Support for MaxPool1D and RQSConv1D for PULPOpen#146
Support for MaxPool1D and RQSConv1D for PULPOpen#146marchioa wants to merge 7 commits intopulp-platform:develfrom
Conversation
📝 WalkthroughWalkthroughAdds 1D MaxPool and RQSConv1D support across Generic and PULPOpen: kernels, templates, bindings, tiler/tiling constraints, parsers, platform mappings, and test config updates; also adjusts Conv1D im2col sizing and MaxPool header consolidation. Changes
Sequence Diagram(s)mermaid Estimated code review effort🎯 4 (Complex) | ⏱️ ~70 minutes Possibly related PRs
Suggested labels
Suggested reviewers
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🤖 Fix all issues with AI agents
In `@Deeploy/Targets/PULPOpen/Templates/MaxPoolTemplate.py`:
- Around line 34-46: The template PULPMaxPool1D_8_Template/PULPMaxPoolTemplate
currently passes ONNX 1D pads into the HEIGHT pad slots of pulp_nn_maxpool (so
padding_top/padding_bottom get ${padding_y}/${padding_y_right}); swap the pad
ordering so height pads are zeros and width pads receive the ONNX values: set
padding_top=0, padding_bottom=0 and padding_left=${padding_y},
padding_right=${padding_y_right} in the pulp_nn_maxpool${signatureString} call
(i.e. move the two zeros before the two ${padding_y} args).
In `@Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.py`:
- Around line 840-844: The effectiveInputLengthVar calculation is wrong: it
subtracts (inputLengthVar - 1) for the tiled case but should subtract the kernel
span (weightLengthVar - 1); update the expression in ConvTileConstraint (the
effectiveInputLengthVar assignment) to replace the final term ((inputLengthVar -
1) * (inputLengthVar != inputBuffer.shape[1])) with ((weightLengthVar - 1) *
(inputLengthVar != inputBuffer.shape[1])) so the receptive field overlap uses
weightLengthVar consistently with the 2D implementation.
- Around line 871-873: The effectiveInputLength calculation in
addPolicyConstraint uses (inputLengthVar - 1) where it should subtract the
kernel length minus one (same bug as in addGeometricalConstraint); update the
ternary expression so the last term uses the kernel size (e.g., kernelLength or
kernelLengthVar) minus one instead of inputLengthVar - 1, i.e., change "-
(inputLengthVar - 1) * (inputLengthVar != inputBuffer.shape[1])" to "-
(kernelLength - 1) * (inputLengthVar != inputBuffer.shape[1])" in the
effectiveInputLength assignment inside addPolicyConstraint.
In `@TargetLibraries/Generic/src/MaxPool_s8.c`:
- Around line 52-69: The MaxPool1d_s8_s8 function currently computes L_out = (L
- K) / S + 1 which can underflow when K > L and divide-by-zero when S == 0;
before calculating L_out, add guards: if S == 0 return (or otherwise abort) and
if K > L set L_out = 0 (or return) to avoid the underflow/OOB behavior; update
the function entry (MaxPool1d_s8_s8) to validate S and the relationship of K and
L and bail out or produce zero-length output before any loops that use L_out.
