我正在尝试使用PAPI库来计算高速缓存未命中数。高速缓存命中性能计数器在我的硬件上不可用，这就是为什么我试图确定没有高速缓存未命中的高速缓存命中的原因。我正在尝试一些事情。我的代码的第一个版本是这样的：
int numEvents = 2;
long long values[2];
int events[2] = {PAPI_L1_DCM, PAPI_L2_TCM};
if (PAPI_start_counters(events, numEvents) != PAPI_OK ) // !=PAPI_OK
printf("PAPI error: %d\n", 1);
for(int i=0; i < arr_size; i++)
{
array[i].value = 1;
}
_mm_mfence();
if ((ret1 = PAPI_read_counters(values, numEvents)) != PAPI_OK) {
fprintf(stderr, "PAPI failed to read counters: %s\n", PAPI_strerror(ret1));
exit(1);
}
miss1 = values[0];
_mm_mfence();
for(int i=0; i < arr_size; i++){
array[i].value = array[i].value + 9; // (int) sum
}
_mm_mfence();
if ((ret2 = PAPI_read_counters(values, numEvents)) != PAPI_OK) {
fprintf(stderr, "PAPI failed to read counters: %s\n", PAPI_strerror(ret2));
exit(1);
}
miss2 = values[0];
printf("before flush miss_1 %lli, miss_2 %lli \n", miss1, miss2);
问题是这段代码应该给我带来高速缓存命中，因此L1高速缓存未命中率应该非常低。但是我对miss_2的结果出乎意料的高。在数组大小为200的情况下，miss_2接近100。由于高速缓存未命中的次数很高，因此无法给出任何有效的结果来判断它是否确实被命中。
我也试图像这样重写它：
if (PAPI_start_counters(events, numEvents) != PAPI_OK ) // !=PAPI_OK
printf("PAPI error: %d\n", 1);
for(int i=0; i < arr_size; i++){
array[i].value = array[i].value + 9; // (int) sum
}
if ( PAPI_stop_counters(values, numEvents) != PAPI_OK)
printf("PAPI error: 2\n");
printf("before flush miss %lli\n", values[0]);
但是这给出的结果甚至更糟，miss_2大于200。我在做错什么吗？本来可以给出更精确的结果，但是现在做起来很糟糕。或者我缺少什么。
我尝试过没有围栏，我相信至少它们不会造成任何伤害。我真的很感谢任何建议。
PAPI_read_counters的缺点是开销大，并且性能不佳，但是现在我不在乎性能，我想正确确定高速缓存命中率。
尽管我也曾在考虑使用RDMPC，但是我没有找到没有覆盖_asm函数的示例。这真的是使用rdpmc的唯一方法吗？没有已经定义的函数，我将不必覆盖它？
编辑： 为PAPI_read添加编译器代码
./prog6: file format elf64-x86-64
Disassembly of section .init:
00000000000009c0 <_init>:
9c0: 48 83 ec 08 sub $0x8,%rsp
9c4: 48 8b 05 1d 16 20 00 mov 0x20161d(%rip),%rax # 201fe8 <__gmon_start__>
9cb: 48 85 c0 test %rax,%rax
9ce: 74 02 je 9d2 <_init+0x12>
9d0: ff d0 callq *%rax
9d2: 48 83 c4 08 add $0x8,%rsp
9d6: c3 retq
Disassembly of section .plt:
00000000000009e0 <.plt>:
9e0: ff 35 6a 15 20 00 pushq 0x20156a(%rip) # 201f50 <_GLOBAL_OFFSET_TABLE_+0x8>
9e6: ff 25 6c 15 20 00 jmpq *0x20156c(%rip) # 201f58 <_GLOBAL_OFFSET_TABLE_+0x10>
9ec: 0f 1f 40 00 nopl 0x0(%rax)
00000000000009f0 <puts@plt>:
9f0: ff 25 6a 15 20 00 jmpq *0x20156a(%rip) # 201f60 <puts@GLIBC_2.2.5>
9f6: 68 00 00 00 00 pushq $0x0
9fb: e9 e0 ff ff ff jmpq 9e0 <.plt>
0000000000000a00 <clock_gettime@plt>:
a00: ff 25 62 15 20 00 jmpq *0x201562(%rip) # 201f68 <clock_gettime@GLIBC_2.17>
a06: 68 01 00 00 00 pushq $0x1
a0b: e9 d0 ff ff ff jmpq 9e0 <.plt>
