARGET_MIN_VLEN > 32")
+ (VNx32SI "TARGET_MIN_VLEN >= 128")
+ (VNx32HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32")
+ (VNx32SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN >= 128")
])
(define_mode_iterator VNX64_QH [
(VNx64QI "TARGET_MIN_VLEN > 32")
(VNx64HI "TARGET_MIN_VLEN >= 128")
+ (VNx64HF "TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN >= 128")
])
(define_mode_iterator VNX128_Q [
])
(define_mode_iterator VNX1_QHSDI [
- (VNx1QI "TARGET_MIN_VLEN < 128") (VNx1HI "TARGET_MIN_VLEN < 128") (VNx1SI "TARGET_MIN_VLEN < 128")
- (VNx1DI "TARGET_64BIT && TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128")
+ (VNx1QI "TARGET_MIN_VLEN < 128")
+ (VNx1HI "TARGET_MIN_VLEN < 128")
+ (VNx1SI "TARGET_MIN_VLEN < 128")
+ (VNx1DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN < 128 && TARGET_64BIT")
])
(define_mode_iterator VNX2_QHSDI [
- VNx2QI VNx2HI VNx2SI
- (VNx2DI "TARGET_64BIT && TARGET_VECTOR_ELEN_64")
+ VNx2QI
+ VNx2HI
+ VNx2SI
+ (VNx2DI "TARGET_VECTOR_ELEN_64 && TARGET_64BIT")
])
(define_mode_iterator VNX4_QHSDI [
- VNx4QI VNx4HI VNx4SI
- (VNx4DI "TARGET_64BIT && TARGET_VECTOR_ELEN_64")
+ VNx4QI
+ VNx4HI
+ VNx4SI
+ (VNx4DI "TARGET_VECTOR_ELEN_64 && TARGET_64BIT")
])
(define_mode_iterator VNX8_QHSDI [
- VNx8QI VNx8HI VNx8SI
- (VNx8DI "TARGET_64BIT && TARGET_VECTOR_ELEN_64")
+ VNx8QI
+ VNx8HI
+ VNx8SI
+ (VNx8DI "TARGET_VECTOR_ELEN_64 && TARGET_64BIT")
])
(define_mode_iterator VNX16_QHSDI [
- VNx16QI VNx16HI (VNx16SI "TARGET_MIN_VLEN > 32") (VNx16DI "TARGET_64BIT && TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128")
+ VNx16QI
+ VNx16HI
+ (VNx16SI "TARGET_MIN_VLEN > 32")
+ (VNx16DI "TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128 && TARGET_64BIT")
])
(define_mode_iterator VNX32_QHSI [
- VNx32QI (VNx32HI "TARGET_MIN_VLEN > 32") (VNx32SI "TARGET_MIN_VLEN >= 128")
+ VNx32QI
+ (VNx32HI "TARGET_MIN_VLEN > 32")
+ (VNx32SI "TARGET_MIN_VLEN >= 128")
])
(define_mode_iterator VNX64_QHI [
- VNx64QI (VNx64HI "TARGET_MIN_VLEN >= 128")
+ (VNx64QI "TARGET_MIN_VLEN > 32")
+ (VNx64HI "TARGET_MIN_VLEN >= 128")
])
(define_mode_iterator V_WHOLE [
(define_mode_attr VINDEX_DOUBLE_TRUNC [
(VNx1HI "VNx1QI") (VNx2HI "VNx2QI") (VNx4HI "VNx4QI") (VNx8HI "VNx8QI")
(VNx16HI "VNx16QI") (VNx32HI "VNx32QI") (VNx64HI "VNx64QI")
+ (VNx1HF "VNx1QI") (VNx2HF "VNx2QI") (VNx4HF "VNx4QI") (VNx8HF "VNx8QI")
+ (VNx16HF "VNx16QI") (VNx32HF "VNx32QI") (VNx64HF "VNx64QI")
(VNx1SI "VNx1HI") (VNx2SI "VNx2HI") (VNx4SI "VNx4HI") (VNx8SI "VNx8HI")
(VNx16SI "VNx16HI") (VNx32SI "VNx32HI")
(VNx1SF "VNx1HI") (VNx2SF "VNx2HI") (VNx4SF "VNx4HI") (VNx8SF "VNx8HI")
(define_mode_attr VINDEX_DOUBLE_EXT [
(VNx1QI "VNx1HI") (VNx2QI "VNx2HI") (VNx4QI "VNx4HI") (VNx8QI "VNx8HI") (VNx16QI "VNx16HI") (VNx32QI "VNx32HI") (VNx64QI "VNx64HI")
(VNx1HI "VNx1SI") (VNx2HI "VNx2SI") (VNx4HI "VNx4SI") (VNx8HI "VNx8SI") (VNx16HI "VNx16SI") (VNx32HI "VNx32SI")
+ (VNx1HF "VNx1SI") (VNx2HF "VNx2SI") (VNx4HF "VNx4SI") (VNx8HF "VNx8SI") (VNx16HF "VNx16SI") (VNx32HF "VNx32SI")
(VNx1SI "VNx1DI") (VNx2SI "VNx2DI") (VNx4SI "VNx4DI") (VNx8SI "VNx8DI") (VNx16SI "VNx16DI")
(VNx1SF "VNx1DI") (VNx2SF "VNx2DI") (VNx4SF "VNx4DI") (VNx8SF "VNx8DI") (VNx16SF "VNx16DI")
])
(define_mode_attr VINDEX_QUAD_EXT [
(VNx1QI "VNx1SI") (VNx2QI "VNx2SI") (VNx4QI "VNx4SI") (VNx8QI "VNx8SI") (VNx16QI "VNx16SI") (VNx32QI "VNx32SI")
(VNx1HI "VNx1DI") (VNx2HI "VNx2DI") (VNx4HI "VNx4DI") (VNx8HI "VNx8DI") (VNx16HI "VNx16DI")
+ (VNx1HF "VNx1DI") (VNx2HF "VNx2DI") (VNx4HF "VNx4DI") (VNx8HF "VNx8DI") (VNx16HF "VNx16DI")
])
(define_mode_attr VINDEX_OCT_EXT [
(VNx4DI "VNx8BI") (VNx8DI "VNx16BI") (VNx16DI "VNx32BI")
])
+(define_mode_attr gs_extension [
+ (VNx1QI "immediate_operand") (VNx2QI "immediate_operand") (VNx4QI "immediate_operand") (VNx8QI "immediate_operand") (VNx16QI "immediate_operand")
+ (VNx32QI "vector_gs_extension_operand") (VNx64QI "const_1_operand")
+ (VNx1HI "immediate_operand") (VNx2HI "immediate_operand") (VNx4HI "immediate_operand") (VNx8HI "immediate_operand") (VNx16HI "immediate_operand")
+ (VNx32HI "vector_gs_extension_operand") (VNx64HI "const_1_operand")
+ (VNx1SI "immediate_operand") (VNx2SI "immediate_operand") (VNx4SI "immediate_operand") (VNx8SI "immediate_operand") (VNx16SI "immediate_operand")
+ (VNx32SI "vector_gs_extension_operand")
+ (VNx1DI "immediate_operand") (VNx2DI "immediate_operand") (VNx4DI "immediate_operand") (VNx8DI "immediate_operand") (VNx16DI "immediate_operand")
+
+ (VNx1HF "immediate_operand") (VNx2HF "immediate_operand") (VNx4HF "immediate_operand") (VNx8HF "immediate_operand") (VNx16HF "immediate_operand")
+ (VNx32HF "vector_gs_extension_operand") (VNx64HF "const_1_operand")
+ (VNx1SF "immediate_operand") (VNx2SF "immediate_operand") (VNx4SF "immediate_operand") (VNx8SF "immediate_operand") (VNx16SF "immediate_operand")
+ (VNx32SF "vector_gs_extension_operand")
+ (VNx1DF "immediate_operand") (VNx2DF "immediate_operand") (VNx4DF "immediate_operand") (VNx8DF "immediate_operand") (VNx16DF "immediate_operand")
+])
+
+(define_mode_attr gs_scale [
+ (VNx1QI "const_1_operand") (VNx2QI "const_1_operand") (VNx4QI "const_1_operand") (VNx8QI "const_1_operand")
+ (VNx16QI "const_1_operand") (VNx32QI "const_1_operand") (VNx64QI "const_1_operand")
+ (VNx1HI "vector_gs_scale_operand_16") (VNx2HI "vector_gs_scale_operand_16") (VNx4HI "vector_gs_scale_operand_16") (VNx8HI "vector_gs_scale_operand_16")
+ (VNx16HI "vector_gs_scale_operand_16") (VNx32HI "vector_gs_scale_operand_16_rv32") (VNx64HI "const_1_operand")
+ (VNx1SI "vector_gs_scale_operand_32") (VNx2SI "vector_gs_scale_operand_32") (VNx4SI "vector_gs_scale_operand_32") (VNx8SI "vector_gs_scale_operand_32")
+ (VNx16SI "vector_gs_scale_operand_32") (VNx32SI "vector_gs_scale_operand_32_rv32")
+ (VNx1DI "vector_gs_scale_operand_64") (VNx2DI "vector_gs_scale_operand_64") (VNx4DI "vector_gs_scale_operand_64") (VNx8DI "vector_gs_scale_operand_64")
+ (VNx16DI "vector_gs_scale_operand_64")
+
+ (VNx1HF "vector_gs_scale_operand_16") (VNx2HF "vector_gs_scale_operand_16") (VNx4HF "vector_gs_scale_operand_16") (VNx8HF "vector_gs_scale_operand_16")
+ (VNx16HF "vector_gs_scale_operand_16") (VNx32HF "vector_gs_scale_operand_16_rv32") (VNx64HF "const_1_operand")
