https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102171
Bug ID: 102171
Summary: vget_low_*/vget_high_* intrinsics should become
BIT_FIELD_REF during gimple
Product: gcc
Version: 12.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: enhancement
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: pinskia at gcc dot gnu.org
Blocks: 95958
Target Milestone: ---
Target: aarch64*-linux-gnu
#include <arm_neon.h>
float16x4_t f0(float16x8_t b)
{
return vget_low_f16 (b);
}
float16x4_t f(float16x8_t b)
{
return vget_high_f16 (b);
}
float16x4_t f1(float16x8_t b)
{
return ((float16x4_t*)&b)[0];
}
float16x4_t f2(float16x8_t b)
{
return ((float16x4_t*)&b)[1];
}
---- CUT ----
For little-endian f0 and f1 are the same, and f and f2 are the same.
For big-endian f0 and f2 are the same, and f0 and f1 are the same.
The reason why we should simplify them at the gimple level is to allow the
gimple optimizers do the work for us.
Referenced Bugs:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=95958
[Bug 95958] [meta-bug] Inefficient arm_neon.h code for AArch64
