@@ -1565,30 +1565,10 @@ public:
rtx expand (function_expander &e) const override
{
- e.add_input_operand (0);
- switch (e.op_info->ret.base_type)
- {
- case RVV_BASE_vlmul_ext_x2:
- return e.generate_insn (
- code_for_vlmul_extx2 (e.vector_mode ()));
- case RVV_BASE_vlmul_ext_x4:
- return e.generate_insn (
- code_for_vlmul_extx4 (e.vector_mode ()));
- case RVV_BASE_vlmul_ext_x8:
- return e.generate_insn (
- code_for_vlmul_extx8 (e.vector_mode ()));
- case RVV_BASE_vlmul_ext_x16:
- return e.generate_insn (
- code_for_vlmul_extx16 (e.vector_mode ()));
- case RVV_BASE_vlmul_ext_x32:
- return e.generate_insn (
- code_for_vlmul_extx32 (e.vector_mode ()));
- case RVV_BASE_vlmul_ext_x64:
- return e.generate_insn (
- code_for_vlmul_extx64 (e.vector_mode ()));
- default:
- gcc_unreachable ();
- }
+ tree arg = CALL_EXPR_ARG (e.exp, 0);
+ rtx src = expand_normal (arg);
+ emit_insn (gen_rtx_SET (gen_lowpart (e.vector_mode (), e.target), src));
+ return e.target;
}
};
@@ -498,126 +498,6 @@
}
)
-(define_expand "@vlmul_extx2<mode>"
- [(set (match_operand:<VLMULX2> 0 "register_operand")
- (subreg:<VLMULX2>
- (match_operand:VLMULEXT2 1 "register_operand") 0))]
- "TARGET_VECTOR"
-{})
-
-(define_expand "@vlmul_extx4<mode>"
- [(set (match_operand:<VLMULX4> 0 "register_operand")
- (subreg:<VLMULX4>
- (match_operand:VLMULEXT4 1 "register_operand") 0))]
- "TARGET_VECTOR"
-{})
-
-(define_expand "@vlmul_extx8<mode>"
- [(set (match_operand:<VLMULX8> 0 "register_operand")
- (subreg:<VLMULX8>
- (match_operand:VLMULEXT8 1 "register_operand") 0))]
- "TARGET_VECTOR"
-{})
-
-(define_expand "@vlmul_extx16<mode>"
- [(set (match_operand:<VLMULX16> 0 "register_operand")
- (subreg:<VLMULX16>
- (match_operand:VLMULEXT16 1 "register_operand") 0))]
- "TARGET_VECTOR"
-{})
-
-(define_expand "@vlmul_extx32<mode>"
- [(set (match_operand:<VLMULX32> 0 "register_operand")
- (subreg:<VLMULX32>
- (match_operand:VLMULEXT32 1 "register_operand") 0))]
- "TARGET_VECTOR"
-{})
-
-(define_expand "@vlmul_extx64<mode>"
- [(set (match_operand:<VLMULX64> 0 "register_operand")
- (subreg:<VLMULX64>
- (match_operand:VLMULEXT64 1 "register_operand") 0))]
- "TARGET_VECTOR"
-{})
-
-(define_insn_and_split "*vlmul_extx2<mode>"
- [(set (match_operand:<VLMULX2> 0 "register_operand" "=vr, ?&vr")
- (subreg:<VLMULX2>
- (match_operand:VLMULEXT2 1 "register_operand" " 0, vr") 0))]
- "TARGET_VECTOR"
- "#"
- "&& reload_completed"
- [(const_int 0)]
-{
- emit_insn (gen_rtx_SET (gen_lowpart (<MODE>mode, operands[0]), operands[1]));
- DONE;
-})
-
-(define_insn_and_split "*vlmul_extx4<mode>"
- [(set (match_operand:<VLMULX4> 0 "register_operand" "=vr, ?&vr")
- (subreg:<VLMULX4>
- (match_operand:VLMULEXT4 1 "register_operand" " 0, vr") 0))]
- "TARGET_VECTOR"
- "#"
- "&& reload_completed"
- [(const_int 0)]
-{
