https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119187
--- Comment #14 from Tamar Christina <tnfchris at gcc dot gnu.org> ---
boolean vector handling now works.
#include <arm_neon.h>
void foo (uint8_t *a, uint8_t *b, uint8_t *c, int n)
{
for (int i = 0; i < n; i+=8, a+=8, b+=8, c+=8)
{
uint8x8_t av1 = vld1_u8 (a);
uint8x8_t bv1 = vld1_u8 (b);
vst1_u8 (c, vcgt_u8 (av1, bv1));
}
}
compiled with -march=armv9-a+sve -O3 gives
.L5:
ldr q31, [x1, x3]
ldr q30, [x0, x3]
cmhi v30.16b, v30.16b, v31.16b
str q30, [x2, x3]
add x3, x3, 16
cmp x3, x5
bne .L5
lsl w3, w4, 4
cmp w6, w3
beq .L1
.L4:
sub w6, w6, w3
ptrue p6.b, all
ubfiz x3, x3, 3, 32
whilelo p7.b, xzr, x6
ld1b z28.b, p7/z, [x0, x3]
ld1b z27.b, p7/z, [x1, x3]
cmplo p15.b, p6/z, z27.b, z28.b
mov z29.b, p15/z, #-1
st1b z29.b, p7, [x2, x3]
.L1:
ret
.p2align 2,,3
.L6:
mov x4, 0
.p2align 5,,15
.L3:
ldr d26, [x0, x4]
ldr d25, [x1, x4]
cmhi v25.8b, v26.8b, v25.8b
str d25, [x2, x4]
add x4, x4, 8
cmp w3, w4
bgt .L3
ret
.L7:
mov w3, 0
b .L4
and so the vectorizer is now able to handle the conversion between different
boolean modes.
working on MASK_CALL now and then moving on to live values with e.g.
#include <arm_neon.h>
uint8_t foo (uint8_t *a, uint8_t *b, uint8_t *c, int n)
{
uint8x8_t sum = {0};
for (int i = 0; i < n; i+=8, a+=8, b+=8, c+=8)
{
uint8x8_t av1 = vld1_u8 (a);
uint8x8_t bv1 = vld1_u8 (b);
sum = vadd_u8 (sum, vadd_u8 (av1, bv1));
}
return vaddv_u8 (sum);
}