https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70159
Bug ID: 70159
Summary: missed CSE optimization
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: spop at gcc dot gnu.org
Target Milestone: ---
$ cat h.c
float foo_p(float d, float min, float max, float a)
{
float tmin;
float tmax;
float inv = 1.0f / d;
if (inv >= 0) {
tmin = (min - a) * inv;
tmax = (max - a) * inv;
} else {
tmin = (max - a) * inv;
tmax = (min - a) * inv;
}
return tmax + tmin;
}
$ gcc h.c -Ofast -S -o-
foo_p:
fmov s4, 1.0e+0
fdiv s0, s4, s0
fcmpe s0, #0.0
blt .L6
fsub s1, s1, s3
fsub s2, s2, s3
fmul s1, s1, s0
fmul s0, s2, s0
fadd s0, s1, s0
ret
.p2align 3
.L6:
fsub s4, s2, s3
fsub s2, s1, s3
fmul s1, s4, s0
fmul s0, s2, s0
fadd s0, s1, s0
ret
$ clang h.c -Ofast -S -o-
foo_p: // @foo_p
// BB#0: // %entry
fmov s4, #1.00000000
fdiv s0, s4, s0
fcmp s0, #0.0
fcsel s4, s1, s2, lt
fcsel s1, s2, s1, lt
fsub s1, s1, s3
fsub s2, s4, s3
fadd s1, s2, s1
fmul s0, s1, s0
ret
The computations in both branches are redundant.
Even without if-conversion (fcsel), GCC should be able to sink/hoist fsub and
fmul.