- emit_insn (gen_rtx_SET (gen_lowpart (<MODE>mode, operands[0]), operands[1]));
- DONE;
-})
-
-(define_insn_and_split "*vlmul_extx8<mode>"
- [(set (match_operand:<VLMULX8> 0 "register_operand" "=vr, ?&vr")
- (subreg:<VLMULX8>
- (match_operand:VLMULEXT8 1 "register_operand" " 0, vr") 0))]
- "TARGET_VECTOR"
- "#"
- "&& reload_completed"
- [(const_int 0)]
-{
- emit_insn (gen_rtx_SET (gen_lowpart (<MODE>mode, operands[0]), operands[1]));
- DONE;
-})
-
-(define_insn_and_split "*vlmul_extx16<mode>"
- [(set (match_operand:<VLMULX16> 0 "register_operand" "=vr, ?&vr")
- (subreg:<VLMULX16>
- (match_operand:VLMULEXT16 1 "register_operand" " 0, vr") 0))]
- "TARGET_VECTOR"
- "#"
- "&& reload_completed"
- [(const_int 0)]
-{
- emit_insn (gen_rtx_SET (gen_lowpart (<MODE>mode, operands[0]), operands[1]));
- DONE;
-})
-
-(define_insn_and_split "*vlmul_extx32<mode>"
- [(set (match_operand:<VLMULX32> 0 "register_operand" "=vr, ?&vr")
- (subreg:<VLMULX32>
- (match_operand:VLMULEXT32 1 "register_operand" " 0, vr") 0))]
- "TARGET_VECTOR"
- "#"
- "&& reload_completed"
- [(const_int 0)]
-{
- emit_insn (gen_rtx_SET (gen_lowpart (<MODE>mode, operands[0]), operands[1]));
- DONE;
-})
-
-(define_insn_and_split "*vlmul_extx64<mode>"
- [(set (match_operand:<VLMULX64> 0 "register_operand" "=vr, ?&vr")
- (subreg:<VLMULX64>
- (match_operand:VLMULEXT64 1 "register_operand" " 0, vr") 0))]
- "TARGET_VECTOR"
- "#"
- "&& reload_completed"
- [(const_int 0)]
-{
- emit_insn (gen_rtx_SET (gen_lowpart (<MODE>mode, operands[0]), operands[1]));
- DONE;
-})
-
;; This pattern is used to hold the AVL operand for
;; RVV instructions that implicity use VLMAX AVL.
;; RVV instruction implicitly use GPR that is ultimately
new file mode 100644
@@ -0,0 +1,40 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv32gcv -mabi=ilp32d" } */
+
+#include "riscv_vector.h"
+
+void __attribute__ ((noinline, noclone))
+clean_subreg (int32_t *in, int32_t *out, size_t m)
+{
+ vint16m8_t v24, v8, v16;
+ vint32m8_t result = __riscv_vle32_v_i32m8 (in, 32);
+ vint32m1_t v0 = __riscv_vget_v_i32m8_i32m1 (result, 0);
+ vint32m1_t v1 = __riscv_vget_v_i32m8_i32m1 (result, 1);
+ vint32m1_t v2 = __riscv_vget_v_i32m8_i32m1 (result, 2);
+ vint32m1_t v3 = __riscv_vget_v_i32m8_i32m1 (result, 3);
+ vint32m1_t v4 = __riscv_vget_v_i32m8_i32m1 (result, 4);
+ vint32m1_t v5 = __riscv_vget_v_i32m8_i32m1 (result, 5);
+ vint32m1_t v6 = __riscv_vget_v_i32m8_i32m1 (result, 6);
+ vint32m1_t v7 = __riscv_vget_v_i32m8_i32m1 (result, 7);
+ for (size_t i = 0; i < m; i++)
+ {
+ v0 = __riscv_vadd_vv_i32m1(v0, v0, 4);
+ v1 = __riscv_vadd_vv_i32m1(v1, v1, 4);
+ v2 = __riscv_vadd_vv_i32m1(v2, v2, 4);
+ v3 = __riscv_vadd_vv_i32m1(v3, v3, 4);
+ v4 = __riscv_vadd_vv_i32m1(v4, v4, 4);
+ v5 = __riscv_vadd_vv_i32m1(v5, v5, 4);
+ v6 = __riscv_vadd_vv_i32m1(v6, v6, 4);
+ v7 = __riscv_vadd_vv_i32m1(v7, v7, 4);
+ }
