Memory Optimization for Hcontainer Class in Parallel Execution #6440
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request addresses issue #6377

44b2136
Fix memory statistics error
- The memory for the record variable
hRGintCd
was not accounted for.- When calculating the memory for the record variable
DMRGint
, it was multiplied by 4 twice.07a9a23
Removed the temporary variable
DMRGint_full
when transitioning from 2D block parallelism to serial in Hcontainer.A temporary variable
DM2D_tmp
was created to split the 2D block parallelDM2D
into smaller blocks. The functiontransferParallels2Serials
is directly called to convertDM2D_tmp
intoDMRGint[]
. This approach avoids the large memory consumption that would occur if a large matrixDMRGint_full
was first used to holdDM2D
and then split into smaller matricesDMRGint
.some detail need to modify
0a799ba
Following a similar approach as described above, the temporary variable
hRGintCd
, which was used in the conversion of HContainer from serial to 2D block distributed parallel layout, has been removed. Instead, a smaller auxiliary matrixhR_tmp
is now used to partitionhR
into blocks, facilitating the type conversion. The data transfer path has been changed from the originalhRGint_tmp → hRGintCd → hR
tohRGint_tmp → hR_tmp → hR
.todo: