-
Couldn't load subscription status.
- Fork 62
Open
Labels
comp-LogicRelated to internal code logicRelated to internal code logicmaintainabilitySimplifies further code development (standardization, robustness)Simplifies further code development (standardization, robustness)performanceSimulation speed, memory consumptionSimulation speed, memory consumptionpri-MediumWorth assigning to a milestoneWorth assigning to a milestonesparseSparse (non-FFT) modeSparse (non-FFT) mode
Milestone
Description
Recent optimizations of imExp (#169) made SSE3 code only marginally faster than the standard c99 one (with compiler optimizations). It also showed that part of the SSE3 speedup is due to unsafe optimizations (can lead to precision loss).
Thus, better maintainability can be obtained if SSE3 code is removed altogether. However, it is worth studying where the remaining 10% speedup due to SSE3 comes from and optimizing the standard code accordingly.
/cc @jleinonen
Metadata
Metadata
Assignees
Labels
comp-LogicRelated to internal code logicRelated to internal code logicmaintainabilitySimplifies further code development (standardization, robustness)Simplifies further code development (standardization, robustness)performanceSimulation speed, memory consumptionSimulation speed, memory consumptionpri-MediumWorth assigning to a milestoneWorth assigning to a milestonesparseSparse (non-FFT) modeSparse (non-FFT) mode