+ vint32m8_t result2 = __riscv_vundefined_i32m8 ();
+ result2 = __riscv_vset_v_i32m1_i32m8 (result2, 0, v0);
+ result2 = __riscv_vset_v_i32m1_i32m8 (result2, 1, v1);
+ result2 = __riscv_vset_v_i32m1_i32m8 (result2, 2, v2);
+ result2 = __riscv_vset_v_i32m1_i32m8 (result2, 3, v3);
+ result2 = __riscv_vset_v_i32m1_i32m8 (result2, 4, v4);
+ result2 = __riscv_vset_v_i32m1_i32m8 (result2, 5, v5);
+ result2 = __riscv_vset_v_i32m1_i32m8 (result2, 6, v6);
+ result2 = __riscv_vset_v_i32m1_i32m8 (result2, 7, v7);
+ __riscv_vse32_v_i32m8((out), result2, 64);
+}
new file mode 100644
@@ -0,0 +1,485 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv32gcv -mabi=ilp32d" } */
+
+#include "riscv_vector.h"
+
+vfloat32m1_t test_vlmul_ext_v_f32mf2_f32m1(vfloat32mf2_t op1) {
+ return __riscv_vlmul_ext_v_f32mf2_f32m1(op1);
+}
+
+vfloat32m2_t test_vlmul_ext_v_f32mf2_f32m2(vfloat32mf2_t op1) {
+ return __riscv_vlmul_ext_v_f32mf2_f32m2(op1);
+}
+
+vfloat32m4_t test_vlmul_ext_v_f32mf2_f32m4(vfloat32mf2_t op1) {
+ return __riscv_vlmul_ext_v_f32mf2_f32m4(op1);
+}
+
+vfloat32m8_t test_vlmul_ext_v_f32mf2_f32m8(vfloat32mf2_t op1) {
+ return __riscv_vlmul_ext_v_f32mf2_f32m8(op1);
+}
+
+vfloat32m2_t test_vlmul_ext_v_f32m1_f32m2(vfloat32m1_t op1) {
+ return __riscv_vlmul_ext_v_f32m1_f32m2(op1);
+}
+
+vfloat32m4_t test_vlmul_ext_v_f32m1_f32m4(vfloat32m1_t op1) {
+ return __riscv_vlmul_ext_v_f32m1_f32m4(op1);
+}
+
+vfloat32m8_t test_vlmul_ext_v_f32m1_f32m8(vfloat32m1_t op1) {
+ return __riscv_vlmul_ext_v_f32m1_f32m8(op1);
+}
+
+vfloat32m4_t test_vlmul_ext_v_f32m2_f32m4(vfloat32m2_t op1) {
+ return __riscv_vlmul_ext_v_f32m2_f32m4(op1);
+}
+
+vfloat32m8_t test_vlmul_ext_v_f32m2_f32m8(vfloat32m2_t op1) {
+ return __riscv_vlmul_ext_v_f32m2_f32m8(op1);
+}
+
+vfloat32m8_t test_vlmul_ext_v_f32m4_f32m8(vfloat32m4_t op1) {
+ return __riscv_vlmul_ext_v_f32m4_f32m8(op1);
+}
+
+vfloat64m2_t test_vlmul_ext_v_f64m1_f64m2(vfloat64m1_t op1) {
+ return __riscv_vlmul_ext_v_f64m1_f64m2(op1);
+}
+
+vfloat64m4_t test_vlmul_ext_v_f64m1_f64m4(vfloat64m1_t op1) {
+ return __riscv_vlmul_ext_v_f64m1_f64m4(op1);
+}
+
+vfloat64m8_t test_vlmul_ext_v_f64m1_f64m8(vfloat64m1_t op1) {
+ return __riscv_vlmul_ext_v_f64m1_f64m8(op1);
+}
+
+vfloat64m4_t test_vlmul_ext_v_f64m2_f64m4(vfloat64m2_t op1) {
+ return __riscv_vlmul_ext_v_f64m2_f64m4(op1);
+}
+
+vfloat64m8_t test_vlmul_ext_v_f64m2_f64m8(vfloat64m2_t op1) {
+ return __riscv_vlmul_ext_v_f64m2_f64m8(op1);
+}
+
+vfloat64m8_t test_vlmul_ext_v_f64m4_f64m8(vfloat64m4_t op1) {
+ return __riscv_vlmul_ext_v_f64m4_f64m8(op1);
+}
+
+vint8mf4_t test_vlmul_ext_v_i8mf8_i8mf4(vint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_i8mf8_i8mf4(op1);
+}
+
+vint8mf2_t test_vlmul_ext_v_i8mf8_i8mf2(vint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_i8mf8_i8mf2(op1);
+}
+
