Merge branch 'pulp-platform:devel' into fix-gemm-nobias

Author: marchioa

.github/workflows/ci-platform-generic.yml

@@ -96,3 +96,4 @@ jobs:
         CCT/CCT_1_16_16_8
         CCT/CCT_2_32_32_128_Opset20
         testFloatDemoTinyViT
+        Autoencoder1D

.github/workflows/ci-platform-mempool.yml

@@ -69,6 +69,5 @@ jobs:
         ICCT
         ICCT_ITA
         ICCT_8
-        ICCT_ITA_8
         miniMobileNet
         miniMobileNetv2

CHANGELOG.md

@@ -4,6 +4,11 @@ This file contains the changelog for the Deeploy project. The changelog is divid
 ## Unreleased (Planned Release Target: v0.2.1)
 
 ### List of Pull Requests
+- Disallow shape inference [#128](https://github.com/pulp-platform/Deeploy/pull/128)
+- Remove memory-aware node bindings [#123](https://github.com/pulp-platform/Deeploy/pull/123)
+- Fix missing const's layout transformation and refactor NCHWtoNHWC passes [#122](https://github.com/pulp-platform/Deeploy/pull/122)
+- Fix aliasing [#125](https://github.com/pulp-platform/Deeploy/pull/125)
+- Support for 1D Autoencoder [#98](https://github.com/pulp-platform/Deeploy/pull/98)
 - Refactor Logging for Improved Debugging [#115](https://github.com/pulp-platform/Deeploy/pull/115)
 - Add reuse-tool as an SPDX license header linter [#113](https://github.com/pulp-platform/Deeploy/pull/113)
 - Bug fixes, API Cleanup and Reduce Compiler Warning on PULP [#112](https://github.com/pulp-platform/Deeploy/pull/112)
@@ -46,6 +51,8 @@ This file contains the changelog for the Deeploy project. The changelog is divid
 - Buffer utilities: `checkNumLevels` validation and `sizeInBytes` method
 - Per–memory-level usage tracking and worst-case reporting in `NetworkContext`
 - Memory/I/O summaries and input/output logging in deployers
+- RequantHelpers.py for Neureka's TileConstraints
+- Added assertion that all the graph tensors after lowering have a shape annotated
 
 ### Changed
 - Replaced platform-specific tags (`*-amd64`, `*-arm64`) with direct digest references in `Noelware/docker-manifest-action`.
@@ -73,6 +80,15 @@ This file contains the changelog for the Deeploy project. The changelog is divid
 - Changed types and added correct casts to fix many compiler warnings in the PULP target library
 - Use [reuse-tool](https://github.com/fsfe/reuse-tool) in pre-commit, CI, and Makefile for SPDX license header linting
 - Deployer workflow now uses `prepare(...)` instead of `generateFunction(...)`.
+- Removed `fromVariableBuffer`
+- Refactored `hoistConstant`
+- Refactored TransientBuffer's `__init__`
+- Refactor of the NCHWtoNHWC passes
+- Removed NodeMemoryLevelChecker, MemoryAwareNodeBinding
+- Removed _parseNode from MemoryNetworkDeployer since we don't need the annotations before typeChecking anymore
+- Removed Wmem variants of bindings and tile constraints from Neureka
+- Disabled ICCT_ITA_8 MemPool test because it was using a lowering that created shapeless tensors
+- Added missing shape annotation to the testTypeInferenceDifferentTypes
 
 ### Fixed
 - Prevent node duplication for graphs generated via GraphSurgeon
@@ -83,6 +99,9 @@ This file contains the changelog for the Deeploy project. The changelog is divid
 - Corrected method usage in `importDeeployState` to call `NetworkContext.importNetworkContext` instead of the incorrect method name
 - Correctly return `signProp` from `setupDeployer` instead of hardcoding the value to `False` in `testMVP.py`
 - Fixed `Unsqueeze` Op. when using ONNX opset 13 or higher (from attribute to input)
+- Fixed aliasing
+- Missing layout transformation of the const's (bias, mul, add, shift in Conv/RequantizedConv)
+- Keep mul/add rank of requantized Neureka tile constraints
 
 ### Removed
 - Delete outdated and unused `.gitlab-ci.yml` file
@@ -158,6 +177,13 @@ This release containing major architectural changes, new platform support, enhan
 
 
 ### Added
+- BatchNorm kernel 
+- ConvTranspose kernel 
+- MaxPool1D kernel 
+- Template for 1D Convolution
+- Support for float32 data type in the previous kernels
+- Float binding for Pad1D kernel
+- Test for Autoencoder1D in the CI pipeline
 - ChimeraDeployer, currently mainly a placeholder
 - Allocate templates for Chimera
 - ChimeraPlatform, using appropriate allocation templates and using the generic Parser + Binding for the Add node
@@ -291,6 +317,8 @@ This release containing major architectural changes, new platform support, enhan
 - `dev-requirements.txt` tracking the dependencies of the build system, linting, documentation, and QOL.
 
 ### Changed
+- FloatConvTemplate file
+- Platform.py file  
 - Bump the CMake version to 3.24 as required for the chimera-sdk
 - Bump GVSoC's version and add chimera simulation target
 - Rename the generic source util to utils to avoid name collision with chimera-sdk

Deeploy/CommonExtensions/CodeTransformationPasses/MemoryAllocation.py

@@ -141,7 +141,7 @@ def apply(self,
             assert buffer._live == True, f"Tried to deallocate already dead buffer {buffer.name}"
             buffer._live = False
             # Don't deallocate if it's an alias of a live buffer
-            if not buffer.has_live_ancestors(ctxt = ctxt):
+            if not buffer.has_live_aliases(ctxt):
                 memoryLevel = "None" if not hasattr(buffer, "_memoryLevel") else buffer._memoryLevel
                 if memoryLevel not in ctxt._dynamicSize:
                     ctxt._dynamicSize[memoryLevel] = 0

Deeploy/CommonExtensions/NetworkDeployers/NetworkDeployerWrapper.py

@@ -2,7 +2,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
-from typing import Any, Tuple, Union
+from typing import Any, Union
 
 import onnx_graphsurgeon as gs
 
@@ -63,11 +63,6 @@ def lower(self, graph: gs.Graph) -> gs.Graph:
     def codeTransform(self, verbose: CodeGenVerbosity = _NoVerbosity):
         return self._innerObject.codeTransform(verbose)
 
-    # MemoryAwareDeployer augment
-    def _parseNode(self, node: ONNXLayer, ctxt: NetworkContext,
-                   default_channels_first: bool) -> Tuple[NetworkContext, bool]:
-        return self._innerObject._parseNode(node, ctxt, default_channels_first)
-
     # PULPDeployer augment
     def generateBufferAllocationCode(self) -> str:
         return self._innerObject.generateBufferAllocationCode()