C vs C++ size/speed benchmark

CvsCppBenchmark.txt

GCC-generated code for searching 1000 first primes:

.LC0:
  .string "2 "
.LC1:
  .string "%d "
.LC2:
  .string "Time elapsed: %d"
primes:
  pushq %rbp
  movq %rsp, %rbp
  subq $32, %rsp
  movl $0, %edi
  movl $0, %eax
  call time
  movl %eax, -16(%rbp)
  movl $.LC0, %edi
  movl $0, %eax
  call printf
  movl $3, -4(%rbp)
  movl $0, -8(%rbp)
  movl $2, -12(%rbp)
  jmp .L2
.L8:
  movl $2, -8(%rbp)
  jmp .L3
.L6:
  movl -4(%rbp), %eax
  cltd
  idivl -8(%rbp)
  movl %edx, %eax
  testl %eax, %eax
  je .L9
  addl $1, -8(%rbp)
.L3:
  movl -4(%rbp), %eax
  subl $1, %eax
  cmpl %eax, -8(%rbp)
  jle .L6
  jmp .L5
.L9:
  nop
.L5:
  movl -8(%rbp), %eax
  cmpl -4(%rbp), %eax
  jne .L7
  movl -4(%rbp), %eax
  movl %eax, %esi
  movl $.LC1, %edi
  movl $0, %eax
  call printf
  addl $1, -12(%rbp)
.L7:
  addl $1, -4(%rbp)
.L2:
  cmpl $1000, -12(%rbp)
  jle .L8
  movl $0, %edi
  movl $0, %eax
  call time
  movl %eax, -20(%rbp)
  movl -20(%rbp), %eax
  subl -16(%rbp), %eax
  movl %eax, %esi
  movl $.LC2, %edi
  movl $0, %eax
  call printf
  nop
  leave
  ret