+vint8m1_t test_vlmul_ext_v_i8mf8_i8m1(vint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_i8mf8_i8m1(op1);
+}
+
+vint8m2_t test_vlmul_ext_v_i8mf8_i8m2(vint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_i8mf8_i8m2(op1);
+}
+
+vint8m4_t test_vlmul_ext_v_i8mf8_i8m4(vint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_i8mf8_i8m4(op1);
+}
+
+vint8m8_t test_vlmul_ext_v_i8mf8_i8m8(vint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_i8mf8_i8m8(op1);
+}
+
+vint8mf2_t test_vlmul_ext_v_i8mf4_i8mf2(vint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_i8mf4_i8mf2(op1);
+}
+
+vint8m1_t test_vlmul_ext_v_i8mf4_i8m1(vint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_i8mf4_i8m1(op1);
+}
+
+vint8m2_t test_vlmul_ext_v_i8mf4_i8m2(vint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_i8mf4_i8m2(op1);
+}
+
+vint8m4_t test_vlmul_ext_v_i8mf4_i8m4(vint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_i8mf4_i8m4(op1);
+}
+
+vint8m8_t test_vlmul_ext_v_i8mf4_i8m8(vint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_i8mf4_i8m8(op1);
+}
+
+vint8m1_t test_vlmul_ext_v_i8mf2_i8m1(vint8mf2_t op1) {
+ return __riscv_vlmul_ext_v_i8mf2_i8m1(op1);
+}
+
+vint8m2_t test_vlmul_ext_v_i8mf2_i8m2(vint8mf2_t op1) {
+ return __riscv_vlmul_ext_v_i8mf2_i8m2(op1);
+}
+
+vint8m4_t test_vlmul_ext_v_i8mf2_i8m4(vint8mf2_t op1) {
+ return __riscv_vlmul_ext_v_i8mf2_i8m4(op1);
+}
+
+vint8m8_t test_vlmul_ext_v_i8mf2_i8m8(vint8mf2_t op1) {
+ return __riscv_vlmul_ext_v_i8mf2_i8m8(op1);
+}
+
+vint8m2_t test_vlmul_ext_v_i8m1_i8m2(vint8m1_t op1) {
+ return __riscv_vlmul_ext_v_i8m1_i8m2(op1);
+}
+
+vint8m4_t test_vlmul_ext_v_i8m1_i8m4(vint8m1_t op1) {
+ return __riscv_vlmul_ext_v_i8m1_i8m4(op1);
+}
+
+vint8m8_t test_vlmul_ext_v_i8m1_i8m8(vint8m1_t op1) {
+ return __riscv_vlmul_ext_v_i8m1_i8m8(op1);
+}
+
+vint8m4_t test_vlmul_ext_v_i8m2_i8m4(vint8m2_t op1) {
+ return __riscv_vlmul_ext_v_i8m2_i8m4(op1);
+}
+
+vint8m8_t test_vlmul_ext_v_i8m2_i8m8(vint8m2_t op1) {
+ return __riscv_vlmul_ext_v_i8m2_i8m8(op1);
+}
+
+vint8m8_t test_vlmul_ext_v_i8m4_i8m8(vint8m4_t op1) {
+ return __riscv_vlmul_ext_v_i8m4_i8m8(op1);
+}
+
+vint16mf2_t test_vlmul_ext_v_i16mf4_i16mf2(vint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_i16mf4_i16mf2(op1);
+}
+
+vint16m1_t test_vlmul_ext_v_i16mf4_i16m1(vint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_i16mf4_i16m1(op1);
+}
+
+vint16m2_t test_vlmul_ext_v_i16mf4_i16m2(vint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_i16mf4_i16m2(op1);
+}
+
+vint16m4_t test_vlmul_ext_v_i16mf4_i16m4(vint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_i16mf4_i16m4(op1);
+}
+
+vint16m8_t test_vlmul_ext_v_i16mf4_i16m8(vint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_i16mf4_i16m8(op1);
+}
+
+vint16m1_t test_vlmul_ext_v_i16mf2_i16m1(vint16mf2_t op1) {
