diff --git a/src/PIM/Compiler/PimCodeGen.cpp b/src/PIM/Compiler/PimCodeGen.cpp
index 873fe21..1312fa9 100644
--- a/src/PIM/Compiler/PimCodeGen.cpp
+++ b/src/PIM/Compiler/PimCodeGen.cpp
@@ -695,13 +695,16 @@ void PimCodeGen::codeGenSendOp(pim::PimSendOp sendOp, const StaticValueKnowledge
 void PimCodeGen::codeGenWaitOp(
     pim::PimWaitOp waitOp, const StaticValueKnowledge& knowledge) const {
   auto eventRegister = indexOf(waitOp.getEventRegister(), knowledge);
-  assert(succeeded(eventRegister)
-         && "pim.wait event register must be statically resolvable during codegen");
+  auto waitValue = indexOf(waitOp.getWaitValue(), knowledge);
+  assert(succeeded(eventRegister) && succeeded(waitValue)
+         && "pim.wait operands must be statically resolvable during codegen");
+  if (*waitValue == 0)
+    return;
   pim_binary::InstructionRecord instruction;
   instruction.opcode = pim_binary::Opcode::wait;
   instruction.generic1 = pim::checkedI32OrCrash(
     *eventRegister, "wait event register");
-  instruction.generic2 = waitOp.getWaitValue();
+  instruction.generic2 = pim::checkedI32OrCrash(*waitValue, "wait value");
   emitInstruction(instruction);
 }
 
diff --git a/src/PIM/Compiler/PimCompilerUtils.cpp b/src/PIM/Compiler/PimCompilerUtils.cpp
index d172285..f95b8ff 100644
--- a/src/PIM/Compiler/PimCompilerUtils.cpp
+++ b/src/PIM/Compiler/PimCompilerUtils.cpp
@@ -12,6 +12,7 @@
 #include <limits>
 #include <tuple>
 
+#include "src/Accelerators/PIM/Common/PimCommon.hpp"
 #include "src/Accelerators/PIM/Compiler/PimCompilerOptions.hpp"
 #include "src/Accelerators/PIM/Compiler/PimCompilerUtils.hpp"
 #include "src/Accelerators/PIM/Conversion/ONNXToSpatial/ONNXToSpatialOptions.hpp"
@@ -78,6 +79,7 @@ spatial::SchedulingTarget getDefaultPimSchedulingTarget() {
   target.residentWeightCapacity = crossbarCountInCore.getValue();
   target.matrixRows = crossbarSize.getValue();
   target.matrixColumns = crossbarSize.getValue();
+  target.synchronizationRegisterCount = kPimEventRegisterCount;
 
   setDefaultPimInterProcessorLatencies(target);
   return target;
diff --git a/src/PIM/Conversion/SpatialToPim/CoreLoweringPatterns.cpp b/src/PIM/Conversion/SpatialToPim/CoreLoweringPatterns.cpp
index 4dc6101..02dad5b 100644
--- a/src/PIM/Conversion/SpatialToPim/CoreLoweringPatterns.cpp
+++ b/src/PIM/Conversion/SpatialToPim/CoreLoweringPatterns.cpp
@@ -368,11 +368,14 @@ LogicalResult raptor::SpatialToPimPass::lowerComputeOp(spatial::SpatScheduledCom
           return failure();
         PimWaitOp::create(
           rewriter, receiveOp->getLoc(), hostWaitLoad.getEventRegister(),
-          rewriter.getI32IntegerAttr(1));
+          hostWaitLoad.getWaitValue());
         received = PimMemCopyHostToDevOp::create(
           rewriter, receiveOp->getLoc(), outputBuffer.getType(), zero,
           hostWaitLoad.getHostOffset(), outputBuffer, *hostBuffer, *sizeAttr)
           .getOutput();
+        PimSyncOp::create(
+          rewriter, receiveOp->getLoc(), hostWaitLoad.getSourceCoreId(),
+          hostWaitLoad.getAcknowledgementEventRegister());
       } else {
         received = PimReceiveOp::create(
           rewriter, receiveOp->getLoc(), outputBuffer.getType(), outputBuffer,
diff --git a/src/PIM/Conversion/SpatialToPim/Patterns/ChannelLowering.cpp b/src/PIM/Conversion/SpatialToPim/Patterns/ChannelLowering.cpp
index 08d2902..81f4537 100644
--- a/src/PIM/Conversion/SpatialToPim/Patterns/ChannelLowering.cpp
+++ b/src/PIM/Conversion/SpatialToPim/Patterns/ChannelLowering.cpp
@@ -147,15 +147,42 @@ struct HostWaitLoadLowering : OpRewritePattern<spatial::SpatHostWaitLoadOp> {
         return failure();
       auto wait = pim::PimWaitOp::create(
         rewriter, op.getLoc(), op.getEventRegister(),
-        rewriter.getI32IntegerAttr(1));
+        op.getWaitValue());
       copyRaptorDebugAttrs(op.getOperation(), wait.getOperation());
-      return pim::PimMemCopyHostToDevOp::create(
+      Value output = pim::PimMemCopyHostToDevOp::create(
         rewriter, op.getLoc(), outputBuffer.getType(), zero,
         op.getHostOffset(), outputBuffer, *hostBuffer, sizeAttr).getOutput();
+      auto sync = pim::PimSyncOp::create(
+        rewriter, op.getLoc(), op.getSourceCoreId(),
+        op.getAcknowledgementEventRegister());
+      copyRaptorDebugAttrs(op.getOperation(), sync.getOperation());
+      return output;
     });
   }
 };
 
+struct SyncLowering : OpRewritePattern<spatial::SpatSyncOp> {
+  using OpRewritePattern::OpRewritePattern;
+
+  LogicalResult matchAndRewrite(spatial::SpatSyncOp op,
+                                PatternRewriter& rewriter) const override {
+    rewriter.replaceOpWithNewOp<pim::PimSyncOp>(
+      op, op.getTargetCoreId(), op.getEventRegister());
+    return success();
+  }
+};
+
+struct WaitLowering : OpRewritePattern<spatial::SpatWaitOp> {
+  using OpRewritePattern::OpRewritePattern;
+
+  LogicalResult matchAndRewrite(spatial::SpatWaitOp op,
+                                PatternRewriter& rewriter) const override {
+    rewriter.replaceOpWithNewOp<pim::PimWaitOp>(
+      op, op.getEventRegister(), op.getWaitValue());
+    return success();
+  }
+};
+
 struct ExtractRowsLowering : OpRewritePattern<spatial::SpatExtractRowsOp> {
   using OpRewritePattern::OpRewritePattern;
 
@@ -200,7 +227,8 @@ struct ConcatLowering : OpRewritePattern<spatial::SpatConcatOp> {
 void populateChannelLoweringPatterns(RewritePatternSet& patterns) {
   patterns.add<ChannelSendLowering, ChannelReceiveLowering,
                HostStoreSyncLowering, HostWaitLoadLowering,
-               ExtractRowsLowering, ConcatLowering>(patterns.getContext());
+               SyncLowering, WaitLowering, ExtractRowsLowering,
+               ConcatLowering>(patterns.getContext());
 }
 
 } // namespace onnx_mlir
diff --git a/src/PIM/Conversion/SpatialToPim/SpatialToPimPass.cpp b/src/PIM/Conversion/SpatialToPim/SpatialToPimPass.cpp
index f9b4ebd..70db2d9 100644
--- a/src/PIM/Conversion/SpatialToPim/SpatialToPimPass.cpp
+++ b/src/PIM/Conversion/SpatialToPim/SpatialToPimPass.cpp
@@ -128,6 +128,8 @@ void onnx_mlir::raptor::SpatialToPimPass::runOnOperation() {
                     spatial::SpatChannelSendOp,
                     spatial::SpatHostStoreSyncOp,
                     spatial::SpatHostWaitLoadOp,
+                    spatial::SpatSyncOp,
+                    spatial::SpatWaitOp,
                     spatial::SpatExtractRowsOp>();
 
   RewritePatternSet initialPatterns(ctx);
@@ -223,6 +225,8 @@ void onnx_mlir::raptor::SpatialToPimPass::runOnOperation() {
                             spatial::SpatChannelSendOp,
                             spatial::SpatHostStoreSyncOp,
                             spatial::SpatHostWaitLoadOp,
+                            spatial::SpatSyncOp,
+                            spatial::SpatWaitOp,
                             spatial::SpatExtractRowsOp>();
 
   SmallVector<pim::PimCoreOp> coreOps;
@@ -274,6 +278,8 @@ void onnx_mlir::raptor::SpatialToPimPass::runOnOperation() {
                                    spatial::SpatChannelSendOp,
                                    spatial::SpatHostStoreSyncOp,
                                    spatial::SpatHostWaitLoadOp,
+                                   spatial::SpatSyncOp,
+                                   spatial::SpatWaitOp,
                                    spatial::SpatExtractRowsOp>();
 
   RewritePatternSet communicationPatterns(ctx);
diff --git a/src/PIM/Dialect/Pim/Passes/Transforms/Bufferization/ContiguityPatterns.cpp b/src/PIM/Dialect/Pim/Passes/Transforms/Bufferization/ContiguityPatterns.cpp
index 2e70a85..48172a5 100644
--- a/src/PIM/Dialect/Pim/Passes/Transforms/Bufferization/ContiguityPatterns.cpp
+++ b/src/PIM/Dialect/Pim/Passes/Transforms/Bufferization/ContiguityPatterns.cpp
@@ -302,12 +302,19 @@ static FailureOr<int64_t> getShapedByteSize(MemRefType type) {
   return static_cast<int64_t>(*byteSize);
 }
 
-static FailureOr<SmallVector<int64_t>>
+struct LogicalCopyShape {
+  SmallVector<int64_t> dimensions;
+  Type elementType;
+};
+
+static bool isPackedByteBuffer(MemRefType type) {
+  return type.getRank() == 1 && type.getElementType().isInteger(8);
+}
+
+static FailureOr<LogicalCopyShape>
 inferLogicalCopyShape(MemRefType targetType, MemRefType sourceType, int64_t size) {
   if (!targetType.hasStaticShape() || !sourceType.hasStaticShape())
     return failure();
-  if (targetType.getElementType() != sourceType.getElementType() || targetType.getRank() != sourceType.getRank())
-    return failure();
 
   auto targetBytes = getShapedByteSize(targetType);
   auto sourceBytes = getShapedByteSize(sourceType);
@@ -316,18 +323,37 @@ inferLogicalCopyShape(MemRefType targetType, MemRefType sourceType, int64_t size
 
   bool targetMatches = *targetBytes == size;
   bool sourceMatches = *sourceBytes == size;
-  if (targetMatches && sourceMatches && targetType.getShape() != sourceType.getShape())
+  bool matchingTypes = targetType.getElementType() == sourceType.getElementType()
+                    && targetType.getRank() == sourceType.getRank();
+  if (matchingTypes) {
+    if (targetMatches && sourceMatches
+        && targetType.getShape() != sourceType.getShape())
+      return failure();
+    MemRefType logicalType = targetMatches ? targetType : sourceType;
+    if (targetMatches || sourceMatches)
+      return LogicalCopyShape {
+        SmallVector<int64_t>(logicalType.getShape()),
+        logicalType.getElementType()};
     return failure();
-  if (targetMatches)
-    return SmallVector<int64_t>(targetType.getShape().begin(), targetType.getShape().end());
-  if (sourceMatches)
-    return SmallVector<int64_t>(sourceType.getShape().begin(), sourceType.getShape().end());
+  }
+  if (targetMatches && isPackedByteBuffer(sourceType))
+    return LogicalCopyShape {
+      SmallVector<int64_t>(targetType.getShape()),
+      targetType.getElementType()};
+  if (sourceMatches && isPackedByteBuffer(targetType))
+    return LogicalCopyShape {
+      SmallVector<int64_t>(sourceType.getShape()),
+      sourceType.getElementType()};
   return failure();
 }
 
-static FailureOr<int64_t> getContiguousSuffixRank(Value value, ArrayRef<int64_t> copyShape) {
+static FailureOr<int64_t> getContiguousSuffixRank(
+    Value value, ArrayRef<int64_t> copyShape, Type elementType = {}) {
   auto type = dyn_cast<MemRefType>(value.getType());
+  if (type && elementType && isPackedByteBuffer(type))
+    return copyShape.size();
   if (!type || !type.hasStaticShape() || !hasByteSizedElementType(type.getElementType())
+      || (elementType && type.getElementType() != elementType)
       || type.getRank() != static_cast<int64_t>(copyShape.size()))
     return failure();
   if (llvm::any_of(copyShape, [](int64_t dim) { return dim <= 0; }))
@@ -351,6 +377,30 @@ static FailureOr<int64_t> getContiguousSuffixRank(Value value, ArrayRef<int64_t>
   return contiguousSuffixRank;
 }
 