🧹 Nitpick comments (5)
TargetLibraries/Generic/inc/kernel/MaxPool.h (1)
42-48: Consider aligning parameter naming between int8 and fp32 variants.The
MaxPool1d_s8_s8function usesLfor the spatial dimension whileMaxPool1d_fp32_fp32usesW. For consistency across the API, consider using the same parameter name (e.g.,Lfor "Length" in 1D operations) in both declarations.Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.py (4)
618-618: Remove unused variabledilation.The
dilationvariable is assigned but never used inaddGeometricalConstraint. If dilation support is intended for future use, consider adding a TODO comment; otherwise, remove it.♻️ Suggested fix
- dilation = parseDict["dilations"][0] + # Note: dilation not currently used in 1D constraint; add if needed
651-658: Remove unused variablepadsinaddPolicyConstraint.The
padsvariable is assigned on line 657 but never used in this method.♻️ Suggested fix
inputBuffer = ctxt.lookup(name = parseDict['data_in']) weightBuffer = ctxt.lookup(name = parseDict['weight']) - pads = parseDict["pads"] stride = parseDict["strides"][0]
768-769: Consider addingstrict=Truetozip()calls.Using
zip()withoutstrict=Truemay silently truncate if the input lists have different lengths, potentially masking bugs.♻️ Suggested fix
- for a, b, add, mul in zip(inputInCubes, inputWeightCubes, inputAddCubes, inputMulCubes): + for a, b, add, mul in zip(inputInCubes, inputWeightCubes, inputAddCubes, inputMulCubes, strict=True):
1046-1056: Consider addingstrict=Truetozip()calls.Same recommendation as in
RQConv1DTileConstraintfor defensive programming.♻️ Suggested fix
if varBias == "NULL": - for a, b in zip(inputInCubes, inputWeightCubes): + for a, b in zip(inputInCubes, inputWeightCubes, strict=True): inputLoadSchedule.append({"data_in": a, "weight": b}) else: - for a, b, c in zip(inputInCubes, inputWeightCubes, inputBiasCubes): + for a, b, c in zip(inputInCubes, inputWeightCubes, inputBiasCubes, strict=True): inputLoadSchedule.append({"data_in": a, "weight": b, "bias": c})
| effectiveInputLengthVar = inputLengthVar \ | ||
| + (sum(pads) * (inputLengthVar == inputBuffer.shape[1])) \ | ||
| - ((inputLengthVar - 1) * (inputLengthVar != inputBuffer.shape[1])) | ||
|
|
||
| _outputLengthVar = (effectiveInputLengthVar - dilation * (weightLengthVar - 1) - 1) // stride + 1 |
There was a problem hiding this comment.
Potential bug in effectiveInputLengthVar formula.
The formula subtracts (inputLengthVar - 1) when tiling, but comparing with Conv2DTileConstraint.addGeometricalConstraint (lines 305-308), the 2D version subtracts (weightHeightVar - 1). This appears to be a copy-paste error—it should likely be (weightLengthVar - 1) to account for the kernel receptive field overlap.
🐛 Suggested fix
# Assume worst case scenario (data padding on all sides) when tiling on a ceratin dimension.
effectiveInputLengthVar = inputLengthVar \
+ (sum(pads) * (inputLengthVar == inputBuffer.shape[1])) \
- - ((inputLengthVar - 1) * (inputLengthVar != inputBuffer.shape[1]))
+ - ((weightLengthVar - 1) * (inputLengthVar != inputBuffer.shape[1]))🤖 Prompt for AI Agents
In `@Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.py` around lines
840 - 844, The effectiveInputLengthVar calculation is wrong: it subtracts
(inputLengthVar - 1) for the tiled case but should subtract the kernel span
(weightLengthVar - 1); update the expression in ConvTileConstraint (the
effectiveInputLengthVar assignment) to replace the final term ((inputLengthVar -
1) * (inputLengthVar != inputBuffer.shape[1])) with ((weightLengthVar - 1) *
(inputLengthVar != inputBuffer.shape[1])) so the receptive field overlap uses
weightLengthVar consistently with the 2D implementation.
| effectiveInputLength = inputLengthVar \ | ||
| + (sum(pads) * (inputLengthVar == inputBuffer.shape[1])) \ | ||
| - (inputLengthVar - 1) * (inputLengthVar != inputBuffer.shape[1]) |
There was a problem hiding this comment.
Same formula issue in addPolicyConstraint.
This has the same issue as addGeometricalConstraint—it subtracts (inputLengthVar - 1) instead of the kernel length minus one.