+ return __riscv_vlmul_ext_v_i16mf2_i16m1(op1);
+}
+
+vint16m2_t test_vlmul_ext_v_i16mf2_i16m2(vint16mf2_t op1) {
+ return __riscv_vlmul_ext_v_i16mf2_i16m2(op1);
+}
+
+vint16m4_t test_vlmul_ext_v_i16mf2_i16m4(vint16mf2_t op1) {
+ return __riscv_vlmul_ext_v_i16mf2_i16m4(op1);
+}
+
+vint16m8_t test_vlmul_ext_v_i16mf2_i16m8(vint16mf2_t op1) {
+ return __riscv_vlmul_ext_v_i16mf2_i16m8(op1);
+}
+
+vint16m2_t test_vlmul_ext_v_i16m1_i16m2(vint16m1_t op1) {
+ return __riscv_vlmul_ext_v_i16m1_i16m2(op1);
+}
+
+vint16m4_t test_vlmul_ext_v_i16m1_i16m4(vint16m1_t op1) {
+ return __riscv_vlmul_ext_v_i16m1_i16m4(op1);
+}
+
+vint16m8_t test_vlmul_ext_v_i16m1_i16m8(vint16m1_t op1) {
+ return __riscv_vlmul_ext_v_i16m1_i16m8(op1);
+}
+
+vint16m4_t test_vlmul_ext_v_i16m2_i16m4(vint16m2_t op1) {
+ return __riscv_vlmul_ext_v_i16m2_i16m4(op1);
+}
+
+vint16m8_t test_vlmul_ext_v_i16m2_i16m8(vint16m2_t op1) {
+ return __riscv_vlmul_ext_v_i16m2_i16m8(op1);
+}
+
+vint16m8_t test_vlmul_ext_v_i16m4_i16m8(vint16m4_t op1) {
+ return __riscv_vlmul_ext_v_i16m4_i16m8(op1);
+}
+
+vint32m1_t test_vlmul_ext_v_i32mf2_i32m1(vint32mf2_t op1) {
+ return __riscv_vlmul_ext_v_i32mf2_i32m1(op1);
+}
+
+vint32m2_t test_vlmul_ext_v_i32mf2_i32m2(vint32mf2_t op1) {
+ return __riscv_vlmul_ext_v_i32mf2_i32m2(op1);
+}
+
+vint32m4_t test_vlmul_ext_v_i32mf2_i32m4(vint32mf2_t op1) {
+ return __riscv_vlmul_ext_v_i32mf2_i32m4(op1);
+}
+
+vint32m8_t test_vlmul_ext_v_i32mf2_i32m8(vint32mf2_t op1) {
+ return __riscv_vlmul_ext_v_i32mf2_i32m8(op1);
+}
+
+vint32m2_t test_vlmul_ext_v_i32m1_i32m2(vint32m1_t op1) {
+ return __riscv_vlmul_ext_v_i32m1_i32m2(op1);
+}
+
+vint32m4_t test_vlmul_ext_v_i32m1_i32m4(vint32m1_t op1) {
+ return __riscv_vlmul_ext_v_i32m1_i32m4(op1);
+}
+
+vint32m8_t test_vlmul_ext_v_i32m1_i32m8(vint32m1_t op1) {
+ return __riscv_vlmul_ext_v_i32m1_i32m8(op1);
+}
+
+vint32m4_t test_vlmul_ext_v_i32m2_i32m4(vint32m2_t op1) {
+ return __riscv_vlmul_ext_v_i32m2_i32m4(op1);
+}
+
+vint32m8_t test_vlmul_ext_v_i32m2_i32m8(vint32m2_t op1) {
+ return __riscv_vlmul_ext_v_i32m2_i32m8(op1);
+}
+
+vint32m8_t test_vlmul_ext_v_i32m4_i32m8(vint32m4_t op1) {
+ return __riscv_vlmul_ext_v_i32m4_i32m8(op1);
+}
+
+vint64m2_t test_vlmul_ext_v_i64m1_i64m2(vint64m1_t op1) {
+ return __riscv_vlmul_ext_v_i64m1_i64m2(op1);
+}
+
+vint64m4_t test_vlmul_ext_v_i64m1_i64m4(vint64m1_t op1) {
+ return __riscv_vlmul_ext_v_i64m1_i64m4(op1);
+}
+
+vint64m8_t test_vlmul_ext_v_i64m1_i64m8(vint64m1_t op1) {
+ return __riscv_vlmul_ext_v_i64m1_i64m8(op1);
+}
+
+vint64m4_t test_vlmul_ext_v_i64m2_i64m4(vint64m2_t op1) {
+ return __riscv_vlmul_ext_v_i64m2_i64m4(op1);
+}
+
+vint64m8_t test_vlmul_ext_v_i64m2_i64m8(vint64m2_t op1) {
+ return __riscv_vlmul_ext_v_i64m2_i64m8(op1);
+}
+
+vint64m8_t test_vlmul_ext_v_i64m4_i64m8(vint64m4_t op1) {
+ return __riscv_vlmul_ext_v_i64m4_i64m8(op1);
