RISC-V: Support widening register overlap for vf4/vf8
size_t
foo (char const *buf, size_t len)
{
size_t sum = 0;
size_t vl = __riscv_vsetvlmax_e8m8 ();
size_t step = vl * 4;
const char *it = buf, *end = buf + len;
for (; it + step <= end;)
{
vint8m1_t v0 = __riscv_vle8_v_i8m1 ((void *) it, vl);
it += vl;
vint8m1_t v1 = __riscv_vle8_v_i8m1 ((void *) it, vl);
it += vl;
vint8m1_t v2 = __riscv_vle8_v_i8m1 ((void *) it, vl);
it += vl;
vint8m1_t v3 = __riscv_vle8_v_i8m1 ((void *) it, vl);
it += vl;
asm volatile("nop" ::: "memory");
vint64m8_t vw0 = __riscv_vsext_vf8_i64m8 (v0, vl);
vint64m8_t vw1 = __riscv_vsext_vf8_i64m8 (v1, vl);
vint64m8_t vw2 = __riscv_vsext_vf8_i64m8 (v2, vl);
vint64m8_t vw3 = __riscv_vsext_vf8_i64m8 (v3, vl);
asm volatile("nop" ::: "memory");
size_t sum0 = __riscv_vmv_x_s_i64m8_i64 (vw0);
size_t sum1 = __riscv_vmv_x_s_i64m8_i64 (vw1);
size_t sum2 = __riscv_vmv_x_s_i64m8_i64 (vw2);
size_t sum3 = __riscv_vmv_x_s_i64m8_i64 (vw3);
sum += sumation (sum0, sum1, sum2, sum3);
}
return sum;
}
Before this patch:
add a3,s0,s1
add a4,s6,s1
add a5,s7,s1
vsetvli zero,s0,e64,m8,ta,ma
vle8.v v4,0(s1)
vle8.v v3,0(a3)
mv s1,s2
vle8.v v2,0(a4)
vle8.v v1,0(a5)
nop
vsext.vf8 v8,v4
vsext.vf8 v16,v2
vs8r.v v8,0(sp)
vsext.vf8 v24,v1
vsext.vf8 v8,v3
nop
vmv.x.s a1,v8
vl8re64.v v8,0(sp)
vmv.x.s a3,v24
vmv.x.s a2,v16
vmv.x.s a0,v8
add s2,s2,s5
call sumation
add s3,s3,a0
bgeu s4,s2,.L5
After this patch:
add a3,s0,s1
add a4,s6,s1
add a5,s7,s1
vsetvli zero,s0,e64,m8,ta,ma
vle8.v v15,0(s1)
vle8.v v23,0(a3)
mv s1,s2
vle8.v v31,0(a4)
vle8.v v7,0(a5)
vsext.vf8 v8,v15
vsext.vf8 v16,v23
vsext.vf8 v24,v31
vsext.vf8 v0,v7
vmv.x.s a3,v0
vmv.x.s a2,v24
vmv.x.s a1,v16
vmv.x.s a0,v8
add s2,s2,s5
call sumation
add s3,s3,a0
bgeu s4,s2,.L5
PR target/112431
gcc/ChangeLog:
* config/riscv/vector.md: Add widening overlap of vf2/vf4.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/pr112431-16.c: New test.
* gcc.target/riscv/rvv/base/pr112431-17.c: New test.
* gcc.target/riscv/rvv/base/pr112431-18.c: New test.