def MTTKRP(self,
mode,
mats=None,
matsorder=None,
type="default",
testing=False):
if mats == None:
serial = 0 # TODO make code to make mats inside here
if type == "default":
serial = 0 # TODO make params
if type == "serial":
PTI.ptiMTTKRP(self.address, mats.address, matsorder, mode)
if type == "CPU":
PTI.ptiOMPMTTKRP(self.address, mats.address, matsorder, mode)
if type == "CPU_Reduce": PTI.ptiOmpMTTKRP_Reduce()
if type == "CPU_Lock": PTI.ptiOmpMTTKRP_Lock()
if type == "CUDA": PTI.ptiCudaMTTKRP()
if type == "CUDA_1K": PTI.ptiCudaMTTKRPOneKernal()
if type == "CUDA_SM": PTI.ptiCudaMTTKRPSM()
if type == "CUDA_Device": PTI.ptiCudaMTTKRPDevice()
if type == "CUDA_Coarse": PTI.ptiCudaCoareMTTKRP()
if type == "Splitted": PTI.ptiSplittedMTTKRP()
return mats
def MTTKRP(self,
mode,
mats=None,
matsorder=None,
type="default",
testing=False):
if mats == None:
serial = 0 #TODO make code to make mats inside here
if type == "default":
print(
"Default Cases not learned yet. Make sure you spedify your run type."
)
if type == "serial":
PTI.ptiMTTKRPHiCOO(self.address, mats.address, matsorder, mode)
elif type == "CPU":
PTI.ptiOMPMTTKRPHiCOO(self.address, mats.address, matsorder, mode)
elif type == "CPU_Reduce":
PTI.ptiOmpMTTKRP_Reduce()
elif type == "CPU_Lock":
PTI.ptiOmpMTTKRP_Lock()
elif type == "CUDA":
PTI.ptiCudaMTTKRP()
elif type == "CUDA_1K":
PTI.ptiCudaMTTKRPOneKernal()
elif type == "CUDA_SM":
PTI.ptiCudaMTTKRPSM()
elif type == "CUDA_Device":
PTI.ptiCudaMTTKRPDevice()
elif type == "CUDA_Coarse":
PTI.ptiCudaCoareMTTKRP()
elif type == "Splitted":
PTI.ptiSplittedMTTKRP()
if not testing: return mats