0000000000000a10 <getpid@plt>:
a10: ff 25 5a 15 20 00 jmpq *0x20155a(%rip) # 201f70 <getpid@GLIBC_2.2.5>
a16: 68 02 00 00 00 pushq $0x2
a1b: e9 c0 ff ff ff jmpq 9e0 <.plt>
0000000000000a20 <__stack_chk_fail@plt>:
a20: ff 25 52 15 20 00 jmpq *0x201552(%rip) # 201f78 <__stack_chk_fail@GLIBC_2.4>
a26: 68 03 00 00 00 pushq $0x3
a2b: e9 b0 ff ff ff jmpq 9e0 <.plt>
0000000000000a30 <PAPI_read_counters@plt>:
a30: ff 25 4a 15 20 00 jmpq *0x20154a(%rip) # 201f80 <PAPI_read_counters>
a36: 68 04 00 00 00 pushq $0x4
a3b: e9 a0 ff ff ff jmpq 9e0 <.plt>
0000000000000a40 <sched_setaffinity@plt>:
a40: ff 25 42 15 20 00 jmpq *0x201542(%rip) # 201f88 <sched_setaffinity@GLIBC_2.3.4>
a46: 68 05 00 00 00 pushq $0x5
a4b: e9 90 ff ff ff jmpq 9e0 <.plt>
0000000000000a50 <PAPI_start_counters@plt>:
a50: ff 25 3a 15 20 00 jmpq *0x20153a(%rip) # 201f90 <PAPI_start_counters>
a56: 68 06 00 00 00 pushq $0x6
a5b: e9 80 ff ff ff jmpq 9e0 <.plt>
0000000000000a60 <PAPI_stop_counters@plt>:
a60: ff 25 32 15 20 00 jmpq *0x201532(%rip) # 201f98 <PAPI_stop_counters>
a66: 68 07 00 00 00 pushq $0x7
a6b: e9 70 ff ff ff jmpq 9e0 <.plt>
0000000000000a70 <malloc@plt>:
a70: ff 25 2a 15 20 00 jmpq *0x20152a(%rip) # 201fa0 <malloc@GLIBC_2.2.5>
a76: 68 08 00 00 00 pushq $0x8
a7b: e9 60 ff ff ff jmpq 9e0 <.plt>
0000000000000a80 <PAPI_strerror@plt>:
a80: ff 25 22 15 20 00 jmpq *0x201522(%rip) # 201fa8 <PAPI_strerror>
a86: 68 09 00 00 00 pushq $0x9
a8b: e9 50 ff ff ff jmpq 9e0 <.plt>
0000000000000a90 <__printf_chk@plt>:
a90: ff 25 1a 15 20 00 jmpq *0x20151a(%rip) # 201fb0 <__printf_chk@GLIBC_2.3.4>
a96: 68 0a 00 00 00 pushq $0xa
a9b: e9 40 ff ff ff jmpq 9e0 <.plt>
0000000000000aa0 <getrusage@plt>:
aa0: ff 25 12 15 20 00 jmpq *0x201512(%rip) # 201fb8 <getrusage@GLIBC_2.2.5>
aa6: 68 0b 00 00 00 pushq $0xb
aab: e9 30 ff ff ff jmpq 9e0 <.plt>
0000000000000ab0 <exit@plt>:
ab0: ff 25 0a 15 20 00 jmpq *0x20150a(%rip) # 201fc0 <exit@GLIBC_2.2.5>
ab6: 68 0c 00 00 00 pushq $0xc
abb: e9 20 ff ff ff jmpq 9e0 <.plt>
0000000000000ac0 <fwrite@plt>:
ac0: ff 25 02 15 20 00 jmpq *0x201502(%rip) # 201fc8 <fwrite@GLIBC_2.2.5>
ac6: 68 0d 00 00 00 pushq $0xd
acb: e9 10 ff ff ff jmpq 9e0 <.plt>
0000000000000ad0 <__fprintf_chk@plt>:
ad0: ff 25 fa 14 20 00 jmpq *0x2014fa(%rip) # 201fd0 <__fprintf_chk@GLIBC_2.3.4>
ad6: 68 0e 00 00 00 pushq $0xe
adb: e9 00 ff ff ff jmpq 9e0 <.plt>
Disassembly of section .plt.got:
0000000000000ae0 <__cxa_finalize@plt>:
ae0: ff 25 12 15 20 00 jmpq *0x201512(%rip) # 201ff8 <__cxa_finalize@GLIBC_2.2.5>
ae6: 66 90 xchg %ax,%ax
Disassembly of section .text:
