[Performance] cuTN circuit2einsum slower than opt_einsum
@haidarazzam 已经在做这个了。
开始于 2023年9月26日。
评估
这个 Issue 还没有评估数据。
描述
Discussed in https://github.com/NVIDIA/cuQuantum/discussions/53
Originally posted by rht May 12, 2023
I was benchmarking cuTensorNet and opt_einsum on the QFT and QAOA circuit, and I found the former to be consistently slower than the latter.
I used the same code in https://github.com/NVIDIA/cuQuantum/discussions/23 for cuTensorNet, and for opt_einsum:
bitstring = "0" * len(qubits)
# https://optimized-einsum.readthedocs.io/en/stable/autosummary/opt_einsum.contract_path.html#opt_einsum.contract_path
expression, operands = myconverter.amplitude(bitstring=bitstring)
tic = time.time()
path, path_info = oe.contract_path(expression, *operands)
elapsed1 = time.time() - tic
print("Elapsed opt_einsum path finding", elapsed1)
tic = time.time()
output = oe.contract(expression, *operands, optimize=path)
elapsed2 = time.time() - tic
print("Elapsed opt_einsum contract", elapsed2)
Plot for QFT:
I think it has something to do with cuTensorNet's path finding being closer to the global optimum. Is there a way to tweak the hyperoptimizer to either stop early, or to have a larger error tolerance, so as to minimize the overall time?
- 主要语言
- Jupyter Notebook
- 星标
- 502
- 派生
- 102
- PR 合并指标
- 30 天内没有已合并 PR
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 没有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
NVIDIA/cuQuantum 的其他 Issue
-
难度 1/5 1 小时以内 新手友好度 94/100
-
难度 5/5 一周以上 新手友好度 8/100
-
CUDA 12 cuquantum-appliance image ships a UCX `libucm_cuda.so.0` linked against `libcudart.so.13`未关闭
难度 4/5 3-5 天 新手友好度 25/100
-
难度 4/5 3-5 天 新手友好度 48/100
-
难度 4/5 3-5 天 新手友好度 48/100