py/sunhpc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add init pxe cmd

Browse Source
This commit is contained in:
Qichao
2026-05-05 02:12:33 +08:00
parent 9ec1cf4fdd
commit 2cc70998d1
24 changed files with 30461 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

87
var/pkgs/cuda/13.0/nvml/example/Makefile Normal file
View File

@@ -0,0 +1,87 @@
ARCH := $(shell getconf LONG_BIT)
OS := $(shell cat /etc/issue)
ifneq (,$(wildcard /etc/redhat-release))
RHEL_OS := $(shell cat /etc/redhat-release)
endif
# Gets Driver Branch
DRIVER_BRANCH := $(shell nvidia-smi | grep Driver | cut -f 3 -d' ' | cut -f 1 -d '.')
# Location of the CUDA Toolkit
CUDA_PATH ?= "/usr/local/cuda-8.0"
ifeq (${ARCH},$(filter ${ARCH},32 64))
# If correct architecture and libnvidia-ml library is not found
# within the environment, build using the stub library
ifneq (,$(findstring Ubuntu,$(OS)))
DEB := $(shell dpkg -l | grep cuda)
ifneq (,$(findstring cuda, $(DEB)))
NVML_LIB := /usr/lib/nvidia-$(DRIVER_BRANCH)
else
NVML_LIB := /lib${ARCH}
endif
endif
ifneq (,$(findstring SUSE,$(OS)))
RPM := $(shell rpm -qa cuda*)
ifneq (,$(findstring cuda, $(RPM)))
NVML_LIB := /usr/lib${ARCH}
else
NVML_LIB := /lib${ARCH}
endif
endif
ifneq (,$(findstring CentOS,$(RHEL_OS)))
RPM := $(shell rpm -qa cuda*)
ifneq (,$(findstring cuda, $(RPM)))
NVML_LIB := /usr/lib${ARCH}/nvidia
else
NVML_LIB := /lib${ARCH}
endif
endif
ifneq (,$(findstring Red Hat,$(RHEL_OS)))
RPM := $(shell rpm -qa cuda*)
ifneq (,$(findstring cuda, $(RPM)))
NVML_LIB := /usr/lib${ARCH}/nvidia
else
NVML_LIB := /lib${ARCH}
endif
endif
ifneq (,$(findstring Fedora,$(RHEL_OS)))
RPM := $(shell rpm -qa cuda*)
ifneq (,$(findstring cuda, $(RPM)))
NVML_LIB := /usr/lib${ARCH}/nvidia
else
NVML_LIB := /lib${ARCH}
endif
endif
else
NVML_LIB := ../../lib${ARCH}/stubs/
$(info "libnvidia-ml.so.1" not found, using stub library.)
endif
ifneq (${ARCH},$(filter ${ARCH},32 64))
$(error Unknown architecture!)
endif
NVML_LIB += ../lib/
NVML_LIB_L := $(addprefix -L , $(NVML_LIB))
CFLAGS := -I ../../include -I ../include
LDFLAGS := -lnvidia-ml $(NVML_LIB_L)
all: example supportedVgpus
example: example.o
$(CC) $< $(CFLAGS) $(LDFLAGS) -o $@
supportedVgpus: supportedVgpus.o
$(CC) $< $(CFLAGS) $(LDFLAGS) -o $@
clean:
-@rm -f example.o
-@rm -f example
-@rm -f supportedVgpus.o
-@rm -f supportedVgpus

10
var/pkgs/cuda/13.0/nvml/example/README.txt Normal file
View File

@@ -0,0 +1,10 @@
The NVIDIA GDK provides a simple example program that shows how to build an
NVML client. When running an NVML client while the GDK is installed, be
sure your library path first includes the actual NVML library (installed
with the driver), not the stub library that exists solely for
compilation on systems without an NVIDIA driver available.
If you have installed this example code via your packaging system,
you should first copy it to a user directory before compilation.
The packaging system uninstall feature will not remove this directory if it
contains new files beyond what were installed as part of the GDK.

