You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
taco: ensure assembly is included in timing for all benchmarks #8
For comparisons against other Python libraries, I think it'd make sense to include the assembly time when benchmarking so that the comparison is more apples-to-apples, particularly since assembly can take a significant amount of time when the output is sparse. (Note though that assembly time can be significantly reduced if it is done with the compute step using a fused kernel. With the C++ API at least, you should be able to tell TACO to generate code that simultaneously assembles and computes the output by invoking TensorBase::setAssembleWhileCompute(true) before invoking compile.)
Activity
stephenchouca commentedon Mar 9, 2021
For comparisons against other Python libraries, I think it'd make sense to include the assembly time when benchmarking so that the comparison is more apples-to-apples, particularly since assembly can take a significant amount of time when the output is sparse. (Note though that assembly time can be significantly reduced if it is done with the compute step using a fused kernel. With the C++ API at least, you should be able to tell TACO to generate code that simultaneously assembles and computes the output by invoking
TensorBase::setAssembleWhileCompute(true)before invoking compile.)[-]benchmark timing inclusion[/-][+]taco: ensure assembly is included in timing for all benchmarks[/+]rohany commentedon Mar 9, 2021
If
setAssembleWhileCompute(true)is used, then doesassembleeven need to be called before compute?stephenchouca commentedon Mar 9, 2021
You shouldn't have to call
assemblein that case.