Frankd35
commented
1 month ago compute.py
import torch
import numpy as np
from nonmlu_ops.base import *
@registerTensorList("lgamma")
class LgammaTensorList(TensorList):
pass
@registerOp("lgamma")
class LgammaOp(OpTest):
def __init__(self, tensorlist, params):
super().__init__(tensorlist, params)
def compute(self):
# 确定输出张量
input_tensor = self.tensor_list_.getInputTensor(0)
output_tensor = self.tensor_list_.getOutputTensor(0)
output_shape = self.tensor_list_.getInputTensor(0).getShape()
datatype = input_tensor.getDataType().getNumpyStr()
if datatype == 'float16':
torch_input = torch.tensor(input_tensor.getDataNode().getData()).half().cuda()
else:
torch_input = torch.tensor(input_tensor.getDataNode().getData()).float().cuda()
# compute baseline
# torch_input = torch.tensor(input_tensor.getData()).cuda()
torch_output = torch_input.new_zeros(output_shape)
device = torch.device("cuda:0")
lgamma_result = torch.lgamma(torch_input)
input_has_inf = np.isinf(torch_input.cpu()).any()
input_has_nan = np.isnan(torch_input.cpu()).any()
result_has_inf = np.isinf(lgamma_result.cpu()).any()
result_has_nan = np.isnan(lgamma_result.cpu()).any()
# 转移数据到 CPU 并转换为 NumPy 数组
lgamma_result = lgamma_result.cpu().numpy()
# 设置输出张量的形状和数据
output_tensor.setShape(lgamma_result.shape)
output_tensor.setData(lgamma_result)
# if dynamic threshold
if self.params_.get("if_dynamic_threshold", False):
base_node = DataNode("double")
torch_input_fp64 = torch_input.double()
lgamma_result_fp64 = torch.lgamma(torch_input_fp64)
base_node.setData(lgamma_result_fp64.cpu().numpy())
eva = diff_utils.Evaluator(base_node, output_tensor.getDataNode())
output_tensor.setData(lgamma_result_fp64.cpu().numpy())
if(input_has_inf or input_has_nan or result_has_inf or result_has_nan):
output_tensor.setDiff( 0.003, 0.003)
else:
output_tensor.setDiff(eva.computeDiff1(), eva.computeDiff2())
@registerProtoWriter("lgamma")
class LgammaProtoWriter(MluOpProtoWriter):
pass
DanieeelLiu
Thanks for your contribution and we appreciate it a lot. :rocket::rocket:
1. Motivation
add new operator lgamma
2. Modification
add implementation of lgamma
3. Test Report
not yet
3.1 Modification Details
3.1.1 Accuracy Acceptance Standard
For static threshold standard details, see: MLU-OPS™ Accuracy Acceptance Standard.
3.1.2 Operator Scheme checklist
3.2 Accuracy Test
3.2.1 Accuracy Test
If you have checked the following items, please tick the relevant box.
3.2.2 Parameter Check
Test Point-1:
When a new operator is submitted, the test points are given and the test results are stated. Acceptance Standard:Normal error.Test Point-2:
Whether illegal parameters are passed. Acceptance Standard:Normal error.3.3 Performance Test
See MLU-OPS™ Performance Acceptance Standard for details.
Platform：MLU370
3.4 Summary Analysis
the v1.0 lgamma implemtentation is a simd operator, and lack of stride support
Please give a brief overview here, if you want to note and summarize the content.