180
var/pkgs/cuda/13.0/nvml/example/example.c Normal file
View File

@@ -0,0 +1,180 @@
/***************************************************************************\
|* *|
|* Copyright 2010-2016 NVIDIA Corporation. All rights reserved. *|
|* *|
|* NOTICE TO USER: *|
|* *|
|* This source code is subject to NVIDIA ownership rights under U.S. *|
|* and international Copyright laws. Users and possessors of this *|
|* source code are hereby granted a nonexclusive, royalty-free *|
|* license to use this code in individual and commercial software. *|
|* *|
|* NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE *|
|* CODE FOR ANY PURPOSE. IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR *|
|* IMPLIED WARRANTY OF ANY KIND. NVIDIA DISCLAIMS ALL WARRANTIES WITH *|
|* REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF *|
|* MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR *|
|* PURPOSE. IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, *|
|* INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES *|
|* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN *|
|* AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING *|
|* OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOURCE *|
|* CODE. *|
|* *|
|* U.S. Government End Users. This source code is a "commercial item" *|
|* as that term is defined at 48 C.F.R. 2.101 (OCT 1995), consisting *|
|* of "commercial computer software" and "commercial computer software *|
|* documentation" as such terms are used in 48 C.F.R. 12.212 (SEPT 1995) *|
|* and is provided to the U.S. Government only as a commercial end item. *|
|* Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through *|
|* 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the *|
|* source code with only those rights set forth herein. *|
|* *|
|* Any use of this source code in individual and commercial software must *|
|* include, in the user documentation and internal comments to the code, *|
|* the above Disclaimer and U.S. Government End Users Notice. *|
|* *|
|* *|
\***************************************************************************/
#include <stdio.h>
#include <nvml.h>
static const char * convertToComputeModeString(nvmlComputeMode_t mode)
{
switch (mode)
{
case NVML_COMPUTEMODE_DEFAULT:
return "Default";
case NVML_COMPUTEMODE_EXCLUSIVE_THREAD:
return "Exclusive_Thread";
case NVML_COMPUTEMODE_PROHIBITED:
return "Prohibited";
case NVML_COMPUTEMODE_EXCLUSIVE_PROCESS:
return "Exclusive Process";
default:
return "Unknown";
}
}
int main(void)
{
nvmlReturn_t result;
unsigned int device_count, i;
// First initialize NVML library
result = nvmlInit();
if (NVML_SUCCESS != result)
{
printf("Failed to initialize NVML: %s\n", nvmlErrorString(result));
printf("Press ENTER to continue...\n");
getchar();
return 1;
}
result = nvmlDeviceGetCount(&device_count);
if (NVML_SUCCESS != result)
{
printf("Failed to query device count: %s\n", nvmlErrorString(result));
goto Error;