+static FailureOr<SmallVector<int64_t>> getOuterByteStrides(
+    Value value, const LogicalCopyShape &copyShape, size_t outerRank) {
+  auto type = cast<MemRefType>(value.getType());
+  SmallVector<int64_t> strides;
+  if (isPackedByteBuffer(type))
+    strides = computeRowMajorStrides(copyShape.dimensions);
+  else {
+    auto proven = getProvenMemRefStrides(value);
+    if (failed(proven))
+      return failure();
+    strides = std::move(*proven);
+  }
+  int64_t elementByteWidth = static_cast<int64_t>(
+    getElementTypeSizeInBytes(copyShape.elementType));
+  SmallVector<int64_t> result;
+  for (int64_t stride : ArrayRef<int64_t>(strides).take_front(outerRank)) {
+    auto byteStride = checkedPositiveMul(stride, elementByteWidth);
+    if (failed(byteStride))
+      return failure();
+    result.push_back(*byteStride);
+  }
+  return result;
+}
+
 static FailureOr<CopyEndpointPlan> analyzeCopyEndpoint(Value value, Value initialByteOffset, MemRefType logicalType) {
   if (!logicalType.hasStaticShape() || !hasByteSizedElementType(logicalType.getElementType()))
     return failure();
@@ -448,8 +498,10 @@ analyzeCopyRewrite(Value target, Value source, Value targetOffset, Value sourceO
   if (failed(logicalCopyShape))
     return failure();
 
-  auto targetSuffixRank = getContiguousSuffixRank(target, *logicalCopyShape);
-  auto sourceSuffixRank = getContiguousSuffixRank(source, *logicalCopyShape);
+  auto targetSuffixRank = getContiguousSuffixRank(
+    target, logicalCopyShape->dimensions, logicalCopyShape->elementType);
+  auto sourceSuffixRank = getContiguousSuffixRank(
+    source, logicalCopyShape->dimensions, logicalCopyShape->elementType);
   if (failed(targetSuffixRank) || failed(sourceSuffixRank))
     return failure();
 
@@ -458,23 +510,24 @@ analyzeCopyRewrite(Value target, Value source, Value targetOffset, Value sourceO
   plan.source = *sourcePlan;
 
   int64_t contiguousSuffixRank = std::min(*targetSuffixRank, *sourceSuffixRank);
-  if (contiguousSuffixRank == static_cast<int64_t>(logicalCopyShape->size())) {
+  if (contiguousSuffixRank
+      == static_cast<int64_t>(logicalCopyShape->dimensions.size())) {
     plan.kind = CopyRewritePlan::Kind::Direct;
     plan.directBytes = size;
     return plan;
   }
 
-  auto targetStrides = getProvenMemRefStrides(target);
-  auto sourceStrides = getProvenMemRefStrides(source);
-  if (failed(targetStrides) || failed(sourceStrides))
-    return failure();
-
-  int64_t elementByteWidth = static_cast<int64_t>(getElementTypeSizeInBytes(targetType.getElementType()));
+  int64_t elementByteWidth = static_cast<int64_t>(
+    getElementTypeSizeInBytes(logicalCopyShape->elementType));
   plan.kind = CopyRewritePlan::Kind::Loop;
   plan.loop.targetBaseOffset = plan.target.offset;
   plan.loop.sourceBaseOffset = plan.source.offset;
-  plan.loop.outerShape.assign(logicalCopyShape->begin(), logicalCopyShape->end() - contiguousSuffixRank);
-  SmallVector<int64_t> chunkShape(logicalCopyShape->end() - contiguousSuffixRank, logicalCopyShape->end());
+  plan.loop.outerShape.assign(
+    logicalCopyShape->dimensions.begin(),
+    logicalCopyShape->dimensions.end() - contiguousSuffixRank);
+  SmallVector<int64_t> chunkShape(
+    logicalCopyShape->dimensions.end() - contiguousSuffixRank,
+    logicalCopyShape->dimensions.end());
   auto outerElements = checkedPositiveProduct(plan.loop.outerShape);
   auto chunkElements = checkedPositiveProduct(chunkShape);
   auto chunkBytes = failed(chunkElements)
@@ -484,18 +537,14 @@ analyzeCopyRewrite(Value target, Value source, Value targetOffset, Value sourceO
     return failure();
   plan.loop.outerElements = *outerElements;
   plan.loop.chunkBytes = *chunkBytes;
-  for (int64_t stride : ArrayRef<int64_t>(*targetStrides).take_front(plan.loop.outerShape.size())) {
-    auto byteStride = checkedPositiveMul(stride, elementByteWidth);
-    if (failed(byteStride))
-      return failure();
-    plan.loop.targetOuterByteStrides.push_back(*byteStride);
-  }
-  for (int64_t stride : ArrayRef<int64_t>(*sourceStrides).take_front(plan.loop.outerShape.size())) {
-    auto byteStride = checkedPositiveMul(stride, elementByteWidth);
-    if (failed(byteStride))
-      return failure();
-    plan.loop.sourceOuterByteStrides.push_back(*byteStride);
-  }
+  auto targetStrides = getOuterByteStrides(
+    target, *logicalCopyShape, plan.loop.outerShape.size());
+  auto sourceStrides = getOuterByteStrides(
+    source, *logicalCopyShape, plan.loop.outerShape.size());
+  if (failed(targetStrides) || failed(sourceStrides))
+    return failure();
+  plan.loop.targetOuterByteStrides = std::move(*targetStrides);
+  plan.loop.sourceOuterByteStrides = std::move(*sourceStrides);
   if (plan.loop.chunkBytes <= 0)
     return failure();
   return plan;
diff --git a/src/PIM/Dialect/Pim/Passes/Transforms/Bufferization/PimBufferizationPass.cpp b/src/PIM/Dialect/Pim/Passes/Transforms/Bufferization/PimBufferizationPass.cpp
index 7988e3f..33c3c40 100644
--- a/src/PIM/Dialect/Pim/Passes/Transforms/Bufferization/PimBufferizationPass.cpp
+++ b/src/PIM/Dialect/Pim/Passes/Transforms/Bufferization/PimBufferizationPass.cpp
@@ -602,18 +602,30 @@ static LogicalResult normalizePimMemory(ModuleOp moduleOp, func::FuncOp funcOp)
   PatternRewriter rewriter(ctx);
 
   SmallVector<MemRefCopyWorkItem> copyWorklist;
+  SmallVector<PimMemCopyDevToHostOp> hostToHostCopies;
   llvm::SmallPtrSet<Operation*, 16> seenCopyOps;
+  llvm::SmallPtrSet<Operation*, 4> seenHostToHostCopies;
   auto addCopyOp = [&](memref::CopyOp copyOp, const StaticValueKnowledge& knowledge) {
     if (seenCopyOps.insert(copyOp.getOperation()).second)
       copyWorklist.push_back({copyOp, knowledge});
   };
+  auto collectCopy = [&](Operation &op,
+                         const StaticValueKnowledge &knowledge) {
+    if (auto copyOp = dyn_cast<memref::CopyOp>(&op))
+      addCopyOp(copyOp, knowledge);
+    if (auto copyOp = dyn_cast<PimMemCopyDevToHostOp>(&op);
+        copyOp
+        && isHostBackedPimAddress(copyOp.getDeviceSource(), knowledge)
+        && isHostBackedPimAddress(copyOp.getHostTarget(), knowledge)
+        && seenHostToHostCopies.insert(copyOp).second)
+      hostToHostCopies.push_back(copyOp);
+  };
 
   moduleOp.walk([&](pim::PimCoreOp coreOp) {
     StaticValueKnowledge knowledge = seedCoreKnowledge(coreOp);
     (void) walkPimCoreBlockStructurally(
       coreOp.getBody().front(), knowledge, [&](Operation& op, const StaticValueKnowledge& opKnowledge) {
-        if (auto copyOp = dyn_cast<memref::CopyOp>(&op))
-          addCopyOp(copyOp, opKnowledge);
+        collectCopy(op, opKnowledge);
         return success();
       });
   });
@@ -622,8 +634,7 @@ static LogicalResult normalizePimMemory(ModuleOp moduleOp, func::FuncOp funcOp)
       StaticValueKnowledge knowledge = seedCoreBatchKnowledge(coreBatchOp, lane);
       (void) walkPimCoreBlockStructurally(
         coreBatchOp.getBody().front(), knowledge, [&](Operation& op, const StaticValueKnowledge& opKnowledge) {
-          if (auto copyOp = dyn_cast<memref::CopyOp>(&op))
-            addCopyOp(copyOp, opKnowledge);
+          collectCopy(op, opKnowledge);
           return success();
         });
     }
@@ -631,6 +642,22 @@ static LogicalResult normalizePimMemory(ModuleOp moduleOp, func::FuncOp funcOp)
 
   bool hasFailed = false;
   Value zeroOffset = getOrCreateIndexConstant(rewriter, funcOp, 0);
+  for (PimMemCopyDevToHostOp copyOp : hostToHostCopies) {
+    rewriter.setInsertionPoint(copyOp);
+    auto scratchType = MemRefType::get(
+      {copyOp.getSize()}, rewriter.getI8Type());
+    Value scratch = memref::AllocOp::create(
+      rewriter, copyOp.getLoc(), scratchType);
+    auto load = PimMemCopyHostToDevOp::create(
+      rewriter, copyOp.getLoc(), scratchType, zeroOffset,
+      copyOp.getDeviceSourceOffset(), scratch, copyOp.getDeviceSource(),
+      copyOp.getSizeAttr());
+    auto store = PimMemCopyDevToHostOp::create(
+      rewriter, copyOp.getLoc(), copyOp.getHostTarget().getType(),
+      copyOp.getHostTargetOffset(), zeroOffset, copyOp.getHostTarget(),
+      load.getOutput(), copyOp.getSizeAttr());
+    rewriter.replaceOp(copyOp, store.getOutput());
+  }
   for (const MemRefCopyWorkItem& workItem : copyWorklist) {
     memref::CopyOp copyOp = workItem.copyOp;
     rewriter.setInsertionPoint(copyOp);
diff --git a/src/PIM/Dialect/Pim/Pim.td b/src/PIM/Dialect/Pim/Pim.td
index 80a67d9..f0a7b9a 100644
--- a/src/PIM/Dialect/Pim/Pim.td
+++ b/src/PIM/Dialect/Pim/Pim.td
@@ -136,7 +136,7 @@ def PimWaitOp : PimOp<"wait", []> {
 
   let arguments = (ins
     Index:$eventRegister,
-    I32Attr:$waitValue
+    Index:$waitValue
   );
 
   let assemblyFormat = [{
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryPlanning.cpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryPlanning.cpp
index e685537..72edd54 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryPlanning.cpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryPlanning.cpp
@@ -242,11 +242,146 @@ static void appendReceive(BoundaryProgram &boundary,
     target.collection, {slice}, {0, 1}, {target.position}, {lanes}, lanes});
 }
 
