From: Pan Li <pan2...@intel.com>
This patch would like to combine the vec_duplicate + vadd.vv to the
vadd.vx. From example as below:
#define DEF_VX_BINARY(T, OP) \
void \
test_vx_binary (T * restrict out, T * restrict in, T x, unsigned n) \
{ \
for (unsigned i = 0; i < n; i++) \
out[i] = in[i] OP x; \
}
DEF_VX_BINARY(int32_t, +)
Before this patch:
10 │ test_binary_vx_add:
11 │ beq a3,zero,.L8
12 │ vsetvli a5,zero,e32,m1,ta,ma // eliminated
13 │ vmv.v.x v2,a2 // Ditto.
14 │ slli a3,a3,32
15 │ srli a3,a3,32
16 │ .L3:
17 │ vsetvli a5,a3,e32,m1,ta,ma
18 │ vle32.v v1,0(a1)
19 │ slli a4,a5,2
20 │ sub a3,a3,a5
21 │ add a1,a1,a4
22 │ vadd.vv v1,v2,v1
23 │ vse32.v v1,0(a0)
24 │ add a0,a0,a4
25 │ bne a3,zero,.L3
After this patch:
10 │ test_binary_vx_add:
11 │ beq a3,zero,.L8
12 │ slli a3,a3,32
13 │ srli a3,a3,32
14 │ .L3:
15 │ vsetvli a5,a3,e32,m1,ta,ma
16 │ vle32.v v1,0(a1)
17 │ slli a4,a5,2
18 │ sub a3,a3,a5
19 │ add a1,a1,a4
20 │ vadd.vx v1,v1,a2
21 │ vse32.v v1,0(a0)
22 │ add a0,a0,a4
23 │ bne a3,zero,.L3
The below test suites are passed for this patch.
* The rv64gcv fully regression test.
gcc/ChangeLog:
* config/riscv/autovec-opt.md (*<optab>_vx_<mode>): Add new
combine to convert vec_duplicate + vadd.vv to vaddvx.
* config/riscv/vector-iterators.md: Add new iterator for vx.
Signed-off-by: Pan Li <pan2...@intel.com>
---
gcc/config/riscv/autovec-opt.md | 22 ++++++++++++++++++++++
gcc/config/riscv/vector-iterators.md | 4 ++++
2 files changed, 26 insertions(+)
diff --git a/gcc/config/riscv/autovec-opt.md b/gcc/config/riscv/autovec-opt.md
index 4b33a145c17..6bc0388a087 100644
--- a/gcc/config/riscv/autovec-opt.md
+++ b/gcc/config/riscv/autovec-opt.md
@@ -1611,3 +1611,25 @@ (define_insn_and_split "*vandn_<mode>"
DONE;
}
[(set_attr "type" "vandn")])
+
+;;
=============================================================================
+;; Combine vec_duplicate + op.vv to op.vx
+;; Include
+;; - vadd.vx
+;;
=============================================================================
+(define_insn_and_split "*<optab>_vx_<mode>"
+ [(set (match_operand:V_VLSI 0 "register_operand")
+ (any_int_binop_no_shift_vx:V_VLSI
+ (vec_duplicate:V_VLSI
+ (match_operand:<VEL> 1 "register_operand"))
+ (match_operand:V_VLSI 2 "<binop_rhs2_predicate>")))]
+ "TARGET_VECTOR && can_create_pseudo_p ()"
+ "#"
+ "&& 1"
+ [(const_int 0)]
+ {
+ rtx ops[] = {operands[0], operands[2], operands[1]};
+ riscv_vector::emit_vlmax_insn (code_for_pred_scalar (<CODE>, <MODE>mode),
+ riscv_vector::BINARY_OP, ops);
+ }
+ [(set_attr "type" "vialu")])
diff --git a/gcc/config/riscv/vector-iterators.md
b/gcc/config/riscv/vector-iterators.md
index 92cb651ce49..80c184e297b 100644
--- a/gcc/config/riscv/vector-iterators.md
+++ b/gcc/config/riscv/vector-iterators.md
@@ -3987,6 +3987,10 @@ (define_code_iterator any_int_binop_no_shift
[plus minus and ior xor smax umax smin umin mult div udiv mod umod
])
+(define_code_iterator any_int_binop_no_shift_vx
+ [plus
+])
+
(define_code_iterator any_sat_int_binop [ss_plus ss_minus us_plus us_minus])
(define_code_iterator sat_int_plus_binop [ss_plus us_plus])
(define_code_iterator sat_int_minus_binop [ss_minus us_minus])
--
2.43.0