+ (VNx1SF "vector_gs_scale_operand_32") (VNx2SF "vector_gs_scale_operand_32") (VNx4SF "vector_gs_scale_operand_32") (VNx8SF "vector_gs_scale_operand_32")
+ (VNx16SF "vector_gs_scale_operand_32") (VNx32SF "vector_gs_scale_operand_32_rv32")
+ (VNx1DF "vector_gs_scale_operand_64") (VNx2DF "vector_gs_scale_operand_64") (VNx4DF "vector_gs_scale_operand_64") (VNx8DF "vector_gs_scale_operand_64")
+ (VNx16DF "vector_gs_scale_operand_64")
+])
+
(define_int_iterator WREDUC [UNSPEC_WREDUC_SUM UNSPEC_WREDUC_USUM])
(define_int_iterator ORDER [UNSPEC_ORDERED UNSPEC_UNORDERED])
;; This pattern only handles duplicates of non-constant inputs.
;; Constant vectors go through the movm pattern instead.
;; So "direct_broadcast_operand" can only be mem or reg, no CONSTANT.
-(define_expand "vec_duplicate<mode>"
+(define_expand "@vec_duplicate<mode>"
[(set (match_operand:V 0 "register_operand")
(vec_duplicate:V
(match_operand:<VEL> 1 "direct_broadcast_operand")))]
}
}
else if (GET_MODE_BITSIZE (<VEL>mode) > GET_MODE_BITSIZE (Pmode)
- && immediate_operand (operands[3], Pmode))
- operands[3] = gen_rtx_SIGN_EXTEND (<VEL>mode, force_reg (Pmode, operands[3]));
+ && (immediate_operand (operands[3], Pmode)
+ || (CONST_POLY_INT_P (operands[3])
+ && known_ge (rtx_to_poly_int64 (operands[3]), 0U)
+ && known_le (rtx_to_poly_int64 (operands[3]), GET_MODE_SIZE (<MODE>mode)))))
+ {
+ rtx tmp = gen_reg_rtx (Pmode);
+ poly_int64 value = rtx_to_poly_int64 (operands[3]);
+ emit_move_insn (tmp, gen_int_mode (value, Pmode));
+ operands[3] = gen_rtx_SIGN_EXTEND (<VEL>mode, tmp);
+ }
else
operands[3] = force_reg (<VEL>mode, operands[3]);
})
vlse<sew>.v\t%0,%3,zero
vmv.s.x\t%0,%3
vmv.s.x\t%0,%3"
- "register_operand (operands[3], <VEL>mode)
+ "(register_operand (operands[3], <VEL>mode)
+ || CONST_POLY_INT_P (operands[3]))
&& GET_MODE_BITSIZE (<VEL>mode) > GET_MODE_BITSIZE (Pmode)"
[(set (match_dup 0)
(if_then_else:VI (unspec:<VM> [(match_dup 1) (match_dup 4)
(match_dup 2)))]
{
gcc_assert (can_create_pseudo_p ());
+ if (CONST_POLY_INT_P (operands[3]))
+ {
+ rtx tmp = gen_reg_rtx (<VEL>mode);
+ emit_move_insn (tmp, operands[3]);
+ operands[3] = tmp;
+ }
rtx m = assign_stack_local (<VEL>mode, GET_MODE_SIZE (<VEL>mode),
GET_MODE_ALIGNMENT (<VEL>mode));
m = validize_mem (m);
(match_operand 5 "vector_length_operand" " rK, rK, rK")
(match_operand 6 "const_int_operand" " i, i, i")
(match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:V
[(set_attr "type" "vst<order>x")
(set_attr "mode" "<VNX8_QHSD:MODE>")])
-(define_insn "@pred_indexed_<order>store<VNX16_QHS:mode><VNX16_QHSDI:mode>"
+(define_insn "@pred_indexed_<order>store<VNX16_QHSD:mode><VNX16_QHSDI:mode>"
[(set (mem:BLK (scratch))
(unspec:BLK
[(unspec:<VM>
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operand 1 "pmode_reg_or_0_operand" " rJ")
(match_operand:VNX16_QHSDI 2 "register_operand" " vr")
- (match_operand:VNX16_QHS 3 "register_operand" " vr")] ORDER))]
+ (match_operand:VNX16_QHSD 3 "register_operand" " vr")] ORDER))]
"TARGET_VECTOR"
"vs<order>xei<VNX16_QHSDI:sew>.v\t%3,(%z1),%2%p0"
[(set_attr "type" "vst<order>x")
- (set_attr "mode" "<VNX16_QHS:MODE>")])
+ (set_attr "mode" "<VNX16_QHSD:MODE>")])
(define_insn "@pred_indexed_<order>store<VNX32_QHS:mode><VNX32_QHSI:mode>"
[(set (mem:BLK (scratch))
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 uint8_t
+#define INDEX16 uint16_t
+#define INDEX32 uint32_t
+#define INDEX64 uint64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX64 int64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 64) \
+ T (uint8_t, 64) \
+ T (int16_t, 64) \
+ T (uint16_t, 64) \
+ T (_Float16, 64) \
+ T (int32_t, 64) \
+ T (uint32_t, 64) \
+ T (float, 64) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_LOOP(DATA_TYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict *src) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += *src[i]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t) \
+ T (uint8_t) \
+ T (int16_t) \
+ T (uint16_t) \
+ T (_Float16) \
+ T (int32_t) \
+ T (uint32_t) \
+ T (float) \
+ T (int64_t) \
+ T (uint64_t) \
+ T (double)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-vect-cost-model -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_LOOP(DATA_TYPE, INDEX_TYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE##_##INDEX_TYPE (DATA_TYPE *restrict y, DATA_TYPE *restrict x, \
+ INDEX_TYPE *restrict index) \
+ { \
+ for (int i = 0; i < 100; ++i) \
+ { \
+ y[i * 2] = x[index[i * 2]] + 1; \
+ y[i * 2 + 1] = x[index[i * 2 + 1]] + 2; \
+ } \
+ }
+
+TEST_LOOP (int8_t, int8_t)
+TEST_LOOP (uint8_t, int8_t)
+TEST_LOOP (int16_t, int8_t)
+TEST_LOOP (uint16_t, int8_t)
+TEST_LOOP (int32_t, int8_t)
+TEST_LOOP (uint32_t, int8_t)
+TEST_LOOP (int64_t, int8_t)
+TEST_LOOP (uint64_t, int8_t)
+TEST_LOOP (_Float16, int8_t)
+TEST_LOOP (float, int8_t)
+TEST_LOOP (double, int8_t)
+TEST_LOOP (int8_t, int16_t)
+TEST_LOOP (uint8_t, int16_t)
+TEST_LOOP (int16_t, int16_t)
+TEST_LOOP (uint16_t, int16_t)
+TEST_LOOP (int32_t, int16_t)
+TEST_LOOP (uint32_t, int16_t)
+TEST_LOOP (int64_t, int16_t)
+TEST_LOOP (uint64_t, int16_t)
+TEST_LOOP (_Float16, int16_t)
+TEST_LOOP (float, int16_t)
+TEST_LOOP (double, int16_t)
+TEST_LOOP (int8_t, int32_t)
+TEST_LOOP (uint8_t, int32_t)
+TEST_LOOP (int16_t, int32_t)
+TEST_LOOP (uint16_t, int32_t)
+TEST_LOOP (int32_t, int32_t)
+TEST_LOOP (uint32_t, int32_t)
+TEST_LOOP (int64_t, int32_t)
+TEST_LOOP (uint64_t, int32_t)
+TEST_LOOP (_Float16, int32_t)
+TEST_LOOP (float, int32_t)
+TEST_LOOP (double, int32_t)
+TEST_LOOP (int8_t, int64_t)
+TEST_LOOP (uint8_t, int64_t)
+TEST_LOOP (int16_t, int64_t)
+TEST_LOOP (uint16_t, int64_t)
+TEST_LOOP (int32_t, int64_t)
+TEST_LOOP (uint32_t, int64_t)
+TEST_LOOP (int64_t, int64_t)
+TEST_LOOP (uint64_t, int64_t)
+TEST_LOOP (_Float16, int64_t)
+TEST_LOOP (float, int64_t)
+TEST_LOOP (double, int64_t)
+TEST_LOOP (int8_t, uint8_t)
+TEST_LOOP (uint8_t, uint8_t)
+TEST_LOOP (int16_t, uint8_t)
+TEST_LOOP (uint16_t, uint8_t)
+TEST_LOOP (int32_t, uint8_t)
+TEST_LOOP (uint32_t, uint8_t)
+TEST_LOOP (int64_t, uint8_t)
+TEST_LOOP (uint64_t, uint8_t)
+TEST_LOOP (_Float16, uint8_t)
+TEST_LOOP (float, uint8_t)
+TEST_LOOP (double, uint8_t)
+TEST_LOOP (int8_t, uint16_t)
+TEST_LOOP (uint8_t, uint16_t)
+TEST_LOOP (int16_t, uint16_t)