+struct HostTransferRef {
+  ExternalTransferFamily *family = nullptr;
+  size_t index = 0;
+};
+
+static unsigned getBarrierRoundCount(size_t coreCount) {
+  unsigned rounds = 0;
+  for (size_t distance = 1; distance < coreCount; distance *= 2)
+    ++rounds;
+  return rounds;
+}
+
+static LogicalResult assignPipelineSynchronization(
+    DeferredTransferPlan &transfers,
+    ArrayRef<BoundaryProgram> boundaries,
+    size_t synchronizationRegisterCount) {
+  bool pipelined = false;
+  for (ScheduledInfo &scheduled : transfers.scheduled) {
+    if (scheduled.pipelineStages.empty())
+      continue;
+    pipelined = true;
+    llvm::append_range(transfers.downstreamCores, scheduled.cores);
+    for (auto [core, stage] :
+         llvm::zip_equal(scheduled.cores, scheduled.pipelineStages))
+      if (stage == 0)
+        transfers.stageZeroCores.push_back(core);
+  }
+  if (!pipelined)
+    return success();
+  transfers.synchronizationRegisterCount = synchronizationRegisterCount;
+  llvm::sort(transfers.stageZeroCores);
+  transfers.stageZeroCores.erase(
+    llvm::unique(transfers.stageZeroCores), transfers.stageZeroCores.end());
+  llvm::sort(transfers.downstreamCores);
+  transfers.downstreamCores.erase(
+    llvm::unique(transfers.downstreamCores),
+    transfers.downstreamCores.end());
+  llvm::erase_if(transfers.downstreamCores, [&](int64_t core) {
+    return llvm::is_contained(transfers.stageZeroCores, core);
+  });
+
+  DenseMap<int64_t, SmallVector<HostTransferRef>> incomingByCore;
+  DenseMap<ExternalTransferFamily *, SmallVector<int64_t>> eventRegisters;
+  DenseMap<ExternalTransferFamily *, SmallVector<int64_t>> waitValues;
+  DenseMap<ExternalTransferFamily *, SmallVector<int64_t>> acknowledgementRegisters;
+  auto initialize = [&](ExternalTransferFamily &family) {
+    size_t count = family.targetCores.size();
+    eventRegisters.try_emplace(&family, count, 0);
+    waitValues.try_emplace(&family, count, 0);
+    acknowledgementRegisters.try_emplace(&family, count, 0);
+  };
+  for (const BoundaryProgram &boundary : boundaries)
+    for (const BoundaryInstruction &instruction : boundary.instructions) {
+      auto *receive = std::get_if<EmitReceiveAssemblyRun>(&instruction);
+      if (!receive || receive->slices.empty()
+          || !receive->slices.front().family->hostRouted)
+        continue;
+      for (const ScheduledTransferSlice &slice : receive->slices) {
+        ExternalTransferFamily &family = *slice.family;
+        initialize(family);
+        for (size_t offset = 0; offset < slice.transferCount; ++offset) {
+          size_t index = slice.familyOffset + offset;
+          int64_t source = family.sourceCores.valueAt(index);
+          int64_t target = family.targetCores.valueAt(index);
+          incomingByCore[target].push_back({&family, index});
+          ++transfers.hostAcknowledgementCounts[source];
+        }
+      }
+    }
+
+  unsigned barrierRounds = getBarrierRoundCount(
+    transfers.stageZeroCores.size());
+  bool stageZeroNeedsAcknowledgements = llvm::any_of(
+    transfers.stageZeroCores, [&](int64_t core) {
+      return transfers.hostAcknowledgementCounts.contains(core);
+    });
+  for (auto &[target, incoming] : incomingByCore) {
+    bool needsAcknowledgementRegister =
+      transfers.hostAcknowledgementCounts.contains(target);
+    bool stageZero = llvm::is_contained(transfers.stageZeroCores, target);
+    size_t reserved = stageZero
+      ? barrierRounds + (stageZeroNeedsAcknowledgements ? 1 : 0)
+      : 1 + (needsAcknowledgementRegister ? 1 : 0);
+    if (reserved >= synchronizationRegisterCount) {
+      incoming.front().family->requirement->exchange->deferred.emitOpError(
+        "pipeline synchronization leaves no event register for incoming host transfers");
+      return failure();
+    }
+    size_t groupCount = std::min(
+      incoming.size(), synchronizationRegisterCount - reserved);
+    // One wait consumes a complete consecutive group of producer signals.
+    SmallVector<size_t> groupSizes(groupCount);
+    for (size_t ordinal = 0; ordinal < incoming.size(); ++ordinal)
+      ++groupSizes[ordinal * groupCount / incoming.size()];
+    SmallVector<bool> first(groupCount, true);
+    for (size_t ordinal = 0; ordinal < incoming.size(); ++ordinal) {
+      size_t group = ordinal * groupCount / incoming.size();
+      HostTransferRef transfer = incoming[ordinal];
+      eventRegisters[transfer.family][transfer.index] = group;
+      acknowledgementRegisters[transfer.family][transfer.index] =
+        synchronizationRegisterCount - 1;
+      if (first[group]) {
+        waitValues[transfer.family][transfer.index] = groupSizes[group];
+        first[group] = false;
+      }
+    }
+  }
+  for (auto &[family, values] : eventRegisters) {
+    family->eventRegisters = StaticIntSequence::fromValues(values);
+    family->waitValues = StaticIntSequence::fromValues(waitValues[family]);
+    family->acknowledgementEventRegisters =
+      StaticIntSequence::fromValues(acknowledgementRegisters[family]);
+  }
+
+  if (!transfers.stageZeroCores.empty()) {
+    size_t reserved = barrierRounds
+                    + (stageZeroNeedsAcknowledgements ? 1 : 0);
+    if (reserved > synchronizationRegisterCount)
+      return transfers.scheduled.front().op->emitOpError(
+        "pipeline stage-zero barrier requires more synchronization registers than the target provides");
+  }
+  if (!transfers.downstreamCores.empty()) {
+    bool needsAcknowledgements = llvm::any_of(
+      transfers.downstreamCores, [&](int64_t core) {
+        return transfers.hostAcknowledgementCounts.contains(core);
+      });
+    if (1 + (needsAcknowledgements ? 1 : 0)
+        > synchronizationRegisterCount)
+      return transfers.scheduled.front().op->emitOpError(
+        "pipeline stage-zero release requires more synchronization registers than the target provides");
+  }
+  return success();
+}
+
 } // namespace
 
 FailureOr<DeferredBoundaryPlan> buildDeferredBoundaryPlan(
     DeferredTransferPlan &transfers,
-    const ScheduledCommunicationPlan &schedule) {
+    const ScheduledCommunicationPlan &schedule,
+    size_t synchronizationRegisterCount) {
   DeferredBoundaryPlan result;
   SmallVector<BoundaryProgram> boundaries;
   DenseMap<BoundaryKey, unsigned> indices;
@@ -373,6 +508,9 @@ FailureOr<DeferredBoundaryPlan> buildDeferredBoundaryPlan(
     return std::tie(scheduledOrder[lhs.key.first], lhs.key.second)
          < std::tie(scheduledOrder[rhs.key.first], rhs.key.second);
   });
+  if (failed(assignPipelineSynchronization(
+        transfers, boundaries, synchronizationRegisterCount)))
+    return failure();
   result.boundaries = std::move(boundaries);
   return result;
 }
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryPlanning.hpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryPlanning.hpp
index 748374d..2d7db41 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryPlanning.hpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryPlanning.hpp
@@ -53,6 +53,7 @@ struct DeferredBoundaryPlan {
 };
 
 mlir::FailureOr<DeferredBoundaryPlan> buildDeferredBoundaryPlan(DeferredTransferPlan& transfers,
-                                                                const ScheduledCommunicationPlan& schedule);
+                                                                const ScheduledCommunicationPlan& schedule,
+                                                                size_t synchronizationRegisterCount);
 
 } // namespace onnx_mlir::spatial
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryRealization.cpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryRealization.cpp
index 28c0e14..6ca51c0 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryRealization.cpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryRealization.cpp
@@ -4,6 +4,7 @@
 #include "DeferredBoundaryRealization.hpp"
 #include "DeferredProjectionAnalysis.hpp"
 #include "DeferredResultRealization.hpp"
+#include "DeferredTransferPlanning.hpp"
 #include "src/Accelerators/PIM/Common/IR/LoopUtils.hpp"
 #include "src/Accelerators/PIM/Common/IR/StaticIntGrid.hpp"
 #include "src/Accelerators/PIM/Common/IR/StaticIntSequence.hpp"
@@ -21,6 +22,8 @@ struct LogicalTransferMetadataView {
   StaticIntSequenceChain targetCores;
   StaticIntSequenceChain hostOffsets;
   StaticIntSequenceChain eventRegisters;
+  StaticIntSequenceChain waitValues;
+  StaticIntSequenceChain acknowledgementEventRegisters;
   StaticIntSequenceChain targetLanes;
   StaticIntSequenceChain localOffsets;
   SmallVector<StaticIntSequenceChain> projectionOffsets;
@@ -91,6 +94,9 @@ static void appendMetadata(const ScheduledTransferSlice &slice, LogicalTransferM
     metadata.hostOffsets.append(family.hostOffsets, familyIndex, count);
     metadata.eventRegisters.append(
       family.eventRegisters, familyIndex, count);
+    metadata.waitValues.append(family.waitValues, familyIndex, count);
+    metadata.acknowledgementEventRegisters.append(
+      family.acknowledgementEventRegisters, familyIndex, count);
   }
   metadata.targetLanes.append(StaticIntSequence::affine(targetLane, 1, count));
   if (family.requirement->producerLocalOffsets)
@@ -296,13 +302,21 @@ static FailureOr<Value> emitReceiveValue(ArrayRef<ScheduledTransferSlice> slices
   if (failed(grids)) return failure();
   std::optional<StaticIntGrid> hostOffsets;
   std::optional<StaticIntGrid> eventRegisters;
+  std::optional<StaticIntGrid> waitValues;
+  std::optional<StaticIntGrid> acknowledgementEventRegisters;
   if (slices.front().family->hostRouted) {
     auto offsets = buildGrid(metadata.hostOffsets);
     auto events = buildGrid(metadata.eventRegisters);
-    if (failed(offsets) || failed(events))
+    auto waits = buildGrid(metadata.waitValues);
+    auto acknowledgements = buildGrid(
+      metadata.acknowledgementEventRegisters);
+    if (failed(offsets) || failed(events) || failed(waits)
+        || failed(acknowledgements))
       return failure();
     hostOffsets = std::move(*offsets);
     eventRegisters = std::move(*events);
+    waitValues = std::move(*waits);
+    acknowledgementEventRegisters = std::move(*acknowledgements);
   }
   Value position = lane ? lane : context.constants.getIndex(0);
   Value row = context.constants.getIndex(0);
@@ -319,6 +333,10 @@ static FailureOr<Value> emitReceiveValue(ArrayRef<ScheduledTransferSlice> slices
       hostOffsets->emitLookup(
         row, position, anchor, context.constants, context.rewriter, anchor->getLoc()),
       eventRegisters->emitLookup(
+        row, position, anchor, context.constants, context.rewriter, anchor->getLoc()),
+      waitValues->emitLookup(
+        row, position, anchor, context.constants, context.rewriter, anchor->getLoc()),
+      acknowledgementEventRegisters->emitLookup(
         row, position, anchor, context.constants, context.rewriter, anchor->getLoc()));
     receive = op;
     output = op.getOutput();
@@ -387,6 +405,8 @@ static FailureOr<Value> emitReceiveAssembly(const EmitReceiveAssemblyRun &run, V
   std::optional<StaticIntGrid> positions;
   std::optional<StaticIntGrid> hostOffsets;
   std::optional<StaticIntGrid> eventRegisters;
+  std::optional<StaticIntGrid> waitValues;
+  std::optional<StaticIntGrid> acknowledgementEventRegisters;
   bool hostRouted = run.slices.front().family->hostRouted;
   auto metadataByEntry = buildRectangularReceiveMetadata(run, laneCount);
   if (succeeded(metadataByEntry)) {
@@ -402,10 +422,17 @@ static FailureOr<Value> emitReceiveAssembly(const EmitReceiveAssemblyRun &run, V
         &LogicalTransferMetadataView::hostOffsets);
       auto events = buildRows(
         &LogicalTransferMetadataView::eventRegisters);
-      if (failed(offsets) || failed(events))
+      auto waits = buildRows(
+        &LogicalTransferMetadataView::waitValues);
+      auto acknowledgements = buildRows(
+        &LogicalTransferMetadataView::acknowledgementEventRegisters);
+      if (failed(offsets) || failed(events) || failed(waits)
+          || failed(acknowledgements))
         return failure();
       hostOffsets = std::move(*offsets);
       eventRegisters = std::move(*events);
+      waitValues = std::move(*waits);
+      acknowledgementEventRegisters = std::move(*acknowledgements);
     }
     SmallVector<StaticIntSequence> positionRows;
     for (unsigned position : run.positions)
@@ -456,10 +483,17 @@ static FailureOr<Value> emitReceiveAssembly(const EmitReceiveAssemblyRun &run, V
         &LogicalTransferMetadataView::hostOffsets);
       auto events = buildGrid(
         &LogicalTransferMetadataView::eventRegisters);
-      if (failed(offsets) || failed(events))
+      auto waits = buildGrid(
+        &LogicalTransferMetadataView::waitValues);
+      auto acknowledgements = buildGrid(
+        &LogicalTransferMetadataView::acknowledgementEventRegisters);
+      if (failed(offsets) || failed(events) || failed(waits)
+          || failed(acknowledgements))
         return failure();
       hostOffsets = std::move(*offsets);
       eventRegisters = std::move(*events);
+      waitValues = std::move(*waits);
+      acknowledgementEventRegisters = std::move(*acknowledgements);
     }
     SmallVector<StaticIntSequence> positionColumns;
     for (const StaticIntSequenceChain &values : positionsByLane)
@@ -491,6 +525,10 @@ static FailureOr<Value> emitReceiveAssembly(const EmitReceiveAssemblyRun &run, V
         hostOffsets->emitLookup(
           entry, runtimeLane, anchor, context.constants, context.rewriter, loc),
         eventRegisters->emitLookup(
+          entry, runtimeLane, anchor, context.constants, context.rewriter, loc),
+        waitValues->emitLookup(
+          entry, runtimeLane, anchor, context.constants, context.rewriter, loc),
+        acknowledgementEventRegisters->emitLookup(
           entry, runtimeLane, anchor, context.constants, context.rewriter, loc));
       receive = op;
       output = op.getOutput();
@@ -1158,9 +1196,199 @@ static LogicalResult emitBoundary(const BoundaryProgram &boundary, ArrayRef<Defe
   return failed(values) ? failure() : replaceResults(exchanges, *values, replacements);
 }
 
