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

Bye Bye DCP

Browse Source
This commit is contained in:
ilgeco
2026-05-25 15:44:30 +02:00
parent 4855a2e105
commit eea9261c7b
42 changed files with 176 additions and 3994 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/PIM/Conversion/ONNXToSpatial/Patterns/Math/Conv.cpp
+4 -4
View File
@@ -11,7 +11,7 @@
#include "src/Accelerators/PIM/Common/Support/Diagnostics.hpp"
#include "src/Accelerators/PIM/Compiler/PimCompilerOptions.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/Common/Common.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/HostFoldability.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/CompileTime.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/SpatialOps.hpp"
#include "src/Dialect/ONNX/ONNXOps.hpp"
@@ -391,7 +391,7 @@ static Value lowerSingleConvGroup(Value x,
const int64_t xbarSize = static_cast<int64_t>(crossbarSize.getValue());
const int64_t wMaxDim = std::max(patchSize, numChannelsOut);
const int64_t maxParallelPixels = std::max<int64_t>(1, xbarSize / wMaxDim);
auto wDenseAttr = getHostFoldableDenseElementsAttr(w);
auto wDenseAttr = getHostConstDenseElementsAttr(w);
// Prepare weight matrix W for crossbar storage:
// W: [numChannelsOut, numChannelsIn, wHeight, wWidth] -> [numChannelsOut, patchSize] -> [patchSize, numChannelsOut]
@@ -412,7 +412,7 @@ static Value lowerSingleConvGroup(Value x,
DenseElementsAttr biasDenseAttr;
if (hasB) {
gemmBias = b;
biasDenseAttr = getHostFoldableDenseElementsAttr(b);
biasDenseAttr = getHostConstDenseElementsAttr(b);
biasMatrix = expandBiasIfNeeded(b, rewriter, loc);
}
const bool canPackWeightsAsConstants = static_cast<bool>(wDenseAttr);
@@ -717,7 +717,7 @@ LogicalResult ConvToGemm::matchAndRewrite(ONNXConvOp convOp,
}
Value result;
if (llvm::all_of(groupResults, isHostFoldableValue)) {
if (llvm::all_of(groupResults, isCompileTimeComputable)) {
result = createSpatConcat(rewriter, loc, /*axis=*/1, groupResults);
}
else {
src/PIM/Conversion/ONNXToSpatial/Patterns/Math/Gemm.cpp
+4 -4
View File
@@ -11,7 +11,7 @@
#include "src/Accelerators/PIM/Common/PimCommon.hpp"
#include "src/Accelerators/PIM/Common/Support/Diagnostics.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/Common/Common.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/HostFoldability.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/CompileTime.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/SpatialOps.hpp"
#include "src/Dialect/ONNX/ONNXOps.hpp"
@@ -55,7 +55,7 @@ static Value transposeForSpatial(Value value,
ArrayRef<int64_t> permutation,
ConversionPatternRewriter& rewriter,
Location loc) {
if (isHostFoldableValue(value))
if (isCompileTimeComputable(value))
return ONNXTransposeOp::create(rewriter, loc, resultType, value, rewriter.getI64ArrayAttr(permutation));
auto computeOp = createSpatCompute<1>(rewriter, loc, TypeRange {resultType}, {}, value, [&](Value input) {
@@ -67,7 +67,7 @@ static Value transposeForSpatial(Value value,
static Value
expandRankOneBias(Value value, RankedTensorType resultType, ConversionPatternRewriter& rewriter, Location loc) {
if (isHostFoldableValue(value))
if (isCompileTimeComputable(value))
return tensor::ExpandShapeOp::create(rewriter,
loc,
resultType,
@@ -121,7 +121,7 @@ static SmallVector<Value> materializeBatchRowSlices(Value matrix,
auto rowType = RankedTensorType::get({1, matrixType.getDimSize(1)}, matrixType.getElementType());
SmallVector<Type> resultTypes(static_cast<size_t>(numRows), rowType);
if (isHostFoldableValue(matrix)) {
if (isCompileTimeComputable(matrix)) {
auto extractRowsOp = spatial::SpatExtractRowsOp::create(rewriter, loc, TypeRange(resultTypes), matrix);
return SmallVector<Value>(extractRowsOp->result_begin(), extractRowsOp->result_end());
}
src/PIM/Conversion/ONNXToSpatial/Patterns/Math/MatMul.cpp
+6 -6
View File
@@ -10,7 +10,7 @@
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/Common/Common.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/ConversionPatterns.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/HostFoldability.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/CompileTime.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/SpatialOps.hpp"
#include "src/Dialect/ONNX/ONNXOps.hpp"
@@ -55,7 +55,7 @@ collapseBatchDims(Value value, int64_t batchSize, int64_t rows, int64_t cols, Pa
return tensor::CollapseShapeOp::create(rewriter, loc, collapsedType, input, reassociation);
};
if (isHostFoldableValue(value))
if (isCompileTimeComputable(value))
return buildCollapsed(value);
auto collapseCompute =
@@ -114,7 +114,7 @@ static Value extractBatchMatrix(Value value,
});
};
if (isHostFoldableValue(value))
if (isCompileTimeComputable(value))
return buildMatrix(value);
auto batchMatrixCompute =
@@ -142,7 +142,7 @@ static Value transposeLastTwoDims(Value value, PatternRewriter& rewriter, Locati
return ONNXTransposeOp::create(rewriter, loc, transposedType, input, rewriter.getI64ArrayAttr(perm));
};
