https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100855
--- Comment #5 from Nadav Halahmi <nadavhalahmi560 at gmail dot com> ---
(In reply to Richard Biener from comment #3)
> Might be interesting to see whether ifort does any expression simplification
> here. Can you share the produced assembly?
ifort pow.f90 -O3 -no-vec -S -o intel.s:
# mark_description "Intel(R) Fortran Intel(R) 64 Compiler for applications
running on Intel(R) 64, Version 19.1.3.304 Build 2020";
# mark_description "0925_000000";
# mark_description "-O3 -no-vec -S -o intel.s";
.file "pow.f90"
.text
..TXTST0:
.L_2__routine_start_MAIN___0:
# -- Begin MAIN__
.text
# mark_begin;
.align 16,0x90
.globl MAIN__
# --- POWER
MAIN__:
..B1.1: # Preds ..B1.0
# Execution count [1.00e+00]
.cfi_startproc
..___tag_value_MAIN__.1:
..L2:
#1.9
pushq %rbp #1.9
.cfi_def_cfa_offset 16
movq %rsp, %rbp #1.9
.cfi_def_cfa 6, 16
.cfi_offset 6, -16
andq $-128, %rsp #1.9
subq $128, %rsp #1.9
movl $3, %edi #1.9
xorl %esi, %esi #1.9
call __intel_new_feature_proc_init #1.9
# LOE rbx r12 r13 r14 r15
..B1.13: # Preds ..B1.1
# Execution count [1.00e+00]
stmxcsr (%rsp) #1.9
movl $__NLITPACK_0.0.1, %edi #1.9
orl $32832, (%rsp) #1.9
ldmxcsr (%rsp) #1.9
call for_set_reentrancy #1.9
# LOE rbx r12 r13 r14 r15
..B1.2: # Preds ..B1.13
# Execution count [1.00e+00]
movss .L_2il0floatpacket.0(%rip), %xmm1 #11.5
lea 80(%rsp), %rdi #13.10
movss %xmm1, -64(%rdi) #11.5[spill]
pxor %xmm0, %xmm0 #9.5
movss %xmm0, -8(%rdi) #9.5[spill]
call for_cpusec #13.10
# LOE rbx r12 r13 r14 r15
..B1.3: # Preds ..B1.2
# Execution count [8.67e-01]
movl $1, %eax #14.5
movq %r15, (%rsp) #12.5[spill]
movq %rbx, 8(%rsp) #12.5[spill]
.cfi_escape 0x10, 0x03, 0x0e, 0x38, 0x1c, 0x0d, 0x80, 0xff, 0xff, 0xff,
0x1a, 0x0d, 0x88, 0xff, 0xff, 0xff, 0x22
.cfi_escape 0x10, 0x0f, 0x0e, 0x38, 0x1c, 0x0d, 0x80, 0xff, 0xff, 0xff,
0x1a, 0x0d, 0x80, 0xff, 0xff, 0xff, 0x22
movl %eax, %ebx #12.5
# LOE r12 r13 r14 ebx
..B1.4: # Preds ..B1.6 ..B1.3
# Execution count [5.33e+00]
movl $1, %r15d #15.9
# LOE r12 r13 r14 ebx r15d
..B1.5: # Preds ..B1.14 ..B1.4
# Execution count [2.96e+01]
movss 16(%rsp), %xmm2 #16.13[spill]
pxor %xmm0, %xmm0 #17.28
mulss .L_2il0floatpacket.1(%rip), %xmm2 #16.13
cvtsi2ss %r15d, %xmm0 #17.28
movss .L_2il0floatpacket.2(%rip), %xmm1 #17.28
movss %xmm2, 16(%rsp) #16.13[spill]
addss %xmm2, %xmm1 #17.28
call powf #17.28
# LOE r12 r13 r14 ebx r15d xmm0
..B1.14: # Preds ..B1.5
# Execution count [2.96e+01]
movss 72(%rsp), %xmm1 #17.13[spill]
incl %r15d #18.9
addss %xmm0, %xmm1 #17.13
movss %xmm1, 72(%rsp) #17.13[spill]
cmpl $10000, %r15d #18.9
jle ..B1.5 # Prob 82% #18.9
# LOE r12 r13 r14 ebx r15d
..B1.6: # Preds ..B1.14