+static unsigned getBarrierRoundCount(size_t coreCount) {
+  unsigned rounds = 0;
+  for (size_t distance = 1; distance < coreCount; distance *= 2)
+    ++rounds;
+  return rounds;
+}
+
+static LogicalResult emitCompletionSynchronization(
+    DeferredTransferPlan &transfers, DeferredEmissionContext &context) {
+  if (transfers.synchronizationRegisterCount == 0)
+    return success();
+  size_t acknowledgementRegister =
+    transfers.synchronizationRegisterCount - 1;
+  unsigned barrierRounds = getBarrierRoundCount(
+    transfers.stageZeroCores.size());
+  bool stageZeroNeedsAcknowledgements = llvm::any_of(
+    transfers.stageZeroCores, [&](int64_t core) {
+      return transfers.hostAcknowledgementCounts.contains(core);
+    });
+  size_t firstBarrierRegister = acknowledgementRegister
+                              - (stageZeroNeedsAcknowledgements ? 1 : 0);
+  DenseMap<int64_t, unsigned> stageZeroRank;
+  for (auto [rank, core] : llvm::enumerate(transfers.stageZeroCores))
+    stageZeroRank[core] = rank;
+  DenseMap<int64_t, unsigned> downstreamRank;
+  for (auto [rank, core] : llvm::enumerate(transfers.downstreamCores))
+    downstreamRank[core] = rank;
+  auto getReleaseRegister = [&](int64_t core) {
+    return acknowledgementRegister
+         - (transfers.hostAcknowledgementCounts.contains(core) ? 1 : 0);
+  };
+
+  for (ScheduledInfo &scheduled : transfers.scheduled) {
+    Block *block = scheduled.blocks.front();
+    context.rewriter.setInsertionPoint(block->getTerminator());
+    Location loc = scheduled.op->getLoc();
+    Value lane;
+    if (auto batch = dyn_cast<SpatScheduledComputeBatch>(scheduled.op))
+      lane = *batch.getLaneArgument();
+
+    SmallVector<int64_t> acknowledgementCounts, releaseRegisters;
+    SmallVector<int64_t> releaseWaitValues, leftTargets, leftRegisters;
+    SmallVector<int64_t> rightTargets, rightRegisters;
+    LaneSet barrierLanes, leaderLanes, leftLanes, rightLanes;
+    for (auto [index, core] : llvm::enumerate(scheduled.cores)) {
+      acknowledgementCounts.push_back(
+        transfers.hostAcknowledgementCounts.lookup(core));
+      if (stageZeroRank.contains(core))
+        barrierLanes = barrierLanes.unite(
+          LaneSet::range(index, index + 1));
+      if (!transfers.stageZeroCores.empty()
+          && core == transfers.stageZeroCores.front())
+        leaderLanes = leaderLanes.unite(LaneSet::range(index, index + 1));
+
+      auto rank = downstreamRank.find(core);
+      if (rank == downstreamRank.end()) {
+        releaseRegisters.push_back(0);
+        releaseWaitValues.push_back(0);
+        leftTargets.push_back(core);
+        leftRegisters.push_back(0);
+        rightTargets.push_back(core);
+        rightRegisters.push_back(0);
+        continue;
+      }
+      releaseRegisters.push_back(getReleaseRegister(core));
+      releaseWaitValues.push_back(1);
+      size_t left = 2 * rank->second + 1;
+      size_t right = left + 1;
+      if (left < transfers.downstreamCores.size()) {
+        int64_t child = transfers.downstreamCores[left];
+        leftTargets.push_back(child);
+        leftRegisters.push_back(getReleaseRegister(child));
+        leftLanes = leftLanes.unite(LaneSet::range(index, index + 1));
+      } else {
+        leftTargets.push_back(core);
+        leftRegisters.push_back(0);
+      }
+      if (right < transfers.downstreamCores.size()) {
+        int64_t child = transfers.downstreamCores[right];
+        rightTargets.push_back(child);
+        rightRegisters.push_back(getReleaseRegister(child));
+        rightLanes = rightLanes.unite(LaneSet::range(index, index + 1));
+      } else {
+        rightTargets.push_back(core);
+        rightRegisters.push_back(0);
+      }
+    }
+    Value runtimeLane = lane ? lane : context.constants.getIndex(0);
+    auto emitForLanes = [&](const LaneSet &active, auto emit) -> LogicalResult {
+      if (active.empty())
+        return success();
+      if (!lane) {
+        if (active.contains(0))
+          emit();
+        return success();
+      }
+      auto condition = emitLaneCondition(
+        active, lane, scheduled.cores.size(), scheduled.op, context, loc);
+      if (failed(condition))
+        return failure();
+      auto conditional = scf::IfOp::create(
+        context.rewriter, loc, TypeRange {}, *condition, false);
+      OpBuilder::InsertionGuard guard(context.rewriter);
+      context.rewriter.setInsertionPoint(
+        conditional.getThenRegion().front().getTerminator());
+      emit();
+      return success();
+    };
+    Value acknowledgementCount = emitStaticIntLookup(
+      StaticIntSequence::fromValues(acknowledgementCounts),
+      runtimeLane, scheduled.op,
+      context.constants, context.rewriter, loc);
+    SpatWaitOp::create(
+      context.rewriter, loc,
+      context.constants.getIndex(acknowledgementRegister),
+      acknowledgementCount);
+
+    // Dissemination barrier: every round doubles the covered stage-zero peers.
+    auto emitBarrier = [&]() {
+      for (unsigned round = 0; round < barrierRounds; ++round) {
+        SmallVector<int64_t> targets;
+        targets.reserve(scheduled.cores.size());
+        size_t distance = size_t {1} << round;
+        for (int64_t core : scheduled.cores) {
+          auto rank = stageZeroRank.find(core);
+          targets.push_back(rank == stageZeroRank.end()
+            ? core
+            : transfers.stageZeroCores[
+                (rank->second + distance)
+                % transfers.stageZeroCores.size()]);
+        }
+        Value target = emitStaticIntLookup(
+          StaticIntSequence::fromValues(targets),
+          runtimeLane, scheduled.op,
+          context.constants, context.rewriter, loc);
+        Value eventRegister = context.constants.getIndex(
+          firstBarrierRegister - round);
+        SpatSyncOp::create(
+          context.rewriter, loc, target, eventRegister);
+        SpatWaitOp::create(
+          context.rewriter, loc, eventRegister,
+          context.constants.getIndex(1));
+      }
+    };
+    if (barrierRounds > 0
+        && failed(emitForLanes(barrierLanes, emitBarrier)))
+      return failure();
+
+    // Gate downstream restarts so no core advances the simulator input
+    // iteration ahead of stage zero.
+    if (!transfers.downstreamCores.empty()
+        && failed(emitForLanes(leaderLanes, [&]() {
+          int64_t root = transfers.downstreamCores.front();
+          SpatSyncOp::create(
+            context.rewriter, loc, context.constants.getIndex(root),
+            context.constants.getIndex(getReleaseRegister(root)));
+        })))
+      return failure();
+
+    Value releaseRegister = emitStaticIntLookup(
+      StaticIntSequence::fromValues(releaseRegisters), runtimeLane,
+      scheduled.op, context.constants, context.rewriter, loc);
+    Value releaseWaitValue = emitStaticIntLookup(
+      StaticIntSequence::fromValues(releaseWaitValues), runtimeLane,
+      scheduled.op, context.constants, context.rewriter, loc);
+    SpatWaitOp::create(
+      context.rewriter, loc, releaseRegister, releaseWaitValue);
+
+    auto emitChild = [&](ArrayRef<int64_t> targets,
+                         ArrayRef<int64_t> registers) {
+      Value target = emitStaticIntLookup(
+        StaticIntSequence::fromValues(targets), runtimeLane, scheduled.op,
+        context.constants, context.rewriter, loc);
+      Value eventRegister = emitStaticIntLookup(
+        StaticIntSequence::fromValues(registers), runtimeLane, scheduled.op,
+        context.constants, context.rewriter, loc);
+      SpatSyncOp::create(context.rewriter, loc, target, eventRegister);
+    };
+    if (failed(emitForLanes(leftLanes, [&]() {
+          emitChild(leftTargets, leftRegisters);
+        }))
+        || failed(emitForLanes(rightLanes, [&]() {
+          emitChild(rightTargets, rightRegisters);
+        })))
+      return failure();
+  }
+  return success();
+}
+
 } // namespace
 
-LogicalResult realizeDeferredBoundaries(ArrayRef<BoundaryProgram> boundaries, ArrayRef<DeferredResultPlan> results, DeferredEmissionContext &context,
+LogicalResult realizeDeferredBoundaries(ArrayRef<BoundaryProgram> boundaries, ArrayRef<DeferredResultPlan> results,
+                                        DeferredTransferPlan &transfers, DeferredEmissionContext &context,
                                         DeferredReplacementMap &replacements) {
   ScheduledInfo *scheduled = nullptr;
   for (const BoundaryProgram &boundary : boundaries) {
@@ -1171,7 +1399,7 @@ LogicalResult realizeDeferredBoundaries(ArrayRef<BoundaryProgram> boundaries, Ar
     if (failed(emitBoundary(boundary, results, context, replacements)))
       return boundary.key.first->op->emitOpError("phase 2 failed to realize a communication boundary");
   }
-  return success();
+  return emitCompletionSynchronization(transfers, context);
 }
 
 } // namespace onnx_mlir::spatial
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryRealization.hpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryRealization.hpp
index b41c9a0..00677c4 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryRealization.hpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredBoundaryRealization.hpp
@@ -42,6 +42,7 @@ using DeferredReplacementMap =
 
 mlir::LogicalResult realizeDeferredBoundaries(mlir::ArrayRef<BoundaryProgram> boundaries,
                                               mlir::ArrayRef<DeferredResultPlan> results,
+                                              DeferredTransferPlan& transfers,
                                               DeferredEmissionContext& context,
                                               DeferredReplacementMap& replacements);
 
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationModel.hpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationModel.hpp
index 6ac6617..5f446a5 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationModel.hpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationModel.hpp
@@ -236,6 +236,9 @@ struct ExternalTransferFamily {
   StaticIntSequence channelIds = StaticIntSequence::uniform(0, 1);
   StaticIntSequence hostOffsets = StaticIntSequence::uniform(0, 1);
   StaticIntSequence eventRegisters = StaticIntSequence::uniform(0, 1);
+  StaticIntSequence waitValues = StaticIntSequence::uniform(1, 1);
+  StaticIntSequence acknowledgementEventRegisters =
+    StaticIntSequence::uniform(0, 1);
   bool hostRouted = false;
 };
 
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationRealization.cpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationRealization.cpp
index a64dbbe..ee60db8 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationRealization.cpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredCommunicationRealization.cpp
@@ -232,7 +232,8 @@ LogicalResult realizeDeferredCommunication(func::FuncOp funcOp,
   auto schedule = scheduleDeferredCommunication(funcOp, *transfers);
   if (failed(schedule) || failed(verifyPlannedCommunicationDeadlockFree(funcOp, transfers->stepCounts, *schedule)))
     return funcOp.emitOpError("phase 2 failed to schedule symbolic communication");
-  auto boundaries = buildDeferredBoundaryPlan(*transfers, *schedule);
+  auto boundaries = buildDeferredBoundaryPlan(
+    *transfers, *schedule, target.synchronizationRegisterCount);
   if (failed(boundaries))
     return funcOp.emitOpError("phase 2 failed to build sparse boundary programs");
 
