Musa Mahmood
41d3543141
bin/gpu-bench times every GPU model (OCR mobile and server, the label image encoder, segmentation; optionally the CPU and the label text encoder) over a fixed 30-image corpus in tools/gpu_bench/corpus. Every corpus file is checked against corpus.txt's SHA-256 before anything runs; each model's files and models.config entry are fingerprinted; the GPU, driver, power limit, CUDA runtime, cuDNN and onnxruntime are recorded, and NVML samples memory, load, power and clocks during the timed passes. Results go to bin/gpu-bench-results as text files. The GPU Bench button opens a window that runs gpu-bench in its own process (no console) and lays results files from several machines side by side against a baseline, marking a different corpus or model.
215 lines
10 KiB
Plaintext
215 lines
10 KiB
Plaintext
// What gpu-bench says about the machine: the computer, CPU and memory, and the NVIDIA GPU through
|
|
// NVML (the driver's management library, nvml.dll / libnvidia-ml.so.1), which also gives the GPU's
|
|
// memory, load, temperature, power and clock while the models run. Without NVML (no NVIDIA driver)
|
|
// the GPU lines say so and the samples are empty.
|
|
|
|
System_Info :: struct {
|
|
machine: string;
|
|
os: string;
|
|
cpu: string;
|
|
logical_cores: s64;
|
|
ram_gb: float64;
|
|
gpu: string; // "" without NVML
|
|
vram_gb: float64;
|
|
driver: string;
|
|
cuda_driver: string; // the CUDA version the driver supports, such as 13.0
|
|
power_limit_w: float64; // the board's enforced limit: a laptop's GPU is often far below the desktop part's
|
|
max_sm_clock_mhz: s64;
|
|
max_mem_clock_mhz: s64;
|
|
gpu_error: string; // why there is no GPU information
|
|
power_source: string; // a laptop's: "AC" or "battery", which can change its GPU's speed several times over
|
|
}
|
|
|
|
// One sample of the GPU while a model runs.
|
|
Gpu_Sample :: struct {
|
|
memory_used_mb: float64; // the whole device's, every process's
|
|
util_percent: float64;
|
|
temperature_c: float64;
|
|
power_w: float64;
|
|
sm_clock_mhz: float64;
|
|
}
|
|
|
|
system_info :: () -> System_Info {
|
|
info: System_Info;
|
|
info.logical_cores = get_number_of_processors(.ALL_LOGICAL);
|
|
#if OS == .WINDOWS {
|
|
name: [256] u16;
|
|
size: u32 = name.count;
|
|
if GetComputerNameW(name.data, *size) info.machine = wide_to_utf8(name.data, cast(s32) size);
|
|
v: OSVERSIONINFOW;
|
|
v.dwOSVersionInfoSize = size_of(OSVERSIONINFOW);
|
|
RtlGetVersion(*v);
|
|
info.os = sprint("Windows %.%.%", v.dwMajorVersion, v.dwMinorVersion, v.dwBuildNumber);
|
|
buffer: [256] u8;
|
|
bytes: u32 = buffer.count;
|
|
if RegGetValueA(HKEY_LOCAL_MACHINE, "HARDWARE\\DESCRIPTION\\System\\CentralProcessor\\0", "ProcessorNameString", RRF_RT_REG_SZ, null, buffer.data, *bytes) == 0
|
|
info.cpu = copy_string(trim(to_string(buffer.data)));
|
|
memory: MEMORYSTATUSEX;
|
|
memory.dwLength = size_of(MEMORYSTATUSEX);
|
|
if GlobalMemoryStatusEx(*memory) info.ram_gb = memory.ullTotalPhys / (1024.0 * 1024 * 1024);
|
|
power: SYSTEM_POWER_STATUS;
|
|
