From: Pan Li <pan2...@intel.com>
This patch would like to combine the vec_duplicate + vssub.vv to the
vssub.vx. From example as below code. The related pattern will depend
on the cost of vec_duplicate from GR2VR. Then the late-combine will
take action if the cost of GR2VR is zero, and reject the combination
if the GR2VR cost is greater than zero.
Assume we have example code like below, GR2VR cost is 0.
#define DEF_SAT_S_ADD(T, UT, MIN, MAX) \
T \
test_##T##_sat_add (T x, T y) \
{ \
T sum = (UT)x + (UT)y; \
return (x ^ y) < 0 \
? sum \
: (sum ^ x) >= 0 \
? sum \
: x < 0 ? MIN : MAX; \
}
DEF_SAT_S_ADD(int32_t, uint32_t, INT32_MIN, INT32_MAX)
DEF_VX_BINARY_CASE_2_WRAP(T, SAT_S_ADD_FUNC(T), sat_add)
Before this patch:
10 │ test_vx_binary_or_int32_t_case_0:
11 │ beq a3,zero,.L8
12 │ vsetvli a5,zero,e32,m1,ta,ma
13 │ vmv.v.x v2,a2
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 │ vssub.vv v1,v1,v2
23 │ vse32.v v1,0(a0)
24 │ add a0,a0,a4
25 │ bne a3,zero,.L3
After this patch:
10 │ test_vx_binary_or_int32_t_case_0:
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 │ vssub.vx v1,v1,a2
21 │ vse32.v v1,0(a0)
22 │ add a0,a0,a4
23 │ bne a3,zero,.L3
gcc/ChangeLog:
* config/riscv/riscv-v.cc (expand_vx_binary_vec_vec_dup): Add
new case SS_MINUS.
* config/riscv/riscv.cc (riscv_rtx_costs): Ditto.
* config/riscv/vector-iterators.md: Add new op ss_minus.
Signed-off-by: Pan Li <pan2...@intel.com>
---
gcc/config/riscv/riscv-v.cc | 1 +
gcc/config/riscv/riscv.cc | 1 +
gcc/config/riscv/vector-iterators.md | 3 ++-
3 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index a5ab8dd4e2f..dad23d5c670 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -5586,6 +5586,7 @@ expand_vx_binary_vec_vec_dup (rtx op_0, rtx op_1, rtx
op_2,
case US_PLUS:
case US_MINUS:
case SS_PLUS:
+ case SS_MINUS:
icode = code_for_pred_scalar (code, mode);
break;
default:
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index ecdb61e1899..1ad756fa2f8 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -3998,6 +3998,7 @@ riscv_rtx_costs (rtx x, machine_mode mode, int
outer_code, int opno ATTRIBUTE_UN
case US_PLUS:
case US_MINUS:
case SS_PLUS:
+ case SS_MINUS:
*total = get_vector_binary_rtx_cost (op, scalar2vr_cost);
break;
default:
diff --git a/gcc/config/riscv/vector-iterators.md
b/gcc/config/riscv/vector-iterators.md
index fd0959c1a4b..e60e3a8399c 100644
--- a/gcc/config/riscv/vector-iterators.md
+++ b/gcc/config/riscv/vector-iterators.md
@@ -4042,7 +4042,8 @@ (define_code_iterator any_int_binop [plus minus and ior
xor ashift ashiftrt lshi
])
(define_code_iterator any_int_binop_no_shift_v_vdup [
- plus minus and ior xor mult div udiv mod umod smax umax smin umin us_plus
us_minus ss_plus
+ plus minus and ior xor mult div udiv mod umod smax umax smin umin us_plus
+ us_minus ss_plus ss_minus
])
(define_code_iterator any_int_binop_no_shift_vdup_v [
--
2.43.0