0000000000000af0 <main>:
af0: 41 57 push %r15
af2: b9 0f 00 00 00 mov $0xf,%ecx
af7: 41 56 push %r14
af9: 41 55 push %r13
afb: 41 54 push %r12
afd: 55 push %rbp
afe: 53 push %rbx
aff: 48 81 ec 78 01 00 00 sub $0x178,%rsp
b06: 64 48 8b 04 25 28 00 mov %fs:0x28,%rax
b0d: 00 00
b0f: 48 89 84 24 68 01 00 mov %rax,0x168(%rsp)
b16: 00
b17: 31 c0 xor %eax,%eax
b19: 48 8d 9c 24 e0 00 00 lea 0xe0(%rsp),%rbx
b20: 00
b21: 48 b8 00 00 00 80 07 movabs $0x8000000780000000,%rax
b28: 00 00 80
b2b: 48 c7 84 24 e0 00 00 movq $0x1,0xe0(%rsp)
b32: 00 01 00 00 00
b37: 48 8d 53 08 lea 0x8(%rbx),%rdx
b3b: 48 89 84 24 c8 00 00 mov %rax,0xc8(%rsp)
b42: 00
b43: 31 c0 xor %eax,%eax
b45: 48 89 d7 mov %rdx,%rdi
b48: f3 48 ab rep stos %rax,%es:(%rdi)
b4b: e8 c0 fe ff ff callq a10 <getpid@plt>
b50: 48 89 da mov %rbx,%rdx
b53: be 80 00 00 00 mov $0x80,%esi
b58: 89 c7 mov %eax,%edi
b5a: e8 e1 fe ff ff callq a40 <sched_setaffinity@plt>
b5f: 85 c0 test %eax,%eax
b61: 0f 85 17 03 00 00 jne e7e <main+0x38e>
b67: 0f ae f0 mfence
b6a: 48 8d 74 24 10 lea 0x10(%rsp),%rsi
b6f: bf 02 00 00 00 mov $0x2,%edi
b74: 0f ae f0 mfence
b77: e8 84 fe ff ff callq a00 <clock_gettime@plt>
b7c: 0f 31 rdtsc
b7e: bf 00 fa 00 00 mov $0xfa00,%edi
b83: 0f ae f0 mfence
b86: 48 c1 e2 20 shl $0x20,%rdx
b8a: 49 89 c6 mov %rax,%r14
b8d: 49 09 d6 or %rdx,%r14
b90: e8 db fe ff ff callq a70 <malloc@plt>
b95: 48 8d bc 24 c8 00 00 lea 0xc8(%rsp),%rdi
b9c: 00
b9d: be 02 00 00 00 mov $0x2,%esi
ba2: 49 89 c4 mov %rax,%r12
ba5: e8 a6 fe ff ff callq a50 <PAPI_start_counters@plt>
baa: 85 c0 test %eax,%eax
bac: 0f 85 88 02 00 00 jne e3a <main+0x34a>
bb2: 4d 89 e7 mov %r12,%r15
bb5: 49 8d 84 24 00 fa 00 lea 0xfa00(%r12),%rax
bbc: 00
bbd: 4c 89 e5 mov %r12,%rbp
bc0: c7 45 00 01 00 00 00 movl $0x1,0x0(%rbp)
bc7: 48 83 c5 40 add $0x40,%rbp
bcb: 48 39 e8 cmp %rbp,%rax
bce: 75 f0 jne bc0 <main+0xd0>
bd0: 4c 8d ac 24 d0 00 00 lea 0xd0(%rsp),%r13
bd7: 00
bd8: be 02 00 00 00 mov $0x2,%esi
bdd: 4c 89 ef mov %r13,%rdi
be0: e8 4b fe ff ff callq a30 <PAPI_read_counters@plt>
be5: 85 c0 test %eax,%eax
be7: 0f 85 b8 02 00 00 jne ea5 <main+0x3b5>
bed: 48 8b 84 24 d0 00 00 mov 0xd0(%rsp),%rax
bf4: 00
bf5: 4c 89 e3 mov %r12,%rbx
bf8: 48 89 44 24 08 mov %rax,0x8(%rsp)
bfd: 0f 1f 00 nopl (%rax)
c00: 83 03 09 addl $0x9,(%rbx)
c03: 48 83 c3 40 add $0x40,%rbx
c07: 48 39 dd cmp %rbx,%rbp
c0a: 75 f4 jne c00 <main+0x110>
c0c: 31 d2 xor %edx,%edx
c0e: 48 8d 35 88 04 00 00 lea 0x488(%rip),%rsi # 109d <_IO_stdin_used+0x2d>
c15: bf 01 00 00 00 mov $0x1,%edi
c1a: 31 c0 xor %eax,%eax