+TEST_LOOP (uint16_t, uint16_t)
+TEST_LOOP (int32_t, uint16_t)
+TEST_LOOP (uint32_t, uint16_t)
+TEST_LOOP (int64_t, uint16_t)
+TEST_LOOP (uint64_t, uint16_t)
+TEST_LOOP (_Float16, uint16_t)
+TEST_LOOP (float, uint16_t)
+TEST_LOOP (double, uint16_t)
+TEST_LOOP (int8_t, uint32_t)
+TEST_LOOP (uint8_t, uint32_t)
+TEST_LOOP (int16_t, uint32_t)
+TEST_LOOP (uint16_t, uint32_t)
+TEST_LOOP (int32_t, uint32_t)
+TEST_LOOP (uint32_t, uint32_t)
+TEST_LOOP (int64_t, uint32_t)
+TEST_LOOP (uint64_t, uint32_t)
+TEST_LOOP (_Float16, uint32_t)
+TEST_LOOP (float, uint32_t)
+TEST_LOOP (double, uint32_t)
+TEST_LOOP (int8_t, uint64_t)
+TEST_LOOP (uint8_t, uint64_t)
+TEST_LOOP (int16_t, uint64_t)
+TEST_LOOP (uint16_t, uint64_t)
+TEST_LOOP (int32_t, uint64_t)
+TEST_LOOP (uint32_t, uint64_t)
+TEST_LOOP (int64_t, uint64_t)
+TEST_LOOP (uint64_t, uint64_t)
+TEST_LOOP (_Float16, uint64_t)
+TEST_LOOP (float, uint64_t)
+TEST_LOOP (double, uint64_t)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 88 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-assembler-not "vluxei64\.v" } } */
+/* { dg-final { scan-assembler-not "vsuxei64\.v" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 int8_t
+#define INDEX16 int16_t
+#define INDEX32 int32_t
+#define INDEX64 int64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 uint8_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 8) \
+ T (uint16_t, 8) \
+ T (_Float16, 8) \
+ T (int32_t, 8) \
+ T (uint32_t, 8) \
+ T (float, 8) \
+ T (int64_t, 8) \
+ T (uint64_t, 8) \
+ T (double, 8)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 int8_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 8) \
+ T (uint16_t, 8) \
+ T (_Float16, 8) \
+ T (int32_t, 8) \
+ T (uint32_t, 8) \
+ T (float, 8) \
+ T (int64_t, 8) \
+ T (uint64_t, 8) \
+ T (double, 8)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX16 uint16_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 16) \
+ T (uint8_t, 16) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 16) \
+ T (uint32_t, 16) \
+ T (float, 16) \
+ T (int64_t, 16) \
+ T (uint64_t, 16) \
+ T (double, 16)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX16 int16_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 16) \
+ T (uint8_t, 16) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 16) \
+ T (uint32_t, 16) \
+ T (float, 16) \
+ T (int64_t, 16) \
+ T (uint64_t, 16) \
+ T (double, 16)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX32 uint32_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 32) \
+ T (uint8_t, 32) \
+ T (int16_t, 32) \
+ T (uint16_t, 32) \
+ T (_Float16, 32) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 32) \
+ T (uint64_t, 32) \
+ T (double, 32)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX32 int32_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 32) \
+ T (uint8_t, 32) \
+ T (int16_t, 32) \
+ T (uint16_t, 32) \
+ T (_Float16, 32) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 32) \
+ T (uint64_t, 32) \
+ T (double, 32)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX64 uint64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 64) \
+ T (uint8_t, 64) \
+ T (int16_t, 64) \
+ T (uint16_t, 64) \
+ T (_Float16, 64) \
+ T (int32_t, 64) \
+ T (uint32_t, 64) \
+ T (float, 64) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-1.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]));
+
+ RUN_LOOP (int8_t, 8)
+ RUN_LOOP (uint8_t, 8)
+ RUN_LOOP (int16_t, 16)
+ RUN_LOOP (uint16_t, 16)
+ RUN_LOOP (_Float16, 16)
+ RUN_LOOP (int32_t, 32)
+ RUN_LOOP (uint32_t, 32)
+ RUN_LOOP (float, 32)
+ RUN_LOOP (int64_t, 64)
+ RUN_LOOP (uint64_t, 64)
+ RUN_LOOP (double, 64)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-10.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]));
+
+ 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;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-11.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE *src_##DATA_TYPE[128]; \
+ DATA_TYPE src2_##DATA_TYPE[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = src2_##DATA_TYPE + i; \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] + src_##DATA_TYPE[i][0]));
+
+ RUN_LOOP (int8_t, 8)
+ RUN_LOOP (uint8_t, 8)
+ RUN_LOOP (int16_t, 16)
+ RUN_LOOP (uint16_t, 16)
+ RUN_LOOP (_Float16, 16)
+ RUN_LOOP (int32_t, 32)
+ RUN_LOOP (uint32_t, 32)
+ RUN_LOOP (float, 32)
+ RUN_LOOP (int64_t, 64)
+ RUN_LOOP (uint64_t, 64)
+ RUN_LOOP (double, 64)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-12.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, INDEX_TYPE) \
+ DATA_TYPE dest_##DATA_TYPE##_##INDEX_TYPE[202] = {0}; \
+ DATA_TYPE src_##DATA_TYPE##_##INDEX_TYPE[202] = {0}; \
+ INDEX_TYPE index_##DATA_TYPE##_##INDEX_TYPE[202] = {0}; \
+ for (int i = 0; i < 202; i++) \
+ { \
+ src_##DATA_TYPE##_##INDEX_TYPE[i] \
+ = (DATA_TYPE) ((i * 19 + 735) & (sizeof (DATA_TYPE) * 7 - 1)); \
+ index_##DATA_TYPE##_##INDEX_TYPE[i] = (i * 7) % (55); \
+ } \
+ f_##DATA_TYPE##_##INDEX_TYPE (dest_##DATA_TYPE##_##INDEX_TYPE, \
+ src_##DATA_TYPE##_##INDEX_TYPE, \
+ index_##DATA_TYPE##_##INDEX_TYPE); \
+ for (int i = 0; i < 100; i++) \
+ { \
+ assert (dest_##DATA_TYPE##_##INDEX_TYPE[i * 2] \
+ == (src_##DATA_TYPE##_##INDEX_TYPE \
+ [index_##DATA_TYPE##_##INDEX_TYPE[i * 2]] \
+ + 1)); \
+ assert (dest_##DATA_TYPE##_##INDEX_TYPE[i * 2 + 1] \
+ == (src_##DATA_TYPE##_##INDEX_TYPE \
+ [index_##DATA_TYPE##_##INDEX_TYPE[i * 2 + 1]] \
+ + 2)); \
+ }
+
+ RUN_LOOP (int8_t, int8_t)
+ RUN_LOOP (uint8_t, int8_t)
+ RUN_LOOP (int16_t, int8_t)
+ RUN_LOOP (uint16_t, int8_t)
+ RUN_LOOP (int32_t, int8_t)
+ RUN_LOOP (uint32_t, int8_t)
+ RUN_LOOP (int64_t, int8_t)
+ RUN_LOOP (uint64_t, int8_t)
+ RUN_LOOP (_Float16, int8_t)
+ RUN_LOOP (float, int8_t)
+ RUN_LOOP (double, int8_t)
+ RUN_LOOP (int8_t, int16_t)
+ RUN_LOOP (uint8_t, int16_t)
+ RUN_LOOP (int16_t, int16_t)
+ RUN_LOOP (uint16_t, int16_t)
+ RUN_LOOP (int32_t, int16_t)
+ RUN_LOOP (uint32_t, int16_t)
+ RUN_LOOP (int64_t, int16_t)
+ RUN_LOOP (uint64_t, int16_t)
+ RUN_LOOP (_Float16, int16_t)
+ RUN_LOOP (float, int16_t)
+ RUN_LOOP (double, int16_t)
+ RUN_LOOP (int8_t, int32_t)
+ RUN_LOOP (uint8_t, int32_t)
+ RUN_LOOP (int16_t, int32_t)
+ RUN_LOOP (uint16_t, int32_t)
+ RUN_LOOP (int32_t, int32_t)
+ RUN_LOOP (uint32_t, int32_t)