@@ -242,7 +243,9 @@ LogicalResult realizeDeferredCommunication(func::FuncOp funcOp,
   ConstantPool constants(funcOp, rewriter);
   DeferredEmissionContext context(rewriter, constants);
   DeferredReplacementMap replacements;
-  if (failed(realizeDeferredBoundaries(boundaries->boundaries, boundaries->results, context, replacements)))
+  if (failed(realizeDeferredBoundaries(
+        boundaries->boundaries, boundaries->results, *transfers,
+        context, replacements)))
     return failure();
   for (auto [op, replacement] : replacements) {
     if (op->getResult(0) == replacement)
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredTransferPlanning.cpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredTransferPlanning.cpp
index a8ebdac..e855295 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredTransferPlanning.cpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredTransferPlanning.cpp
@@ -322,8 +322,7 @@ static LogicalResult buildRequirementFamilies(DeferredTransferPlan& plan,
 static LogicalResult buildAvailabilityFamilies(
     DeferredTransferPlan &plan,
     DeferredExchangePlan& exchange,
-    uint64_t& nextChannel,
-    DenseMap<int64_t, DenseMap<int64_t, unsigned>>& eventRegistersByTarget) {
+    uint64_t& nextChannel) {
   enum class Availability { Local, Direct, Host };
   for (RequirementFamily& requirement : exchange.requirements) {
     for (LaneInterval interval : requirement.targetLanes.intervals()) {
@@ -357,18 +356,6 @@ static LogicalResult buildAvailabilityFamilies(
           family.channelIds = StaticIntSequence::affine(nextChannel, 1, count);
           family.hostRouted = runAvailability == Availability::Host;
           if (family.hostRouted) {
-            SmallVector<int64_t> eventRegisters;
-            for (int64_t targetCore : targetCores) {
-              auto &registers = eventRegistersByTarget[targetCore];
-              auto it = registers.try_emplace(
-                requirement.producer->core, registers.size()).first;
-              if (it->second >= kPimEventRegisterCount)
-                return exchange.deferred.emitOpError(
-                  "pipeline host transfer requires more event registers than the target core provides");
-              eventRegisters.push_back(it->second);
-            }
-            family.eventRegisters = StaticIntSequence::fromValues(
-              eventRegisters);
             auto fragmentType = dyn_cast<ShapedType>(
               requirement.publicationFragmentType);
             auto fragmentBytes = fragmentType
@@ -431,7 +418,6 @@ static LogicalResult buildExchanges(func::FuncOp funcOp, DeferredTransferPlan& p
   funcOp.walk([&](SpatDeferredCommunicationOp op) { deferredOps.push_back(op); });
   GraphBatchPublicationCache publicationCache;
   uint64_t nextChannel = 0;
-  DenseMap<int64_t, DenseMap<int64_t, unsigned>> eventRegistersByTarget;
   for (SpatDeferredCommunicationOp deferred : deferredOps) {
     Operation* targetOp = deferred->getParentOfType<SpatScheduledCompute>();
     if (!targetOp)
@@ -451,8 +437,7 @@ static LogicalResult buildExchanges(func::FuncOp funcOp, DeferredTransferPlan& p
     exchange->program = std::move(*program);
     if (failed(buildRequirementFamilies(plan, *exchange, publicationCache)))
       return failure();
-    if (failed(buildAvailabilityFamilies(
-          plan, *exchange, nextChannel, eventRegistersByTarget)))
+    if (failed(buildAvailabilityFamilies(plan, *exchange, nextChannel)))
       return failure();
     plan.exchanges.push_back(std::move(exchange));
   }
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredTransferPlanning.hpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredTransferPlanning.hpp
index 0b26fd3..96d915d 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredTransferPlanning.hpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/DeferredTransferPlanning.hpp
@@ -13,6 +13,10 @@ struct DeferredTransferPlan {
   llvm::DenseMap<int64_t, llvm::SmallVector<ProducedValue*>> producedByGraph;
   llvm::SmallVector<std::unique_ptr<DeferredExchangePlan>> exchanges;
   llvm::SmallVector<unsigned> stepCounts;
+  llvm::DenseMap<int64_t, unsigned> hostAcknowledgementCounts;
+  llvm::SmallVector<int64_t> stageZeroCores;
+  llvm::SmallVector<int64_t> downstreamCores;
+  size_t synchronizationRegisterCount = 0;
   size_t pipelineHostBufferBytes = 0;
 };
 
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/ScheduledSpatialPasses.cpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/ScheduledSpatialPasses.cpp
index f6fd9fd..dff6291 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/ScheduledSpatialPasses.cpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/ScheduledSpatialPasses.cpp
@@ -89,6 +89,8 @@ struct ScheduleAndRealizeSpatialPass final
       return;
     }
     if (pipelineStages == 0 || target.processorCount % pipelineStages != 0
+        || (pipelineStages > 1
+            && target.synchronizationRegisterCount == 0)
         || target.residentWeightCapacity
              > std::numeric_limits<size_t>::max() / pipelineStages) {
       moduleOp.emitError("ScheduleAndRealizeSpatial requires valid pipeline stages and resource counts");
diff --git a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/Scheduling/SchedulingTarget.hpp b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/Scheduling/SchedulingTarget.hpp
index d607288..6f2c941 100644
--- a/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/Scheduling/SchedulingTarget.hpp
+++ b/src/PIM/Dialect/Spatial/Passes/Transforms/MergeComputeNodes/Scheduling/SchedulingTarget.hpp
@@ -23,6 +23,7 @@ struct SchedulingTarget {
   Cost transferWidthBytes = 8;
   Cost vectorWidth = 16;
   Cost vectorLatencyCycles = 4;
+  size_t synchronizationRegisterCount = 0;
 
   Cost matrixRows = 128;
   Cost matrixColumns = 128;
diff --git a/src/PIM/Dialect/Spatial/Spatial.td b/src/PIM/Dialect/Spatial/Spatial.td
index 83bc064..81bd576 100644
--- a/src/PIM/Dialect/Spatial/Spatial.td
+++ b/src/PIM/Dialect/Spatial/Spatial.td
@@ -592,13 +592,15 @@ def SpatHostStoreSyncOp : SpatOp<"host_store_sync", []> {
 }
 
 def SpatHostWaitLoadOp : SpatOp<"host_wait_load", []> {
-  let summary = "Wait for a producer and load its tensor from host memory";
+  let summary = "Wait for producers, load from host memory, and acknowledge consumption";
 
   let arguments = (ins
     Index:$sourceCoreId,
     Index:$targetCoreId,
     Index:$hostOffset,
-    Index:$eventRegister
+    Index:$eventRegister,
+    Index:$waitValue,
+    Index:$acknowledgementEventRegister
   );
 
   let results = (outs
@@ -607,7 +609,34 @@ def SpatHostWaitLoadOp : SpatOp<"host_wait_load", []> {
 
   let assemblyFormat = [{
     `from` $sourceCoreId `to` $targetCoreId
-      `host_offset` $hostOffset `event` $eventRegister attr-dict `:` type($output)
+      `host_offset` $hostOffset `event` $eventRegister `count` $waitValue
+      `ack` $acknowledgementEventRegister attr-dict `:` type($output)
+  }];
+}
+
+def SpatSyncOp : SpatOp<"sync", []> {
+  let summary = "Signal a synchronization register on another processor";
+
+  let arguments = (ins
+    Index:$targetCoreId,
+    Index:$eventRegister
+  );
+
+  let assemblyFormat = [{
+    $targetCoreId `event` $eventRegister attr-dict
+  }];
+}
+
+def SpatWaitOp : SpatOp<"wait", []> {
+  let summary = "Wait for a synchronization register value";
+
+  let arguments = (ins
+    Index:$eventRegister,
+    Index:$waitValue
+  );
+
+  let assemblyFormat = [{
+    $eventRegister `value` $waitValue attr-dict
   }];
 }
 