c1c: e8 6f fe ff ff callq a90 <__printf_chk@plt>
c21: be 02 00 00 00 mov $0x2,%esi
c26: 4c 89 ef mov %r13,%rdi
c29: e8 02 fe ff ff callq a30 <PAPI_read_counters@plt>
c2e: 85 c0 test %eax,%eax
c30: 0f 85 6f 02 00 00 jne ea5 <main+0x3b5>
c36: 48 8b 8c 24 d0 00 00 mov 0xd0(%rsp),%rcx
c3d: 00
c3e: 48 8b 54 24 08 mov 0x8(%rsp),%rdx
c43: 48 8d 35 e6 04 00 00 lea 0x4e6(%rip),%rsi # 1130 <_IO_stdin_used+0xc0>
c4a: 31 c0 xor %eax,%eax
c4c: bf 01 00 00 00 mov $0x1,%edi
c51: e8 3a fe ff ff callq a90 <__printf_chk@plt>
c56: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
c5d: 00 00 00
c60: 41 0f ae 3c 24 clflush (%r12)
c65: 49 83 c4 40 add $0x40,%r12
c69: 49 39 dc cmp %rbx,%r12
c6c: 75 f2 jne c60 <main+0x170>
c6e: be 02 00 00 00 mov $0x2,%esi
c73: 4c 89 ef mov %r13,%rdi
c76: e8 b5 fd ff ff callq a30 <PAPI_read_counters@plt>
c7b: 85 c0 test %eax,%eax
c7d: 0f 85 22 02 00 00 jne ea5 <main+0x3b5>
c83: 48 8b ac 24 d0 00 00 mov 0xd0(%rsp),%rbp
c8a: 00
c8b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1)
c90: 41 83 07 09 addl $0x9,(%r15)
c94: 49 83 c7 40 add $0x40,%r15
c98: 49 39 df cmp %rbx,%r15
c9b: 75 f3 jne c90 <main+0x1a0>
c9d: be 02 00 00 00 mov $0x2,%esi
ca2: 4c 89 ef mov %r13,%rdi
ca5: e8 86 fd ff ff callq a30 <PAPI_read_counters@plt>
caa: 85 c0 test %eax,%eax
cac: 0f 85 f3 01 00 00 jne ea5 <main+0x3b5>
cb2: 48 8b 8c 24 d0 00 00 mov 0xd0(%rsp),%rcx
cb9: 00
cba: 48 8d 35 97 04 00 00 lea 0x497(%rip),%rsi # 1158 <_IO_stdin_used+0xe8>
cc1: bf 01 00 00 00 mov $0x1,%edi
cc6: 31 c0 xor %eax,%eax
cc8: 48 89 ea mov %rbp,%rdx
ccb: e8 c0 fd ff ff callq a90 <__printf_chk@plt>
cd0: be 02 00 00 00 mov $0x2,%esi
cd5: 4c 89 ef mov %r13,%rdi
cd8: e8 83 fd ff ff callq a60 <PAPI_stop_counters@plt>
cdd: 85 c0 test %eax,%eax
cdf: 0f 85 72 01 00 00 jne e57 <main+0x367>
ce5: 0f ae f0 mfence
ce8: 0f 31 rdtsc
cea: bf 02 00 00 00 mov $0x2,%edi
cef: 48 c1 e2 20 shl $0x20,%rdx
cf3: 48 89 c3 mov %rax,%rbx
cf6: 48 8d 74 24 20 lea 0x20(%rsp),%rsi
cfb: 48 09 d3 or %rdx,%rbx
cfe: e8 fd fc ff ff callq a00 <clock_gettime@plt>
d03: bf 01 00 00 00 mov $0x1,%edi
d08: 48 be db 34 b6 d7 82 movabs $0x431bde82d7b634db,%rsi
d0f: de 1b 43
d12: 0f ae f0 mfence
d15: 48 8b 4c 24 20 mov 0x20(%rsp),%rcx
d1a: 48 2b 4c 24 10 sub 0x10(%rsp),%rcx
d1f: 48 69 c9 00 ca 9a 3b imul $0x3b9aca00,%rcx,%rcx
d26: 48 03 4c 24 28 add 0x28(%rsp),%rcx
d2b: 48 2b 4c 24 18 sub 0x18(%rsp),%rcx
d30: 48 89 c8 mov %rcx,%rax
d33: 48 c1 f9 3f sar $0x3f,%rcx
d37: 48 f7 ee imul %rsi
d3a: 48 8d 35 3f 04 00 00 lea 0x43f(%rip),%rsi # 1180 <_IO_stdin_used+0x110>
