nnicolosi/Raptor
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Now something work but not trust us (phase 1 + phase 2 of merge)
Validate Operations / validate-operations (push) Has been cancelled
Details

Browse Source
This commit is contained in:
ilgeco
2026-07-13 16:21:54 +02:00
parent 61e3ea9996
commit d1a29ace3c
12 changed files with 1269 additions and 736 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/PIM/Conversion/SpatialToPim/BatchCoreLoweringPatterns.cpp
+7 -2
View File
@@ -141,7 +141,8 @@ collectTopLevelFragmentAssemblyCopies(OpResult result, RankedTensorType packedRe
std::optional<StringRef> mode = blueprint.getMode();
std::optional<ArrayRef<int64_t>> operandIndicesAttr = blueprint.getFragmentOperandIndices();
std::optional<ArrayRef<int64_t>> sourceOffsetsAttr = blueprint.getFragmentSourceOffsets();
if (!mode || *mode != "fragment_assembly" || !operandIndicesAttr || !sourceOffsetsAttr)
std::optional<ArrayRef<int64_t>> sourceSlotsAttr = blueprint.getFragmentSourceSlots();
if (!mode || *mode != "fragment_assembly" || !operandIndicesAttr || !sourceOffsetsAttr || !sourceSlotsAttr)
return failure();
if (!blueprint.getOutput().hasOneUse() || !isa<func::ReturnOp>(*blueprint.getOutput().getUsers().begin()))
return failure();
@@ -153,6 +154,9 @@ collectTopLevelFragmentAssemblyCopies(OpResult result, RankedTensorType packedRe
ArrayRef<int64_t> operandIndices = *operandIndicesAttr;
ArrayRef<int64_t> sourceOffsets = *sourceOffsetsAttr;
ArrayRef<int64_t> sourceSlots = *sourceSlotsAttr;
if (sourceSlots.size() != operandIndices.size())
return failure();
ArrayRef<int64_t> flatOffsets = blueprint.getFragmentOffsets();
ArrayRef<int64_t> flatSizes = blueprint.getFragmentSizes();
ArrayRef<int64_t> flatStrides = *stridesAttr;
@@ -174,7 +178,8 @@ collectTopLevelFragmentAssemblyCopies(OpResult result, RankedTensorType packedRe
if (operandIndices[fragmentIndex] != static_cast<int64_t>(use.getOperandNumber()))
continue;
int64_t sourceElementOffset = sourceOffsets[fragmentIndex];
int64_t sourceElementOffset =
sourceSlots[fragmentIndex] * payloadElementCount + sourceOffsets[fragmentIndex];
int64_t lane = sourceElementOffset / payloadElementCount;
if (lane < 0 || lane >= static_cast<int64_t>(laneCount))
return failure();