https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79709
--- Comment #9 from Thomas Koenig <tkoenig at gcc dot gnu.org> ---
The generated code for the loop seems to be on par with what
clang and icc do, so that part is fixed.
Initialization is strange for icc. For clang, it really quite short:
foo: # @foo
.cfi_startproc
# BB#0:
vxorps %ymm2, %ymm2, %ymm2
vmovapd .LCPI0_0(%rip), %ymm8 # ymm8 =
[4.000000e+00,4.000000e+00,4.000000e+00,4.000000e+00]
vmovapd %ymm1, %ymm4
vmovapd %ymm0, %ymm5
.p2align 4, 0x90
.LBB0_1: # =>This I
vs. gcc:
foo:
.LFB0:
.cfi_startproc
vmovsd .LC0(%rip), %xmm2
vmovapd %ymm1, %ymm7
vpxor %xmm5, %xmm5, %xmm5
vmovq %xmm2, %xmm9
vmulpd %ymm1, %ymm1, %ymm10
vmovapd %xmm9, %xmm9
vunpcklpd %xmm2, %xmm9, %xmm3
vinsertf128 $0x0, %xmm3, %ymm9, %ymm9
vextractf128 $0x1, %ymm9, %xmm3
vmovsd %xmm2, %xmm3, %xmm3
vinsertf128 $0x1, %xmm3, %ymm9, %ymm9
vextractf128 $0x1, %ymm9, %xmm3
vunpcklpd %xmm2, %xmm3, %xmm3
vmovsd .LC1(%rip), %xmm2
vmovq %xmm2, %xmm8
vinsertf128 $0x1, %xmm3, %ymm9, %ymm9
vmovapd %xmm8, %xmm8
vunpcklpd %xmm2, %xmm8, %xmm3
vinsertf128 $0x0, %xmm3, %ymm8, %ymm8
vextractf128 $0x1, %ymm8, %xmm3
vmovsd %xmm2, %xmm3, %xmm3
vinsertf128 $0x1, %xmm3, %ymm8, %ymm8
vextractf128 $0x1, %ymm8, %xmm3
vunpcklpd %xmm2, %xmm3, %xmm3
vinsertf128 $0x1, %xmm3, %ymm8, %ymm8
vmovapd %ymm0, %ymm3
jmp .L3
.p2align 4,,10
.p2align 3
.L13:
