https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100638
Bug ID: 100638
Summary: FP16 vector compare missed optimization on AArch64
Product: gcc
Version: 11.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: tnfchris at gcc dot gnu.org
Target Milestone: ---
Target: aarch64-*
The following testcase
```
#include <arm_neon.h>
void foo(float16_t *x, uint16x8_t *out) {
float16x8x2_t xk = vld2q_f16(x);
float16x8_t xk_re = xk.val[0];
float16x8_t xk_im = xk.val[1];
uint16x8_t theta_rx = xk_re < 0;
uint16x8_t theta_ix = xk_im < 0;
out[0] = theta_rx;
out[1] = theta_ix;
}
```
on AArch64 with `-Ofast -march=armv8.2-a+fp16` generates
```
foo:
ld2 {v0.8h - v1.8h}, [x0]
mov w2, -1
fcvt s2, h0
fcvt s18, h1
dup h3, v0.h[1]
dup h24, v0.h[2]
dup h23, v0.h[3]
fcmpe s2, #0.0
fcvt s3, h3
fcvt s24, h24
dup h22, v0.h[4]
csel w0, w2, wzr, mi
fcvt s23, h23
fcmpe s3, #0.0
dup v2.4h, w0
dup h17, v1.h[1]
dup h16, v1.h[2]
csel w0, w2, wzr, mi
fcmpe s24, #0.0
dup h7, v1.h[3]
dup h6, v1.h[4]
dup h5, v1.h[5]
dup h4, v1.h[6]
dup h3, v1.h[7]
mov v1.16b, v2.16b
dup h21, v0.h[5]
fcvt s22, h22
fcvt s17, h17
dup h20, v0.h[6]
ins v1.h[1], w0
csel w0, w2, wzr, mi
fcmpe s23, #0.0
fcvt s21, h21
dup h19, v0.h[7]
fcvt s20, h20
fcvt s16, h16
ins v1.h[2], w0
fcvt s7, h7
csel w0, w2, wzr, mi
fcmpe s22, #0.0
fcvt s19, h19
fcvt s6, h6
fcvt s5, h5
fcvt s4, h4
ins v1.h[3], w0
fcvt s3, h3
csel w0, w2, wzr, mi
fcmpe s21, #0.0
ins v1.h[4], w0
csel w0, w2, wzr, mi
fcmpe s20, #0.0
ins v1.h[5], w0
csel w0, w2, wzr, mi
fcmpe s19, #0.0
ins v1.h[6], w0
csel w0, w2, wzr, mi
fcmpe s18, #0.0
ins v1.h[7], w0
csel w0, w2, wzr, mi
fcmpe s17, #0.0
dup v0.4h, w0
csel w0, w2, wzr, mi
fcmpe s16, #0.0
ins v0.h[1], w0
csel w0, w2, wzr, mi
fcmpe s7, #0.0
ins v0.h[2], w0
csel w0, w2, wzr, mi
fcmpe s6, #0.0
ins v0.h[3], w0
csel w0, w2, wzr, mi
fcmpe s5, #0.0
ins v0.h[4], w0
csel w0, w2, wzr, mi
fcmpe s4, #0.0
ins v0.h[5], w0
csel w0, w2, wzr, mi
fcmpe s3, #0.0
ins v0.h[6], w0
csel w2, w2, wzr, mi
ins v0.h[7], w2
stp q1, q0, [x1]
ret
```
instead of simply
```
foo:
ld2 { v0.8h, v1.8h }, [x0]
fcmlt v2.8h, v0.8h, #0.0
fcmlt v0.8h, v1.8h, #0.0
stp q2, q0, [x1]
ret
```
This is happening because veclower doesn't find a pattern for the FP16 vector
compare and then lowers to operations on scalar.
However even the lowered operations are inefficient:
```
fcvt s23, h23
fcmpe s23, #0.0
```
indicates that the backend doesn't know how to do this operation on fp16.
