def packing(self, src_tensor):
src_tensor = src_tensor.to(self.device)
self.compression_python.set()
self.compression_specific.set()
#torch.cuda.synchronize()
self.compression_specific.record()
src_tensor = torch.sign(src_tensor)
src_tensor_size = src_tensor.size()
src_tensor = src_tensor.view(-1)
src_len = len(src_tensor)
add_elm = 32 - (src_len % 32)
if src_len % 32 == 0:
add_elm = 0
new_tensor = torch.zeros([add_elm],
dtype=torch.float32,
device=self.device)
src_tensor = torch.cat((src_tensor, new_tensor), 0)
src_tensor = src_tensor.view(32, -1)
src_tensor = src_tensor.to(dtype=torch.int32)
#torch.cuda.synchronize()
self.compression_python.record()
self.compression_cuda.set()
#torch.cuda.synchronize()
dst_tensor = bit2byte.packing(src_tensor)
dst_tensor = dst_tensor.to(dtype=torch.int32)
#torch.cuda.synchronize()
self.compression_cuda.record()
return dst_tensor.to(self.source_device), src_tensor_size
def majority_vote(self, src_tensor_list):
self.majority_vote_decompression.set()
#torch.cuda.synchronize()
voter_num = len(src_tensor_list)
src_tensor = torch.stack(src_tensor_list)
src_tensor = src_tensor.view(-1)
full_size = 32 * len(src_tensor)
new_tensor = torch.ones(full_size, device=self.device, dtype=torch.int32)
new_tensor = new_tensor.view(32,-1)
new_tensor = bit2byte.unpacking(src_tensor,new_tensor)
new_tensor = - new_tensor.add_(-1)
#torch.cuda.synchronize()
self.majority_vote_decompression.record()
#sum
self.majority_vote_sum_calculation.set()
#torch.cuda.synchronize()
new_tensor = new_tensor.permute(1,0).contiguous().view(voter_num,-1)
new_tensor = torch.sum(new_tensor,0)
new_tensor = new_tensor.view(-1,32).permute(1,0)
#torch.cuda.synchronize()
self.majority_vote_sum_calculation.record()
self.majority_vote_compression.set()
#torch.cuda.synchronize()
new_tensor = torch.sign(new_tensor)
new_tensor = bit2byte.packing(new_tensor)
new_tensor = new_tensor.to(dtype=torch.int32)
#torch.cuda.synchronize()
self.majority_vote_compression.record()
return new_tensor
def packing(self, src_tensor):
src_tensor = torch.sign(src_tensor)
src_tensor_size = src_tensor.size()
src_tensor = src_tensor.view(-1)
src_len = len(src_tensor)
add_elm = 32 - (src_len % 32)
if src_len % 32 == 0:
add_elm = 0
new_tensor = torch.zeros([add_elm], dtype=torch.float32, device=src_tensor.device)
src_tensor = torch.cat((src_tensor, new_tensor), 0)
src_tensor = src_tensor.view(32, -1)
src_tensor = src_tensor.to(dtype=torch.int32)
dst_tensor = bit2byte.packing(src_tensor)
dst_tensor = dst_tensor.to(dtype=torch.int32)
return dst_tensor, src_tensor_size
def majority_vote(self, src_tensor_list):
voter_num = len(src_tensor_list)
src_tensor = torch.stack(src_tensor_list)
src_tensor = src_tensor.view(-1)
full_size = 32 * len(src_tensor)
new_tensor = torch.ones(full_size, device=src_tensor.device, dtype=torch.int32)
new_tensor = new_tensor.view(32, -1)
new_tensor = bit2byte.unpacking(src_tensor, new_tensor)
new_tensor = -new_tensor.add_(-1)
# sum
new_tensor = new_tensor.permute(1, 0).contiguous().view(voter_num, -1)
new_tensor = torch.sum(new_tensor, 0)
new_tensor = new_tensor.view(-1, 32).permute(1, 0)
new_tensor = torch.sign(new_tensor)
new_tensor = bit2byte.packing(new_tensor)
new_tensor = new_tensor.to(dtype=torch.int32)
return new_tensor
