我写了一个简单的程序，在一个循环中执行一堆NOP指令，令我惊讶的是，它每秒执行大约10600000000条指令，或者大约10Ghz，而我的CPU只有2.2GHz。
这怎么可能?是CPU将它们视为单个的mega-NOP，还是我刚刚发现了"指令级并行"的含义?
每秒指令数的更好度量是什么?执行add指令的速度只有414900000/s，是我的CPU所报告速度的十分之一:4390.03
C代码:
#include <stdio.h>
#include <stdint.h>
#include <time.h>
#define ten(a) a a a a a a a a a a
#define hundred(a) ten(a) ten(a) ten(a) ten(a) ten(a) ten(a) ten(a)
ten(a) ten(a) ten(a)
#define ITER 10000000
int main(void) {
uint64_t i=0;
uint64_t t=time(NULL);
while(1) {
for(int j=0; j<ITER;j++) {
hundred(asm volatile ("nop");)
}
i+=ITER*100;
printf("%lu/%lun", i, time(NULL)-t);
}
return 0;
}
编制装配:
.file "gbloopinc.c"
.section .rodata
.LC0:
.string "%lu/%lun"
.text
.globl main
.type main, @function
main:
.LFB0:
.cfi_startproc
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
movq %rsp, %rbp
.cfi_def_cfa_register 6
subq $32, %rsp
movq $0, -16(%rbp)
movl $0, %edi
call time
movq %rax, -8(%rbp)
.L4:
movl $0, -20(%rbp)
jmp .L2
.L3:
#APP
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
# 15 "gbloopinc.c" 1
nop
# 0 "" 2
#NO_APP
addl $1, -20(%rbp)
.L2:
cmpl $9999999, -20(%rbp)
jle .L3
addq $1000000000, -16(%rbp)
movl $0, %edi
call time
subq -8(%rbp), %rax
movq %rax, %rdx
movq -16(%rbp), %rax
movq %rax, %rsi
movl $.LC0, %edi
movl $0, %eax
call printf
jmp .L4
.cfi_endproc
.LFE0:
.size main, .-main
.ident "GCC: (Ubuntu 5.4.0-6ubuntu1~16.04.2) 5.4.0 20160609"
.section .note.GNU-stack,"",@progbits
这与多核无关。核心不是"端口"。
每个时钟4 NOPs是超标量/乱序CPU的问题/退役管道宽度。nop甚至不需要执行单元/执行端口(ALU或加载或存储)，因此您甚至不受整数执行单元数量的限制。即使是Core2 (Intel的首款4-wide x86 CPU)每个时钟也可以运行4个nop。
正如您所猜测的，这是指令级并行的一个示例。nop当然没有输入依赖。
在你的Sandybridge CPU(每核有3个ALU执行单元)，你可以运行3个ADD和一个加载或存储指令每个时钟，因为它的管道宽度是4个上限。请参阅Agner Fog的microarch pdf和x86标签wiki中的其他链接。在一个独立的ADD指令流上，比如
add eax, eax
add ebx, ebx
add ecx, ecx
add edx, edx
...
您将看到SnB上的每时钟吞吐量约为3，在整数ALU执行端口上出现瓶颈。Haswell可以在每个时钟运行4个add，因为它有第4个ALU执行端口，可以处理非向量整数操作(和分支)。
乱序cpu通常具有比执行单元数量更宽的前端和发行/退役宽度。一旦有空闲的执行单元，就对更多的指令进行解码并准备好执行，这就增加了它们的利用率。否则，如果执行由于串行依赖而停滞或减慢，无序机器只能提前看到当前正在执行的内容。(例如，add eax,eax/add eax,eax需要第一个add的输出作为第二个add的输入，因此每个时钟只能运行一次。)
我将进一步阐述HansPassant的评论。
现代处理器既是超标量又是多核的。多核处理器很容易理解——它有多个核心。另一方面，Superscalar需要更多的硬件知识。这是一个堆栈交换问题，它解释了处理器是超标量意味着什么。超标量处理器在同一个核心中有许多功能单元，并且是高度流水线化的。这就是为什么多个指令可以在单个内核中同时调度和运行的原因。以下是处理器中的一些功能单元:整数加减、浮点乘法、浮点除法、整数乘法、整数除法。
我鼓励你去谷歌更多关于超标量处理器的信息，特别是查找更多关于你的处理器的信息。