+ RUN_LOOP (int64_t, int32_t)
+ RUN_LOOP (uint64_t, int32_t)
+ RUN_LOOP (_Float16, int32_t)
+ RUN_LOOP (float, int32_t)
+ RUN_LOOP (double, int32_t)
+ RUN_LOOP (int8_t, int64_t)
+ RUN_LOOP (uint8_t, int64_t)
+ RUN_LOOP (int16_t, int64_t)
+ RUN_LOOP (uint16_t, int64_t)
+ RUN_LOOP (int32_t, int64_t)
+ RUN_LOOP (uint32_t, int64_t)
+ RUN_LOOP (int64_t, int64_t)
+ RUN_LOOP (uint64_t, int64_t)
+ RUN_LOOP (_Float16, int64_t)
+ RUN_LOOP (float, int64_t)
+ RUN_LOOP (double, int64_t)
+ RUN_LOOP (int8_t, uint8_t)
+ RUN_LOOP (uint8_t, uint8_t)
+ RUN_LOOP (int16_t, uint8_t)
+ RUN_LOOP (uint16_t, uint8_t)
+ RUN_LOOP (int32_t, uint8_t)
+ RUN_LOOP (uint32_t, uint8_t)
+ RUN_LOOP (int64_t, uint8_t)
+ RUN_LOOP (uint64_t, uint8_t)
+ RUN_LOOP (_Float16, uint8_t)
+ RUN_LOOP (float, uint8_t)
+ RUN_LOOP (double, uint8_t)
+ RUN_LOOP (int8_t, uint16_t)
+ RUN_LOOP (uint8_t, uint16_t)
+ RUN_LOOP (int16_t, uint16_t)
+ RUN_LOOP (uint16_t, uint16_t)
+ RUN_LOOP (int32_t, uint16_t)
+ RUN_LOOP (uint32_t, uint16_t)
+ RUN_LOOP (int64_t, uint16_t)
+ RUN_LOOP (uint64_t, uint16_t)
+ RUN_LOOP (_Float16, uint16_t)
+ RUN_LOOP (float, uint16_t)
+ RUN_LOOP (double, uint16_t)
+ RUN_LOOP (int8_t, uint32_t)
+ RUN_LOOP (uint8_t, uint32_t)
+ RUN_LOOP (int16_t, uint32_t)
+ RUN_LOOP (uint16_t, uint32_t)
+ RUN_LOOP (int32_t, uint32_t)
+ RUN_LOOP (uint32_t, uint32_t)
+ RUN_LOOP (int64_t, uint32_t)
+ RUN_LOOP (uint64_t, uint32_t)
+ RUN_LOOP (_Float16, uint32_t)
+ RUN_LOOP (float, uint32_t)
+ RUN_LOOP (double, uint32_t)
+ RUN_LOOP (int8_t, uint64_t)
+ RUN_LOOP (uint8_t, uint64_t)
+ RUN_LOOP (int16_t, uint64_t)
+ RUN_LOOP (uint16_t, uint64_t)
+ RUN_LOOP (int32_t, uint64_t)
+ RUN_LOOP (uint32_t, uint64_t)
+ RUN_LOOP (int64_t, uint64_t)
+ RUN_LOOP (uint64_t, uint64_t)
+ RUN_LOOP (_Float16, uint64_t)
+ RUN_LOOP (float, uint64_t)
+ RUN_LOOP (double, uint64_t)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-2.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]));
+
+ RUN_LOOP (int8_t, 8)
+ RUN_LOOP (uint8_t, 8)
+ RUN_LOOP (int16_t, 16)
+ RUN_LOOP (uint16_t, 16)
+ RUN_LOOP (_Float16, 16)
+ RUN_LOOP (int32_t, 32)
+ RUN_LOOP (uint32_t, 32)
+ RUN_LOOP (float, 32)
+ RUN_LOOP (int64_t, 64)
+ RUN_LOOP (uint64_t, 64)
+ RUN_LOOP (double, 64)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-3.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-4.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-5.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-6.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-7.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-8.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "gather_load-9.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]));
+
+ 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;
+}
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 uint8_t
+#define INDEX16 uint16_t
+#define INDEX32 uint32_t
+#define INDEX64 uint64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX64 int64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 64) \
+ T (uint8_t, 64) \
+ T (int16_t, 64) \
+ T (uint16_t, 64) \
+ T (_Float16, 64) \
+ T (int32_t, 64) \
+ T (uint32_t, 64) \
+ T (float, 64) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-vect-cost-model -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define TEST_LOOP(DATA_TYPE, INDEX_TYPE) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE##_##INDEX_TYPE (DATA_TYPE *restrict y, DATA_TYPE *restrict x, \
+ INDEX_TYPE *restrict index, \
+ INDEX_TYPE *restrict cond) \
+ { \
+ for (int i = 0; i < 100; ++i) \
+ { \
+ if (cond[i * 2]) \
+ y[i * 2] = x[index[i * 2]] + 1; \
+ if (cond[i * 2 + 1]) \
+ y[i * 2 + 1] = x[index[i * 2 + 1]] + 2; \
+ } \
+ }
+
+TEST_LOOP (int8_t, int8_t)
+TEST_LOOP (uint8_t, int8_t)
+TEST_LOOP (int16_t, int8_t)
+TEST_LOOP (uint16_t, int8_t)
+TEST_LOOP (int32_t, int8_t)
+TEST_LOOP (uint32_t, int8_t)
+TEST_LOOP (int64_t, int8_t)
+TEST_LOOP (uint64_t, int8_t)
+TEST_LOOP (_Float16, int8_t)
+TEST_LOOP (float, int8_t)
+TEST_LOOP (double, int8_t)
+TEST_LOOP (int8_t, int16_t)
+TEST_LOOP (uint8_t, int16_t)
+TEST_LOOP (int16_t, int16_t)
+TEST_LOOP (uint16_t, int16_t)
+TEST_LOOP (int32_t, int16_t)
+TEST_LOOP (uint32_t, int16_t)
+TEST_LOOP (int64_t, int16_t)
+TEST_LOOP (uint64_t, int16_t)
+TEST_LOOP (_Float16, int16_t)
+TEST_LOOP (float, int16_t)
+TEST_LOOP (double, int16_t)
+TEST_LOOP (int8_t, int32_t)
+TEST_LOOP (uint8_t, int32_t)
+TEST_LOOP (int16_t, int32_t)
+TEST_LOOP (uint16_t, int32_t)
+TEST_LOOP (int32_t, int32_t)
+TEST_LOOP (uint32_t, int32_t)
+TEST_LOOP (int64_t, int32_t)
+TEST_LOOP (uint64_t, int32_t)
+TEST_LOOP (_Float16, int32_t)
+TEST_LOOP (float, int32_t)
+TEST_LOOP (double, int32_t)
+TEST_LOOP (int8_t, int64_t)
+TEST_LOOP (uint8_t, int64_t)
+TEST_LOOP (int16_t, int64_t)
+TEST_LOOP (uint16_t, int64_t)
+TEST_LOOP (int32_t, int64_t)
+TEST_LOOP (uint32_t, int64_t)
+TEST_LOOP (int64_t, int64_t)
+TEST_LOOP (uint64_t, int64_t)
+TEST_LOOP (_Float16, int64_t)
+TEST_LOOP (float, int64_t)
+TEST_LOOP (double, int64_t)
+TEST_LOOP (int8_t, uint8_t)
+TEST_LOOP (uint8_t, uint8_t)
+TEST_LOOP (int16_t, uint8_t)
+TEST_LOOP (uint16_t, uint8_t)
+TEST_LOOP (int32_t, uint8_t)
+TEST_LOOP (uint32_t, uint8_t)
+TEST_LOOP (int64_t, uint8_t)
+TEST_LOOP (uint64_t, uint8_t)
+TEST_LOOP (_Float16, uint8_t)
+TEST_LOOP (float, uint8_t)
+TEST_LOOP (double, uint8_t)
+TEST_LOOP (int8_t, uint16_t)
+TEST_LOOP (uint8_t, uint16_t)
+TEST_LOOP (int16_t, uint16_t)
+TEST_LOOP (uint16_t, uint16_t)
+TEST_LOOP (int32_t, uint16_t)
+TEST_LOOP (uint32_t, uint16_t)
+TEST_LOOP (int64_t, uint16_t)
+TEST_LOOP (uint64_t, uint16_t)
+TEST_LOOP (_Float16, uint16_t)
+TEST_LOOP (float, uint16_t)
+TEST_LOOP (double, uint16_t)
+TEST_LOOP (int8_t, uint32_t)
+TEST_LOOP (uint8_t, uint32_t)
+TEST_LOOP (int16_t, uint32_t)
+TEST_LOOP (uint16_t, uint32_t)
+TEST_LOOP (int32_t, uint32_t)
+TEST_LOOP (uint32_t, uint32_t)
+TEST_LOOP (int64_t, uint32_t)
+TEST_LOOP (uint64_t, uint32_t)
+TEST_LOOP (_Float16, uint32_t)
+TEST_LOOP (float, uint32_t)
+TEST_LOOP (double, uint32_t)
+TEST_LOOP (int8_t, uint64_t)
+TEST_LOOP (uint8_t, uint64_t)
+TEST_LOOP (int16_t, uint64_t)
+TEST_LOOP (uint16_t, uint64_t)
+TEST_LOOP (int32_t, uint64_t)
+TEST_LOOP (uint32_t, uint64_t)
+TEST_LOOP (int64_t, uint64_t)