d41: 31 c0 xor %eax,%eax
d43: 48 c1 fa 12 sar $0x12,%rdx
d47: 48 29 ca sub %rcx,%rdx
d4a: e8 41 fd ff ff callq a90 <__printf_chk@plt>
d4f: 48 89 da mov %rbx,%rdx
d52: bf 01 00 00 00 mov $0x1,%edi
d57: 31 c0 xor %eax,%eax
d59: 4c 29 f2 sub %r14,%rdx
d5c: 48 8d 35 53 03 00 00 lea 0x353(%rip),%rsi # 10b6 <_IO_stdin_used+0x46>
d63: e8 28 fd ff ff callq a90 <__printf_chk@plt>
d68: 31 d2 xor %edx,%edx
d6a: 48 8d 35 56 03 00 00 lea 0x356(%rip),%rsi # 10c7 <_IO_stdin_used+0x57>
d71: 31 c0 xor %eax,%eax
d73: bf 01 00 00 00 mov $0x1,%edi
d78: e8 13 fd ff ff callq a90 <__printf_chk@plt>
d7d: 31 ff xor %edi,%edi
d7f: 48 8d 74 24 30 lea 0x30(%rsp),%rsi
d84: e8 17 fd ff ff callq aa0 <getrusage@plt>
d89: 83 f8 ff cmp $0xffffffff,%eax
d8c: 0f 84 d6 00 00 00 je e68 <main+0x378>
d92: 48 8b 8c 24 b8 00 00 mov 0xb8(%rsp),%rcx
d99: 00
d9a: 48 8b 94 24 b0 00 00 mov 0xb0(%rsp),%rdx
da1: 00
da2: 48 8d 35 3e 03 00 00 lea 0x33e(%rip),%rsi # 10e7 <_IO_stdin_used+0x77>
da9: 31 c0 xor %eax,%eax
dab: bf 01 00 00 00 mov $0x1,%edi
db0: e8 db fc ff ff callq a90 <__printf_chk@plt>
db5: c5 f9 57 c0 vxorpd %xmm0,%xmm0,%xmm0
db9: bf 01 00 00 00 mov $0x1,%edi
dbe: c5 fb 10 0d 12 04 00 vmovsd 0x412(%rip),%xmm1 # 11d8 <_IO_stdin_used+0x168>
dc5: 00
dc6: 48 69 44 24 30 40 42 imul $0xf4240,0x30(%rsp),%rax
dcd: 0f 00
dcf: 48 03 44 24 38 add 0x38(%rsp),%rax
dd4: 48 8d 35 d5 03 00 00 lea 0x3d5(%rip),%rsi # 11b0 <_IO_stdin_used+0x140>
ddb: c4 e1 fb 2a c0 vcvtsi2sd %rax,%xmm0,%xmm0
de0: 48 69 54 24 40 40 42 imul $0xf4240,0x40(%rsp),%rdx
de7: 0f 00
de9: 48 03 54 24 48 add 0x48(%rsp),%rdx
dee: c5 fb 59 c1 vmulsd %xmm1,%xmm0,%xmm0
df2: c4 e1 fb 2c c0 vcvttsd2si %xmm0,%rax
df7: c5 f9 57 c0 vxorpd %xmm0,%xmm0,%xmm0
dfb: c4 e1 fb 2a c2 vcvtsi2sd %rdx,%xmm0,%xmm0
e00: c5 fb 59 c1 vmulsd %xmm1,%xmm0,%xmm0
e04: c4 e1 fb 2c d0 vcvttsd2si %xmm0,%rdx
e09: 48 01 c2 add %rax,%rdx
e0c: 31 c0 xor %eax,%eax
e0e: e8 7d fc ff ff callq a90 <__printf_chk@plt>
e13: 31 c0 xor %eax,%eax
e15: 48 8b 8c 24 68 01 00 mov 0x168(%rsp),%rcx
e1c: 00
e1d: 64 48 33 0c 25 28 00 xor %fs:0x28,%rcx
e24: 00 00
e26: 75 51 jne e79 <main+0x389>
e28: 48 81 c4 78 01 00 00 add $0x178,%rsp
e2f: 5b pop %rbx
e30: 5d pop %rbp
e31: 41 5c pop %r12
e33: 41 5d pop %r13
e35: 41 5e pop %r14
e37: 41 5f pop %r15
e39: c3 retq
e3a: ba 01 00 00 00 mov $0x1,%edx
e3f: 48 8d 35 47 02 00 00 lea 0x247(%rip),%rsi # 108d <_IO_stdin_used+0x1d>
e46: bf 01 00 00 00 mov $0x1,%edi
e4b: 31 c0 xor %eax,%eax
e4d: e8 3e fc ff ff callq a90 <__printf_chk@plt>
e52: e9 5b fd ff ff jmpq bb2 <main+0xc2>
