Discovery CPU details for default thread selection (#6264)

On windows, detect large multi-socket systems and reduce to the number of cores
in one socket for best performance

gpu/gpu.go

@@ -229,7 +229,10 @@ func GetGPUInfo() GpuInfoList {
 			slog.Warn("error looking up system memory", "error", err)
 		}
 		depPath := LibraryDir()
-
+		details, err := GetCPUDetails()
+		if err != nil {
+			slog.Warn("failed to lookup CPU details", "error", err)
+		}
 		cpus = []CPUInfo{
 			{
 				GpuInfo: GpuInfo{
@@ -239,6 +242,7 @@ func GetGPUInfo() GpuInfoList {
 					ID:             "0",
 					DependencyPath: depPath,
 				},
+				CPUs: details,
 			},
 		}
 

gpu/gpu_darwin.go

@@ -10,7 +10,9 @@ package gpu
 import "C"
 
 import (
+	"log/slog"
 	"runtime"
+	"syscall"
 
 	"github.com/ollama/ollama/format"
 )
@@ -69,11 +71,30 @@ func (l GpuInfoList) GetVisibleDevicesEnv() (string, string) {
 
 func GetSystemInfo() SystemInfo {
 	mem, _ := GetCPUMem()
+	query := "hw.perflevel0.physicalcpu"
+	perfCores, err := syscall.SysctlUint32(query)
+	if err != nil {
+		slog.Warn("failed to discover physical CPU details", "query", query, "error", err)
+	}
+	query = "hw.perflevel1.physicalcpu"
+	efficiencyCores, _ := syscall.SysctlUint32(query) // On x86 xeon this wont return data
+
+	// Determine thread count
+	query = "hw.logicalcpu"
+	logicalCores, _ := syscall.SysctlUint32(query)
+
 	return SystemInfo{
 		System: CPUInfo{
 			GpuInfo: GpuInfo{
 				memInfo: mem,
 			},
+			CPUs: []CPU{
+				{
+					CoreCount:           int(perfCores + efficiencyCores),
+					EfficiencyCoreCount: int(efficiencyCores),
+					ThreadCount:         int(logicalCores),
+				},
+			},
 		},
 		GPUs: GetGPUInfo(),
 	}

gpu/gpu_linux.go

@@ -4,6 +4,8 @@ import (
 	"bufio"
 	"fmt"
 	"os"
+	"reflect"
+	"regexp"
 	"strings"
 
 	"github.com/ollama/ollama/format"
@@ -90,3 +92,95 @@ func GetCPUMem() (memInfo, error) {
 	}
 	return mem, nil
 }
+
+const CpuInfoFilename = "/proc/cpuinfo"
+
+type linuxCpuInfo struct {
+	ID         string `cpuinfo:"processor"`
+	VendorID   string `cpuinfo:"vendor_id"`
+	ModelName  string `cpuinfo:"model name"`
+	PhysicalID string `cpuinfo:"physical id"`
+	Siblings   string `cpuinfo:"siblings"`
+	CoreID     string `cpuinfo:"core id"`
+}
+
+func GetCPUDetails() ([]CPU, error) {
+	file, err := os.Open(CpuInfoFilename)
+	if err != nil {
+		return nil, err
+	}
+	reColumns := regexp.MustCompile("\t+: ")
+	scanner := bufio.NewScanner(file)
+	cpuInfos := []linuxCpuInfo{}
+	cpu := &linuxCpuInfo{}
+	for scanner.Scan() {
+		line := scanner.Text()
+		if sl := reColumns.Split(line, 2); len(sl) > 1 {
+			t := reflect.TypeOf(cpu).Elem()
+			s := reflect.ValueOf(cpu).Elem()
+			for i := range t.NumField() {
+				field := t.Field(i)
+				tag := field.Tag.Get("cpuinfo")
+				if tag == sl[0] {
+					s.FieldByName(field.Name).SetString(sl[1])
+					break
+				}
+			}
+		} else if strings.TrimSpace(line) == "" && cpu.ID != "" {
+			cpuInfos = append(cpuInfos, *cpu)
+			cpu = &linuxCpuInfo{}
+		}
+	}
+
+	// Process the sockets/cores/threads
+	socketByID := map[string]*CPU{}
+	coreBySocket := map[string]map[string]struct{}{}
+	threadsByCoreBySocket := map[string]map[string]int{}
+	for _, c := range cpuInfos {
+		if _, found := socketByID[c.PhysicalID]; !found {
+			socketByID[c.PhysicalID] = &CPU{
+				ID:        c.PhysicalID,
+				VendorID:  c.VendorID,
+				ModelName: c.ModelName,
+			}
+			coreBySocket[c.PhysicalID] = map[string]struct{}{}
+			threadsByCoreBySocket[c.PhysicalID] = map[string]int{}
+		}
+		if c.CoreID != "" {
+			coreBySocket[c.PhysicalID][c.PhysicalID+":"+c.CoreID] = struct{}{}
+			threadsByCoreBySocket[c.PhysicalID][c.PhysicalID+":"+c.CoreID]++
+		} else {
+			coreBySocket[c.PhysicalID][c.PhysicalID+":"+c.ID] = struct{}{}
+			threadsByCoreBySocket[c.PhysicalID][c.PhysicalID+":"+c.ID]++
+		}
+	}
+
+	// Tally up the values from the tracking maps
+	for id, s := range socketByID {
+		s.CoreCount = len(coreBySocket[id])
+		s.ThreadCount = 0
+		for _, tc := range threadsByCoreBySocket[id] {
+			s.ThreadCount += tc
+		}
+
+		// This only works if HT is enabled, consider a more reliable model, maybe cache size comparisons?
+		efficiencyCoreCount := 0
+		for _, threads := range threadsByCoreBySocket[id] {
+			if threads == 1 {
+				efficiencyCoreCount++
+			}
+		}
+		if efficiencyCoreCount == s.CoreCount {
+			// 1:1 mapping means they're not actually efficiency cores, but regular cores
+			s.EfficiencyCoreCount = 0
+		} else {
+			s.EfficiencyCoreCount = efficiencyCoreCount
+		}
+	}
+
+	result := []CPU{}
+	for _, c := range socketByID {
+		result = append(result, *c)
+	}
+	return result, nil
+}