}
printf("Found %u device%s\n\n", device_count, device_count != 1 ? "s" : "");
printf("Listing devices:\n");
for (i = 0; i < device_count; i++)
{
nvmlDevice_t device;
char name[NVML_DEVICE_NAME_BUFFER_SIZE];
nvmlPciInfo_t pci;
nvmlComputeMode_t compute_mode;
// Query for device handle to perform operations on a device
// You can also query device handle by other features like:
// nvmlDeviceGetHandleBySerial
// nvmlDeviceGetHandleByPciBusId
result = nvmlDeviceGetHandleByIndex(i, &device);
if (NVML_SUCCESS != result)
{
printf("Failed to get handle for device %u: %s\n", i, nvmlErrorString(result));
goto Error;
}
result = nvmlDeviceGetName(device, name, NVML_DEVICE_NAME_BUFFER_SIZE);
if (NVML_SUCCESS != result)
{
printf("Failed to get name of device %u: %s\n", i, nvmlErrorString(result));
goto Error;
}
// pci.busId is very useful to know which device physically you're talking to
// Using PCI identifier you can also match nvmlDevice handle to CUDA device.
result = nvmlDeviceGetPciInfo(device, &pci);
if (NVML_SUCCESS != result)
{
printf("Failed to get pci info for device %u: %s\n", i, nvmlErrorString(result));
goto Error;
}
printf("%u. %s [%s]\n", i, name, pci.busId);
// This is a simple example on how you can modify GPU's state
result = nvmlDeviceGetComputeMode(device, &compute_mode);
if (NVML_ERROR_NOT_SUPPORTED == result)
printf("\t This is not CUDA capable device\n");
else if (NVML_SUCCESS != result)
{
printf("Failed to get compute mode for device %u: %s\n", i, nvmlErrorString(result));
goto Error;
}
else
{
// try to change compute mode
printf("\t Changing device's compute mode from '%s' to '%s'\n",
convertToComputeModeString(compute_mode),
convertToComputeModeString(NVML_COMPUTEMODE_PROHIBITED));
result = nvmlDeviceSetComputeMode(device, NVML_COMPUTEMODE_PROHIBITED);
if (NVML_ERROR_NO_PERMISSION == result)
printf("\t\t Need root privileges to do that: %s\n", nvmlErrorString(result));
else if (NVML_ERROR_NOT_SUPPORTED == result)
printf("\t\t Compute mode prohibited not supported. You might be running on\n"
"\t\t windows in WDDM driver model or on non-CUDA capable GPU\n");
else if (NVML_SUCCESS != result)
{
printf("\t\t Failed to set compute mode for device %u: %s\n", i, nvmlErrorString(result));
goto Error;
}
else
{
printf("\t Restoring device's compute mode back to '%s'\n",
convertToComputeModeString(compute_mode));
result = nvmlDeviceSetComputeMode(device, compute_mode);
if (NVML_SUCCESS != result)
{
printf("\t\t Failed to restore compute mode for device %u: %s\n", i, nvmlErrorString(result));
goto Error;
}
}
}
}
result = nvmlShutdown();
if (NVML_SUCCESS != result)
printf("Failed to shutdown NVML: %s\n", nvmlErrorString(result));
printf("All done.\n");
printf("Press ENTER to continue...\n");
getchar();
return 0;
Error:
result = nvmlShutdown();
if (NVML_SUCCESS != result)
printf("Failed to shutdown NVML: %s\n", nvmlErrorString(result));
printf("Press ENTER to continue...\n");
getchar();
return 1;
}