e57: 48 8d 3d 4a 02 00 00 lea 0x24a(%rip),%rdi # 10a8 <_IO_stdin_used+0x38>
e5e: e8 8d fb ff ff callq 9f0 <puts@plt>
e63: e9 7d fe ff ff jmpq ce5 <main+0x1f5>
e68: 48 8d 3d 62 02 00 00 lea 0x262(%rip),%rdi # 10d1 <_IO_stdin_used+0x61>
e6f: e8 7c fb ff ff callq 9f0 <puts@plt>
e74: e9 19 ff ff ff jmpq d92 <main+0x2a2>
e79: e8 a2 fb ff ff callq a20 <__stack_chk_fail@plt>
e7e: 48 8b 0d 9b 11 20 00 mov 0x20119b(%rip),%rcx # 202020 <stderr@@GLIBC_2.2.5>
e85: ba 18 00 00 00 mov $0x18,%edx
e8a: be 01 00 00 00 mov $0x1,%esi
e8f: 48 8d 3d de 01 00 00 lea 0x1de(%rip),%rdi # 1074 <_IO_stdin_used+0x4>
e96: e8 25 fc ff ff callq ac0 <fwrite@plt>
e9b: bf 01 00 00 00 mov $0x1,%edi
ea0: e8 0b fc ff ff callq ab0 <exit@plt>
ea5: 89 c7 mov %eax,%edi
ea7: e8 d4 fb ff ff callq a80 <PAPI_strerror@plt>
eac: 48 8b 3d 6d 11 20 00 mov 0x20116d(%rip),%rdi # 202020 <stderr@@GLIBC_2.2.5>
eb3: be 01 00 00 00 mov $0x1,%esi
eb8: 48 8d 15 49 02 00 00 lea 0x249(%rip),%rdx # 1108 <_IO_stdin_used+0x98>
ebf: 48 89 c1 mov %rax,%rcx
ec2: 31 c0 xor %eax,%eax
ec4: e8 07 fc ff ff callq ad0 <__fprintf_chk@plt>
ec9: bf 01 00 00 00 mov $0x1,%edi
ece: e8 dd fb ff ff callq ab0 <exit@plt>
ed3: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
eda: 00 00 00
edd: 0f 1f 00 nopl (%rax)
0000000000000ee0 <_start>:
ee0: 31 ed xor %ebp,%ebp
ee2: 49 89 d1 mov %rdx,%r9
ee5: 5e pop %rsi
ee6: 48 89 e2 mov %rsp,%rdx
ee9: 48 83 e4 f0 and $0xfffffffffffffff0,%rsp
eed: 50 push %rax
eee: 54 push %rsp
eef: 4c 8d 05 6a 01 00 00 lea 0x16a(%rip),%r8 # 1060 <__libc_csu_fini>
ef6: 48 8d 0d f3 00 00 00 lea 0xf3(%rip),%rcx # ff0 <__libc_csu_init>
efd: 48 8d 3d ec fb ff ff lea -0x414(%rip),%rdi # af0 <main>
f04: ff 15 d6 10 20 00 callq *0x2010d6(%rip) # 201fe0 <__libc_start_main@GLIBC_2.2.5>
f0a: f4 hlt
f0b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1)
0000000000000f10 <deregister_tm_clones>:
f10: 48 8d 3d f9 10 20 00 lea 0x2010f9(%rip),%rdi # 202010 <__TMC_END__>
f17: 55 push %rbp
f18: 48 8d 05 f1 10 20 00 lea 0x2010f1(%rip),%rax # 202010 <__TMC_END__>
f1f: 48 39 f8 cmp %rdi,%rax
f22: 48 89 e5 mov %rsp,%rbp
f25: 74 19 je f40 <deregister_tm_clones+0x30>
f27: 48 8b 05 aa 10 20 00 mov 0x2010aa(%rip),%rax # 201fd8 <_ITM_deregisterTMCloneTable>
f2e: 48 85 c0 test %rax,%rax
f31: 74 0d je f40 <deregister_tm_clones+0x30>
f33: 5d pop %rbp
f34: ff e0 jmpq *%rax
f36: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
f3d: 00 00 00
f40: 5d pop %rbp
f41: c3 retq
f42: 0f 1f 40 00 nopl 0x0(%rax)
f46: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
