[v0.30] Build pciutils only if neccesary
If only HSA is enabled we dont need pciutils since AMD detection does not rely on it. Therefore we change CMakeLists.txt to build pciutils only if required. This commit has some side-effects: 1. We now don't build Intel backend by default. In other words, no backend is built by default, the user must specify which backend to use. 2. There were some issues with includes and wrongly used defines and variables. This commit fixes all that.
This commit is contained in:
@@ -5,8 +5,8 @@
|
||||
|
||||
#include "cuda.hpp"
|
||||
#include "uarch.hpp"
|
||||
#include "pci.hpp"
|
||||
#include "gpufetch_helper_cuda.hpp"
|
||||
#include "../common/pci.hpp"
|
||||
#include "../common/global.hpp"
|
||||
#include "../common/uarch.hpp"
|
||||
|
||||
@@ -33,10 +33,8 @@ int get_tensor_cores(struct uarch* arch, int sm, int major) {
|
||||
if(major == 7) {
|
||||
// TU116 does not have tensor cores!
|
||||
// https://www.anandtech.com/show/13973/nvidia-gtx-1660-ti-review-feat-evga-xc-gaming/2
|
||||
if(arch->chip == CHIP_TU116 || arch->chip == CHIP_TU116BM ||
|
||||
arch->chip == CHIP_TU116GL || arch->chip == CHIP_TU116M) {
|
||||
if (is_chip_TU116(arch))
|
||||
return 0;
|
||||
}
|
||||
return sm * 8;
|
||||
}
|
||||
else if(major == 8) return sm * 4;
|
||||
|
||||
Reference in New Issue
Block a user