+}
+
+vuint8mf4_t test_vlmul_ext_v_u8mf8_u8mf4(vuint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_u8mf8_u8mf4(op1);
+}
+
+vuint8mf2_t test_vlmul_ext_v_u8mf8_u8mf2(vuint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_u8mf8_u8mf2(op1);
+}
+
+vuint8m1_t test_vlmul_ext_v_u8mf8_u8m1(vuint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_u8mf8_u8m1(op1);
+}
+
+vuint8m2_t test_vlmul_ext_v_u8mf8_u8m2(vuint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_u8mf8_u8m2(op1);
+}
+
+vuint8m4_t test_vlmul_ext_v_u8mf8_u8m4(vuint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_u8mf8_u8m4(op1);
+}
+
+vuint8m8_t test_vlmul_ext_v_u8mf8_u8m8(vuint8mf8_t op1) {
+ return __riscv_vlmul_ext_v_u8mf8_u8m8(op1);
+}
+
+vuint8mf2_t test_vlmul_ext_v_u8mf4_u8mf2(vuint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_u8mf4_u8mf2(op1);
+}
+
+vuint8m1_t test_vlmul_ext_v_u8mf4_u8m1(vuint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_u8mf4_u8m1(op1);
+}
+
+vuint8m2_t test_vlmul_ext_v_u8mf4_u8m2(vuint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_u8mf4_u8m2(op1);
+}
+
+vuint8m4_t test_vlmul_ext_v_u8mf4_u8m4(vuint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_u8mf4_u8m4(op1);
+}
+
+vuint8m8_t test_vlmul_ext_v_u8mf4_u8m8(vuint8mf4_t op1) {
+ return __riscv_vlmul_ext_v_u8mf4_u8m8(op1);
+}
+
+vuint8m1_t test_vlmul_ext_v_u8mf2_u8m1(vuint8mf2_t op1) {
+ return __riscv_vlmul_ext_v_u8mf2_u8m1(op1);
+}
+
+vuint8m2_t test_vlmul_ext_v_u8mf2_u8m2(vuint8mf2_t op1) {
+ return __riscv_vlmul_ext_v_u8mf2_u8m2(op1);
+}
+
+vuint8m4_t test_vlmul_ext_v_u8mf2_u8m4(vuint8mf2_t op1) {
+ return __riscv_vlmul_ext_v_u8mf2_u8m4(op1);
+}
+
+vuint8m8_t test_vlmul_ext_v_u8mf2_u8m8(vuint8mf2_t op1) {
+ return __riscv_vlmul_ext_v_u8mf2_u8m8(op1);
+}
+
+vuint8m2_t test_vlmul_ext_v_u8m1_u8m2(vuint8m1_t op1) {
+ return __riscv_vlmul_ext_v_u8m1_u8m2(op1);
+}
+
+vuint8m4_t test_vlmul_ext_v_u8m1_u8m4(vuint8m1_t op1) {
+ return __riscv_vlmul_ext_v_u8m1_u8m4(op1);
+}
+
+vuint8m8_t test_vlmul_ext_v_u8m1_u8m8(vuint8m1_t op1) {
+ return __riscv_vlmul_ext_v_u8m1_u8m8(op1);
+}
+
+vuint8m4_t test_vlmul_ext_v_u8m2_u8m4(vuint8m2_t op1) {
+ return __riscv_vlmul_ext_v_u8m2_u8m4(op1);
+}
+
+vuint8m8_t test_vlmul_ext_v_u8m2_u8m8(vuint8m2_t op1) {
+ return __riscv_vlmul_ext_v_u8m2_u8m8(op1);
+}
+
+vuint8m8_t test_vlmul_ext_v_u8m4_u8m8(vuint8m4_t op1) {
+ return __riscv_vlmul_ext_v_u8m4_u8m8(op1);
+}
+
+vuint16mf2_t test_vlmul_ext_v_u16mf4_u16mf2(vuint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_u16mf4_u16mf2(op1);
+}
+
+vuint16m1_t test_vlmul_ext_v_u16mf4_u16m1(vuint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_u16mf4_u16m1(op1);
+}
+
+vuint16m2_t test_vlmul_ext_v_u16mf4_u16m2(vuint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_u16mf4_u16m2(op1);
+}
+