f4d: 00 00 00
0000000000000f50 <register_tm_clones>:
f50: 48 8d 3d b9 10 20 00 lea 0x2010b9(%rip),%rdi # 202010 <__TMC_END__>
f57: 48 8d 35 b2 10 20 00 lea 0x2010b2(%rip),%rsi # 202010 <__TMC_END__>
f5e: 55 push %rbp
f5f: 48 29 fe sub %rdi,%rsi
f62: 48 89 e5 mov %rsp,%rbp
f65: 48 c1 fe 03 sar $0x3,%rsi
f69: 48 89 f0 mov %rsi,%rax
f6c: 48 c1 e8 3f shr $0x3f,%rax
f70: 48 01 c6 add %rax,%rsi
f73: 48 d1 fe sar %rsi
f76: 74 18 je f90 <register_tm_clones+0x40>
f78: 48 8b 05 71 10 20 00 mov 0x201071(%rip),%rax # 201ff0 <_ITM_registerTMCloneTable>
f7f: 48 85 c0 test %rax,%rax
f82: 74 0c je f90 <register_tm_clones+0x40>
f84: 5d pop %rbp
f85: ff e0 jmpq *%rax
f87: 66 0f 1f 84 00 00 00 nopw 0x0(%rax,%rax,1)
f8e: 00 00
f90: 5d pop %rbp
f91: c3 retq
f92: 0f 1f 40 00 nopl 0x0(%rax)
f96: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
f9d: 00 00 00
0000000000000fa0 <__do_global_dtors_aux>:
fa0: 80 3d 81 10 20 00 00 cmpb $0x0,0x201081(%rip) # 202028 <completed.7696>
fa7: 75 2f jne fd8 <__do_global_dtors_aux+0x38>
fa9: 48 83 3d 47 10 20 00 cmpq $0x0,0x201047(%rip) # 201ff8 <__cxa_finalize@GLIBC_2.2.5>
fb0: 00
fb1: 55 push %rbp
fb2: 48 89 e5 mov %rsp,%rbp
fb5: 74 0c je fc3 <__do_global_dtors_aux+0x23>
fb7: 48 8b 3d 4a 10 20 00 mov 0x20104a(%rip),%rdi # 202008 <__dso_handle>
fbe: e8 1d fb ff ff callq ae0 <__cxa_finalize@plt>
fc3: e8 48 ff ff ff callq f10 <deregister_tm_clones>
fc8: c6 05 59 10 20 00 01 movb $0x1,0x201059(%rip) # 202028 <completed.7696>
fcf: 5d pop %rbp
fd0: c3 retq
fd1: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
fd8: f3 c3 repz retq
fda: 66 0f 1f 44 00 00 nopw 0x0(%rax,%rax,1)
0000000000000fe0 <frame_dummy>:
fe0: 55 push %rbp
fe1: 48 89 e5 mov %rsp,%rbp
fe4: 5d pop %rbp
fe5: e9 66 ff ff ff jmpq f50 <register_tm_clones>
fea: 66 0f 1f 44 00 00 nopw 0x0(%rax,%rax,1)
0000000000000ff0 <__libc_csu_init>:
ff0: 41 57 push %r15
ff2: 41 56 push %r14
ff4: 49 89 d7 mov %rdx,%r15
ff7: 41 55 push %r13
ff9: 41 54 push %r12
ffb: 4c 8d 25 36 0d 20 00 lea 0x200d36(%rip),%r12 # 201d38 <__frame_dummy_init_array_entry>
1002: 55 push %rbp
1003: 48 8d 2d 36 0d 20 00 lea 0x200d36(%rip),%rbp # 201d40 <__init_array_end>
100a: 53 push %rbx
100b: 41 89 fd mov %edi,%r13d
100e: 49 89 f6 mov %rsi,%r14
1011: 4c 29 e5 sub %r12,%rbp
1014: 48 83 ec 08 sub $0x8,%rsp
1018: 48 c1 fd 03 sar $0x3,%rbp
101c: e8 9f f9 ff ff callq 9c0 <_init>
1021: 48 85 ed test %rbp,%rbp
1024: 74 20 je 1046 <__libc_csu_init+0x56>
1026: 31 db xor %ebx,%ebx
1028: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1)
102f: 00
