This patch would like to combine the vec_duplicate + vminu.vv to the
vminu.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_VX_BINARY(T, FUNC) \
void \
test_vx_binary (T * restrict out, T * restrict in, T x, unsigned n) \
{ \
for (unsigned i = 0; i < n; i++) \
out[i] = FUNC (in[i], x); \
}
uint32_t min(uint32 a, uint32 b)
{
return a > b ? b : a;
}
DEF_VX_BINARY(uint32_t, min)
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 │ vminu.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 │ vminu.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_dup_vec): Add
new case UMIN.
(expand_vx_binary_vec_vec_dup): Ditto.
* config/riscv/riscv.cc (riscv_rtx_costs): Ditto.
* config/riscv/vector-iterators.md: Add new op umin.
Signed-off-by: Pan Li <pan2.li@intel.com>
case SMAX:
case UMAX:
case SMIN:
+ case UMIN:
icode = code_for_pred_scalar (code, mode);
break;
case MINUS:
case SMAX:
case UMAX:
case SMIN:
+ case UMIN:
icode = code_for_pred_scalar (code, mode);
break;
default:
case SMAX:
case UMAX:
case SMIN:
+ case UMIN:
{
rtx op;
rtx op_0 = XEXP (x, 0);
])
(define_code_iterator any_int_binop_no_shift_v_vdup [
- plus minus and ior xor mult div udiv mod umod smax umax smin
+ plus minus and ior xor mult div udiv mod umod smax umax smin umin
])
(define_code_iterator any_int_binop_no_shift_vdup_v [
- plus minus and ior xor mult smax umax smin
+ plus minus and ior xor mult smax umax smin umin
])
(define_code_iterator any_int_unop [neg not])