nnicolosi/Raptor
1
0
Fork 0
Code Issues Pull Requests Actions 9 Packages Projects Releases Wiki Activity

finally fast googlenet with correct latency artifacts for fair comparison
Validate Operations / validate-operations (push) Has been cancelled
Details

Browse Source
This commit is contained in:
NiccoloN
2026-07-29 18:20:44 +02:00
parent 060a21172e
commit 1b4f070bef
74 changed files with 2773 additions and 1311 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/PIM/Conversion/SpatialToPim/SpatialToPimPass.cpp
+10 -4
View File
@@ -264,7 +264,13 @@ LogicalResult raptor::SpatialToPimPass::enlargeVMMOutTensorsToCrossbarSize(func:
auto outputType = cast<RankedTensorType>(vmmOp.getOutput().getType());
ArrayRef<int64_t> outputShape = outputType.getShape();
assert(isHVectorShape(outputShape) && "expected a horizontal vector output");
assert(outputShape[1] <= static_cast<int64_t>(crossbarSize) && "output width must fit in one crossbar");
auto weightType = cast<RankedTensorType>(vmmOp.getWeight().getType());
const int64_t xbarDim = static_cast<int64_t>(crossbarSize);
const int64_t paddedOutputWidth = ceilIntegerDivide(outputShape[1], xbarDim) * xbarDim;
assert(weightType.getRank() == 2 && weightType.getDimSize(1) == paddedOutputWidth
&& "expected VMM weight width to match the padded output width");
assert(paddedOutputWidth / xbarDim <= static_cast<int64_t>(crossbarCountInCore)
&& "output width must fit in one core");
rewriter.setInsertionPoint(vmmOp);
auto paddedInput = padHVectorInputToCrossbarSize(rewriter, vmmOp.getLoc(), vmmOp.getInput());
@@ -273,8 +279,8 @@ LogicalResult raptor::SpatialToPimPass::enlargeVMMOutTensorsToCrossbarSize(func:
return WalkResult::interrupt();
}
auto paddedOutputType = RankedTensorType::get(
{outputShape[0], static_cast<int64_t>(crossbarSize)}, outputType.getElementType(), outputType.getEncoding());
Value paddedOutputBuffer = outputShape[1] == static_cast<int64_t>(crossbarSize)
{outputShape[0], paddedOutputWidth}, outputType.getElementType(), outputType.getEncoding());
Value paddedOutputBuffer = outputShape[1] == paddedOutputWidth
? vmmOp.getOutputBuffer()
: createEmptyTensorFromShaped(rewriter, vmmOp.getLoc(), paddedOutputType).getResult();
vmmOp.getInputMutable().assign(*paddedInput);
@@ -282,7 +288,7 @@ LogicalResult raptor::SpatialToPimPass::enlargeVMMOutTensorsToCrossbarSize(func:
vmmOp.getOutput().setType(paddedOutputType);
if (outputShape[1] == static_cast<int64_t>(crossbarSize))
if (outputShape[1] == paddedOutputWidth)
return WalkResult::advance();
SmallVector<OpFoldResult> offsets = {rewriter.getIndexAttr(0), rewriter.getIndexAttr(0)};