gpu/gpu_windows.go

@@ -2,6 +2,7 @@ package gpu
 
 import (
 	"fmt"
+	"log/slog"
 	"syscall"
 	"unsafe"
 )
@@ -19,9 +20,10 @@ type MEMORYSTATUSEX struct {
 }
 
 var (
-	k32                      = syscall.NewLazyDLL("kernel32.dll")
-	globalMemoryStatusExProc = k32.NewProc("GlobalMemoryStatusEx")
-	sizeofMemoryStatusEx     = uint32(unsafe.Sizeof(MEMORYSTATUSEX{}))
+	k32                              = syscall.NewLazyDLL("kernel32.dll")
+	globalMemoryStatusExProc         = k32.NewProc("GlobalMemoryStatusEx")
+	sizeofMemoryStatusEx             = uint32(unsafe.Sizeof(MEMORYSTATUSEX{}))
+	GetLogicalProcessorInformationEx = k32.NewProc("GetLogicalProcessorInformationEx")
 )
 
 var CudartGlobs = []string{
@@ -55,3 +57,178 @@ func GetCPUMem() (memInfo, error) {
 	}
 	return memInfo{TotalMemory: memStatus.TotalPhys, FreeMemory: memStatus.AvailPhys, FreeSwap: memStatus.AvailPageFile}, nil
 }
+
+type LOGICAL_PROCESSOR_RELATIONSHIP uint32
+
+const (
+	RelationProcessorCore LOGICAL_PROCESSOR_RELATIONSHIP = iota
+	RelationNumaNode
+	RelationCache
+	RelationProcessorPackage
+	RelationGroup
+	RelationProcessorDie
+	RelationNumaNodeEx
+	RelationProcessorModule
+)
+const RelationAll LOGICAL_PROCESSOR_RELATIONSHIP = 0xffff
+
+type GROUP_AFFINITY struct {
+	Mask     uintptr // KAFFINITY
+	Group    uint16
+	Reserved [3]uint16
+}
+
+type PROCESSOR_RELATIONSHIP struct {
+	Flags           byte
+	EfficiencyClass byte
+	Reserved        [20]byte
+	GroupCount      uint16
+	GroupMask       [1]GROUP_AFFINITY // len GroupCount
+}
+
+// Omitted unused structs: NUMA_NODE_RELATIONSHIP CACHE_RELATIONSHIP GROUP_RELATIONSHIP
+
+type SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX struct {
+	Relationship LOGICAL_PROCESSOR_RELATIONSHIP
+	Size         uint32
+	U            [1]byte // Union len Size
+	// PROCESSOR_RELATIONSHIP
+	// NUMA_NODE_RELATIONSHIP
+	// CACHE_RELATIONSHIP
+	// GROUP_RELATIONSHIP
+}
+
+func (group *GROUP_AFFINITY) IsMember(target *GROUP_AFFINITY) bool {
+	if group == nil || target == nil {
+		return false
+	}
+	return group.Mask&target.Mask != 0
+}
+
+type winPackage struct {
+	groups              []*GROUP_AFFINITY
+	coreCount           int // performance cores = coreCount - efficiencyCoreCount
+	efficiencyCoreCount int
+	threadCount         int
+}
+
+func (pkg *winPackage) IsMember(target *GROUP_AFFINITY) bool {
+	for _, group := range pkg.groups {
+		if group.IsMember(target) {
+			return true
+		}
+	}
+	return false
+}
+
+func getLogicalProcessorInformationEx() ([]byte, error) {
+	buf := make([]byte, 1)
+	bufSize := len(buf)
+	ret, _, err := GetLogicalProcessorInformationEx.Call(
+		uintptr(RelationAll),
+		uintptr(unsafe.Pointer(&buf[0])),
+		uintptr(unsafe.Pointer(&bufSize)),
+	)
+	if ret != 0 {
+		return nil, fmt.Errorf("failed to determine size info ret:%d %w", ret, err)
+	}
+
+	buf = make([]byte, bufSize)
+	ret, _, err = GetLogicalProcessorInformationEx.Call(
+		uintptr(RelationAll),
+		uintptr(unsafe.Pointer(&buf[0])),
+		uintptr(unsafe.Pointer(&bufSize)),
+	)
+	if ret == 0 {
+		return nil, fmt.Errorf("failed to gather processor information ret:%d buflen:%d %w", ret, bufSize, err)
