准确了解如何以汇编语言实现提高的效率

Question

I have generated two assembly files - one that is optimized, and one that is not. The assembly-language code generated with optimization on should be more efficient than the other assembly-language code. I am more interested in how the efficiency is achieved. To my understanding, in the non-optimized version there will always have to be an offset call to the register %rbp to find the address. In the optimized version, the addresses are being stored in the registers, so you don't have to rely and call on %rbp to find them.

Am I correct? And if so, would there ever be a time when the optimized version will not be advantageous? Thank you for your time.

Here is a function that converts from 42 GIF to CYMK.

void rgb2cmyk(int r, int g, int b, int ret[]) {
int c = 255 - r;
int m = 255 - g;
int y = 255 - b;
int k = (c < m) ? (c < y ? c : y) : (m < y ? m : y);
c -= k; m -= k; y -= k;
ret[0] = c; ret[1] = m; ret[2] = y; ret[3] = k;
}

Here is the assembly-language code that has not been optimized. Note I have made notes using ;; in the code.

No Opt:

   .section   __TEXT,__text,regular,pure_instructions
   .globl   _rgb2cmyk
   .align   4, 0x90
_rgb2cmyk: ## @rgb2cmyk
   .cfi_startproc
## BB#0:
   pushq   %rbp
Ltmp2:
   .cfi_def_cfa_offset 16
Ltmp3:
   .cfi_offset %rbp, -16
   movq   %rsp, %rbp
Ltmp4:
   .cfi_def_cfa_register %rbp
   ;;initializing variable c, m, y
   movl   $255, %eax
   movl   %edi, -4(%rbp)
   movl   %esi, -8(%rbp)
   movl   %edx, -12(%rbp)
   movq   %rcx, -24(%rbp)
   movl   %eax, %edx
   subl   -4(%rbp), %edx
   movl   %edx, -28(%rbp)
   movl   %eax, %edx
   subl   -8(%rbp), %edx
   movl   %edx, -32(%rbp)
   subl   -12(%rbp), %eax
   movl   %eax, -36(%rbp)

   movl   -28(%rbp), %eax
   ;;compare
   cmpl   -32(%rbp), %eax
   jge   LBB0_5
## BB#1:
   movl   -28(%rbp), %eax
   cmpl   -36(%rbp), %eax
   jge   LBB0_3
## BB#2:
   movl   -28(%rbp), %eax
   movl   %eax, -44(%rbp) ## 4-byte Spill
   jmp   LBB0_4
LBB0_3:
   movl   -36(%rbp), %eax
   movl   %eax, -44(%rbp) ## 4-byte Spill
LBB0_4:
   movl   -44(%rbp), %eax ## 4-byte Reload
   movl   %eax, -48(%rbp) ## 4-byte Spill
   jmp   LBB0_9
LBB0_5:
   movl   -32(%rbp), %eax
   cmpl   -36(%rbp), %eax
   jge   LBB0_7
## BB#6:
   movl   -32(%rbp), %eax
   movl   %eax, -52(%rbp) ## 4-byte Spill
   jmp   LBB0_8
LBB0_7:
   movl   -36(%rbp), %eax
   movl   %eax, -52(%rbp) ## 4-byte Spill
LBB0_8:
   movl   -52(%rbp), %eax ## 4-byte Reload
   movl   %eax, -48(%rbp) ## 4-byte Spill
LBB0_9:
   movl   -48(%rbp), %eax ## 4-byte Reload
   movl   %eax, -40(%rbp)
   movl   -40(%rbp), %eax
   movl   -28(%rbp), %ecx
   subl   %eax, %ecx
   movl   %ecx, -28(%rbp)
   movl   -40(%rbp), %eax
   movl   -32(%rbp), %ecx
   subl   %eax, %ecx
   movl   %ecx, -32(%rbp)
   movl   -40(%rbp), %eax
   movl   -36(%rbp), %ecx
   subl   %eax, %ecx
   movl   %ecx, -36(%rbp)
   movl   -28(%rbp), %eax
   movq   -24(%rbp), %rdx
   movl   %eax, (%rdx)
   movl   -32(%rbp), %eax
   movq   -24(%rbp), %rdx
   movl   %eax, 4(%rdx)
   movl   -36(%rbp), %eax
   movq   -24(%rbp), %rdx
   movl   %eax, 8(%rdx)
   movl   -40(%rbp), %eax
   movq   -24(%rbp), %rdx
   movl   %eax, 12(%rdx)
   popq   %rbp
   retq
   .cfi_endproc


.subsections_via_symbols

Optimization:

   .section   __TEXT,__text,regular,pure_instructions
   .globl   _rgb2cmyk
   .align   4, 0x90
_rgb2cmyk: ## @rgb2cmyk
   .cfi_startproc
## BB#0:
   pushq   %rbp
Ltmp2:
   .cfi_def_cfa_offset 16
Ltmp3:
   .cfi_offset %rbp, -16
   movq   %rsp, %rbp
Ltmp4:
   .cfi_def_cfa_register %rbp
   movl   $255, %r8d
   movl   $255, %eax
   subl   %edi, %eax
   movl   $255, %edi
   subl   %esi, %edi
   subl   %edx, %r8d
   cmpl   %edi, %eax ##;; compare m and c
   jge   LBB0_2
## BB#1: ;; c < m
   cmpl   %r8d, %eax ## compare y and c
   movl   %r8d, %edx
   cmovlel   %eax, %edx
   jmp   LBB0_3
LBB0_2: ##;; c >= m
   cmpl   %r8d, %edi ## compare y and m
   movl   %r8d, %edx
   cmovlel   %edi, %edx
LBB0_3:
   subl   %edx, %eax
   subl   %edx, %edi
   subl   %edx, %r8d
   movl   %eax, (%rcx)
   movl   %edi, 4(%rcx)
   movl   %r8d, 8(%rcx)
   movl   %edx, 12(%rcx)
   popq   %rbp
   retq
   .cfi_endproc


.subsections_via_symbols

Answer 1

Yes. The optimized version performs many fewer memory read operations by storing intermediate values in registers and not reloading them over and over.

You are using call wrong. It is a technical term that means to push a return address on the stack and branch to a new location for instructions. The term you mean is simply to use the register.

Can you think of a reason that longer, slower code is "better"?