🐛 Suggested fix
effectiveInputLength = inputLengthVar \
+ (sum(pads) * (inputLengthVar == inputBuffer.shape[1])) \
- - (inputLengthVar - 1) * (inputLengthVar != inputBuffer.shape[1])
+ - (weightLengthVar - 1) * (inputLengthVar != inputBuffer.shape[1])🤖 Prompt for AI Agents
In `@Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.py` around lines
871 - 873, The effectiveInputLength calculation in addPolicyConstraint uses
(inputLengthVar - 1) where it should subtract the kernel length minus one (same
bug as in addGeometricalConstraint); update the ternary expression so the last
term uses the kernel size (e.g., kernelLength or kernelLengthVar) minus one
instead of inputLengthVar - 1, i.e., change "- (inputLengthVar - 1) *
(inputLengthVar != inputBuffer.shape[1])" to "- (kernelLength - 1) *
(inputLengthVar != inputBuffer.shape[1])" in the effectiveInputLength assignment
inside addPolicyConstraint.
Victor-Jung
left a comment
Victor-Jung
left a comment
There was a problem hiding this comment.
Ciao Alex, I have a few minor comments but overall it looks good.
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
Deeploy/Targets/Generic/Parsers.py (1)
193-200: PotentialKeyErrorwhenstridesattribute is missing.The stride validation on line 199 accesses
node.attrs['strides']unconditionally. Since this is a list literal passed toall(), Python evaluates all elements before callingall()— no short-circuit evaluation occurs. If'strides' not in node.attrs, this will raise aKeyError.🐛 Proposed fix: move stride validation after the attribute existence check
def parseNode(self, node: gs.Node) -> bool: ret = all([ 'ceil_mode' in node.attrs, 'kernel_shape' in node.attrs, 'pads' in node.attrs, 'strides' in node.attrs, len(node.inputs) == 1, len(node.outputs) >= 1, - all([stride > 0 for stride in node.attrs['strides']]), ]) + if ret: + ret = all(stride > 0 for stride in node.attrs['strides']) + if ret: self.operatorRepresentation['ceil_mode'] = node.attrs['ceil_mode']
🤖 Fix all issues with AI agents
In `@TargetLibraries/Generic/src/MaxPool_s8.c`:
- Around line 55-58: The code lacks a guard for K == 0 which allows a
zero-length kernel and produces invalid outputs; update the input validation in
MaxPool_s8 (the block checking L, K, S) to treat K == 0 as invalid—mirror the
existing stride guard (S == 0) by returning (or asserting) when K == 0 (e.g.,
add K == 0 to the condition that currently checks L < K || S == 0) so the
computation of L_out is never performed with a zero kernel.
|
I handled both conditions directly in the C kernel by early-returning when the parameters are invalid. I couldn’t find an existing pattern for this in other kernels, so this was a best-effort approach on my side — please let me know if there’s a preferred or more idiomatic way to handle it. Should I apply the same kind of guard to MaxPool2d as well? Additionally, since the stride value is available from ONNX, I added a guard in the parser to catch stride == 0. |
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
Deeploy/Targets/Generic/Parsers.py (1)
195-211: KeyError whenstridesattribute is missing.The stride validation on line 202 accesses
node.attrs['strides']unconditionally. Sinceall([...])evaluates all list elements before callingall(), this will raise aKeyErrorif the'strides'attribute is not present—even though the check'strides' in node.attrsexists earlier in the list.🐛 Proposed fix: Move stride validation after initial checks
def parseNode(self, node: gs.Node) -> bool: ret = all([ 'ceil_mode' in node.attrs, 'kernel_shape' in node.attrs, 'pads' in node.attrs, 'strides' in node.attrs, len(node.inputs) == 1, len(node.outputs) >= 1, - all([stride > 0 for stride in node.attrs['strides']]), ]) - if ret: + if ret and not all(stride > 0 for stride in node.attrs['strides']): + return False + + if ret: self.operatorRepresentation['ceil_mode'] = node.attrs['ceil_mode'] self.operatorRepresentation['pads'] = node.attrs['pads'] self.operatorRepresentation['kernel_shape'] = node.attrs['kernel_shape'] self.operatorRepresentation['strides'] = node.attrs['strides'] return ret
🤖 Fix all issues with AI agents
In `@TargetLibraries/Generic/src/MaxPool_fp32.c`:
- Around line 46-50: The guard that validates input parameters in MaxPool_fp32.c
should also treat a kernel size of zero as invalid; update the condition
currently checking "if (W < K || S == 0)" to include "K == 0" so the function
returns early for empty kernels (this affects the validation in the function
containing the W_out calculation and the loop "for (uint32_t c = 0; c < C;
++c)"). Ensure the check prevents proceeding when K == 0 to avoid leaving max
initialized at -inf and producing invalid outputs.