+	}
+	return buf, nil
+}
+
+func processSystemLogicalProcessorInforationList(buf []byte) []*winPackage {
+	var slpi *SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX
+	// Find all the packages first
+	packages := []*winPackage{}
+	for bufOffset := 0; bufOffset < len(buf); bufOffset += int(slpi.Size) {
+		slpi = (*SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX)(unsafe.Pointer(&buf[bufOffset]))
+		if slpi.Relationship != RelationProcessorPackage {
+			continue
+		}
+		pr := (*PROCESSOR_RELATIONSHIP)(unsafe.Pointer(&slpi.U[0]))
+		pkg := &winPackage{}
+		ga0 := unsafe.Pointer(&pr.GroupMask[0])
+		for j := range pr.GroupCount {
+			gm := (*GROUP_AFFINITY)(unsafe.Pointer(uintptr(ga0) + uintptr(j)*unsafe.Sizeof(GROUP_AFFINITY{})))
+			pkg.groups = append(pkg.groups, gm)
+		}
+		packages = append(packages, pkg)
+	}
+
+	slog.Info("packages", "count", len(packages))
+
+	// To identify efficiency cores we have to compare the relative values
+	// Larger values are "less efficient" (aka, more performant)
+	var maxEfficiencyClass byte
+	for bufOffset := 0; bufOffset < len(buf); bufOffset += int(slpi.Size) {
+		slpi = (*SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX)(unsafe.Pointer(&buf[bufOffset]))
+		if slpi.Relationship != RelationProcessorCore {
+			continue
+		}
+		pr := (*PROCESSOR_RELATIONSHIP)(unsafe.Pointer(&slpi.U[0]))
+		if pr.EfficiencyClass > maxEfficiencyClass {
+			maxEfficiencyClass = pr.EfficiencyClass
+		}
+	}
+	if maxEfficiencyClass > 0 {
+		slog.Info("efficiency cores detected", "maxEfficiencyClass", maxEfficiencyClass)
+	}
+
+	// then match up the Cores to the Packages, count up cores, threads and efficiency cores
+	for bufOffset := 0; bufOffset < len(buf); bufOffset += int(slpi.Size) {
+		slpi = (*SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX)(unsafe.Pointer(&buf[bufOffset]))
+		if slpi.Relationship != RelationProcessorCore {
+			continue
+		}
+		pr := (*PROCESSOR_RELATIONSHIP)(unsafe.Pointer(&slpi.U[0]))
+		ga0 := unsafe.Pointer(&pr.GroupMask[0])
+		for j := range pr.GroupCount {
+			gm := (*GROUP_AFFINITY)(unsafe.Pointer(uintptr(ga0) + uintptr(j)*unsafe.Sizeof(GROUP_AFFINITY{})))
+			for _, pkg := range packages {
+				if pkg.IsMember(gm) {
+					pkg.coreCount++
+					if pr.Flags == 0 {
+						pkg.threadCount++
+					} else {
+						pkg.threadCount += 2
+					}
+					if pr.EfficiencyClass < maxEfficiencyClass {
+						pkg.efficiencyCoreCount++
+					}
+				}
+			}
+		}
+	}
+
+	// Sumarize the results
+	for i, pkg := range packages {
+		slog.Info("", "package", i, "cores", pkg.coreCount, "efficiency", pkg.efficiencyCoreCount, "threads", pkg.threadCount)
+	}
+
+	return packages
+}
+
+func GetCPUDetails() ([]CPU, error) {
+	buf, err := getLogicalProcessorInformationEx()
+	if err != nil {
+		return nil, err
+	}
+	packages := processSystemLogicalProcessorInforationList(buf)
+	cpus := make([]CPU, len(packages))
+
+	for i, pkg := range packages {
+		cpus[i].CoreCount = pkg.coreCount
+		cpus[i].EfficiencyCoreCount = pkg.efficiencyCoreCount
+		cpus[i].ThreadCount = pkg.threadCount
+	}
+	return cpus, nil
+}

