https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114577
Bug ID: 114577
Summary: Inefficient codegen for SVE/NEON bridge
Product: gcc
Version: 14.0
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 sequence:
#include <arm_neon_sve_bridge.h>
svint32_t f (int *a, int *b)
{
int32x4_t va = vld1q_s32 (a);
svint32_t za = svset_neonq_s32 (svundef_s32 (), va);
return za;
}
-O2 -march=armv9-a
is expected to be a simple load but generates:
f:
ldr q31, [x0]
ptrue p3.s, vl4
sel z0.s, p3, z31.s, z0.s
ret
instead of the expected (from clang):
f: // @f
ldr q0, [x0]
ret
it looks like GCC's implementation of svset_neonq_s32 with svundef does not
become a view_convert/subreg.