if GetSystemPowerStatus(*power) && power.BatteryFlag != 128 { // 128: no battery
|
|
if power.ACLineStatus == 1 info.power_source = "AC";
|
|
else if power.ACLineStatus == 0 info.power_source = sprint("battery (% percent)", power.BatteryLifePercent);
|
|
}
|
|
} else #if OS == .LINUX {
|
|
host, host_ok := read_entire_file("/etc/hostname", log_errors = false);
|
|
if host_ok info.machine = trim(host);
|
|
release, release_ok := read_entire_file("/proc/sys/kernel/osrelease", log_errors = false);
|
|
info.os = ifx release_ok then sprint("Linux %", trim(release)) else "Linux";
|
|
cpuinfo, cpu_ok := read_entire_file("/proc/cpuinfo", log_errors = false);
|
|
if cpu_ok for split(cpuinfo, "\n",, temp) if begins_with(it, "model name") { info.cpu = trim(advance(it, find_index_from_left(it, #char ":") + 1)); break; }
|
|
meminfo, mem_ok := read_entire_file("/proc/meminfo", log_errors = false);
|
|
if mem_ok for split(meminfo, "\n",, temp) if begins_with(it, "MemTotal:") { info.ram_gb = string_to_int(trim(trim(advance(it, 9)), " kB")) / (1024.0 * 1024); break; }
|
|
} else {
|
|
info.os = tprint("%", OS);
|
|
}
|
|
if !info.machine info.machine = "unknown";
|
|
|
|
if !nvml_start() { info.gpu_error = nvml.error; return info; }
|
|
text: [96] u8;
|
|
if nvml.DeviceGetName(nvml.device, text.data, text.count) == 0 info.gpu = copy_string(to_string(text.data));
|
|
if nvml.SystemGetDriverVersion(text.data, text.count) == 0 info.driver = copy_string(to_string(text.data));
|
|
cuda: s32;
|
|
if nvml.SystemGetCudaDriverVersion(*cuda) == 0 info.cuda_driver = sprint("%.%", cuda / 1000, (cuda % 1000) / 10);
|
|
vram: Nvml_Memory;
|
|
if nvml.DeviceGetMemoryInfo(nvml.device, *vram) == 0 info.vram_gb = vram.total / (1024.0 * 1024 * 1024);
|
|
limit: u32;
|
|
if nvml.DeviceGetEnforcedPowerLimit(nvml.device, *limit) == 0 info.power_limit_w = limit / 1000.0;
|
|
clock: u32;
|
|
if nvml.DeviceGetMaxClockInfo(nvml.device, NVML_CLOCK_SM, *clock) == 0 info.max_sm_clock_mhz = clock;
|
|
if nvml.DeviceGetMaxClockInfo(nvml.device, NVML_CLOCK_MEM, *clock) == 0 info.max_mem_clock_mhz = clock;
|
|
return info;
|
|
}
|
|
|
|
// The GPU now; false without NVML.
|
|
gpu_sample :: () -> Gpu_Sample, ok: bool {
|
|
s: Gpu_Sample;
|
|
if !nvml.started return s, false;
|
|
memory: Nvml_Memory;
|
|
if nvml.DeviceGetMemoryInfo(nvml.device, *memory) == 0 s.memory_used_mb = memory.used / (1024.0 * 1024);
|
|
util: Nvml_Utilization;
|
|
if nvml.DeviceGetUtilizationRates(nvml.device, *util) == 0 s.util_percent = cast(float64) util.gpu;
|
|
value: u32;
|
|
if nvml.DeviceGetTemperature(nvml.device, NVML_TEMPERATURE_GPU, *value) == 0 s.temperature_c = cast(float64) value;
|
|
if nvml.DeviceGetPowerUsage(nvml.device, *value) == 0 s.power_w = value / 1000.0;
|
|
if nvml.DeviceGetClockInfo(nvml.device, NVML_CLOCK_SM, *value) == 0 s.sm_clock_mhz = cast(float64) value;
|
|
return s, true;
|
|
}
|
|
|
|
// The CUDA runtime's and cuDNN's versions, as loaded into this process by onnxruntime's CUDA provider,
|
|
// with where each came from; "" for one not loaded (before a GPU engine is made).