diff --git a/validation/operations/validation_results.csv b/validation/operations/validation_results.csv
index 8c172cd..93b0945 100644
--- a/validation/operations/validation_results.csv
+++ b/validation/operations/validation_results.csv
@@ -1,178 +1,178 @@
 Operation,Arch,Result (l),Result (t),Compile (l),Host mem (l),Cores mem (l),Cores (l),Xbars (l),Latency (l),Power (l),Energy (l),Compile (t),Host mem (t),Cores mem (t),Cores (t),Xbars (t),Avg latency (t),Throughput (t),Avg power (t),Avg energy (t)
-add/after_gemm,arch-a,PASS,FAIL,0.057 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,104.70 mW,815012.96 pJ,0.055 s,0.01 MiB,0.01 MiB,6,4,277000.00 samples/s,0.00 ms,45.81 mW,190085.16 pJ/it
-add/basic,arch-a,PASS,PASS,0.047 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-add/broadcast_row,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-add/channel_broadcast_1024,arch-a,PASS,PASS,0.048 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.048 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
-add/leading_dimension_broadcast,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-concat/channel_axis,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.16 mW,35718.00 pJ,0.047 s,0.00 MiB,0.00 MiB,1,0,2200000.00 samples/s,0.00 ms,2.16 mW,934.67 pJ/it
-concat/negative_axis,arch-a,PASS,PASS,0.047 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.09 mW,81450.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,961000.00 samples/s,0.00 ms,2.09 mW,2108.00 pJ/it
-concat/three_inputs_channel_axis,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.15 mW,50328.00 pJ,0.045 s,0.00 MiB,0.00 MiB,1,0,1560000.00 samples/s,0.00 ms,2.15 mW,1332.67 pJ/it
-conv/batch_2,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.00 MiB,2,2,0.01 ms,82.62 mW,1131451.48 pJ,0.057 s,0.00 MiB,0.01 MiB,4,2,168000.00 samples/s,0.01 ms,53.33 mW,343254.69 pJ/it
-conv/batch_4_pointwise,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.01 MiB,5,4,0.00 ms,116.08 mW,456420.96 pJ,0.060 s,0.00 MiB,0.01 MiB,5,4,486000.00 samples/s,0.00 ms,70.89 mW,160104.45 pJ/it
-conv/depthwise_1024_channels,arch-a,PASS,FAIL,0.081 s,0.19 MiB,0.38 MiB,129,128,0.22 ms,178.45 mW,39393966.72 pJ,-,-,-,-,-,-,-,-,-
-conv/depthwise_grouped,arch-a,PASS,FAIL,0.055 s,0.01 MiB,0.00 MiB,5,4,0.01 ms,107.78 mW,671878.96 pJ,-,-,-,-,-,-,-,-,-
-conv/dilated_3x3,arch-a,PASS,PASS,0.060 s,0.01 MiB,0.01 MiB,10,9,0.01 ms,118.77 mW,1034819.16 pJ,0.067 s,0.01 MiB,0.01 MiB,12,9,189000.00 samples/s,0.01 ms,75.03 mW,435165.28 pJ/it
-conv/dynamic,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,92.28 mW,169336.00 pJ,0.057 s,0.00 MiB,0.00 MiB,6,0,661000.00 samples/s,0.00 ms,18.68 mW,30964.00 pJ/it
-conv/explicit_padding,arch-a,PASS,FAIL,0.062 s,0.01 MiB,0.02 MiB,17,16,0.01 ms,145.34 mW,1454397.84 pJ,-,-,-,-,-,-,-,-,-
-conv/grouped_many_groups,arch-a,PASS,FAIL,0.486 s,0.05 MiB,0.09 MiB,65,64,0.18 ms,142.21 mW,25867112.36 pJ,0.500 s,0.11 MiB,0.79 MiB,127,64,569.00 samples/s,1.76 ms,141.19 mW,252570125.00 pJ/it
-conv/grouped_two_groups,arch-a,PASS,FAIL,0.063 s,0.00 MiB,0.00 MiB,3,2,0.01 ms,101.46 mW,543914.48 pJ,0.061 s,0.00 MiB,0.01 MiB,9,2,327000.00 samples/s,0.00 ms,116.36 mW,453237.70 pJ/it
-conv/huge_pointwise_1024,arch-a,PASS,FAIL,0.160 s,0.01 MiB,0.11 MiB,73,64,0.02 ms,249.55 mW,3896647.36 pJ,0.176 s,0.04 MiB,0.11 MiB,74,64,35300.00 samples/s,0.03 ms,136.81 mW,4031965.75 pJ/it
-conv/huge_pointwise_1024_dynamic,arch-a,PASS,FAIL,0.101 s,8.04 MiB,12.61 MiB,168,0,2.63 ms,169.52 mW,445489032.00 pJ,-,-,-,-,-,-,-,-,-
-conv/input_224_7x7_stride2,arch-a,PASS,FAIL,1.124 s,24.14 MiB,61.87 MiB,168,169,38.41 ms,185.26 mW,7116544212.12 pJ,-,-,-,-,-,-,-,-,-
-conv/kernel_2x2,arch-a,PASS,FAIL,0.064 s,0.00 MiB,0.00 MiB,1,1,0.00 ms,83.83 mW,360568.24 pJ,0.099 s,0.00 MiB,0.00 MiB,3,1,380000.00 samples/s,0.00 ms,52.64 mW,151421.99 pJ/it
-conv/kernel_3x3,arch-a,PASS,FAIL,0.057 s,0.01 MiB,0.01 MiB,10,9,0.01 ms,123.80 mW,889640.16 pJ,-,-,-,-,-,-,-,-,-
-conv/kernel_equals_input_spatial,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,2,2,0.00 ms,89.61 mW,415689.48 pJ,0.059 s,0.00 MiB,0.00 MiB,4,2,464000.00 samples/s,0.00 ms,68.91 mW,166273.89 pJ/it
-conv/large_input_channels_1x1,arch-a,PASS,PASS,0.087 s,0.01 MiB,0.02 MiB,9,8,0.01 ms,117.82 mW,901121.92 pJ,0.087 s,0.01 MiB,0.02 MiB,10,8,306000.00 samples/s,0.00 ms,91.39 mW,360779.57 pJ/it
-conv/large_output_channels_1x1,arch-a,PASS,PASS,0.088 s,0.01 MiB,0.02 MiB,17,8,0.01 ms,128.44 mW,1139415.92 pJ,0.089 s,0.01 MiB,0.02 MiB,18,8,207000.00 samples/s,0.00 ms,73.39 mW,358350.06 pJ/it
-conv/large_spatial,arch-a,PASS,FAIL,0.060 s,0.01 MiB,0.04 MiB,37,36,0.02 ms,172.07 mW,2928344.64 pJ,-,-,-,-,-,-,-,-,-
-conv/multi_channel,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,105.68 mW,685040.72 pJ,0.057 s,0.00 MiB,0.00 MiB,4,3,178000.00 samples/s,0.01 ms,32.10 mW,185757.05 pJ/it
-conv/non_square_kernel_1x3,arch-a,PASS,PASS,0.066 s,0.00 MiB,0.00 MiB,3,2,0.01 ms,99.35 mW,679752.48 pJ,0.054 s,0.00 MiB,0.00 MiB,3,2,163000.00 samples/s,0.01 ms,13.04 mW,81630.31 pJ/it
-conv/non_square_kernel_3x1,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,3,2,0.01 ms,95.89 mW,1292976.48 pJ,0.065 s,0.00 MiB,0.00 MiB,3,2,77500.00 samples/s,0.01 ms,9.04 mW,117499.65 pJ/it
-conv/non_uniform_stride,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,104.05 mW,790874.72 pJ,0.056 s,0.00 MiB,0.00 MiB,4,3,161000.00 samples/s,0.01 ms,30.89 mW,198689.55 pJ/it
-conv/output_channel_grouping_minimal,arch-a,PASS,FAIL,0.083 s,0.10 MiB,0.34 MiB,131,128,0.26 ms,170.73 mW,44125916.72 pJ,-,-,-,-,-,-,-,-,-
-conv/pointwise_1x1,arch-a,PASS,FAIL,0.052 s,0.00 MiB,0.00 MiB,1,1,0.01 ms,80.24 mW,987244.24 pJ,0.055 s,0.00 MiB,0.00 MiB,3,1,135000.00 samples/s,0.01 ms,47.15 mW,371973.57 pJ/it
-conv/pointwise_tiled_chain,arch-a,PASS,PASS,0.699 s,0.01 MiB,0.04 MiB,20,80,0.04 ms,153.88 mW,6445455.20 pJ,0.634 s,0.05 MiB,0.08 MiB,22,80,14300.00 samples/s,0.07 ms,71.96 mW,5297594.20 pJ/it
-conv/real_asymmetric_padding,arch-a,PASS,FAIL,0.063 s,0.01 MiB,0.03 MiB,29,28,0.01 ms,153.67 mW,2221606.72 pJ,-,-,-,-,-,-,-,-,-
-conv/relu_conv_store,arch-a,PASS,FAIL,0.094 s,0.16 MiB,0.67 MiB,168,184,0.56 ms,183.08 mW,103057892.80 pJ,-,-,-,-,-,-,-,-,-
-conv/same_lower_3x3,arch-a,PASS,FAIL,0.061 s,0.01 MiB,0.02 MiB,26,25,0.01 ms,166.15 mW,2215009.00 pJ,-,-,-,-,-,-,-,-,-
-conv/same_padding_3x3,arch-a,PASS,FAIL,0.059 s,0.01 MiB,0.02 MiB,26,25,0.01 ms,166.15 mW,2215009.00 pJ,-,-,-,-,-,-,-,-,-
-conv/strategy_depthwise_16,arch-a,PASS,FAIL,0.092 s,0.06 MiB,0.35 MiB,168,168,0.34 ms,197.94 mW,66331479.08 pJ,-,-,-,-,-,-,-,-,-
-conv/strategy_input_k_tiled,arch-a,PASS,FAIL,0.084 s,0.08 MiB,0.27 MiB,109,108,0.35 ms,170.81 mW,60422605.92 pJ,-,-,-,-,-,-,-,-,-
-conv/strategy_output_channel_tiled,arch-a,PASS,FAIL,0.071 s,0.03 MiB,0.16 MiB,74,72,0.09 ms,155.74 mW,14244739.28 pJ,-,-,-,-,-,-,-,-,-
-conv/strategy_streamed_packed,arch-a,PASS,FAIL,0.184 s,3.34 MiB,7.89 MiB,168,168,9.35 ms,179.86 mW,1682364509.56 pJ,-,-,-,-,-,-,-,-,-
-conv/strategy_streamed_patch,arch-a,PASS,FAIL,0.098 s,0.34 MiB,1.32 MiB,168,168,1.90 ms,181.91 mW,346476645.64 pJ,-,-,-,-,-,-,-,-,-
-conv/strategy_tiled_2d,arch-a,PASS,FAIL,0.117 s,0.11 MiB,0.44 MiB,168,168,0.42 ms,182.13 mW,75690907.84 pJ,-,-,-,-,-,-,-,-,-
-conv/stride_2,arch-a,PASS,FAIL,0.059 s,0.01 MiB,0.00 MiB,5,4,0.01 ms,110.78 mW,580154.96 pJ,-,-,-,-,-,-,-,-,-
-conv/with_bias_3x3,arch-a,PASS,FAIL,0.057 s,0.00 MiB,0.01 MiB,4,3,0.01 ms,104.16 mW,776220.72 pJ,0.057 s,0.00 MiB,0.01 MiB,4,3,165000.00 samples/s,0.01 ms,30.99 mW,196092.89 pJ/it
-conv/with_constant,arch-a,PASS,FAIL,0.057 s,0.00 MiB,0.00 MiB,1,1,0.01 ms,81.74 mW,541270.24 pJ,0.059 s,0.00 MiB,0.00 MiB,4,1,232000.00 samples/s,0.00 ms,92.34 mW,438607.24 pJ/it
-conv/without_kernel_shape_attr,arch-a,PASS,FAIL,0.055 s,0.01 MiB,0.01 MiB,10,9,0.01 ms,123.80 mW,889640.16 pJ,-,-,-,-,-,-,-,-,-
-conv/yolo11n_depthwise_head,arch-a,PASS,FAIL,2.274 s,8.66 MiB,34.24 MiB,168,255,42.70 ms,200.52 mW,8562449708.00 pJ,-,-,-,-,-,-,-,-,-
-conv/yolo11n_heavy,arch-a,PASS,FAIL,0.478 s,4.82 MiB,19.10 MiB,161,800,8.54 ms,350.86 mW,2994764012.00 pJ,-,-,-,-,-,-,-,-,-
-conv/yolo11n_stem,arch-a,PASS,FAIL,0.975 s,12.86 MiB,37.59 MiB,168,488,14.24 ms,301.23 mW,4289558753.00 pJ,-,-,-,-,-,-,-,-,-
-div/after_gemm,arch-a,PASS,FAIL,0.056 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,104.70 mW,815012.96 pJ,0.056 s,0.01 MiB,0.01 MiB,6,4,277000.00 samples/s,0.00 ms,45.81 mW,190085.16 pJ/it
-div/basic,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-div/channel_broadcast_1024,arch-a,PASS,PASS,0.051 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.055 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
-div/leading_dimension_broadcast,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-div/runtime_scalar_rhs,arch-a,PASS,PASS,0.048 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.051 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
-div/scalar_constant,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.059 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-gather/3d_input_axis1,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.08 mW,45990.00 pJ,0.053 s,0.00 MiB,0.00 MiB,1,0,1700000.00 samples/s,0.00 ms,2.08 mW,1174.67 pJ/it
-gather/axis0_matrix_indices,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.07 mW,54414.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,1440000.00 samples/s,0.00 ms,2.07 mW,1390.67 pJ/it
-gather/axis1,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.06 mW,62526.00 pJ,0.053 s,0.00 MiB,0.00 MiB,1,0,1250000.00 samples/s,0.00 ms,2.06 mW,1598.67 pJ/it
-gather/negative_axis,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.03 mW,112134.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,697000.00 samples/s,0.00 ms,2.03 mW,2870.67 pJ/it
-gather/negative_indices,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.13 mW,29376.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,2670000.00 samples/s,0.00 ms,2.12 mW,748.67 pJ/it
-gemm/alpha_beta,arch-a,PASS,FAIL,0.059 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,105.27 mW,784908.96 pJ,0.061 s,0.01 MiB,0.01 MiB,6,4,304000.00 samples/s,0.00 ms,48.12 mW,184972.16 pJ/it
-gemm/bias_rank2_broadcast,arch-a,PASS,FAIL,0.061 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,105.98 mW,749484.96 pJ,0.058 s,0.01 MiB,0.01 MiB,6,4,351000.00 samples/s,0.00 ms,52.58 mW,176636.66 pJ/it
-gemm/dynamic,arch-a,PASS,FAIL,0.053 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.48 mW,221475.00 pJ,0.056 s,0.00 MiB,0.00 MiB,5,0,785000.00 samples/s,0.00 ms,20.31 mW,27813.50 pJ/it
-gemm/dynamic_alpha,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.42 mW,298198.00 pJ,0.056 s,0.00 MiB,0.00 MiB,5,0,612000.00 samples/s,0.00 ms,20.35 mW,37289.67 pJ/it
-gemm/dynamic_beta,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.32 mW,398595.00 pJ,0.056 s,0.00 MiB,0.00 MiB,5,0,359000.00 samples/s,0.00 ms,20.22 mW,60212.83 pJ/it
-gemm/dynamic_bias,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.45 mW,243703.00 pJ,0.055 s,0.00 MiB,0.00 MiB,5,0,785000.00 samples/s,0.00 ms,20.32 mW,28385.00 pJ/it
-gemm/dynamic_bias_alpha_beta,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.01 ms,91.28 mW,513811.00 pJ,0.056 s,0.00 MiB,0.00 MiB,5,0,247000.00 samples/s,0.00 ms,20.20 mW,85611.50 pJ/it
