windows NUMA API example from a presentation for a NUMA Seminar

win-numa.c

/* origin: http://technet.microsoft.com/de-de/ms683194%28v=vs.80%29 */

#include <windows.h>
#include <malloc.h>    
#include <stdio.h>
#include <tchar.h>

typedef BOOL (WINAPI *LPFN_GLPI)(
    PSYSTEM_LOGICAL_PROCESSOR_INFORMATION, 
    PDWORD);


// Helper function to count set bits in the processor mask.
DWORD CountSetBits(ULONG_PTR bitMask)
{
    DWORD LSHIFT = sizeof(ULONG_PTR)*8 - 1;
    DWORD bitSetCount = 0;
    ULONG_PTR bitTest = (ULONG_PTR)1 << LSHIFT;    
    DWORD i;
    
    for (i = 0; i <= LSHIFT; ++i)
    {
        bitSetCount += ((bitMask & bitTest)?1:0);
        bitTest/=2;
    }

    return bitSetCount;
}

int _cdecl _tmain ()
{
    PSYSTEM_LOGICAL_PROCESSOR_INFORMATION buffer = NULL;
    PSYSTEM_LOGICAL_PROCESSOR_INFORMATION buffer_begin = NULL;
    DWORD returnLength = 0;
    DWORD logicalProcessorCount = 0;
    DWORD numaNodeCount = 0;
    DWORD processorCoreCount = 0;
    DWORD processorL1CacheCount = 0;
    DWORD processorL2CacheCount = 0;
    DWORD processorL3CacheCount = 0;
    DWORD processorPackageCount = 0;
    DWORD byteOffset = 0;
    PCACHE_DESCRIPTOR Cache;

    while (GetLogicalProcessorInformation(buffer, &returnLength) == FALSE)
    {	
        if (GetLastError() == ERROR_INSUFFICIENT_BUFFER) 
        {
            if (buffer) 
                free(buffer);

            buffer = (PSYSTEM_LOGICAL_PROCESSOR_INFORMATION) malloc(returnLength);

            if (NULL == buffer) 
            {
                _tprintf(TEXT("\nError: Allocation failure\n"));
                return (2);
            }
        } 
        else 
        {
            _tprintf(TEXT("\nError %d\n"), GetLastError());
            return (3);
        }
        
    }
	
	buffer_begin = buffer;
	
    while (byteOffset + sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION) <= returnLength) 
    {
        switch (buffer->Relationship) 
        {
        case RelationNumaNode:
            // Non-NUMA systems report a single record of this type.
            numaNodeCount++;
            break;

        case RelationProcessorCore:
            processorCoreCount++;

            // A hyperthreaded core supplies more than one logical processor.
            logicalProcessorCount += CountSetBits(buffer->ProcessorMask);
            break;

        case RelationCache:
            // Cache data is in buffer->Cache, one CACHE_DESCRIPTOR structure for each cache. 
            Cache = &buffer->Cache;
            if (Cache->Level == 1)
            {
                processorL1CacheCount++;
            }
            else if (Cache->Level == 2)
            {
                processorL2CacheCount++;
            }
            else if (Cache->Level == 3)
            {
                processorL3CacheCount++;
            }
            break;

        case RelationProcessorPackage:
            // Logical processors share a physical package.
            processorPackageCount++;
            break;

        default:
            _tprintf(TEXT("\nError: Unsupported LOGICAL_PROCESSOR_RELATIONSHIP value.\n"));
            break;
        }
        byteOffset += sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION);
        buffer++;
    }

    _tprintf(TEXT("\nGetLogicalProcessorInformation results:\n"));
    _tprintf(TEXT("Number of NUMA nodes: %d\n"), 
             numaNodeCount);
    _tprintf(TEXT("Number of physical processor packages: %d\n"), 
             processorPackageCount);
    _tprintf(TEXT("Number of processor cores: %d\n"), 
             processorCoreCount);
    _tprintf(TEXT("Number of logical processors: %d\n"), 
             logicalProcessorCount);
    _tprintf(TEXT("Number of processor L1/L2/L3 caches: %d/%d/%d\n"), 
             processorL1CacheCount,
             processorL2CacheCount,
             processorL3CacheCount);
    
    free(buffer_begin);

    return 0;
}