|
|
cuda_library_versions :: () -> cudart: string, cudnn: string {
|
|
cudart, cudnn: string;
|
|
#if OS == .WINDOWS {
|
|
module := GetModuleHandleA("cudart64_13.dll");
|
|
if module {
|
|
get := cast(#type (version: *s32) -> s32 #c_call) GetProcAddress(module, "cudaRuntimeGetVersion");
|
|
version: s32;
|
|
if get && get(*version) == 0 cudart = sprint("%.% (%)", version / 1000, (version % 1000) / 10, module_path(module));
|
|
}
|
|
module = GetModuleHandleA("cudnn64_9.dll");
|
|
if module {
|
|
get := cast(#type () -> u64 #c_call) GetProcAddress(module, "cudnnGetVersion");
|
|
if get {
|
|
version := get(); // 9.x: major * 10000 + minor * 100 + patch
|
|
cudnn = sprint("%.%.% (%)", version / 10000, (version % 10000) / 100, version % 100, module_path(module));
|
|
}
|
|
}
|
|
}
|
|
return cudart, cudnn;
|
|
}
|
|
|
|
#scope_file
|
|
|
|
#if OS == .WINDOWS {
|
|
SYSTEM_POWER_STATUS :: struct {
|
|
ACLineStatus, BatteryFlag, BatteryLifePercent, SystemStatusFlag: u8;
|
|
BatteryLifeTime, BatteryFullLifeTime: u32;
|
|
}
|
|
GetSystemPowerStatus :: (status: *SYSTEM_POWER_STATUS) -> BOOL #foreign kernel32;
|
|
kernel32 :: #system_library "kernel32";
|
|
|
|
module_path :: (module: HANDLE) -> string {
|
|
name: [1024] u16;
|
|
count := GetModuleFileNameW(module, name.data, name.count);
|
|
return wide_to_utf8(name.data, count,, temp);
|
|
}
|
|
}
|
|
|
|
Nvml_Device :: *void;
|
|
Nvml_Memory :: struct { total, free, used: u64; }
|
|
Nvml_Utilization :: struct { gpu, memory: u32; }
|
|
NVML_CLOCK_SM :: 1;
|
|
NVML_CLOCK_MEM :: 2;
|
|
NVML_TEMPERATURE_GPU :: 0;
|
|
|
|
nvml: struct {
|
|
started: bool;
|
|
error: string;
|
|
device: Nvml_Device;
|
|
|
|
Init: #type () -> s32 #c_call;
|
|
DeviceGetHandleByIndex: #type (index: u32, device: *Nvml_Device) -> s32 #c_call;
|
|
DeviceGetName: #type (device: Nvml_Device, name: *u8, length: u32) -> s32 #c_call;
|
|
SystemGetDriverVersion: #type (version: *u8, length: u32) -> s32 #c_call;
|
|
SystemGetCudaDriverVersion: #type (version: *s32) -> s32 #c_call;
|
|
DeviceGetMemoryInfo: #type (device: Nvml_Device, memory: *Nvml_Memory) -> s32 #c_call;
|
|
DeviceGetUtilizationRates: #type (device: Nvml_Device, util: *Nvml_Utilization) -> s32 #c_call;
|
|
DeviceGetTemperature: #type (device: Nvml_Device, sensor: s32, value: *u32) -> s32 #c_call;
|
|
DeviceGetPowerUsage: #type (device: Nvml_Device, milliwatts: *u32) -> s32 #c_call;
|
|
DeviceGetEnforcedPowerLimit: #type (device: Nvml_Device, milliwatts: *u32) -> s32 #c_call;
|
|
DeviceGetClockInfo: #type (device: Nvml_Device, type: s32, mhz: *u32) -> s32 #c_call;
|
|
DeviceGetMaxClockInfo: #type (device: Nvml_Device, type: s32, mhz: *u32) -> s32 #c_call;
|
|
}
|
|
|
|
// NVML, and its first GPU: the one onnxruntime's CUDA provider uses (device 0) on a machine with one.