# Execution count [5.44e+00]
incl %ebx #19.5
cmpl $10000, %ebx #19.5
jle ..B1.4 # Prob 82% #19.5
# LOE r12 r13 r14 ebx
..B1.7: # Preds ..B1.6
# Execution count [1.00e+00]
movq (%rsp), %r15 #[spill]
.cfi_restore 15
lea 84(%rsp), %rdi #20.10
movq 8(%rsp), %rbx #[spill]
.cfi_restore 3
call for_cpusec #20.10
.cfi_escape 0x10, 0x03, 0x0e, 0x38, 0x1c, 0x0d, 0x80, 0xff, 0xff, 0xff,
0x1a, 0x0d, 0x88, 0xff, 0xff, 0xff, 0x22
.cfi_escape 0x10, 0x0f, 0x0e, 0x38, 0x1c, 0x0d, 0x80, 0xff, 0xff, 0xff,
0x1a, 0x0d, 0x80, 0xff, 0xff, 0xff, 0x22
# LOE rbx r12 r13 r14 r15
..B1.8: # Preds ..B1.7
# Execution count [1.00e+00]
movss 72(%rsp), %xmm0 #21.5[spill]
lea (%rsp), %rdi #21.5
movl $-1, %esi #21.5
movq $0x1208384ff00, %rdx #21.5
movl $__STRLITPACK_3.0.1, %ecx #21.5
lea 64(%rsp), %r8 #21.5
xorl %eax, %eax #21.5
movq $0, (%rdi) #21.5
movss %xmm0, 64(%rdi) #21.5
call for_write_seq_lis #21.5
# LOE rbx r12 r13 r14 r15
..B1.9: # Preds ..B1.8
# Execution count [1.00e+00]
movss 84(%rsp), %xmm0 #22.5
lea (%rsp), %rdi #22.5
movl $-1, %esi #22.5
movq $0x1208384ff00, %rdx #22.5
movl $__STRLITPACK_4.0.1, %ecx #22.5
lea 72(%rsp), %r8 #22.5
movl $power_$format_pack.0.1, %r9d #22.5
xorl %eax, %eax #22.5
movq $0, (%rdi) #22.5
subss 80(%rdi), %xmm0 #22.5
movss %xmm0, 72(%rdi) #22.5
call for_write_seq_fmt #22.5
# LOE rbx r12 r13 r14 r15
..B1.10: # Preds ..B1.9
# Execution count [1.00e+00]
xorl %eax, %eax #23.1
movq %rbp, %rsp #23.1
popq %rbp #23.1
.cfi_def_cfa 7, 8
.cfi_restore 6
ret #23.1
.align 16,0x90
# LOE
.cfi_endproc
# mark_end;
.type MAIN__,@function
.size MAIN__,.-MAIN__
..LNMAIN__.0:
.section .rodata, "a"
.align 4
.align 4
__NLITPACK_0.0.1:
.long 2
.align 4
__STRLITPACK_3.0.1:
.long 65818
.byte 0
.space 3, 0x00 # pad
.align 4
__STRLITPACK_4.0.1:
.long 65818
.byte 0
.space 3, 0x00 # pad
.align 4
power_$format_pack.0.1:
.byte 54
.byte 0
.byte 0
.byte 0
.byte 28
.byte 0
.byte 7
.byte 0
.byte 84
.byte 105
.byte 109
.byte 101
.byte 32
.byte 61
.byte 32
.byte 0
.byte 33
.byte 0
.byte 0
.byte 3
.byte 1
.byte 0
.byte 0
.byte 0
.byte 6
.byte 0
.byte 0
.byte 0
.byte 28
.byte 0
.byte 9
.byte 0
.byte 32
.byte 115
.byte 101
.byte 99
.byte 111
.byte 110
.byte 100
.byte 115
.byte 46
.byte 0
.byte 0
.byte 0
.byte 55
.byte 0
.byte 0
.byte 0
.data
# -- End MAIN__
.section .rodata, "a"
.align 4
.L_2il0floatpacket.0:
.long 0x40000000
.type .L_2il0floatpacket.0,@object
.size .L_2il0floatpacket.0,4
.align 4
.L_2il0floatpacket.1:
.long 0x3f000000
.type .L_2il0floatpacket.1,@object
.size .L_2il0floatpacket.1,4
.align 4
.L_2il0floatpacket.2:
.long 0x3d4ccccd
.type .L_2il0floatpacket.2,@object
.size .L_2il0floatpacket.2,4
.data
.section .note.GNU-stack, ""
# End