♻️ Duplicate comments (1)
TargetLibraries/Generic/src/MaxPool_s8.c (1)
55-58: Still missing guard forK == 0.As flagged in a previous review, a zero-length kernel bypasses the current guard, causes the inner loop to never execute, and writes
-128 + output_offsetto all output positions. AddK == 0to the validation.Proposed fix
- if (L < K || S == 0) { + if (K == 0 || S == 0 || L < K) { return; }
Sorry, I missed the guard statement 😁 Sure, if you can add the guard to the other maxpool kernels, it would be amazing! Thanks for the contribution. I am approving this PR, and we can merge it soon. |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@Deeploy/Targets/Generic/Parsers.py`:
- Around line 195-203: The current boolean expression assigned to ret eagerly
accesses node.attrs['strides'] and can raise KeyError; modify the condition so
the positivity check runs only when 'strides' is present (e.g., replace the
inner all([stride > 0 for stride in node.attrs['strides']]) with a
short-circuiting check like ('strides' in node.attrs and all(stride > 0 for
stride in node.attrs['strides'])) or restructure the overall predicate to use
generator expressions that only evaluate node.attrs['strides'] after confirming
'strides' in node.attrs); update the expression that sets ret (and reference
node.attrs, 'strides', and the ret assignment) accordingly so missing strides
yields False without an exception.
In `@TargetLibraries/Generic/src/MaxPool_fp32.c`:
- Around line 14-16: The early-return in MaxPool_fp32.c currently checks if (H <
P || W < Q || SP == 0 || SQ == 0) but misses guarding P == 0 || Q == 0, which
allows empty pooling windows to leave max as -inf; update the condition in the
MaxPool_fp32 function to also return when P == 0 or Q == 0 (i.e., include P == 0
|| Q == 0 alongside the existing H, W, SP, SQ checks) so no invalid -inf outputs
are written.
🧹 Nitpick comments (1)
TargetLibraries/Generic/src/MaxPool_s8.c (1)
13-15: Add guards forP == 0andQ == 0.For consistency with the 1D variant feedback, a zero kernel size (
P == 0orQ == 0) would cause the inner loops to never execute, leavingmax = -128and producing semantically incorrect output. Consider guarding these cases as well.♻️ Proposed fix
- if (H < P || W < Q || SP == 0 || SQ == 0) { + if (P == 0 || Q == 0 || SP == 0 || SQ == 0 || H < P || W < Q) { return; }
| ret = all([ | ||
| 'ceil_mode' in node.attrs, 'kernel_shape' in node.attrs, 'pads' in node.attrs, 'strides' in node.attrs, | ||
| 'ceil_mode' in node.attrs, | ||
| 'kernel_shape' in node.attrs, | ||
| 'pads' in node.attrs, | ||
| 'strides' in node.attrs, | ||
| len(node.inputs) == 1, | ||
| len(node.outputs) >= 1 | ||
| len(node.outputs) >= 1, | ||
| all([stride > 0 for stride in node.attrs['strides']]), | ||
| ]) |
There was a problem hiding this comment.
Avoid KeyError when strides is absent (Line 195–203).
all([...]) eagerly evaluates the list, so node.attrs['strides'] will throw if the attribute is missing; previously this would just return False. Guard the access and run the positivity check only when strides is present.