+vuint16m4_t test_vlmul_ext_v_u16mf4_u16m4(vuint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_u16mf4_u16m4(op1);
+}
+
+vuint16m8_t test_vlmul_ext_v_u16mf4_u16m8(vuint16mf4_t op1) {
+ return __riscv_vlmul_ext_v_u16mf4_u16m8(op1);
+}
+
+vuint16m1_t test_vlmul_ext_v_u16mf2_u16m1(vuint16mf2_t op1) {
+ return __riscv_vlmul_ext_v_u16mf2_u16m1(op1);
+}
+
+vuint16m2_t test_vlmul_ext_v_u16mf2_u16m2(vuint16mf2_t op1) {
+ return __riscv_vlmul_ext_v_u16mf2_u16m2(op1);
+}
+
+vuint16m4_t test_vlmul_ext_v_u16mf2_u16m4(vuint16mf2_t op1) {
+ return __riscv_vlmul_ext_v_u16mf2_u16m4(op1);
+}
+
+vuint16m8_t test_vlmul_ext_v_u16mf2_u16m8(vuint16mf2_t op1) {
+ return __riscv_vlmul_ext_v_u16mf2_u16m8(op1);
+}
+
+vuint16m2_t test_vlmul_ext_v_u16m1_u16m2(vuint16m1_t op1) {
+ return __riscv_vlmul_ext_v_u16m1_u16m2(op1);
+}
+
+vuint16m4_t test_vlmul_ext_v_u16m1_u16m4(vuint16m1_t op1) {
+ return __riscv_vlmul_ext_v_u16m1_u16m4(op1);
+}
+
+vuint16m8_t test_vlmul_ext_v_u16m1_u16m8(vuint16m1_t op1) {
+ return __riscv_vlmul_ext_v_u16m1_u16m8(op1);
+}
+
+vuint16m4_t test_vlmul_ext_v_u16m2_u16m4(vuint16m2_t op1) {
+ return __riscv_vlmul_ext_v_u16m2_u16m4(op1);
+}
+
+vuint16m8_t test_vlmul_ext_v_u16m2_u16m8(vuint16m2_t op1) {
+ return __riscv_vlmul_ext_v_u16m2_u16m8(op1);
+}
+
+vuint16m8_t test_vlmul_ext_v_u16m4_u16m8(vuint16m4_t op1) {
+ return __riscv_vlmul_ext_v_u16m4_u16m8(op1);
+}
+
+vuint32m1_t test_vlmul_ext_v_u32mf2_u32m1(vuint32mf2_t op1) {
+ return __riscv_vlmul_ext_v_u32mf2_u32m1(op1);
+}
+
+vuint32m2_t test_vlmul_ext_v_u32mf2_u32m2(vuint32mf2_t op1) {
+ return __riscv_vlmul_ext_v_u32mf2_u32m2(op1);
+}
+
+vuint32m4_t test_vlmul_ext_v_u32mf2_u32m4(vuint32mf2_t op1) {
+ return __riscv_vlmul_ext_v_u32mf2_u32m4(op1);
+}
+
+vuint32m8_t test_vlmul_ext_v_u32mf2_u32m8(vuint32mf2_t op1) {
+ return __riscv_vlmul_ext_v_u32mf2_u32m8(op1);
+}
+
+vuint32m2_t test_vlmul_ext_v_u32m1_u32m2(vuint32m1_t op1) {
+ return __riscv_vlmul_ext_v_u32m1_u32m2(op1);
+}
+
+vuint32m4_t test_vlmul_ext_v_u32m1_u32m4(vuint32m1_t op1) {
+ return __riscv_vlmul_ext_v_u32m1_u32m4(op1);
+}
+
+vuint32m8_t test_vlmul_ext_v_u32m1_u32m8(vuint32m1_t op1) {
+ return __riscv_vlmul_ext_v_u32m1_u32m8(op1);
+}
+
+vuint32m4_t test_vlmul_ext_v_u32m2_u32m4(vuint32m2_t op1) {
+ return __riscv_vlmul_ext_v_u32m2_u32m4(op1);
+}
+
+vuint32m8_t test_vlmul_ext_v_u32m2_u32m8(vuint32m2_t op1) {
+ return __riscv_vlmul_ext_v_u32m2_u32m8(op1);
+}
+
+vuint32m8_t test_vlmul_ext_v_u32m4_u32m8(vuint32m4_t op1) {
+ return __riscv_vlmul_ext_v_u32m4_u32m8(op1);
+}
+
+vuint64m2_t test_vlmul_ext_v_u64m1_u64m2(vuint64m1_t op1) {
+ return __riscv_vlmul_ext_v_u64m1_u64m2(op1);
+}
+
+vuint64m4_t test_vlmul_ext_v_u64m1_u64m4(vuint64m1_t op1) {
+ return __riscv_vlmul_ext_v_u64m1_u64m4(op1);
+}
+
+vuint64m8_t test_vlmul_ext_v_u64m1_u64m8(vuint64m1_t op1) {
