carma_context.h File Reference

#include <cuda_runtime_api.h>
#include <stdio.h>
#include <stdlib.h>
#include <vector_types.h>
#include <memory>
#include <string>
#include <vector>
#include "carma_cublas.h"
#include "carma_cusparse.h"
#include "carma_utils.h"

Include dependency graph for carma_context.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	CarmaDevice
class	CarmaContext
	this class provides the context in which CarmaObj are created More...

Macros
#define	set_active_device(new_device, silent)   _set_active_device(new_device, silent, __FILE__, __LINE__)
#define	set_active_device_force(new_device, silent)   _set_active_device_force(new_device, silent, __FILE__, __LINE__)
#define	set_active_deviceForCpy(new_device, silent)   _set_active_device_for_copy(new_device, silent, __FILE__, __LINE__)

Functions
int	convert_sm_version2cores (int major, int minor)
	from /usr/local/cuda/samples/common/inc/helper_cuda.h More...

Macro Definition Documentation

set_active_device

#define set_active_device	(		new_device,
			silent
	)		_set_active_device(new_device, silent, __FILE__, __LINE__)

Definition at line 98 of file carma_context.h.

set_active_device_force

#define set_active_device_force	(		new_device,
			silent
	)		_set_active_device_force(new_device, silent, __FILE__, __LINE__)

Definition at line 100 of file carma_context.h.

set_active_deviceForCpy

#define set_active_deviceForCpy	(		new_device,
			silent
	)		_set_active_device_for_copy(new_device, silent, __FILE__, __LINE__)

Definition at line 102 of file carma_context.h.

Function Documentation

convert_sm_version2cores()

int convert_sm_version2cores	(	int	major,
		int	minor
	)

from /usr/local/cuda/samples/common/inc/helper_cuda.h

Definition at line 185 of file carma_context.h.

                                                          {
  // Defines for GPU Architecture types (using the SM version to determine the #
  // of cores per SM
  typedef struct {
    int SM;  // 0xMm (hexidecimal notation), M = SM Major version, and m = SM
             // minor version
    int Cores;
  } sSMtoCores;
 
  sSMtoCores nGpuArchCoresPerSM[] = {
      {0x20, 32},   // Fermi Generation (SM 2.0) GF100 class
      {0x21, 48},   // Fermi Generation (SM 2.1) GF10x class
      {0x30, 192},  // Kepler Generation (SM 3.0) GK10x class
      {0x32, 192},  // Kepler Generation (SM 3.2) GK10x class
      {0x35, 192},  // Kepler Generation (SM 3.5) GK11x class
      {0x37, 192},  // Kepler Generation (SM 3.7) GK21x class
      {0x50, 128},  // Maxwell Generation (SM 5.0) GM10x class
      {0x52, 128},  // Maxwell Generation (SM 5.2) GM20x class
      {0x53, 128},  // Maxwell Generation (SM 5.3) GM20x class
      {0x60, 64},   // Pascal Generation (SM 6.0) GP100 class
      {0x61, 128},  // Pascal Generation (SM 6.1) GP10x class
      {0x62, 128},  // Pascal Generation (SM 6.2) GP10x class
      {0x70, 64},   // Volta Generation (SM 7.0) GV100 class
      {0x72, 64},   // Volta Generation (SM 7.2) GV10B class
      {0x75, 64},   // Turing Generation (SM 7.5) TU100 class
      {-1, -1}};
 
  int index = 0;
 
  while (nGpuArchCoresPerSM[index].SM != -1) {
    if (nGpuArchCoresPerSM[index].SM == ((major << 4) + minor)) {
      return nGpuArchCoresPerSM[index].Cores;
    }
 
    index++;
  }
 
  // If we don't find the values, we default use the previous one to run
  // properly
  printf(
      "MapSMtoCores for SM %d.%d is undefined.  Default to use %d Cores/SM\n",
      major, minor, nGpuArchCoresPerSM[index - 1].Cores);
  return nGpuArchCoresPerSM[index - 1].Cores;
}