🛠️ Proposed fix
- ret = all([
- 'ceil_mode' in node.attrs,
- 'kernel_shape' in node.attrs,
- 'pads' in node.attrs,
- 'strides' in node.attrs,
- len(node.inputs) == 1,
- len(node.outputs) >= 1,
- all([stride > 0 for stride in node.attrs['strides']]),
- ])
+ strides = node.attrs.get('strides')
+ ret = all([
+ 'ceil_mode' in node.attrs,
+ 'kernel_shape' in node.attrs,
+ 'pads' in node.attrs,
+ strides is not None,
+ len(node.inputs) == 1,
+ len(node.outputs) >= 1,
+ ])
+ if ret and not all(stride > 0 for stride in strides):
+ return False🤖 Prompt for AI Agents
In `@Deeploy/Targets/Generic/Parsers.py` around lines 195 - 203, The current
boolean expression assigned to ret eagerly accesses node.attrs['strides'] and
can raise KeyError; modify the condition so the positivity check runs only when
'strides' is present (e.g., replace the inner all([stride > 0 for stride in
node.attrs['strides']]) with a short-circuiting check like ('strides' in
node.attrs and all(stride > 0 for stride in node.attrs['strides'])) or
restructure the overall predicate to use generator expressions that only
evaluate node.attrs['strides'] after confirming 'strides' in node.attrs); update
the expression that sets ret (and reference node.attrs, 'strides', and the ret
assignment) accordingly so missing strides yields False without an exception.
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Fix all issues with AI agents
In `@Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.py`:
- Around line 616-630: Remove or silence the three unused local variables to
satisfy Ruff F841: eliminate the unused assignments to dilation,
inputChannelVar, and weightInChannelVar (or rename them to _dilation,
_inputChannelVar, _weightInChannelVar) in the method that builds the tiler model
where tilerModel.addTensorDimToModel(...) and tilerModel.getTensorDimVar(...)
are called; ensure any remaining needed dimension variables (e.g.,
inputBatchVar, inputLengthVar, weightOutChannelVar, weightLengthVar) are left
intact and no other logic depends on the removed variables.
- Around line 657-658: Remove the unused variable assignment pads =
parseDict["pads"] in ConvTileConstraint.py to satisfy Ruff F841; locate the
occurrence where parseDict is read (the pads assignment near stride =
parseDict["strides"][0]) and either delete that pads line entirely or, if the
read is needed for side effects, replace it with an intentional discard like _ =
parseDict["pads"] so the parser intent remains clear.
- Around line 768-769: Update all zip() calls in ConvTileConstraint.py to pass
strict=True to satisfy B905: add strict=True to the zip used to build
inputLoadSchedule (the loop that zips inputInCubes, inputWeightCubes,
inputAddCubes, inputMulCubes producing inputLoadSchedule), and likewise add
strict=True to the zip calls in the other locations mentioned (the zip usages
around lines where input/weight/add/mul cube lists are zipped and the ones at
lines 221, 583, 586, 1048, and 1051). Locate the loops/functions that use zip
(e.g., the function/method that fills inputLoadSchedule and any helper functions
that iterate over cube lists) and change zip(...) to zip(..., strict=True) for
each occurrence so mismatched-length iterables raise immediately.
| pads = parseDict["pads"] | ||
| stride = parseDict["strides"][0] | ||
| dilation = parseDict["dilations"][0] | ||
|
|
||
| # Add I/O dimensions to the model as variables | ||
| for bufferName in [inputBufferName, weightBufferName, mulBufferName, addBufferName, outputBufferName]: | ||
| tilerModel.addTensorDimToModel(ctxt, bufferName) | ||
|
|
||
| inputBatchVar = tilerModel.getTensorDimVar(tensorName = inputBufferName, dimIdx = 0) | ||
| inputLengthVar = tilerModel.getTensorDimVar(tensorName = inputBufferName, dimIdx = 1) | ||
| inputChannelVar = tilerModel.getTensorDimVar(tensorName = inputBufferName, dimIdx = 2) | ||
|
|
||
| weightOutChannelVar = tilerModel.getTensorDimVar(tensorName = weightBufferName, dimIdx = 0) | ||
| weightLengthVar = tilerModel.getTensorDimVar(tensorName = weightBufferName, dimIdx = 1) | ||
| weightInChannelVar = tilerModel.getTensorDimVar(tensorName = weightBufferName, dimIdx = 2) |
There was a problem hiding this comment.
