在搜索了英特尔指令手册10分钟,并花费另外10分钟编码后,我得到了如下代码(适用于基于英特尔的处理器):
void i386_cpuid_caches () {
int i;
for (i = 0; i < 32; i++) {
// Variables to hold the contents of the 4 i386 legacy registers
uint32_t eax, ebx, ecx, edx;
eax = 4; // get cache info
ecx = i; // cache id
__asm__ (
"cpuid" // call i386 cpuid instruction
: "+a" (eax) // contains the cpuid command code, 4 for cache query
, "=b" (ebx)
, "+c" (ecx) // contains the cache id
, "=d" (edx)
); // generates output in 4 registers eax, ebx, ecx and edx
// See the page 3-191 of the manual.
int cache_type = eax & 0x1F;
if (cache_type == 0) // end of valid cache identifiers
break;
char * cache_type_string;
switch (cache_type) {
case 1: cache_type_string = "Data Cache"; break;
case 2: cache_type_string = "Instruction Cache"; break;
case 3: cache_type_string = "Unified Cache"; break;
default: cache_type_string = "Unknown Type Cache"; break;
}
int cache_level = (eax >>= 5) & 0x7;
int cache_is_self_initializing = (eax >>= 3) & 0x1; // does not need SW initialization
int cache_is_fully_associative = (eax >>= 1) & 0x1;
// See the page 3-192 of the manual.
// ebx contains 3 integers of 10, 10 and 12 bits respectively
unsigned int cache_sets = ecx + 1;
unsigned int cache_coherency_line_size = (ebx & 0xFFF) + 1;
unsigned int cache_physical_line_partitions = ((ebx >>= 12) & 0x3FF) + 1;
unsigned int cache_ways_of_associativity = ((ebx >>= 10) & 0x3FF) + 1;
// Total cache size is the product
size_t cache_total_size = cache_ways_of_associativity * cache_physical_line_partitions * cache_coherency_line_size * cache_sets;
printf(
"Cache ID %d:\n"
"- Level: %d\n"
"- Type: %s\n"
"- Sets: %d\n"
"- System Coherency Line Size: %d bytes\n"
"- Physical Line partitions: %d\n"
"- Ways of associativity: %d\n"
"- Total Size: %zu bytes (%zu kb)\n"
"- Is fully associative: %s\n"
"- Is Self Initializing: %s\n"
"\n"
, i
, cache_level
, cache_type_string
, cache_sets
, cache_coherency_line_size
, cache_physical_line_partitions
, cache_ways_of_associativity
, cache_total_size, cache_total_size >> 10
, cache_is_fully_associative ? "true" : "false"
, cache_is_self_initializing ? "true" : "false"
);
}
}
参考资料:
Intel® 64和IA-32体系结构开发人员手册:卷2A
,第3-190页,CPUID-CPU识别。
与测量缓存延迟相比,这种方法更可靠,因为在现代处理器上几乎不可能关闭缓存预取。如果您需要针对其他处理器架构获取类似的信息,则必须查阅相应的手册。