-gemm/dynamic_transpose_b,arch-a,PASS,FAIL,0.053 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.38 mW,118883.00 pJ,0.055 s,0.00 MiB,0.00 MiB,5,0,1340000.00 samples/s,0.00 ms,20.55 mW,16541.00 pJ/it
-gemm/huge_1024,arch-a,PASS,FAIL,0.144 s,0.01 MiB,0.10 MiB,73,64,0.02 ms,215.04 mW,3767885.36 pJ,0.167 s,0.03 MiB,0.10 MiB,73,64,14900.00 samples/s,0.07 ms,154.31 mW,10866697.65 pJ/it
-gemm/large,arch-a,PASS,FAIL,0.058 s,0.02 MiB,0.03 MiB,17,16,0.01 ms,140.15 mW,1573768.84 pJ,0.063 s,0.02 MiB,0.03 MiB,17,16,142000.00 samples/s,0.01 ms,118.27 mW,830693.99 pJ/it
-gemm/large_k_small_n,arch-a,PASS,FAIL,0.084 s,0.01 MiB,0.01 MiB,9,8,0.00 ms,133.48 mW,633769.92 pJ,0.089 s,0.01 MiB,0.01 MiB,9,8,439000.00 samples/s,0.00 ms,125.25 mW,329671.91 pJ/it
-gemm/non_square,arch-a,PASS,FAIL,0.060 s,0.00 MiB,0.01 MiB,5,4,0.00 ms,118.96 mW,419565.96 pJ,0.060 s,0.00 MiB,0.01 MiB,5,4,486000.00 samples/s,0.00 ms,70.69 mW,160313.79 pJ/it
-gemm/scalar_bias,arch-a,PASS,FAIL,0.059 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,105.98 mW,749484.96 pJ,0.056 s,0.01 MiB,0.01 MiB,6,4,351000.00 samples/s,0.00 ms,52.58 mW,176636.66 pJ/it
-gemm/small,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,2,2,0.00 ms,90.14 mW,398436.48 pJ,0.055 s,0.00 MiB,0.00 MiB,4,2,464000.00 samples/s,0.00 ms,69.74 mW,162693.89 pJ/it
-gemm/small_k_large_n,arch-a,PASS,PASS,0.092 s,0.01 MiB,0.02 MiB,17,8,0.01 ms,131.01 mW,1043061.92 pJ,0.089 s,0.01 MiB,0.02 MiB,18,8,248000.00 samples/s,0.00 ms,82.00 mW,345641.89 pJ/it
-gemm/square_weights,arch-a,PASS,FAIL,0.076 s,0.03 MiB,0.08 MiB,42,40,0.02 ms,151.77 mW,3284393.60 pJ,-,-,-,-,-,-,-,-,-
-gemm/transpose_a,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,109.14 mW,628868.96 pJ,0.057 s,0.00 MiB,0.01 MiB,6,4,424000.00 samples/s,0.00 ms,58.98 mW,162091.12 pJ/it
-gemm/transpose_a_and_b,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,109.14 mW,628868.96 pJ,0.056 s,0.00 MiB,0.01 MiB,6,4,424000.00 samples/s,0.00 ms,58.98 mW,162091.12 pJ/it
-gemm/transpose_b,arch-a,PASS,FAIL,0.061 s,0.00 MiB,0.01 MiB,5,4,0.00 ms,118.96 mW,419565.96 pJ,0.059 s,0.00 MiB,0.01 MiB,5,4,486000.00 samples/s,0.00 ms,70.69 mW,160313.79 pJ/it
-gemm/transpose_b_with_bias,arch-a,PASS,FAIL,0.064 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,110.55 mW,557818.96 pJ,0.057 s,0.01 MiB,0.01 MiB,5,4,339000.00 samples/s,0.00 ms,55.18 mW,180359.12 pJ/it
-gemm/with_bias,arch-a,PASS,FAIL,0.050 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,108.77 mW,604966.96 pJ,0.055 s,0.01 MiB,0.01 MiB,5,4,288000.00 samples/s,0.00 ms,52.44 mW,186098.45 pJ/it
-gemv/all_constant,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,0,0,0.00 ms,2.00 mW,0.00 pJ,0.052 s,0.00 MiB,0.00 MiB,0,0,0.00 samples/s,0.00 ms,2.00 mW,0.00 pJ/it
-gemv/constant_weight,arch-a,PASS,FAIL,0.062 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,111.15 mW,573535.96 pJ,0.063 s,0.00 MiB,0.01 MiB,8,4,412000.00 samples/s,0.00 ms,86.05 mW,242243.79 pJ/it
-gemv/non_uniform_bias,arch-a,PASS,FAIL,0.063 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,109.82 mW,609371.96 pJ,0.063 s,0.00 MiB,0.01 MiB,8,4,376000.00 samples/s,0.00 ms,82.45 mW,254539.29 pJ/it
-gemv/scalar_bias,arch-a,PASS,FAIL,0.063 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,109.82 mW,609371.96 pJ,0.064 s,0.00 MiB,0.01 MiB,8,4,376000.00 samples/s,0.00 ms,82.45 mW,254539.29 pJ/it
-gemv/uniform_bias,arch-a,PASS,FAIL,0.064 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,109.82 mW,609371.96 pJ,0.063 s,0.00 MiB,0.01 MiB,8,4,376000.00 samples/s,0.00 ms,82.45 mW,254539.29 pJ/it
-matmul/basic,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,2,2,0.00 ms,90.14 mW,398436.48 pJ,0.056 s,0.00 MiB,0.00 MiB,4,2,464000.00 samples/s,0.00 ms,69.74 mW,162693.89 pJ/it
-matmul/batched_3d,arch-a,PASS,FAIL,0.058 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,108.59 mW,646972.96 pJ,0.059 s,0.00 MiB,0.01 MiB,6,4,438000.00 samples/s,0.00 ms,59.21 mW,161865.62 pJ/it
-matmul/batched_3d_dynamic,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,92.19 mW,167975.00 pJ,0.054 s,0.00 MiB,0.00 MiB,5,0,1140000.00 samples/s,0.00 ms,17.43 mW,16336.83 pJ/it
-matmul/batched_left_constant,arch-a,PASS,FAIL,0.061 s,0.00 MiB,0.02 MiB,9,8,0.01 ms,114.39 mW,1009105.92 pJ,-,-,-,-,-,-,-,-,-
-matmul/batched_lhs_broadcast,arch-a,PASS,FAIL,0.057 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,109.39 mW,621440.96 pJ,0.071 s,0.00 MiB,0.01 MiB,6,4,441000.00 samples/s,0.00 ms,60.34 mW,160658.62 pJ/it
-matmul/batched_rhs_broadcast,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,108.59 mW,646972.96 pJ,0.056 s,0.00 MiB,0.01 MiB,6,4,438000.00 samples/s,0.00 ms,59.21 mW,161865.62 pJ/it
-matmul/dynamic,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.42 mW,148195.00 pJ,0.058 s,0.00 MiB,0.00 MiB,5,0,1310000.00 samples/s,0.00 ms,20.49 mW,18009.67 pJ/it
-matmul/huge_1024,arch-a,PASS,FAIL,0.151 s,0.01 MiB,0.10 MiB,73,64,0.02 ms,215.04 mW,3767885.36 pJ,0.172 s,0.03 MiB,0.10 MiB,73,64,14900.00 samples/s,0.07 ms,154.31 mW,10866697.65 pJ/it
-matmul/left_constant,arch-a,PASS,FAIL,0.058 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,108.86 mW,637168.96 pJ,0.064 s,0.00 MiB,0.01 MiB,6,4,424000.00 samples/s,0.00 ms,58.67 mW,162346.12 pJ/it
-matmul/matrix_vector,arch-a,PASS,FAIL,0.102 s,0.52 MiB,0.78 MiB,168,173,0.38 ms,202.13 mW,77751814.88 pJ,-,-,-,-,-,-,-,-,-
-matmul/vector_matrix,arch-a,PASS,FAIL,0.085 s,0.01 MiB,0.01 MiB,9,8,0.01 ms,118.68 mW,879301.92 pJ,-,-,-,-,-,-,-,-,-
-matmul/yolo_attention,arch-a,PASS,FAIL,0.483 s,1.02 MiB,43.44 MiB,168,0,8.15 ms,170.00 mW,1385775865.00 pJ,-,-,-,-,-,-,-,-,-
-mul/after_conv,arch-a,PASS,FAIL,0.074 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,107.64 mW,586955.72 pJ,0.062 s,0.00 MiB,0.00 MiB,4,3,220000.00 samples/s,0.00 ms,34.96 mW,162998.05 pJ/it
-mul/after_conv_scalar_constant,arch-a,PASS,FAIL,0.063 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,107.64 mW,586955.72 pJ,0.061 s,0.00 MiB,0.00 MiB,4,3,220000.00 samples/s,0.00 ms,34.96 mW,162998.05 pJ/it
-mul/basic,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-mul/channel_broadcast_1024,arch-a,PASS,PASS,0.049 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.049 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
-mul/leading_dimension_broadcast,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.053 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-mul/scalar_constant,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-pool/avg_basic,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,931506.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,84000.00 samples/s,0.01 ms,2.02 mW,24067.00 pJ/it
-pool/avg_ceil_mode,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.03 mW,340146.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,230000.00 samples/s,0.00 ms,2.03 mW,8810.67 pJ/it
-pool/avg_explicit_padding,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.03 mW,688356.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,114000.00 samples/s,0.01 ms,2.03 mW,17809.00 pJ/it
-pool/avg_include_pad,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,663612.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,118000.00 samples/s,0.01 ms,2.02 mW,17081.00 pJ/it
-pool/avg_large_channels,arch-a,PASS,PASS,0.064 s,0.04 MiB,0.02 MiB,1,0,0.24 ms,78.00 mW,18399156.00 pJ,0.060 s,0.04 MiB,0.02 MiB,1,0,4250.00 samples/s,0.24 ms,2.00 mW,471428.00 pJ/it
-pool/avg_non_uniform_stride,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,1132254.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,69100.00 samples/s,0.01 ms,2.02 mW,29191.00 pJ/it
-pool/avg_real_asymmetric_padding,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.03 ms,78.02 mW,1966692.00 pJ,0.057 s,0.00 MiB,0.00 MiB,1,0,39700.00 samples/s,0.03 ms,2.02 mW,50961.00 pJ/it
-pool/max_after_conv,arch-a,PASS,FAIL,0.059 s,0.00 MiB,0.00 MiB,5,4,0.01 ms,99.12 mW,1210689.96 pJ,0.061 s,0.00 MiB,0.00 MiB,5,4,142000.00 samples/s,0.01 ms,34.60 mW,273954.62 pJ/it
-pool/max_basic,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.06 mW,324744.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,241000.00 samples/s,0.00 ms,2.06 mW,8532.67 pJ/it
-pool/max_ceil_mode,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.07 mW,151464.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,516000.00 samples/s,0.00 ms,2.07 mW,3972.67 pJ/it
-pool/max_global_style_kernel_equals_input,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.01 mW,658626.00 pJ,0.056 s,0.00 MiB,0.00 MiB,1,0,119000.00 samples/s,0.01 ms,2.01 mW,16871.00 pJ/it
-pool/max_non_square_kernel,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,1063068.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,73600.00 samples/s,0.01 ms,2.02 mW,27417.00 pJ/it
-pool/max_real_asymmetric_padding,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.03 mW,814992.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,96100.00 samples/s,0.01 ms,2.03 mW,21173.00 pJ/it
-pool/max_same_upper,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.04 mW,625068.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,125000.00 samples/s,0.01 ms,2.04 mW,16233.00 pJ/it
-pool/max_stride2_multichannel,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.02 ms,78.02 mW,1247274.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,62700.00 samples/s,0.02 ms,2.02 mW,32153.00 pJ/it
-reduce_mean/4d_spatial,arch-a,PASS,FAIL,0.053 s,0.00 MiB,0.00 MiB,3,0,0.00 ms,92.45 mW,29676.00 pJ,0.055 s,0.00 MiB,0.00 MiB,3,0,2560000.00 samples/s,0.00 ms,4.38 mW,1667.33 pJ/it
-reduce_mean/4d_spatial_keepdims_0,arch-a,PASS,FAIL,0.052 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,94.35 mW,61801.00 pJ,0.053 s,0.00 MiB,0.00 MiB,4,0,2390000.00 samples/s,0.00 ms,19.52 mW,9025.83 pJ/it
-reduce_mean/after_conv,arch-a,PASS,FAIL,0.059 s,0.00 MiB,0.00 MiB,5,3,0.01 ms,106.95 mW,571332.72 pJ,0.063 s,0.00 MiB,0.00 MiB,5,3,220000.00 samples/s,0.00 ms,21.90 mW,102726.72 pJ/it
-reduce_mean/all_axes_keepdims_0,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.24 mW,30982.00 pJ,0.052 s,0.00 MiB,0.00 MiB,2,0,4520000.00 samples/s,0.00 ms,3.41 mW,775.00 pJ/it
-reduce_mean/all_axes_keepdims_1,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
-reduce_mean/basic,arch-a,PASS,FAIL,0.052 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,93.51 mW,34881.00 pJ,0.053 s,0.00 MiB,0.00 MiB,4,0,2780000.00 samples/s,0.00 ms,5.56 mW,1904.50 pJ/it
-reduce_mean/channel_axis_nchw,arch-a,PASS,FAIL,0.052 s,0.03 MiB,0.02 MiB,4,0,0.16 ms,93.60 mW,15436518.00 pJ,0.055 s,0.03 MiB,0.08 MiB,4,0,16000.00 samples/s,0.06 ms,5.00 mW,323993.33 pJ/it
-reduce_mean/keepdims_0,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.40 mW,68368.00 pJ,0.054 s,0.00 MiB,0.00 MiB,5,0,1880000.00 samples/s,0.00 ms,20.60 mW,11458.17 pJ/it
-reduce_mean/large_dimension_1024,arch-a,PASS,PASS,0.053 s,0.01 MiB,0.00 MiB,1,0,0.00 ms,78.02 mW,217278.00 pJ,0.052 s,0.01 MiB,0.00 MiB,1,0,359000.00 samples/s,0.00 ms,2.02 mW,5274.00 pJ/it
-reduce_mean/legacy_axes_1_2_keepdims_1,arch-a,PASS,FAIL,0.052 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.35 mW,21505.00 pJ,0.052 s,0.00 MiB,0.00 MiB,2,0,3860000.00 samples/s,0.00 ms,3.37 mW,798.00 pJ/it