160
var/pkgs/cuda/13.0/nvml/example/supportedVgpus.c Normal file
View File

@@ -0,0 +1,160 @@
/***************************************************************************\
|* *|
|* Copyright 2010-2016 NVIDIA Corporation. All rights reserved. *|
|* *|
|* NOTICE TO USER: *|
|* *|
|* This source code is subject to NVIDIA ownership rights under U.S. *|
|* and international Copyright laws. Users and possessors of this *|
|* source code are hereby granted a nonexclusive, royalty-free *|
|* license to use this code in individual and commercial software. *|
|* *|
|* NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE *|
|* CODE FOR ANY PURPOSE. IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR *|
|* IMPLIED WARRANTY OF ANY KIND. NVIDIA DISCLAIMS ALL WARRANTIES WITH *|
|* REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF *|
|* MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR *|
|* PURPOSE. IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, *|
|* INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES *|
|* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN *|
|* AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING *|
|* OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOURCE *|
|* CODE. *|
|* *|
|* U.S. Government End Users. This source code is a "commercial item" *|
|* as that term is defined at 48 C.F.R. 2.101 (OCT 1995), consisting *|
|* of "commercial computer software" and "commercial computer software *|
|* documentation" as such terms are used in 48 C.F.R. 12.212 (SEPT 1995) *|
|* and is provided to the U.S. Government only as a commercial end item. *|
|* Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through *|
|* 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the *|
|* source code with only those rights set forth herein. *|
|* *|
|* Any use of this source code in individual and commercial software must *|
|* include, in the user documentation and internal comments to the code, *|
|* the above Disclaimer and U.S. Government End Users Notice. *|
|* *|
|* *|
\***************************************************************************/
#include <stdio.h>
#include <nvml.h>
#include <stdlib.h>
int main(void)
{
nvmlReturn_t result;
unsigned int device_count, i;
// First initialize NVML library
result = nvmlInit();
if (NVML_SUCCESS != result)
{
printf("Failed to initialize NVML: %s\n", nvmlErrorString(result));
return 1;
}
result = nvmlDeviceGetCount(&device_count);
if (NVML_SUCCESS != result)
{
printf("Failed to query device count: %s\n", nvmlErrorString(result));
goto Error;
}
printf("Found %u device%s\n", device_count, device_count != 1 ? "s" : "");
printf("Listing devices:\n");
for (i = 0; i < device_count; i++)
{
nvmlDevice_t device;
char name[NVML_DEVICE_NAME_BUFFER_SIZE];
nvmlPciInfo_t pci;
// Query for device handle to perform operations on a device
// You can also query device handle by other features like:
// nvmlDeviceGetHandleBySerial
// nvmlDeviceGetHandleByPciBusId
result = nvmlDeviceGetHandleByIndex(i, &device);
if (NVML_SUCCESS != result)
{
printf("Failed to get handle for device %u: %s\n", i, nvmlErrorString(result));
goto Error;
}
result = nvmlDeviceGetName(device, name, NVML_DEVICE_NAME_BUFFER_SIZE);
if (NVML_SUCCESS != result)
{
printf("Failed to get name of device %u: %s\n", i, nvmlErrorString(result));
goto Error;
}
// pci.busId is very useful to know which device physically you're talking to
// Using PCI identifier you can also match nvmlDevice handle to CUDA device.
result = nvmlDeviceGetPciInfo(device, &pci);
if (NVML_SUCCESS != result)
{
printf("Failed to get pci info for device %u: %s\n", i, nvmlErrorString(result));
goto Error;
}
printf("%u. %s [%s]\n", i, name, pci.busId);
// This is an example to get the supported vGPUs type names
unsigned int vgpuCount = 0;
nvmlVgpuTypeId_t *vgpuTypeIds = NULL;
unsigned int j;
result = nvmlDeviceGetSupportedVgpus(device, &vgpuCount, NULL);
if (NVML_ERROR_INSUFFICIENT_SIZE != result)
goto Error;
if (vgpuCount != 0)
{
vgpuTypeIds = malloc(sizeof(nvmlVgpuTypeId_t) * vgpuCount);
if (!vgpuTypeIds)
{
printf("Memory allocation of %d bytes failed \n", (int)(sizeof(*vgpuTypeIds)*vgpuCount));
goto Error;
}
result = nvmlDeviceGetSupportedVgpus(device, &vgpuCount, vgpuTypeIds);
if (NVML_SUCCESS != result)
{
printf("Failed to get the supported vGPUs with status %d \n", (int)result);
goto Error;
}
printf(" Displaying vGPU type names: \n");
for (j = 0; j < vgpuCount; j++)
{
char vgpuTypeName[NVML_DEVICE_NAME_BUFFER_SIZE];
unsigned int bufferSize = NVML_DEVICE_NAME_BUFFER_SIZE;
if (NVML_SUCCESS == (result = nvmlVgpuTypeGetName(vgpuTypeIds[j], vgpuTypeName, &bufferSize)))
{
printf(" %s\n",vgpuTypeName);
}
else
{
printf("Failed to query the vGPU type name with status %d \n", (int)result);
}
}
}
if (vgpuTypeIds)
free(vgpuTypeIds);
}
result = nvmlShutdown();
if (NVML_SUCCESS != result)
printf("Failed to shutdown NVML: %s\n", nvmlErrorString(result));
printf("All done.\n");
return 0;
Error:
result = nvmlShutdown();
if (NVML_SUCCESS != result)
printf("Failed to shutdown NVML: %s\n", nvmlErrorString(result));
return 1;
}