+TEST_LOOP (uint64_t, uint64_t)
+TEST_LOOP (_Float16, uint64_t)
+TEST_LOOP (float, uint64_t)
+TEST_LOOP (double, uint64_t)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 88 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-assembler-not "vluxei64\.v" } } */
+/* { dg-final { scan-assembler-not "vsuxei64\.v" } } */
+/* { dg-final { scan-assembler-not {vlse64\.v\s+v[0-9]+,\s*0\([a-x0-9]+\),\s*zero} } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 int8_t
+#define INDEX16 int16_t
+#define INDEX32 int32_t
+#define INDEX64 int64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 uint8_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 8) \
+ T (uint16_t, 8) \
+ T (_Float16, 8) \
+ T (int32_t, 8) \
+ T (uint32_t, 8) \
+ T (float, 8) \
+ T (int64_t, 8) \
+ T (uint64_t, 8) \
+ T (double, 8)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 int8_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 8) \
+ T (uint16_t, 8) \
+ T (_Float16, 8) \
+ T (int32_t, 8) \
+ T (uint32_t, 8) \
+ T (float, 8) \
+ T (int64_t, 8) \
+ T (uint64_t, 8) \
+ T (double, 8)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX16 uint16_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 16) \
+ T (uint8_t, 16) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 16) \
+ T (uint32_t, 16) \
+ T (float, 16) \
+ T (int64_t, 16) \
+ T (uint64_t, 16) \
+ T (double, 16)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX16 int16_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 16) \
+ T (uint8_t, 16) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 16) \
+ T (uint32_t, 16) \
+ T (float, 16) \
+ T (int64_t, 16) \
+ T (uint64_t, 16) \
+ T (double, 16)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX32 uint32_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 32) \
+ T (uint8_t, 32) \
+ T (int16_t, 32) \
+ T (uint16_t, 32) \
+ T (_Float16, 32) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 32) \
+ T (uint64_t, 32) \
+ T (double, 32)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX32 int32_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 32) \
+ T (uint8_t, 32) \
+ T (int16_t, 32) \
+ T (uint16_t, 32) \
+ T (_Float16, 32) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 32) \
+ T (uint64_t, 32) \
+ T (double, 32)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fno-schedule-insns -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX64 uint64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[i] += src[indices[i]]; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 64) \
+ T (uint8_t, 64) \
+ T (int16_t, 64) \
+ T (uint16_t, 64) \
+ T (_Float16, 64) \
+ T (int32_t, 64) \
+ T (uint32_t, 64) \
+ T (float, 64) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "vect" } } */
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_gather_load-1.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[i]); \
+ }
+
+ RUN_LOOP (int8_t, 8)
+ RUN_LOOP (uint8_t, 8)
+ RUN_LOOP (int16_t, 16)
+ RUN_LOOP (uint16_t, 16)
+ RUN_LOOP (_Float16, 16)
+ RUN_LOOP (int32_t, 32)
+ RUN_LOOP (uint32_t, 32)
+ RUN_LOOP (float, 32)
+ RUN_LOOP (int64_t, 64)
+ RUN_LOOP (uint64_t, 64)
+ RUN_LOOP (double, 64)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_gather_load-10.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[i]); \
+ }
+
+ 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;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-mcmodel=medany" } */
+
+#include "mask_gather_load-11.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, INDEX_TYPE) \
+ DATA_TYPE dest_##DATA_TYPE##_##INDEX_TYPE[202] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE##_##INDEX_TYPE[202] = {0}; \
+ DATA_TYPE src_##DATA_TYPE##_##INDEX_TYPE[202] = {0}; \
+ INDEX_TYPE index_##DATA_TYPE##_##INDEX_TYPE[202] = {0}; \
+ INDEX_TYPE cond_##DATA_TYPE##_##INDEX_TYPE[202] = {0}; \
+ for (int i = 0; i < 202; i++) \
+ { \
+ src_##DATA_TYPE##_##INDEX_TYPE[i] \
+ = (DATA_TYPE) ((i * 19 + 735) & (sizeof (DATA_TYPE) * 7 - 1)); \
+ dest_##DATA_TYPE##_##INDEX_TYPE[i] \
+ = (DATA_TYPE) ((i * 7 + 666) & (sizeof (DATA_TYPE) * 5 - 1)); \
+ dest2_##DATA_TYPE##_##INDEX_TYPE[i] \
+ = (DATA_TYPE) ((i * 7 + 666) & (sizeof (DATA_TYPE) * 5 - 1)); \
+ index_##DATA_TYPE##_##INDEX_TYPE[i] = (i * 7) % (55); \
+ cond_##DATA_TYPE##_##INDEX_TYPE[i] = (INDEX_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE##_##INDEX_TYPE (dest_##DATA_TYPE##_##INDEX_TYPE, \
+ src_##DATA_TYPE##_##INDEX_TYPE, \
+ index_##DATA_TYPE##_##INDEX_TYPE, \
+ cond_##DATA_TYPE##_##INDEX_TYPE); \
+ for (int i = 0; i < 100; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##INDEX_TYPE[i * 2]) \
+ assert (dest_##DATA_TYPE##_##INDEX_TYPE[i * 2] \
+ == (src_##DATA_TYPE##_##INDEX_TYPE \
+ [index_##DATA_TYPE##_##INDEX_TYPE[i * 2]] \
+ + 1)); \
+ else \
+ assert (dest_##DATA_TYPE##_##INDEX_TYPE[i * 2] \
+ == dest2_##DATA_TYPE##_##INDEX_TYPE[i * 2]); \
+ if (cond_##DATA_TYPE##_##INDEX_TYPE[i * 2 + 1]) \
+ assert (dest_##DATA_TYPE##_##INDEX_TYPE[i * 2 + 1] \
+ == (src_##DATA_TYPE##_##INDEX_TYPE \
+ [index_##DATA_TYPE##_##INDEX_TYPE[i * 2 + 1]] \
+ + 2)); \
+ else \
+ assert (dest_##DATA_TYPE##_##INDEX_TYPE[i * 2 + 1] \
+ == dest2_##DATA_TYPE##_##INDEX_TYPE[i * 2 + 1]); \
+ }
+
+ RUN_LOOP (int8_t, int8_t)
+ RUN_LOOP (uint8_t, int8_t)
+ RUN_LOOP (int16_t, int8_t)
+ RUN_LOOP (uint16_t, int8_t)
+ RUN_LOOP (int32_t, int8_t)
+ RUN_LOOP (uint32_t, int8_t)
+ RUN_LOOP (int64_t, int8_t)
+ RUN_LOOP (uint64_t, int8_t)
+ RUN_LOOP (_Float16, int8_t)
+ RUN_LOOP (float, int8_t)
+ RUN_LOOP (double, int8_t)
+ RUN_LOOP (int8_t, int16_t)
+ RUN_LOOP (uint8_t, int16_t)
+ RUN_LOOP (int16_t, int16_t)
+ RUN_LOOP (uint16_t, int16_t)
+ RUN_LOOP (int32_t, int16_t)
+ RUN_LOOP (uint32_t, int16_t)
+ RUN_LOOP (int64_t, int16_t)
+ RUN_LOOP (uint64_t, int16_t)
+ RUN_LOOP (_Float16, int16_t)
+ RUN_LOOP (float, int16_t)
+ RUN_LOOP (double, int16_t)
+ RUN_LOOP (int8_t, int32_t)
+ RUN_LOOP (uint8_t, int32_t)
+ RUN_LOOP (int16_t, int32_t)
+ RUN_LOOP (uint16_t, int32_t)
+ RUN_LOOP (int32_t, int32_t)
+ RUN_LOOP (uint32_t, int32_t)
+ RUN_LOOP (int64_t, int32_t)
+ RUN_LOOP (uint64_t, int32_t)
+ RUN_LOOP (_Float16, int32_t)
+ RUN_LOOP (float, int32_t)
+ RUN_LOOP (double, int32_t)
+ RUN_LOOP (int8_t, int64_t)
