https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66986
Andrew Pinski <pinskia at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Resolution|--- |INVALID
Status|UNCONFIRMED |RESOLVED
--- Comment #6 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Your defined isinf2 is incorrect:
int I2
isinf2 (double dx)
{
unsigned long x;
memcpy(&x, &dx, sizeof(dx));
if (2 * x == 0xffe0000000000000)
return 0;
else
return (int) (x >> 32);
}
With that change, the GCC version that is produced is faster.
isinf2:
.LFB22:
.cfi_startproc
#APP
# 19 "/app/example.cpp" 1
movq %xmm0, %rax
# 0 "" 2
#NO_APP
movabsq $-9007199254740992, %rdx
leaq (%rax,%rax), %rcx
shrq $32, %rax
cmpq %rdx, %rcx
movl $0, %edx
cmove %edx, %eax
ret
vs
isinf2:
.LFB22:
.cfi_startproc
xorl %eax, %eax
andpd .LC0(%rip), %xmm0
ucomisd .LC1(%rip), %xmm0
seta %al
ret
For the inlined inlined case (for the T1):
.L15:
movsd (%rax), %xmm0
addsd %xmm4, %xmm0
andpd %xmm3, %xmm0
ucomisd %xmm2, %xmm0
jbe .L14
addsd %xmm5, %xmm1
.L14:
addq $8, %rax
cmpq %rax, %rdx
jne .L15
vs
.L19:
movsd (%rax), %xmm3
addsd %xmm0, %xmm3
movq %xmm3, %rdx
leaq (%rdx,%rdx), %rcx
cmpq %rdi, %rcx
je .L18
shrq $32, %rdx
testl %edx, %edx
je .L18
addsd %xmm2, %xmm1
.L18:
addq $8, %rax
cmpq %rsi, %rax
jne .L19
A double jump
