https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114134
Bug ID: 114134
Summary: Extra mov instructions for simple function compared
with GCC13
Product: gcc
Version: 14.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: pilarlatiesa at gmail dot com
Target Milestone: ---
In the example below, the function `Key` has some extra (useless?) mov
instructions that are not generated with GCC 13.
$ cat borrar.cpp
#include <cmath>
struct TVec3D { double x, y, z; };
struct TKey { int i, j, k; };
extern double const BinSize;
inline int Index(double const x)
{ return static_cast<int>(std::floor(static_cast<float>(x / BinSize + 1.0) -
1.0f)); };
TKey Key(TVec3D const &r)
{ return {Index(r.x), Index(r.y), Index(r.z)}; }
$ ./gcc-13/bin/g++ -O3 -march=skylake -fno-trapping-math -S borrar.cpp -o-
.file "borrar.cpp"
.text
.p2align 4
.globl _Z3KeyRK6TVec3D
.type _Z3KeyRK6TVec3D, @function
_Z3KeyRK6TVec3D:
.LFB993:
.cfi_startproc
vmovsd BinSize(%rip), %xmm1
vmovupd (%rdi), %xmm3
vmovddup .LC1(%rip), %xmm2
vmovddup %xmm1, %xmm0
vdivpd %xmm0, %xmm3, %xmm0
vaddpd %xmm2, %xmm0, %xmm0
vmovq .LC2(%rip), %xmm2
vcvtpd2psx %xmm0, %xmm0
vaddps %xmm2, %xmm0, %xmm0
vroundps $9, %xmm0, %xmm0
vcvttps2dq %xmm0, %xmm4
vmovsd 16(%rdi), %xmm0
vmovq %xmm4, %rax
vdivsd %xmm1, %xmm0, %xmm0
vaddsd .LC1(%rip), %xmm0, %xmm0
vcvtsd2ss %xmm0, %xmm0, %xmm0
vsubss .LC3(%rip), %xmm0, %xmm0
vroundss $9, %xmm0, %xmm0, %xmm0
vcvttss2sil %xmm0, %edx
movl %edx, %edx
ret
.cfi_endproc
.LFE993:
.size _Z3KeyRK6TVec3D, .-_Z3KeyRK6TVec3D
.section .rodata.cst8,"aM",@progbits,8
.align 8
.LC1:
.long 0
.long 1072693248
.align 8
.LC2:
.long -1082130432
.long -1082130432
.section .rodata.cst4,"aM",@progbits,4
.align 4
.LC3:
.long 1065353216
.ident "GCC: (GNU) 13.1.0"
.section .note.GNU-stack,"",@progbits
$ ./gcc-14/bin/g++ -O3 -march=skylake -fno-trapping-math -S borrar.cpp -o-
.file "borrar.cpp"
.text
.p2align 4
.globl _Z3KeyRK6TVec3D
.type _Z3KeyRK6TVec3D, @function
_Z3KeyRK6TVec3D:
.LFB1032:
.cfi_startproc
vmovsd BinSize(%rip), %xmm2
vmovupd (%rdi), %xmm0
vmovddup %xmm2, %xmm1
vdivpd %xmm1, %xmm0, %xmm0
vmovddup .LC1(%rip), %xmm1
vaddpd %xmm1, %xmm0, %xmm0
vmovq .LC2(%rip), %xmm1
vcvtpd2psx %xmm0, %xmm0
vaddps %xmm1, %xmm0, %xmm0
vroundps $9, %xmm0, %xmm0
vcvttps2dq %xmm0, %xmm0
vmovq %xmm0, %rdx
vmovsd 16(%rdi), %xmm0
vdivsd %xmm2, %xmm0, %xmm0
vaddsd .LC1(%rip), %xmm0, %xmm0
vcvtsd2ss %xmm0, %xmm0, %xmm0
vsubss .LC3(%rip), %xmm0, %xmm0
vroundss $9, %xmm0, %xmm0, %xmm0
vcvttss2sil %xmm0, %eax
movl %eax, %eax
movq %rax, %rdi
movq %rdx, %rax
movq %rdi, %rdx
ret
.cfi_endproc
.LFE1032:
.size _Z3KeyRK6TVec3D, .-_Z3KeyRK6TVec3D
.section .rodata.cst8,"aM",@progbits,8
.align 8
.LC1:
.long 0
.long 1072693248
.align 8
.LC2:
.long -1082130432
.long -1082130432
.section .rodata.cst4,"aM",@progbits,4
.align 4
.LC3:
.long 1065353216
.ident "GCC: (GNU) 14.0.0 20240112 (experimental)"
.section .note.GNU-stack,"",@progbits