|
|
nvml_start :: () -> bool {
|
|
if nvml.started return true;
|
|
#if OS == .WINDOWS {
|
|
library := LoadLibraryA("nvml.dll");
|
|
if !library library = LoadLibraryA("C:\\Program Files\\NVIDIA Corporation\\NVSMI\\nvml.dll");
|
|
if !library { nvml.error = "nvml.dll was not found: no NVIDIA driver."; return false; }
|
|
find :: (name: *u8) -> *void #expand { return GetProcAddress(library, name); }
|
|
} else #if OS == .LINUX {
|
|
library := dlopen("libnvidia-ml.so.1", RTLD_NOW);
|
|
if !library { nvml.error = "libnvidia-ml.so.1 was not found: no NVIDIA driver."; return false; }
|
|
find :: (name: *u8) -> *void #expand { return dlsym(library, name); }
|
|
} else {
|
|
nvml.error = "No NVML on this OS.";
|
|
return false;
|
|
}
|
|
nvml.Init = xx find("nvmlInit_v2");
|
|
nvml.DeviceGetHandleByIndex = xx find("nvmlDeviceGetHandleByIndex_v2");
|
|
nvml.DeviceGetName = xx find("nvmlDeviceGetName");
|
|
nvml.SystemGetDriverVersion = xx find("nvmlSystemGetDriverVersion");
|
|
nvml.SystemGetCudaDriverVersion = xx find("nvmlSystemGetCudaDriverVersion");
|
|
nvml.DeviceGetMemoryInfo = xx find("nvmlDeviceGetMemoryInfo");
|
|
nvml.DeviceGetUtilizationRates = xx find("nvmlDeviceGetUtilizationRates");
|
|
nvml.DeviceGetTemperature = xx find("nvmlDeviceGetTemperature");
|
|
nvml.DeviceGetPowerUsage = xx find("nvmlDeviceGetPowerUsage");
|
|
nvml.DeviceGetEnforcedPowerLimit = xx find("nvmlDeviceGetEnforcedPowerLimit");
|
|
nvml.DeviceGetClockInfo = xx find("nvmlDeviceGetClockInfo");
|
|
nvml.DeviceGetMaxClockInfo = xx find("nvmlDeviceGetMaxClockInfo");
|
|
if !nvml.Init || !nvml.DeviceGetHandleByIndex || !nvml.DeviceGetName || !nvml.SystemGetDriverVersion || !nvml.SystemGetCudaDriverVersion
|
|
|| !nvml.DeviceGetMemoryInfo || !nvml.DeviceGetUtilizationRates || !nvml.DeviceGetTemperature || !nvml.DeviceGetPowerUsage
|
|
|| !nvml.DeviceGetEnforcedPowerLimit || !nvml.DeviceGetClockInfo || !nvml.DeviceGetMaxClockInfo {
|
|
nvml.error = "NVML lacks a function gpu-bench needs: an old driver?";
|
|
return false;
|
|
}
|
|
status := nvml.Init();
|
|
if status != 0 { nvml.error = tprint("NVML did not start (error %).", status); return false; }
|
|
status = nvml.DeviceGetHandleByIndex(0, *nvml.device);
|
|
if status != 0 { nvml.error = tprint("NVML found no GPU (error %).", status); return false; }
|
|
nvml.started = true;
|
|
return true;
|
|
}
|
|
|
|
#if OS == .WINDOWS {
|
|
#import "Windows";
|
|
#import "Windows_Utf8";
|
|
#import "Windows_Registry";
|
|
} else #if OS == .LINUX {
|
|
#import "POSIX";
|
|
}
|