gpu/types.go

@@ -10,11 +10,11 @@ import (
 type memInfo struct {
 	TotalMemory uint64 `json:"total_memory,omitempty"`
 	FreeMemory  uint64 `json:"free_memory,omitempty"`
-	FreeSwap    uint64 `json:"free_swap,omitempty"`
+	FreeSwap    uint64 `json:"free_swap,omitempty"` // TODO split this out for system only
 }
 
 // Beginning of an `ollama info` command
-type GpuInfo struct {
+type GpuInfo struct { // TODO better name maybe "InferenceProcessor"?
 	memInfo
 	Library string `json:"library,omitempty"`
 
@@ -49,6 +49,17 @@ type GpuInfo struct {
 
 type CPUInfo struct {
 	GpuInfo
+	CPUs []CPU
+}
+
+// CPU type represents a CPU Package occupying a socket
+type CPU struct {
+	ID                  string `cpuinfo:"processor"`
+	VendorID            string `cpuinfo:"vendor_id"`
+	ModelName           string `cpuinfo:"model name"`
+	CoreCount           int
+	EfficiencyCoreCount int // Performance = CoreCount - Efficiency
+	ThreadCount         int
 }
 
 type CudaGPUInfo struct {
@@ -158,3 +169,12 @@ type SystemInfo struct {
 	UnsupportedGPUs []UnsupportedGPUInfo `json:"unsupported_gpus"`
 	DiscoveryErrors []string             `json:"discovery_errors"`
 }
+
+// Return the optimal number of threads to use for inference
+func (si SystemInfo) GetOptimalThreadCount() int {
+	if len(si.System.CPUs) == 0 {
+		return 0
+	}
+	// Allocate thread count matching the performance cores on a single socket
+	return si.System.CPUs[0].CoreCount - si.System.CPUs[0].EfficiencyCoreCount
+}

llm/server.go

@@ -98,15 +98,11 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
 	var systemFreeMemory uint64
 	var systemSwapFreeMemory uint64
 
-	systemMemInfo, err := gpu.GetCPUMem()
-	if err != nil {
-		slog.Error("failed to lookup system memory", "error", err)
-	} else {
-		systemTotalMemory = systemMemInfo.TotalMemory
-		systemFreeMemory = systemMemInfo.FreeMemory
-		systemSwapFreeMemory = systemMemInfo.FreeSwap
-		slog.Info("system memory", "total", format.HumanBytes2(systemTotalMemory), "free", format.HumanBytes2(systemFreeMemory), "free_swap", format.HumanBytes2(systemSwapFreeMemory))
-	}
+	systemInfo := gpu.GetSystemInfo()
+	systemTotalMemory = systemInfo.System.TotalMemory
+	systemFreeMemory = systemInfo.System.FreeMemory
+	systemSwapFreeMemory = systemInfo.System.FreeSwap
+	slog.Info("system memory", "total", format.HumanBytes2(systemTotalMemory), "free", format.HumanBytes2(systemFreeMemory), "free_swap", format.HumanBytes2(systemSwapFreeMemory))
 
 	// If the user wants zero GPU layers, reset the gpu list to be CPU/system ram info
 	if opts.NumGPU == 0 {
@@ -217,8 +213,11 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
 		params = append(params, "--mmproj", projectors[0])
 	}
 
+	defaultThreads := systemInfo.GetOptimalThreadCount()
 	if opts.NumThread > 0 {
 		params = append(params, "--threads", strconv.Itoa(opts.NumThread))
+	} else if defaultThreads > 0 {
+		params = append(params, "--threads", strconv.Itoa(defaultThreads))
 	}
 
 	if !opts.F16KV {
@@ -260,15 +259,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
 		params = append(params, "--mlock")
 	}
 
-	if gpu.IsNUMA() && gpus[0].Library == "cpu" {
-		numaMode := "distribute"
-		if runtime.GOOS == "linux" {
-			if _, err := exec.LookPath("numactl"); err == nil {
-				numaMode = "numactl"
-			}
-		}
-		params = append(params, "--numa", numaMode)
-	}
+	// TODO - NUMA support currently doesn't work properly
 
 	params = append(params, "--parallel", strconv.Itoa(numParallel))