+ RUN_LOOP (uint8_t, int64_t)
+ RUN_LOOP (int16_t, int64_t)
+ RUN_LOOP (uint16_t, int64_t)
+ RUN_LOOP (int32_t, int64_t)
+ RUN_LOOP (uint32_t, int64_t)
+ RUN_LOOP (int64_t, int64_t)
+ RUN_LOOP (uint64_t, int64_t)
+ RUN_LOOP (_Float16, int64_t)
+ RUN_LOOP (float, int64_t)
+ RUN_LOOP (double, int64_t)
+ RUN_LOOP (int8_t, uint8_t)
+ RUN_LOOP (uint8_t, uint8_t)
+ RUN_LOOP (int16_t, uint8_t)
+ RUN_LOOP (uint16_t, uint8_t)
+ RUN_LOOP (int32_t, uint8_t)
+ RUN_LOOP (uint32_t, uint8_t)
+ RUN_LOOP (int64_t, uint8_t)
+ RUN_LOOP (uint64_t, uint8_t)
+ RUN_LOOP (_Float16, uint8_t)
+ RUN_LOOP (float, uint8_t)
+ RUN_LOOP (double, uint8_t)
+ RUN_LOOP (int8_t, uint16_t)
+ RUN_LOOP (uint8_t, uint16_t)
+ RUN_LOOP (int16_t, uint16_t)
+ RUN_LOOP (uint16_t, uint16_t)
+ RUN_LOOP (int32_t, uint16_t)
+ RUN_LOOP (uint32_t, uint16_t)
+ RUN_LOOP (int64_t, uint16_t)
+ RUN_LOOP (uint64_t, uint16_t)
+ RUN_LOOP (_Float16, uint16_t)
+ RUN_LOOP (float, uint16_t)
+ RUN_LOOP (double, uint16_t)
+ RUN_LOOP (int8_t, uint32_t)
+ RUN_LOOP (uint8_t, uint32_t)
+ RUN_LOOP (int16_t, uint32_t)
+ RUN_LOOP (uint16_t, uint32_t)
+ RUN_LOOP (int32_t, uint32_t)
+ RUN_LOOP (uint32_t, uint32_t)
+ RUN_LOOP (int64_t, uint32_t)
+ RUN_LOOP (uint64_t, uint32_t)
+ RUN_LOOP (_Float16, uint32_t)
+ RUN_LOOP (float, uint32_t)
+ RUN_LOOP (double, uint32_t)
+ RUN_LOOP (int8_t, uint64_t)
+ RUN_LOOP (uint8_t, uint64_t)
+ RUN_LOOP (int16_t, uint64_t)
+ RUN_LOOP (uint16_t, uint64_t)
+ RUN_LOOP (int32_t, uint64_t)
+ RUN_LOOP (uint32_t, uint64_t)
+ RUN_LOOP (int64_t, uint64_t)
+ RUN_LOOP (uint64_t, uint64_t)
+ RUN_LOOP (_Float16, uint64_t)
+ RUN_LOOP (float, uint64_t)
+ RUN_LOOP (double, uint64_t)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_gather_load-2.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[i]); \
+ }
+
+ RUN_LOOP (int8_t, 8)
+ RUN_LOOP (uint8_t, 8)
+ RUN_LOOP (int16_t, 16)
+ RUN_LOOP (uint16_t, 16)
+ RUN_LOOP (_Float16, 16)
+ RUN_LOOP (int32_t, 32)
+ RUN_LOOP (uint32_t, 32)
+ RUN_LOOP (float, 32)
+ RUN_LOOP (int64_t, 64)
+ RUN_LOOP (uint64_t, 64)
+ RUN_LOOP (double, 64)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_gather_load-3.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_gather_load-4.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_gather_load-5.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[i]); \
+ }
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_gather_load-6.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[i]); \
+ }
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-mcmodel=medany" } */
+
+#include "mask_gather_load-7.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[i]); \
+ }
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-mcmodel=medany" } */
+
+#include "mask_gather_load-8.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[i]); \
+ }
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_gather_load-9.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE dest2_##DATA_TYPE[128] = {0}; \
+ DATA_TYPE src_##DATA_TYPE[128] = {0}; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128] = {0}; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[i] \
+ == (dest2_##DATA_TYPE[i] \
+ + src_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]])); \
+ else \
+ assert (dest_##DATA_TYPE[i] == dest2_##DATA_TYPE[i]); \
+ }
+
+ 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;
+}
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 uint8_t
+#define INDEX16 uint16_t
+#define INDEX32 uint32_t
+#define INDEX64 uint64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX64 int64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 64) \
+ T (uint8_t, 64) \
+ T (int16_t, 64) \
+ T (uint16_t, 64) \
+ T (_Float16, 64) \
+ T (int32_t, 64) \
+ T (uint32_t, 64) \
+ T (float, 64) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 int8_t
+#define INDEX16 int16_t
+#define INDEX32 int32_t
+#define INDEX64 int64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 uint8_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 8) \
+ T (uint16_t, 8) \
+ T (_Float16, 8) \
+ T (int32_t, 8) \
+ T (uint32_t, 8) \
+ T (float, 8) \
+ T (int64_t, 8) \
+ T (uint64_t, 8) \
+ T (double, 8)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 int8_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 8) \
+ T (uint16_t, 8) \
+ T (_Float16, 8) \
+ T (int32_t, 8) \
+ T (uint32_t, 8) \
+ T (float, 8) \
+ T (int64_t, 8) \
+ T (uint64_t, 8) \
+ T (double, 8)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX16 uint16_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 16) \
+ T (uint8_t, 16) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 16) \
+ T (uint32_t, 16) \
+ T (float, 16) \
+ T (int64_t, 16) \
+ T (uint64_t, 16) \
+ T (double, 16)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX16 int16_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 16) \
+ T (uint8_t, 16) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 16) \
+ T (uint32_t, 16) \
+ T (float, 16) \
+ T (int64_t, 16) \
+ T (uint64_t, 16) \
+ T (double, 16)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX32 uint32_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 32) \
+ T (uint8_t, 32) \
+ T (int16_t, 32) \
+ T (uint16_t, 32) \
+ T (_Float16, 32) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 32) \
+ T (uint64_t, 32) \
+ T (double, 32)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX32 int32_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 32) \
+ T (uint8_t, 32) \
+ T (int16_t, 32) \
+ T (uint16_t, 32) \
+ T (_Float16, 32) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 32) \
+ T (uint64_t, 32) \
+ T (double, 32)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX64 uint64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices, INDEX##BITS *restrict cond) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ if (cond[i]) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 64) \
+ T (uint8_t, 64) \
+ T (int16_t, 64) \
+ T (uint16_t, 64) \
+ T (_Float16, 64) \
+ T (int32_t, 64) \
+ T (uint32_t, 64) \
+ T (float, 64) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_scatter_store-1.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]); \
+ }
+
+ RUN_LOOP (int8_t, 8)
+ RUN_LOOP (uint8_t, 8)
+ RUN_LOOP (int16_t, 16)