Remove unused locals to satisfy Ruff F841.
dilation, inputChannelVar, and weightInChannelVar are assigned but unused in this method.
🧹 Proposed fix
- dilation = parseDict["dilations"][0]
-
# Add I/O dimensions to the model as variables
for bufferName in [inputBufferName, weightBufferName, mulBufferName, addBufferName, outputBufferName]:
tilerModel.addTensorDimToModel(ctxt, bufferName)
@@
- inputChannelVar = tilerModel.getTensorDimVar(tensorName = inputBufferName, dimIdx = 2)
-
weightOutChannelVar = tilerModel.getTensorDimVar(tensorName = weightBufferName, dimIdx = 0)
weightLengthVar = tilerModel.getTensorDimVar(tensorName = weightBufferName, dimIdx = 1)
- weightInChannelVar = tilerModel.getTensorDimVar(tensorName = weightBufferName, dimIdx = 2)🧰 Tools
🪛 Ruff (0.14.14)
[error] 618-618: Local variable dilation is assigned to but never used
Remove assignment to unused variable dilation
(F841)
[error] 626-626: Local variable inputChannelVar is assigned to but never used
Remove assignment to unused variable inputChannelVar
(F841)
[error] 630-630: Local variable weightInChannelVar is assigned to but never used
Remove assignment to unused variable weightInChannelVar
(F841)
🤖 Prompt for AI Agents
In `@Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.py` around lines
616 - 630, Remove or silence the three unused local variables to satisfy Ruff
F841: eliminate the unused assignments to dilation, inputChannelVar, and
weightInChannelVar (or rename them to _dilation, _inputChannelVar,
_weightInChannelVar) in the method that builds the tiler model where
tilerModel.addTensorDimToModel(...) and tilerModel.getTensorDimVar(...) are
called; ensure any remaining needed dimension variables (e.g., inputBatchVar,
inputLengthVar, weightOutChannelVar, weightLengthVar) are left intact and no
other logic depends on the removed variables.
| pads = parseDict["pads"] | ||
| stride = parseDict["strides"][0] |
There was a problem hiding this comment.
Remove unused pads to satisfy Ruff F841.
🧹 Proposed fix
- pads = parseDict["pads"]
stride = parseDict["strides"][0]📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| pads = parseDict["pads"] | |
| stride = parseDict["strides"][0] | |
| stride = parseDict["strides"][0] |
🧰 Tools
🪛 Ruff (0.14.14)
[error] 657-657: Local variable pads is assigned to but never used
Remove assignment to unused variable pads
(F841)
🤖 Prompt for AI Agents
In `@Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.py` around lines
657 - 658, Remove the unused variable assignment pads = parseDict["pads"] in
ConvTileConstraint.py to satisfy Ruff F841; locate the occurrence where
parseDict is read (the pads assignment near stride = parseDict["strides"][0])
and either delete that pads line entirely or, if the read is needed for side
effects, replace it with an intentional discard like _ = parseDict["pads"] so
the parser intent remains clear.
| for a, b, add, mul in zip(inputInCubes, inputWeightCubes, inputAddCubes, inputMulCubes): | ||
| inputLoadSchedule.append({"data_in": a, "weight": b, "add": add, "mul": mul}) |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# Find Python version requirements in the project
find . -type f \( -name "setup.py" -o -name "setup.cfg" -o -name "pyproject.toml" -o -name ".python-version" -o -name "tox.ini" -o -name "requirements*.txt" \) | head -20Repository: pulp-platform/Deeploy
Length of output: 115
🏁 Script executed:
# Check the file and locate the code at the mentioned lines
wc -l Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.pyRepository: pulp-platform/Deeploy
Length of output: 132
🏁 Script executed:
# Read the relevant sections of the file
sed -n '765,775p' Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.py
sed -n '1045,1055p' Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.pyRepository: pulp-platform/Deeploy
Length of output: 1084
🏁 Script executed:
# Check Python version requirement
cat setup.py | grep -A 5 "python_requires"Repository: pulp-platform/Deeploy
Length of output: 47
🏁 Script executed:
# Also check pyproject.toml
cat pyproject.toml | grep -A 5 "python"Repository: pulp-platform/Deeploy
Length of output: 166
🌐 Web query:
B905 flake8 rule zip strict parameter Python
💡 Result:
B905 (from flake8-bugbear) flags uses of zip() with 2+ iterables (or any starred *args) that don’t pass an explicit strict= keyword. The intent is to prevent subtle bugs from zip silently truncating to the shortest iterable. Set either:
strict=Trueto raiseValueErrorif lengths differ (safer), orstrict=Falseto keep truncation but make it explicit.