1030: 4c 89 fa mov %r15,%rdx
1033: 4c 89 f6 mov %r14,%rsi
1036: 44 89 ef mov %r13d,%edi
1039: 41 ff 14 dc callq *(%r12,%rbx,8)
103d: 48 83 c3 01 add $0x1,%rbx
1041: 48 39 dd cmp %rbx,%rbp
1044: 75 ea jne 1030 <__libc_csu_init+0x40>
1046: 48 83 c4 08 add $0x8,%rsp
104a: 5b pop %rbx
104b: 5d pop %rbp
104c: 41 5c pop %r12
104e: 41 5d pop %r13
1050: 41 5e pop %r14
1052: 41 5f pop %r15
1054: c3 retq
1055: 90 nop
1056: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
105d: 00 00 00
0000000000001060 <__libc_csu_fini>:
1060: f3 c3 repz retq
Disassembly of section .fini:
0000000000001064 <_fini>:
1064: 48 83 ec 08 sub $0x8,%rsp
1068: 48 83 c4 08 add $0x8,%rsp
106c: c3 retq
我的对象大小为64，并且还添加了初始化：
typedef struct _object{
int value;
int pad_0;
int * pad_2;
int * pad_3;
int * pad_4;
int * pad_5;
int * pad_6;
int * pad_7;
int * pad_8;
} object;
object * array;
int arr_size = 1000;
array = (object *) malloc(arr_size * sizeof(object));
for(int i=0; i < arr_size; i++){
array[i].value = 1;
}
答案 0 :(得分：3)
我已经在Haswell上使用类似于PAPI的LIKWID进行了一些实验。我发现对初始化和读取性能计数器的函数的调用会导致L1缓存中600多个替换。由于L1缓存只有512行，因此这意味着这些功能可能会驱逐您原本希望位于L1中的许多行。通过查看PAPI_start_counters和_internal_hl_read_cnts相对较大的源代码，在我看来这些函数可能会从L1移出许多行，因此数组元素在这些调用中不会在L1中幸存。我已经通过使用负载而不是存储并使用MEM_LOAD_RETIRED.*计算命中和未命中来验证了这一点。我认为解决方案是使用RDPMC指令。我之前没有直接使用过此指令。代码段here看起来很有用。
或者，您可以将循环的两个副本放在PAPI_start_counters / PAPI_read_counters之后，然后从结果中减去循环的一个副本的计数。这种方法效果很好。
顺便说一下，当访问的缓存行数大约大于10时，L1D.REPLACEMENT计数器在Haswell上似乎相当准确。也许通过使用RDPMC来计数是准确的。
从上一个问题开始，您似乎正在使用Skylake。根据{{3}}，PAPI_L1_DCM和PAPI_L2_TCM被映射到Intel处理器上的L1D.REPLACEMENT和LONGEST_LAT_CACHE.REFERENCE性能监视事件。这些在英特尔手册中定义如下：
L1D.REPLACEMENT ：计算L1D数据线的替换次数，包括机会 替代品，以及需要停顿换货或 替换区块。
LONGEST_LAT_CACHE.REFERENCE ：此事件计数引用了源自核心的可缓存需求请求 到最后一级缓存（LLC）。需求请求包括负载，RFO， 从L1D进行硬件和硬件预取，从IFU中获取指令。
在不弄清楚这些事件何时确切发生的细节的情况下，这里有三个与您的问题相关的重要点：
miss2。在Skylake上，还有其他本机事件可用于计算每个加载指令的L1D丢失和命中。您可以使用MEM_LOAD_RETIRED.L1_HIT来计算在L1D中命中的退休装载指令的数量。您可以使用MEM_INST_RETIRED.ALL_LOADS-MEM_LOAD_RETIRED.L1_HIT来计算L1D中缺少的已退休加载指令的数量。他们似乎没有PAPI事件。根据{{3}}，您可以将本机事件代码传递给PAPIF_start_counters。
另一个问题是，我不清楚PAPIF_start_counters是否默认仅计算内核事件和用户事件中的用户事件。看来您可以使用PAPI_create_eventset来控制计数域。
对PAPI API的调用也会影响事件计数。您可以尝试使用空块来对此进行测量，如下所示：
if ((ret1 = PAPI_read_counters(values, numEvents)) != PAPI_OK) {
fprintf(stderr, "PAPI failed to read counters: %s\n", PAPI_strerror(ret1));
exit(1);
}
// Nothing.
if ((ret2 = PAPI_read_counters(values, numEvents)) != PAPI_OK) {
fprintf(stderr, "PAPI failed to read counters: %s\n", PAPI_strerror(ret2));
exit(1);
}
此度量将为您估计由于PAPI本身而可能发生的错误。
此外，我认为您不需要使用_mm_mfence。