Reshape Memory Freeing and Generic Float GEMM Fixes #91
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…lias_of parameter. Fixed GEMM template
diaconuccalin
changed the title
Xeratec
approved these changes
Jun 5, 2025
Member
Xeratec
left a comment
Xeratec
left a comment
There was a problem hiding this comment.
Looks good, just one comment about adding new alias to a buffer. I can live with both options, but would be curious to get your opinion.
Signed-off-by: Călin Diaconu <[email protected]>
diaconuccalin
added a commit
to diaconuccalin/Deeploy
that referenced
this pull request
Jun 13, 2025
Member
|
Looks good. Thanks for the work! |
Closed
Merged
Xeratec
added a commit
that referenced
this pull request
Jul 8, 2025
This release contains major architectural changes, new platform support, enhanced simulation workflows, floating-point kernel support, training infrastructure for CCT models, memory allocation strategies, and documentation improvements. After merging this into `main`, the release process will proceed with: - Pushing a Git tag for the release after merging this PR - Creating a GitHub release with the prepared tag. Note: Since the release tag references the Docker container tagged with the release tag (`ghcr.io/pulp-platform/deeploy:v0.2.0`), the CI will initially fail. The Deeploy Docker image must be built after the release PR is merged and the CI restarted. ### List of Pull Requests - Prepare v0.2.0 release [#102](#102) - Add Luka as Code Owner [#101](#101) - Fix CI, Docker Files, and Documentation Workflow [#100](#100) - Chimera Platform Integration [#96](#96) - Add Tutorial and Refactor README [#97](#97) - Reduce Mean Float Template [#92](#92) - Reshape Memory Freeing and Generic Float GEMM Fixes [#91](#91) - Prepare for Release and Separate Dependencies [#90](#90) - Fix input offsets calculation [#89](#89) - Move PULP SDK to main branch/fork [#88](#88) - Finite Lifetime for IO Tensors [#51](#51) - Improved Memory Visualization and Multi-Layer Tiling Profiling [#56](#56) - Fix Linting in CI and Reformat C Files [#86](#86) - Fix Broken CMake Flow For pulp-sdk [#87](#87) - Refactor Changelog For Release [#85](#85) - ARM Docker Container and Minor Bug Fix [#84](#84) - Added Kernel for Generic Float DW Conv2D [#63](#63) - Autoselect Self-Hosted Runners if the Action is on Upstream [#81](#81) - TEST_RECENT linking on MacOS [#78](#78) - Add RV32IMF Picolibc support for Siracusa platform [#66](#66) - Improve Documentation and VSCode Support [#76](#76) - Debug Print Topology Pass and Code Transformation [#75](#75) - Find all subdirectories of Deeploy when installing with pip install [#70](#70) - Add milestone issue template [#71](#71) - Bunch of fixes and changes [#58](#58) - Add SoftHier platform [#65](#65) - rv32imf_xpulpv2 ISA support for Siracusa platform [#64](#64) - One LLVM To Compile Them All [#60](#60) - One GVSoC to Simulate Them All [#59](#59) - Add Support for CCT Last Layer Training with Embedding Dim 8-128 [#55](#55) - Add CCT Classifier Training Support [#53](#53) - L3 Bugs: DMA Struct Datatype and Maxpool Margin Error [#45](#45) - DeepQuant Quantized Linear Support [#54](#54) - Implemented Dequant Layer for Generic and Siracusa [#52](#52) - Infinite Lifetime Buffers Considered in Tiling & Memory Allocation (+ Visualization) [#44](#44) - Implemented Quant Layer for Generic and Siracusa [#49](#49) - Increase maximal Mchan DMA transfer sizes from 64KiB to 128KiB [#47](#47) - Add MiniMalloc and Decouple Memory Allocation and Tiling [#40](#40) - Float CCT Bugs on L3 [#37](#37) - Memory Allocation Strategies and Visualization [#36](#36) - Add CODEOWNERS [#42](#42) - Add Tiling Support to All CCT Kernels and Fix CCT Operators on Siracusa Platform for L2 [#35](#35) - Add Fp gemm and Softmax for Snitch platform [#31](#31) - Add Float Kernels for CCT [#29](#29) - documentation deployment [#34](#34) - main.c Float Cast Bugs [#28](#28) - Add Float GEMM on PULP with Tiling [#26](#26) - Add Float Support & Float GEMM for Generic [#25](#25) - GVSOC support for the Snitch Cluster platform [#23](#23) - Snitch Cluster Tiling Support [#22](#22) - Snitch support integration [#14](#14) - Update bibtex citation [#20](#20) - the PR template location, bump min python to 3.10, change install command [#17](#17) - Add pre-commit for python formatting [#15](#15) - FP integration (v2) [#12](#12) - shell for sequential tests of Generic, Cortex, and Mempool platforms [#11](#11) - Add issue templates [#10](#10) - Minor CI and Readme Improvements [#8](#8) - Fix GHCR Link for Docker Build [#7](#7) - neureka's ccache id [#6](#6) - GitHub-based CI/CD Flow [#4](#4) - Generic Softmax Kernel [#2](#2) - Port GitLab CI [#1](#1)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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 PR tries to solve 2 issues:
1. Reshape memory freeing:
In the case of a reshape after a skip connection is stored for later use, the created alias may get freed before that later point. In the figure below, C (and, correspondingly, B and A, since they are all pointing to the same data) may get deallocated after it is used on the right branch, but before A is used in the MatMul. To solve this, a list of alises is stored for each variable, which only get deallocated if all their aliases are marked as not live.
2. GEMM Generic float:
Previously, in the general GEMM template, only the equal number of matrices between the A and B terms was supported, which raised issues when the GEMM was actually a fully connected layer (the weight/bias array would usually have a single matrix that should be multiplied with/added to each matrix in the other term). Now this operation should support partial broadcasting, when at least one of the input matrices has all dimensions 1, except for the last 2 dimensions.
Added
Changed
Fixed
PR Merge Checklist
develcommit and pointing todevel.CHANGELOG.mdfile has been updated.