Timing - compare 2GPU with 1GPU for the same case

Open

#21 opened on Mar 25, 2016 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty: 4/5
Estimated time: 3-5 days
Newbie friendliness: 25/100

Issue type: Feature
Clarity: Needs clarification
Activity status: Stale
Domain: hpc, performance

Research direction

Start by locating the CUDA solver entry point where the choice between one and two GPUs is made, then trace how timing or diagnostic output is handled. Check whether an existing test script or case can exercise both configurations; done means a reproducible comparison for the same case with visible timing output.

Written by the indexing model from the issue text.

Description

auto-migrated Priority-Medium Type-Defect

What version of the product are you using? On what operating system?

Opencurrent 1.1.0 on Ubuntu 10.10

Please provide any additional information below.

I am trying to put timing statements into the code to compare the performance 
of a single GPU and a 2GPU solution for the same case. I can't seem to get 
anything to print out. In which function is the choice made whether to solve on 
1 or 2 GPUs? I don't mind which test case is used in the first instance.

Is there by any chance an existing test script for this?

Thanks
Matt

Original issue reported on code.google.com by mattsal...@gmail.com on 29 Feb 2012 at 9:54

Dominant language: Cuda
Stars: 6
Forks: 2
PR merge metrics: No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

Read the whole issue, then the project's contributing guide.
Comment on the issue to say you are picking it up — it saves two people doing the same work.
Fork the repository and make your change on a branch.
Open a pull request that references the issue number.

Similar issues

[H25] `switch_to_safer_KKT` hard-codes an inertia-correction acceptor, which the GPU sparse solvers refuse Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

llnl/hiop#798 · Opened Sep 22, 2026
[E28] `-log_view` aborts every `HIOPSPARSEGPU` solve (unbalanced event in the sparse inequality Jacobian) Open

Difficulty 1/5 Under an hour Newbie friendliness 92/100

ORNL/ExaGO#100 · 1 comment · Opened Sep 22, 2026
[BUG]: cuda.compute: gpu_struct treats NumPy field titles as separate fields Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

NVIDIA/cccl#11576 · 1 comment · Opened Sep 22, 2026
Add `factorise` to lock_exchange.cpp example Open

C++ Enhancement Examples

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

csrc-sdsu/mole#464 · 1 reaction · Opened Sep 18, 2026

More HPC issues