Andrew Pinski wrote:
> Here is a much better benchmark to try, notice that we are doing more
> work now but the point is that ICC is going to be the transformation
> and it not going to see that doit is constant so it will not pull it
> out of the loop and it cannot unroll the loop into just being a
> constant.
Intel does *not* unroll the original code into a constnt. To wit, the
code generated on my system:
.globl main
main:
..B1.1: # Preds ..B1.0
pushl %ebx #14.1
movl %esp, %ebx #14.1
andl $-64, %esp #14.1
pushl %edi #14.1
subl $60, %esp #14.1
call __intel_proc_init_N #14.1
pushl %eax #14.1
pushl %eax #14.1
stmxcsr (%esp) #14.1
popl %eax #14.1
orl $32768, %eax #14.1
pushl %eax #14.1
ldmxcsr (%esp) #14.1
popl %eax #14.1
popl %eax #14.1
movapd _2il0floatpacket.1, %xmm0 #18.14
xorl %edi, %edi #17.5
pxor %xmm1, %xmm1 #
movapd %xmm1, 16(%esp) #
call vmldSin2 #18.14
# LOE ebp esi edi xmm0
..B1.7: # Preds ..B1.1
movapd %xmm0, 32(%esp) #18.14
movapd _2il0floatpacket.1, %xmm0 #18.14
call vmldCos2 #18.14
# LOE ebp esi edi xmm0
..B1.8: # Preds ..B1.7
mulpd %xmm0, %xmm0 #18.14
movapd 32(%esp), %xmm1 #18.14
mulpd %xmm1, %xmm1 #18.14
movapd 16(%esp), %xmm2 #18.14
movapd %xmm1, 32(%esp) #18.14
movapd 32(%esp), %xmm1 #18.14
.align 4,0x90
# LOE ebp esi edi xmm0 xmm1 xmm2
..B1.2: # Preds ..B1.8 ..B1.2
addpd %xmm1, %xmm2 #18.9
addpd %xmm0, %xmm2 #18.14
addl $2, %edi #17.5
cmpl $100000000, %edi #17.5
jb ..B1.2 # Prob 100% #17.5
# LOE ebp esi edi xmm0 xmm1 xmm2
..B1.3: # Preds ..B1.2
movapd %xmm2, 16(%esp) #
movapd 16(%esp), %xmm1 #17.5
movapd %xmm1, %xmm0 #17.5
unpckhpd %xmm0, %xmm0 #17.5
addsd %xmm0, %xmm1 #
movl $__STRING.0, (%esp) #20.12
movsd %xmm1, 4(%esp) #20.23
call printf #20.5
# LOE ebp esi
..B1.4: # Preds ..B1.3
xorl %eax, %eax #21.12
addl $60, %esp #21.12
popl %edi #21.12
movl %ebx, %esp #21.12
popl %ebx #21.12
ret #21.12
I made some minor mention of this in the original post, but it was
likely too vague for you.
--
Scott Robert Ladd
Coyote Gulch Productions (http://www.coyotegulch.com)
Software Invention for High-Performance Computing