对于x86-64,哪个更快,imm64还是m64?

在测试大约100亿次后,如果 imm64 比0.1纳秒快 m64 m64 似乎更快,但我真的不明白。不是的地址吗 val_ptr 在下面的代码中,立即数本身?

# Text section
.section __TEXT,__text,regular,pure_instructions
# 64-bit code
.code64
# Intel syntax
.intel_syntax noprefix
# Target macOS High Sierra
.macosx_version_min 10,13,0

# Make those two test functions global for the C measurer
.globl _test1
.globl _test2

# Test 1, imm64
_test1:
  # Move the immediate value 0xDEADBEEFFEEDFACE to RAX (return value)
  movabs rax, 0xDEADBEEFFEEDFACE
  ret
# Test 2, m64
_test2:
  # Move from the RAM (val_ptr) to RAX (return value)
  mov rax, qword ptr [rip + val_ptr]
  ret
# Data section
.section __DATA,__data
val_ptr:
  .quad 0xDEADBEEFFEEDFACE

#include <stdio.h>            // For printf
#include <stdlib.h>           // For EXIT_SUCCESS
#include <math.h>             // For fabs
#include <stdint.h>           // For uint64_t
#include <stddef.h>           // For size_t
#include <string.h>           // For memset
#include <mach/mach_time.h>   // For time stuff

#define FUNCTION_COUNT  2     // Number of functions to test
#define TEST_COUNT      0x10000000  // Number of times to test each function

// Type aliases
typedef uint64_t rettype_t;
typedef rettype_t(*function_t)();

// External test functions (defined in Assembly)
rettype_t test1();
rettype_t test2();

// Program entry point
int main() {

  // Time measurement stuff
  mach_timebase_info_data_t info;
  mach_timebase_info(&info);

  // Sums to divide by the test count to get average
  double sums[FUNCTION_COUNT];

  // Initialize sums to 0
  memset(&sums, 0, FUNCTION_COUNT * sizeof (double));

  // Functions to test
  function_t functions[FUNCTION_COUNT] = {test1, test2};

  // Useless results (should be 0xDEADBEEFFEEDFACE), but good to have
  rettype_t results[FUNCTION_COUNT];

  // Function loop, may get unrolled based on optimization level
  for (size_t test_fn = 0; test_fn < FUNCTION_COUNT; test_fn++) {
    // Test this MANY times
    for (size_t test_num = 0; test_num < TEST_COUNT; test_num++) {
      // Get the nanoseconds before the action
      double nanoseconds = mach_absolute_time();
      // Do the action
      results[test_fn] = functions[test_fn]();
      // Measure the time it took
      nanoseconds = mach_absolute_time() - nanoseconds;

      // Convert it to nanoseconds
      nanoseconds *= info.numer;
      nanoseconds /= info.denom;

      // Add the nanosecond count to the sum
      sums[test_fn] += nanoseconds;
    }
  }
  // Compute the average
  for (size_t i = 0; i < FUNCTION_COUNT; i++) {
    sums[i] /= TEST_COUNT;
  }

  if (FUNCTION_COUNT == 2) {
    // Print some fancy information
    printf("Test 1 took %f nanoseconds average.\n", sums[0]);
    printf("Test 2 took %f nanoseconds average.\n", sums[1]);
    printf("Test %d was faster, with %f nanoseconds difference\n", sums[0] < sums[1] ? 1 : 2, fabs(sums[0] - sums[1]));
  } else {
    // Else, just print something
    for (size_t fn_i = 0; fn_i < FUNCTION_COUNT; fn_i++) {
      printf("Test %zu took %f clock ticks average.\n", fn_i + 1, sums[fn_i]);
    }
  }

  // Everything went fine!
  return EXIT_SUCCESS;
}

那么,哪一个真的是最快的, 或 imm64 ?

编辑 ret 说明,现在 imm64