+ return __riscv_vlmul_ext_v_u64m1_u64m8(op1);
+}
+
+vuint64m4_t test_vlmul_ext_v_u64m2_u64m4(vuint64m2_t op1) {
+ return __riscv_vlmul_ext_v_u64m2_u64m4(op1);
+}
+
+vuint64m8_t test_vlmul_ext_v_u64m2_u64m8(vuint64m2_t op1) {
+ return __riscv_vlmul_ext_v_u64m2_u64m8(op1);
+}
+
+vuint64m8_t test_vlmul_ext_v_u64m4_u64m8(vuint64m4_t op1) {
+ return __riscv_vlmul_ext_v_u64m4_u64m8(op1);
+}
+
From: Juzhe-Zhong <juzhe.zhong@rivai.ai> PR target/110109 This patch is to fix PR110109 issue. This issue happens is because: (define_insn_and_split "*vlmul_extx2<mode>" [(set (match_operand:<VLMULX2> 0 "register_operand" "=vr, ?&vr") (subreg:<VLMULX2> (match_operand:VLMULEXT2 1 "register_operand" " 0, vr") 0))] "TARGET_VECTOR" "#" "&& reload_completed" [(const_int 0)] { emit_insn (gen_rtx_SET (gen_lowpart (<MODE>mode, operands[0]), operands[1])); DONE; }) Such pattern generate such codes in insn-recog.cc: static int pattern57 (rtx x1) { rtx * const operands ATTRIBUTE_UNUSED = &recog_data.operand[0]; rtx x2; int res ATTRIBUTE_UNUSED; if (maybe_ne (SUBREG_BYTE (x1).to_constant (), 0)) return -1; ... PR110109 ICE at maybe_ne (SUBREG_BYTE (x1).to_constant (), 0) since for scalable RVV modes can not be accessed as SUBREG_BYTE (x1).to_constant () I create that patterns is to optimize the following test: vfloat32m2_t test_vlmul_ext_v_f32mf2_f32m2(vfloat32mf2_t op1) { return __riscv_vlmul_ext_v_f32mf2_f32m2(op1); } codegen: test_vlmul_ext_v_f32mf2_f32m2: vsetvli a5,zero,e32,m2,ta,ma vmv.v.i v2,0 vsetvli a5,zero,e32,mf2,ta,ma vle32.v v2,0(a1) vs2r.v v2,0(a0) ret There is a redundant 'vmv.v.i' here, Since GCC doesn't undefine IR (unlike LLVM, LLVM has undef/poison). For vlmul_ext_* RVV intrinsic, GCC will initiate all zeros into register. However, I think it's not a big issue after we support subreg livness tracking. gcc/ChangeLog: * config/riscv/riscv-vector-builtins-bases.cc: Change expand approach. * config/riscv/vector.md (@vlmul_extx2<mode>): Remove it. (@vlmul_extx4<mode>): Ditto. (@vlmul_extx8<mode>): Ditto. (@vlmul_extx16<mode>): Ditto. (@vlmul_extx32<mode>): Ditto. (@vlmul_extx64<mode>): Ditto. (*vlmul_extx2<mode>): Ditto. (*vlmul_extx4<mode>): Ditto. (*vlmul_extx8<mode>): Ditto. (*vlmul_extx16<mode>): Ditto. (*vlmul_extx32<mode>): Ditto. (*vlmul_extx64<mode>): Ditto. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/base/pr110109-1.c: New test. * gcc.target/riscv/rvv/base/pr110109-2.c: New test. --- .../riscv/riscv-vector-builtins-bases.cc | 28 +- gcc/config/riscv/vector.md | 120 ----- .../gcc.target/riscv/rvv/base/pr110109-1.c | 40 ++ .../gcc.target/riscv/rvv/base/pr110109-2.c | 485 ++++++++++++++++++ 4 files changed, 529 insertions(+), 144 deletions(-) create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110109-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr110109-2.c