+ RUN_LOOP (uint16_t, 16)
+ RUN_LOOP (_Float16, 16)
+ RUN_LOOP (int32_t, 32)
+ RUN_LOOP (uint32_t, 32)
+ RUN_LOOP (float, 32)
+ RUN_LOOP (int64_t, 64)
+ RUN_LOOP (uint64_t, 64)
+ RUN_LOOP (double, 64)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_scatter_store-10.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]); \
+ }
+
+ 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;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_scatter_store-2.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]); \
+ }
+
+ RUN_LOOP (int8_t, 8)
+ RUN_LOOP (uint8_t, 8)
+ RUN_LOOP (int16_t, 16)
+ RUN_LOOP (uint16_t, 16)
+ RUN_LOOP (_Float16, 16)
+ RUN_LOOP (int32_t, 32)
+ RUN_LOOP (uint32_t, 32)
+ RUN_LOOP (float, 32)
+ RUN_LOOP (int64_t, 64)
+ RUN_LOOP (uint64_t, 64)
+ RUN_LOOP (double, 64)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_scatter_store-3.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_scatter_store-4.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_scatter_store-5.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]); \
+ }
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_scatter_store-6.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]); \
+ }
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-mcmodel=medany" } */
+
+#include "mask_scatter_store-7.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]); \
+ }
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_scatter_store-8.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]); \
+ }
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "mask_scatter_store-9.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ INDEX##BITS cond_##DATA_TYPE##_##BITS[128] = {0}; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ cond_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i & 0x3) == 3); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS, cond_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ { \
+ if (cond_##DATA_TYPE##_##BITS[i]) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1)); \
+ else \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == dest2_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]]); \
+ }
+
+ 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;
+}
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 uint8_t
+#define INDEX16 uint16_t
+#define INDEX32 uint32_t
+#define INDEX64 uint64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX64 int64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 64) \
+ T (uint8_t, 64) \
+ T (int16_t, 64) \
+ T (uint16_t, 64) \
+ T (_Float16, 64) \
+ T (int32_t, 64) \
+ T (uint32_t, 64) \
+ T (float, 64) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 int8_t
+#define INDEX16 int16_t
+#define INDEX32 int32_t
+#define INDEX64 int64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 uint8_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 8) \
+ T (uint16_t, 8) \
+ T (_Float16, 8) \
+ T (int32_t, 8) \
+ T (uint32_t, 8) \
+ T (float, 8) \
+ T (int64_t, 8) \
+ T (uint64_t, 8) \
+ T (double, 8)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX8 int8_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 8) \
+ T (uint8_t, 8) \
+ T (int16_t, 8) \
+ T (uint16_t, 8) \
+ T (_Float16, 8) \
+ T (int32_t, 8) \
+ T (uint32_t, 8) \
+ T (float, 8) \
+ T (int64_t, 8) \
+ T (uint64_t, 8) \
+ T (double, 8)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX16 uint16_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 16) \
+ T (uint8_t, 16) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 16) \
+ T (uint32_t, 16) \
+ T (float, 16) \
+ T (int64_t, 16) \
+ T (uint64_t, 16) \
+ T (double, 16)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX16 int16_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 16) \
+ T (uint8_t, 16) \
+ T (int16_t, 16) \
+ T (uint16_t, 16) \
+ T (_Float16, 16) \
+ T (int32_t, 16) \
+ T (uint32_t, 16) \
+ T (float, 16) \
+ T (int64_t, 16) \
+ T (uint64_t, 16) \
+ T (double, 16)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX32 uint32_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 32) \
+ T (uint8_t, 32) \
+ T (int16_t, 32) \
+ T (uint16_t, 32) \
+ T (_Float16, 32) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 32) \
+ T (uint64_t, 32) \
+ T (double, 32)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX32 int32_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 32) \
+ T (uint8_t, 32) \
+ T (int16_t, 32) \
+ T (uint16_t, 32) \
+ T (_Float16, 32) \
+ T (int32_t, 32) \
+ T (uint32_t, 32) \
+ T (float, 32) \
+ T (int64_t, 32) \
+ T (uint64_t, 32) \
+ T (double, 32)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv_zvfh -mabi=ilp32d -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+#define INDEX64 uint64_t
+
+#define TEST_LOOP(DATA_TYPE, BITS) \
+ void __attribute__ ((noinline, noclone)) \
+ f_##DATA_TYPE (DATA_TYPE *restrict dest, DATA_TYPE *restrict src, \
+ INDEX##BITS *restrict indices) \
+ { \
+ for (int i = 0; i < 128; ++i) \
+ dest[indices[i]] = src[i] + 1; \
+ }
+
+#define TEST_ALL(T) \
+ T (int8_t, 64) \
+ T (uint8_t, 64) \
+ T (int16_t, 64) \
+ T (uint16_t, 64) \
+ T (_Float16, 64) \
+ T (int32_t, 64) \
+ T (uint32_t, 64) \
+ T (float, 64) \
+ T (int64_t, 64) \
+ T (uint64_t, 64) \
+ T (double, 64)
+
+TEST_ALL (TEST_LOOP)
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 11 "vect" } } */
+/* { dg-final { scan-tree-dump " \.LEN_MASK_SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "vect" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "vect" } } */
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "scatter_store-1.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ RUN_LOOP (int8_t, 8)
+ RUN_LOOP (uint8_t, 8)
+ RUN_LOOP (int16_t, 16)
+ RUN_LOOP (uint16_t, 16)
+ RUN_LOOP (_Float16, 16)
+ RUN_LOOP (int32_t, 32)
+ RUN_LOOP (uint32_t, 32)
+ RUN_LOOP (float, 32)
+ RUN_LOOP (int64_t, 64)
+ RUN_LOOP (uint64_t, 64)
+ RUN_LOOP (double, 64)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "scatter_store-10.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ 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;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-mcmodel=medany" } */
+
+#include "scatter_store-2.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ RUN_LOOP (int8_t, 8)