Notes:
strict=exists only in Python 3.10+, so don’t enable B905 if you need to support Python <3.10.itertools.count,itertools.cycle, anditertools.repeat(times=None)are excluded as infinite iterators.
Sources: flake8-bugbear docs on PyPI [1] (also mirrored elsewhere [2]); Ruff’s equivalent rule description [3].
🏁 Script executed:
# Search for all zip() calls in the file to ensure the review comment covers all instances
grep -n "zip(" Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.pyRepository: pulp-platform/Deeploy
Length of output: 566
Add explicit strict= to zip() calls to satisfy B905.
The project requires Python 3.10+, which natively supports the strict= parameter. Add strict=True to the following zip() calls:
- Lines 768-769, 1048, and 1051 (as shown in the proposed fix)
- Also lines 221, 583, and 586 have similar patterns that should be updated consistently
Proposed fix for lines 768-769, 1048, 1051
- for a, b, add, mul in zip(inputInCubes, inputWeightCubes, inputAddCubes, inputMulCubes):
+ for a, b, add, mul in zip(inputInCubes, inputWeightCubes, inputAddCubes, inputMulCubes, strict=True):
inputLoadSchedule.append({"data_in": a, "weight": b, "add": add, "mul": mul})- for a, b in zip(inputInCubes, inputWeightCubes):
+ for a, b in zip(inputInCubes, inputWeightCubes, strict=True):
inputLoadSchedule.append({"data_in": a, "weight": b})- for a, b, c in zip(inputInCubes, inputWeightCubes, inputBiasCubes):
+ for a, b, c in zip(inputInCubes, inputWeightCubes, inputBiasCubes, strict=True):
inputLoadSchedule.append({"data_in": a, "weight": b, "bias": c})📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| for a, b, add, mul in zip(inputInCubes, inputWeightCubes, inputAddCubes, inputMulCubes): | |
| inputLoadSchedule.append({"data_in": a, "weight": b, "add": add, "mul": mul}) | |
| for a, b, add, mul in zip(inputInCubes, inputWeightCubes, inputAddCubes, inputMulCubes, strict=True): | |
| inputLoadSchedule.append({"data_in": a, "weight": b, "add": add, "mul": mul}) |
🧰 Tools
🪛 Ruff (0.14.14)
[warning] 768-768: zip() without an explicit strict= parameter
Add explicit value for parameter strict=
(B905)
🤖 Prompt for AI Agents
In `@Deeploy/Targets/PULPOpen/TileConstraints/ConvTileConstraint.py` around lines
768 - 769, Update all zip() calls in ConvTileConstraint.py to pass strict=True
to satisfy B905: add strict=True to the zip used to build inputLoadSchedule (the
loop that zips inputInCubes, inputWeightCubes, inputAddCubes, inputMulCubes
producing inputLoadSchedule), and likewise add strict=True to the zip calls in
the other locations mentioned (the zip usages around lines where
input/weight/add/mul cube lists are zipped and the ones at lines 221, 583, 586,
1048, and 1051). Locate the loops/functions that use zip (e.g., the
function/method that fills inputLoadSchedule and any helper functions that
iterate over cube lists) and change zip(...) to zip(..., strict=True) for each
occurrence so mismatched-length iterables raise immediately.
3 participants
Add integer MaxPool1D for Generic platform and RQSConv1D support for PULPOpen, with corresponding kernel tests.
Added
Changed
Fixed
PR Merge Checklist
develcommit and pointing todevel.CHANGELOG.mdfile has been updated.