if (isHostFoldableValue(value))
if (isCompileTimeComputable(value))
return buildTranspose(value);
auto transposeCompute =
@@ -182,7 +182,7 @@ static Value concatValues(ValueRange inputs, int64_t axis, PatternRewriter& rewr
outputShape[axis] = concatDimSize;
auto resultType = RankedTensorType::get(outputShape, firstType.getElementType(), firstType.getEncoding());
if (llvm::all_of(inputs, isHostFoldableValue))
if (llvm::all_of(inputs, isCompileTimeComputable))
return createSpatConcat(rewriter, loc, axis, inputs);
auto concatCompute = createSpatCompute(rewriter, loc, TypeRange {resultType}, {}, inputs, [&](ValueRange args) {
@@ -235,7 +235,7 @@ struct MatMulToGemm : OpRewritePattern<ONNXMatMulOp> {
}
Location loc = matmulOp.getLoc();
bool useTransposedForm = isHostFoldableValue(matmulOp.getA()) && !isHostFoldableValue(matmulOp.getB());
bool useTransposedForm = isCompileTimeComputable(matmulOp.getA()) && !isCompileTimeComputable(matmulOp.getB());
Value lhs = collapseBatchDims(matmulOp.getA(), lhsBatch, m, k, rewriter, loc);
Value rhs = collapseBatchDims(matmulOp.getB(), rhsBatch, k, n, rewriter, loc);
src/PIM/Conversion/ONNXToSpatial/Patterns/Math/ReduceMean.cpp
+3 -3
View File
@@ -7,7 +7,7 @@
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/Common/Common.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/ConversionPatterns.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/HostFoldability.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/CompileTime.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/SpatialOps.hpp"
#include "src/Dialect/ONNX/ONNXOps.hpp"
@@ -91,7 +91,7 @@ static Value concatValues(ValueRange inputs, int64_t axis, ConversionPatternRewr
outputShape[axis] = concatDimSize;
auto resultType = RankedTensorType::get(outputShape, firstType.getElementType(), firstType.getEncoding());
if (llvm::all_of(inputs, isHostFoldableValue))
if (llvm::all_of(inputs, isCompileTimeComputable))
return createSpatConcat(rewriter, loc, axis, inputs);
auto concatCompute = createSpatCompute(rewriter, loc, TypeRange {resultType}, {}, inputs, [&](ValueRange args) {
@@ -135,7 +135,7 @@ static Value squeezeReducedAxes(Value keepdimsValue,
}
auto reassociation = buildCollapseReassociation(reducedAxes);
if (isHostFoldableValue(keepdimsValue))
if (isCompileTimeComputable(keepdimsValue))
return tensor::CollapseShapeOp::create(rewriter, loc, resultType, keepdimsValue, reassociation).getResult();
auto squeezeCompute =
src/PIM/Conversion/ONNXToSpatial/Patterns/Tensor/Concat.cpp
+2 -2
View File
@@ -3,7 +3,7 @@
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/Common/Common.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/Common/ComputeRegionBuilder.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/HostFoldability.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/CompileTime.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/SpatialOps.hpp"
#include "src/Dialect/ONNX/ONNXOps.hpp"
@@ -20,7 +20,7 @@ struct Concat : public OpConversionPattern<ONNXConcatOp> {
auto inputs = adaptor.getInputs();
int64_t axis = adaptor.getAxis();
if (llvm::all_of(inputs, isHostFoldableValue)) {
if (llvm::all_of(inputs, isCompileTimeComputable)) {
rewriter.replaceOp(maxpoolOp, createSpatConcat(rewriter, maxpoolOp.getLoc(), axis, inputs));
return success();
}
src/PIM/Conversion/ONNXToSpatial/Patterns/Tensor/Reshape.cpp
+2 -2
View File
@@ -5,7 +5,7 @@
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/Common/Common.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/ConversionPatterns.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/HostFoldability.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/CompileTime.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/SpatialOps.hpp"
#include "src/Dialect/ONNX/ONNXOps.hpp"
@@ -115,7 +115,7 @@ struct Reshape : OpConversionPattern<ONNXReshapeOp> {
}
auto replaceWithReshape = [&](auto buildReshape) -> LogicalResult {
if (isHostFoldableValue(adaptor.getData())) {
if (isCompileTimeComputable(adaptor.getData())) {
rewriter.replaceOp(reshapeOp, buildReshape(adaptor.getData()));
return success();
}
src/PIM/Conversion/ONNXToSpatial/Patterns/Tensor/Split.cpp
+2 -2
View File
@@ -3,7 +3,7 @@
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/Common/Common.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/ConversionPatterns.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/HostFoldability.hpp"
#include "src/Accelerators/PIM/Conversion/ONNXToSpatial/CompileTime.hpp"
#include "src/Accelerators/PIM/Dialect/Spatial/SpatialOps.hpp"
#include "src/Dialect/ONNX/ONNXOps.hpp"
@@ -61,7 +61,7 @@ struct Split : OpConversionPattern<ONNXSplitOp> {
sliceSizes.push_back(resultType.getShape()[axis]);
}
if (isHostFoldableValue(adaptor.getInput())) {
if (isCompileTimeComputable(adaptor.getInput())) {
for (int64_t sliceSize : sliceSizes) {
outputs.push_back(extractSliceAt(adaptor.getInput(), axis, offset, sliceSize, rewriter, splitOp.getLoc()));
offset += sliceSize;