G++ generated code for searching 1000 first primes (replaced printf with std::cout, without endl): 
_ZNKSt6chrono8durationIlSt5ratioILl1ELl1000000000EEE5countEv:
  pushq %rbp
  movq %rsp, %rbp
  movq %rdi, -8(%rbp)
  movq -8(%rbp), %rax
  movq (%rax), %rax
  popq %rbp
  ret
_ZNSt6chrono8durationIlSt5ratioILl1ELl1000000000EEEC1IlvEERKT_:
  pushq %rbp
  movq %rsp, %rbp
  movq %rdi, -8(%rbp)
  movq %rsi, -16(%rbp)
  movq -16(%rbp), %rax
  movq (%rax), %rdx
  movq -8(%rbp), %rax
  movq %rdx, (%rax)
  nop
  popq %rbp
  ret
.LC0:
  .string "2 "
.LC1:
  .string " "
.LC2:
  .string "Time difference = "
_Z6primesv:
  pushq %rbp
  movq %rsp, %rbp
  pushq %rbx
  subq $56, %rsp
  call _ZNSt6chrono3_V212steady_clock3nowEv
  movq %rax, -56(%rbp)
  movl $.LC0, %esi
  movl $_ZSt4cout, %edi
  call _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKc
  movl $3, -20(%rbp)
  movl $0, -24(%rbp)
  movl $2, -28(%rbp)
.L10:
  cmpl $1000, -28(%rbp)
  jg .L5
  movl $2, -24(%rbp)
.L8:
  movl -20(%rbp), %eax
  subl $1, %eax
  cmpl %eax, -24(%rbp)
  jg .L6
  movl -20(%rbp), %eax
  cltd
  idivl -24(%rbp)
  movl %edx, %eax
  testl %eax, %eax
  je .L11
  addl $1, -24(%rbp)
  jmp .L8
.L11:
  nop
.L6:
  movl -24(%rbp), %eax
  cmpl -20(%rbp), %eax
  jne .L9
  movl -20(%rbp), %eax
  movl %eax, %esi
  movl $_ZSt4cout, %edi
  call _ZNSolsEi
  movl $.LC1, %esi
  movq %rax, %rdi
  call _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKc
  addl $1, -28(%rbp)
.L9:
  addl $1, -20(%rbp)
  jmp .L10
.L5:
  call _ZNSt6chrono3_V212steady_clock3nowEv
  movq %rax, -64(%rbp)
  movl $.LC2, %esi
  movl $_ZSt4cout, %edi
  call _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKc
  movq %rax, %rbx
  leaq -56(%rbp), %rdx
  leaq -64(%rbp), %rax
  movq %rdx, %rsi
  movq %rax, %rdi
  call _ZNSt6chronomiINS_3_V212steady_clockENS_8durationIlSt5ratioILl1ELl1000000000EEEES6_EENSt11common_typeIJT0_T1_EE4typeERKNS_10time_pointIT_S8_EERKNSC_ISD_S9_EE
  movq %rax, -40(%rbp)
  leaq -40(%rbp), %rax
  movq %rax, %rdi
  call _ZNSt6chrono13duration_castINS_8durationIlSt5ratioILl1ELl1000EEEElS2_ILl1ELl1000000000EEEENSt9enable_ifIXsrNS_13__is_durationIT_EE5valueES8_E4typeERKNS1_IT0_T1_EE
  movq %rax, -48(%rbp)
  leaq -48(%rbp), %rax
  movq %rax, %rdi
  call _ZNKSt6chrono8durationIlSt5ratioILl1ELl1000EEE5countEv
  movq %rax, %rsi
  movq %rbx, %rdi
  call _ZNSolsEl
  movl $_ZSt4endlIcSt11char_traitsIcEERSt13basic_ostreamIT_T0_ES6_, %esi
  movq %rax, %rdi
  call _ZNSolsEPFRSoS_E
  nop
  addq $56, %rsp
  popq %rbx
  popq %rbp
  ret
_ZNSt6chronomiINS_3_V212steady_clockENS_8durationIlSt5ratioILl1ELl1000000000EEEES6_EENSt11common_typeIJT0_T1_EE4typeERKNS_10time_pointIT_S8_EERKNSC_ISD_S9_EE:
  pushq %rbp
  movq %rsp, %rbp
  subq $32, %rsp
  movq %rdi, -24(%rbp)
  movq %rsi, -32(%rbp)
  movq -32(%rbp), %rax
  movq %rax, %rdi
  call _ZNKSt6chrono10time_pointINS_3_V212steady_clockENS_8durationIlSt5ratioILl1ELl1000000000EEEEE16time_since_epochEv
  movq %rax, -16(%rbp)
  movq -24(%rbp), %rax
  movq %rax, %rdi
  call _ZNKSt6chrono10time_pointINS_3_V212steady_clockENS_8durationIlSt5ratioILl1ELl1000000000EEEEE16time_since_epochEv
  movq %rax, -8(%rbp)
  leaq -16(%rbp), %rdx
  leaq -8(%rbp), %rax
  movq %rdx, %rsi
  movq %rax, %rdi
  call _ZNSt6chronomiIlSt5ratioILl1ELl1000000000EElS2_EENSt11common_typeIJNS_8durationIT_T0_EENS4_IT1_T2_EEEE4typeERKS7_RKSA_
  leave
  ret
_ZNSt6chrono13duration_castINS_8durationIlSt5ratioILl1ELl1000EEEElS2_ILl1ELl1000000000EEEENSt9enable_ifIXsrNS_13__is_durationIT_EE5valueES8_E4typeERKNS1_IT0_T1_EE:
  pushq %rbp
  movq %rsp, %rbp
  subq $16, %rsp
  movq %rdi, -8(%rbp)
  movq -8(%rbp), %rax
  movq %rax, %rdi
  call _ZNSt6chrono20__duration_cast_implINS_8durationIlSt5ratioILl1ELl1000EEEES2_ILl1ELl1000000EElLb1ELb0EE6__castIlS2_ILl1ELl1000000000EEEES4_RKNS1_IT_T0_EE
  leave
  ret
_ZNKSt6chrono8durationIlSt5ratioILl1ELl1000EEE5countEv:
  pushq %rbp
  movq %rsp, %rbp
  movq %rdi, -8(%rbp)
  movq -8(%rbp), %rax
  movq (%rax), %rax
  popq %rbp
  ret
_ZNKSt6chrono10time_pointINS_3_V212steady_clockENS_8durationIlSt5ratioILl1ELl1000000000EEEEE16time_since_epochEv:
  pushq %rbp
  movq %rsp, %rbp
  movq %rdi, -8(%rbp)
  movq -8(%rbp), %rax
  movq (%rax), %rax
  popq %rbp
  ret
_ZNSt6chronomiIlSt5ratioILl1ELl1000000000EElS2_EENSt11common_typeIJNS_8durationIT_T0_EENS4_IT1_T2_EEEE4typeERKS7_RKSA_:
  pushq %rbp
  movq %rsp, %rbp
  pushq %rbx
  subq $56, %rsp
  movq %rdi, -56(%rbp)
  movq %rsi, -64(%rbp)
  movq -56(%rbp), %rax
  movq (%rax), %rax
  movq %rax, -32(%rbp)
  leaq -32(%rbp), %rax
  movq %rax, %rdi
  call _ZNKSt6chrono8durationIlSt5ratioILl1ELl1000000000EEE5countEv
  movq %rax, %rbx
  movq -64(%rbp), %rax
  movq (%rax), %rax
  movq %rax, -24(%rbp)
  leaq -24(%rbp), %rax
  movq %rax, %rdi
  call _ZNKSt6chrono8durationIlSt5ratioILl1ELl1000000000EEE5countEv
  subq %rax, %rbx
  movq %rbx, %rax
  movq %rax, -40(%rbp)
  leaq -40(%rbp), %rdx
  leaq -48(%rbp), %rax
  movq %rdx, %rsi
  movq %rax, %rdi
  call _ZNSt6chrono8durationIlSt5ratioILl1ELl1000000000EEEC1IlvEERKT_
  movq -48(%rbp), %rax
  addq $56, %rsp
  popq %rbx
  popq %rbp
  ret
_ZNSt6chrono20__duration_cast_implINS_8durationIlSt5ratioILl1ELl1000EEEES2_ILl1ELl1000000EElLb1ELb0EE6__castIlS2_ILl1ELl1000000000EEEES4_RKNS1_IT_T0_EE:
  pushq %rbp
  movq %rsp, %rbp
  subq $32, %rsp
  movq %rdi, -24(%rbp)
  movq -24(%rbp), %rax
  movq %rax, %rdi
  call _ZNKSt6chrono8durationIlSt5ratioILl1ELl1000000000EEE5countEv
  movq %rax, %rcx
  movabsq $4835703278458516699, %rdx
  movq %rcx, %rax
  imulq %rdx
  sarq $18, %rdx
  movq %rcx, %rax
  sarq $63, %rax
  subq %rax, %rdx
  movq %rdx, %rax
  movq %rax, -8(%rbp)
  leaq -8(%rbp), %rdx
  leaq -16(%rbp), %rax
  movq %rdx, %rsi
  movq %rax, %rdi
  call _ZNSt6chrono8durationIlSt5ratioILl1ELl1000EEEC1IlvEERKT_
  movq -16(%rbp), %rax
  leave
  ret
_ZNSt6chrono8durationIlSt5ratioILl1ELl1000EEEC2IlvEERKT_:
  pushq %rbp
  movq %rsp, %rbp
  movq %rdi, -8(%rbp)
  movq %rsi, -16(%rbp)
  movq -16(%rbp), %rax
  movq (%rax), %rdx
  movq -8(%rbp), %rax
  movq %rdx, (%rax)
  nop
  popq %rbp
  ret
_Z41__static_initialization_and_destruction_0ii:
  pushq %rbp
  movq %rsp, %rbp
  subq $16, %rsp
  movl %edi, -4(%rbp)
  movl %esi, -8(%rbp)
  cmpl $1, -4(%rbp)
  jne .L27
  cmpl $65535, -8(%rbp)
  jne .L27
  movl $_ZStL8__ioinit, %edi
  call _ZNSt8ios_base4InitC1Ev
  movl $__dso_handle, %edx
  movl $_ZStL8__ioinit, %esi
  movl $_ZNSt8ios_base4InitD1Ev, %edi
  call __cxa_atexit
.L27:
  nop
  leave
  ret
_GLOBAL__sub_I__Z6primesv:
  pushq %rbp
  movq %rsp, %rbp
  movl $65535, %esi
  movl $1, %edi
  call _Z41__static_initialization_and_destruction_0ii
  popq %rbp
  ret

GCC-generated code is 3.7 times smaller. Let's check speed of these:
Original C++ version: http://coliru.stacked-crooked.com/a/529a40c04415f34c, execution time: 24 ms
Original C version: http://coliru.stacked-crooked.com/a/b7c10ad54707d226, execution time: 0 ms (propably too fast to even record, while generating 10 times more primes, execution time is 2ms)