+ RUN_LOOP (uint8_t, 8)
+ RUN_LOOP (int16_t, 16)
+ RUN_LOOP (uint16_t, 16)
+ RUN_LOOP (_Float16, 16)
+ RUN_LOOP (int32_t, 32)
+ RUN_LOOP (uint32_t, 32)
+ RUN_LOOP (float, 32)
+ RUN_LOOP (int64_t, 64)
+ RUN_LOOP (uint64_t, 64)
+ RUN_LOOP (double, 64)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "scatter_store-3.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "scatter_store-4.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "scatter_store-5.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "scatter_store-6.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "scatter_store-7.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+
+#include "scatter_store-8.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ 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)
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-mcmodel=medany" } */
+
+#include "scatter_store-9.c"
+#include <assert.h>
+
+int
+main (void)
+{
+#define RUN_LOOP(DATA_TYPE, BITS) \
+ DATA_TYPE dest_##DATA_TYPE[128]; \
+ DATA_TYPE dest2_##DATA_TYPE[128]; \
+ DATA_TYPE src_##DATA_TYPE[128]; \
+ INDEX##BITS indices_##DATA_TYPE##_##BITS[128]; \
+ for (int i = 0; i < 128; i++) \
+ { \
+ dest_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ dest2_##DATA_TYPE[i] = (DATA_TYPE) ((i * 81 + 735) & (BITS - 1)); \
+ src_##DATA_TYPE[i] = (DATA_TYPE) ((i * 13 + 9107) & (BITS - 1)); \
+ indices_##DATA_TYPE##_##BITS[i] = (DATA_TYPE) ((i * 3 + 67) % 128); \
+ } \
+ f_##DATA_TYPE (dest_##DATA_TYPE, src_##DATA_TYPE, \
+ indices_##DATA_TYPE##_##BITS); \
+ for (int i = 0; i < 128; i++) \
+ assert (dest_##DATA_TYPE[indices_##DATA_TYPE##_##BITS[i]] \
+ == (src_##DATA_TYPE[i] + 1));
+
+ 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;
+}
--- /dev/null
+/* { 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, 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 " \.LEN_MASK_GATHER_LOAD" 66 "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "optimized" } } */
--- /dev/null
+/* { 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, INDEX##BITS n) \
+ { \
+ for (INDEX##BITS i = 0; i < (BITS + 13); ++i) \
+ dest[i] += src[i * (BITS - 3)]; \
+ }
+
+#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 " \.LEN_MASK_GATHER_LOAD" 46 "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.GATHER_LOAD" "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_GATHER_LOAD" "optimized" } } */
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+#include "strided_load-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)]; \
+ 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;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+#include "strided_load-2.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;
+}
--- /dev/null
+/* { 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, 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 " \.LEN_MASK_SCATTER_STORE" 66 "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "optimized" } } */
--- /dev/null
+/* { 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, INDEX##BITS n) \
+ { \
+ for (INDEX##BITS i = 0; i < n; ++i) \
+ dest[i * (BITS - 3)] = 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 " \.LEN_MASK_SCATTER_STORE" 44 "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.SCATTER_STORE" "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \.MASK_SCATTER_STORE" "optimized" } } */
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+#include "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)]; \
+ 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;
+}
--- /dev/null
+/* { dg-do run { target { riscv_vector } } } */
+
+#include "strided_store-2.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;
+}
dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/autovec/vls-vlmax/*.\[cS\]]] \
"-std=c99 -O3 -ftree-vectorize --param riscv-autovec-preference=fixed-vlmax" $CFLAGS
+# gather-scatter tests
+set AUTOVEC_TEST_OPTS [list \
+ {-ftree-vectorize -O3 --param riscv-autovec-preference=fixed-vlmax --param riscv-autovec-lmul=m1 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O3 --param riscv-autovec-preference=fixed-vlmax --param riscv-autovec-lmul=m2 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O3 --param riscv-autovec-preference=fixed-vlmax --param riscv-autovec-lmul=m4 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O3 --param riscv-autovec-preference=fixed-vlmax --param riscv-autovec-lmul=m8 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O2 --param riscv-autovec-preference=fixed-vlmax --param riscv-autovec-lmul=m1 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O2 --param riscv-autovec-preference=fixed-vlmax --param riscv-autovec-lmul=m2 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O2 --param riscv-autovec-preference=fixed-vlmax --param riscv-autovec-lmul=m4 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O2 --param riscv-autovec-preference=fixed-vlmax --param riscv-autovec-lmul=m8 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O3 --param riscv-autovec-preference=scalable --param riscv-autovec-lmul=m1 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O3 --param riscv-autovec-preference=scalable --param riscv-autovec-lmul=m2 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O3 --param riscv-autovec-preference=scalable --param riscv-autovec-lmul=m4 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O3 --param riscv-autovec-preference=scalable --param riscv-autovec-lmul=m8 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O2 --param riscv-autovec-preference=scalable --param riscv-autovec-lmul=m1 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O2 --param riscv-autovec-preference=scalable --param riscv-autovec-lmul=m2 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O2 --param riscv-autovec-preference=scalable --param riscv-autovec-lmul=m4 -fno-vect-cost-model -ffast-math} \
+ {-ftree-vectorize -O2 --param riscv-autovec-preference=scalable --param riscv-autovec-lmul=m8 -fno-vect-cost-model -ffast-math} ]
+foreach op $AUTOVEC_TEST_OPTS {
+ dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/autovec/gather-scatter/*.\[cS\]]] \
+ "" "$op"
+}
+
# All done.
dg-finish