-reduce_mean/legacy_axis1_keepdims_0,arch-a,PASS,FAIL,0.071 s,0.00 MiB,0.00 MiB,9,0,0.00 ms,92.50 mW,183708.00 pJ,0.061 s,0.00 MiB,0.00 MiB,9,0,1010000.00 samples/s,0.00 ms,38.63 mW,41198.50 pJ/it
-reduce_mean/legacy_axis1_keepdims_1,arch-a,PASS,FAIL,0.053 s,0.00 MiB,0.00 MiB,8,0,0.00 ms,94.56 mW,129830.00 pJ,0.054 s,0.00 MiB,0.00 MiB,8,0,1390000.00 samples/s,0.00 ms,9.56 mW,6733.50 pJ/it
-reduce_mean/legacy_empty_axes_noop,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
-reduce_mean/legacy_nchw_spatial,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,3,0,0.00 ms,92.45 mW,29676.00 pJ,0.056 s,0.00 MiB,0.00 MiB,3,0,1960000.00 samples/s,0.00 ms,4.28 mW,2167.33 pJ/it
-reduce_mean/legacy_negative_axis,arch-a,PASS,FAIL,0.051 s,0.00 MiB,0.00 MiB,6,0,0.00 ms,93.52 mW,51717.00 pJ,0.057 s,0.00 MiB,0.00 MiB,6,0,1850000.00 samples/s,0.00 ms,7.57 mW,3828.83 pJ/it
-reduce_mean/legacy_reduce_all_keepdims_1,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
-reduce_mean/negative_axis,arch-a,PASS,FAIL,0.058 s,0.00 MiB,0.00 MiB,6,0,0.00 ms,93.52 mW,51717.00 pJ,0.054 s,0.00 MiB,0.00 MiB,6,0,1850000.00 samples/s,0.00 ms,7.57 mW,3828.83 pJ/it
-relu/4d,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.18 mW,40734.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,1930000.00 samples/s,0.00 ms,2.18 mW,1014.00 pJ/it
-relu/after_conv,arch-a,PASS,FAIL,0.058 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,107.89 mW,577437.72 pJ,0.060 s,0.00 MiB,0.00 MiB,4,3,220000.00 samples/s,0.00 ms,34.98 mW,162801.39 pJ/it
-relu/after_gemm,arch-a,PASS,FAIL,0.061 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,105.16 mW,790056.96 pJ,0.059 s,0.01 MiB,0.01 MiB,6,4,291000.00 samples/s,0.00 ms,47.08 mW,187063.49 pJ/it
-relu/basic,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
-reshape/4d_to_2d_flatten,arch-a,PASS,PASS,0.047 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.28 mW,20196.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,3910000.00 samples/s,0.00 ms,2.28 mW,488.00 pJ/it
-reshape/infer_dim_minus_one,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,12684.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,6250000.00 samples/s,0.00 ms,2.30 mW,308.00 pJ/it
-reshape/same_rank,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,12684.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,6250000.00 samples/s,0.00 ms,2.30 mW,308.00 pJ/it
-reshape/zero_copies_input_dim,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,12684.00 pJ,0.056 s,0.00 MiB,0.00 MiB,1,0,6250000.00 samples/s,0.00 ms,2.30 mW,308.00 pJ/it
-resize/height_only,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,93.55 mW,64833.00 pJ,0.055 s,0.00 MiB,0.00 MiB,4,0,2430000.00 samples/s,0.00 ms,5.46 mW,2298.25 pJ/it
-resize/nearest_2x,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,93.57 mW,109761.00 pJ,0.051 s,0.00 MiB,0.00 MiB,4,0,1760000.00 samples/s,0.00 ms,5.33 mW,3085.12 pJ/it
-resize/nearest_downsample,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.45 mW,33925.00 pJ,0.052 s,0.00 MiB,0.00 MiB,2,0,2420000.00 samples/s,0.00 ms,3.22 mW,1262.50 pJ/it
-resize/non_uniform_scales,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,6,0,0.00 ms,93.58 mW,164037.00 pJ,0.055 s,0.00 MiB,0.00 MiB,6,0,1750000.00 samples/s,0.00 ms,7.49 mW,4551.90 pJ/it
-resize/width_only,arch-a,PASS,FAIL,0.051 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.50 mW,53029.00 pJ,0.052 s,0.00 MiB,0.00 MiB,2,0,1750000.00 samples/s,0.00 ms,3.16 mW,1735.50 pJ/it
-resize/with_sizes,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,3,0,0.00 ms,92.54 mW,73756.00 pJ,0.056 s,0.00 MiB,0.00 MiB,3,0,1930000.00 samples/s,0.00 ms,4.27 mW,2196.00 pJ/it
-sigmoid/4d,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.18 mW,40734.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,1930000.00 samples/s,0.00 ms,2.18 mW,1014.00 pJ/it
-sigmoid/after_gemm,arch-a,PASS,FAIL,0.056 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,105.16 mW,790056.96 pJ,0.058 s,0.01 MiB,0.01 MiB,6,4,291000.00 samples/s,0.00 ms,47.08 mW,187063.49 pJ/it
-sigmoid/basic,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
-slice/2d_basic,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,18948.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,4170000.00 samples/s,0.00 ms,2.30 mW,491.67 pJ/it
-slice/after_conv,arch-a,PASS,FAIL,0.062 s,0.00 MiB,0.01 MiB,7,6,0.01 ms,118.19 mW,1335082.88 pJ,0.069 s,0.00 MiB,0.01 MiB,7,6,130000.00 samples/s,0.01 ms,58.48 mW,484364.44 pJ/it
-slice/default_axes,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,18948.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,4170000.00 samples/s,0.00 ms,2.30 mW,491.67 pJ/it
-slice/large_channel_1024,arch-a,PASS,PASS,0.051 s,0.01 MiB,0.00 MiB,1,0,0.00 ms,78.14 mW,221304.00 pJ,0.050 s,0.01 MiB,0.00 MiB,1,0,353000.00 samples/s,0.00 ms,2.14 mW,5058.00 pJ/it
-slice/nchw_spatial_crop,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.24 mW,101868.00 pJ,0.047 s,0.00 MiB,0.00 MiB,1,0,769000.00 samples/s,0.00 ms,2.24 mW,2851.67 pJ/it
-slice/negative_axis,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,44004.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,1790000.00 samples/s,0.00 ms,2.30 mW,1227.67 pJ/it
-slice/negative_indices,arch-a,PASS,PASS,0.048 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,25212.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.30 mW,675.67 pJ/it
-slice/step2,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.29 mW,159876.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,490000.00 samples/s,0.00 ms,2.29 mW,4619.67 pJ/it
-softmax/3d_last_axis,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.053 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
-softmax/basic,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.053 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
-softmax/channel_axis,arch-a,PASS,FAIL,0.051 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.052 s,0.00 MiB,0.00 MiB,3,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
-softmax/large_dimension_1024,arch-a,PASS,PASS,0.049 s,0.01 MiB,0.01 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.052 s,0.01 MiB,0.01 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
-softmax/negative_axis,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.049 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
-split/basic,arch-a,PASS,PASS,0.048 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,31554.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,2490000.00 samples/s,0.00 ms,2.30 mW,861.67 pJ/it
-split/equal_three_way,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,44160.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,1780000.00 samples/s,0.00 ms,2.30 mW,1231.67 pJ/it
-split/negative_axis,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.29 mW,84786.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,925000.00 samples/s,0.00 ms,2.29 mW,2413.67 pJ/it
-split/uneven_channel_axis_4d,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,18948.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,4170000.00 samples/s,0.00 ms,2.30 mW,491.67 pJ/it
-sub/after_gemm,arch-a,PASS,FAIL,0.058 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,104.70 mW,815012.96 pJ,0.057 s,0.01 MiB,0.01 MiB,6,4,277000.00 samples/s,0.00 ms,45.81 mW,190085.16 pJ/it
-sub/basic,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-sub/broadcast_row,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
-sub/channel_broadcast_1024,arch-a,PASS,PASS,0.058 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.053 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
-sub/constant_lhs_broadcast,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25188.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,656.67 pJ/it
-sub/leading_dimension_broadcast,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+add/after_gemm,arch-a,PASS,PASS,0.058 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,104.70 mW,815012.96 pJ,0.057 s,0.01 MiB,0.01 MiB,6,4,145000.00 samples/s,0.01 ms,31.45 mW,216167.21 pJ/it
+add/basic,arch-a,PASS,PASS,0.048 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+add/broadcast_row,arch-a,PASS,PASS,0.048 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+add/channel_broadcast_1024,arch-a,PASS,PASS,0.049 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.051 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
+add/leading_dimension_broadcast,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+concat/channel_axis,arch-a,PASS,PASS,0.048 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.16 mW,35718.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,2200000.00 samples/s,0.00 ms,2.16 mW,934.67 pJ/it
+concat/negative_axis,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.09 mW,81450.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,961000.00 samples/s,0.00 ms,2.09 mW,2108.00 pJ/it
+concat/three_inputs_channel_axis,arch-a,PASS,PASS,0.048 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.15 mW,50328.00 pJ,0.047 s,0.00 MiB,0.00 MiB,1,0,1560000.00 samples/s,0.00 ms,2.15 mW,1332.67 pJ/it
+conv/batch_2,arch-a,PASS,PASS,0.059 s,0.00 MiB,0.00 MiB,2,2,0.01 ms,82.62 mW,1131451.48 pJ,0.062 s,0.00 MiB,0.01 MiB,4,2,129000.00 samples/s,0.01 ms,51.25 mW,406238.48 pJ/it
+conv/batch_4_pointwise,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.01 MiB,5,4,0.00 ms,116.08 mW,456420.96 pJ,0.061 s,0.00 MiB,0.01 MiB,5,4,243000.00 samples/s,0.00 ms,44.13 mW,180813.46 pJ/it
+conv/depthwise_1024_channels,arch-a,PASS,PASS,0.080 s,0.19 MiB,0.38 MiB,129,128,0.22 ms,178.45 mW,39393966.72 pJ,0.141 s,0.36 MiB,0.48 MiB,87,128,3620.00 samples/s,0.28 ms,131.43 mW,37256350.26 pJ/it
+conv/depthwise_grouped,arch-a,PASS,PASS,0.056 s,0.01 MiB,0.00 MiB,5,4,0.01 ms,107.78 mW,671878.96 pJ,0.061 s,0.01 MiB,0.00 MiB,7,4,235000.00 samples/s,0.00 ms,53.10 mW,227356.96 pJ/it
+conv/dilated_3x3,arch-a,PASS,PASS,0.061 s,0.01 MiB,0.01 MiB,10,9,0.01 ms,118.77 mW,1034819.16 pJ,0.071 s,0.01 MiB,0.01 MiB,12,9,119000.00 samples/s,0.01 ms,61.00 mW,511357.16 pJ/it
+conv/dynamic,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,92.28 mW,169336.00 pJ,0.057 s,0.00 MiB,0.00 MiB,6,0,784000.00 samples/s,0.00 ms,18.61 mW,26517.00 pJ/it
+conv/explicit_padding,arch-a,PASS,PASS,0.060 s,0.01 MiB,0.02 MiB,17,16,0.01 ms,145.34 mW,1454397.84 pJ,0.064 s,0.01 MiB,0.02 MiB,19,16,153000.00 samples/s,0.01 ms,109.61 mW,715669.59 pJ/it
+conv/grouped_many_groups,arch-a,PASS,PASS,0.498 s,0.05 MiB,0.09 MiB,65,64,0.18 ms,142.21 mW,25867112.36 pJ,0.547 s,0.11 MiB,0.79 MiB,127,64,3750.00 samples/s,0.27 ms,141.11 mW,43353235.67 pJ/it
+conv/grouped_two_groups,arch-a,PASS,PASS,0.064 s,0.00 MiB,0.00 MiB,3,2,0.01 ms,101.46 mW,543914.48 pJ,0.066 s,0.00 MiB,0.01 MiB,9,2,146000.00 samples/s,0.01 ms,108.34 mW,741101.98 pJ/it
+conv/huge_pointwise_1024,arch-a,PASS,PASS,0.166 s,0.01 MiB,0.11 MiB,73,64,0.02 ms,249.55 mW,3896647.36 pJ,0.182 s,0.04 MiB,0.11 MiB,74,64,33300.00 samples/s,0.03 ms,133.89 mW,4052259.07 pJ/it
+conv/huge_pointwise_1024_dynamic,arch-a,PASS,PASS,0.084 s,8.04 MiB,12.61 MiB,168,0,2.63 ms,169.52 mW,445489032.00 pJ,0.263 s,11.49 MiB,10.61 MiB,127,0,213.00 samples/s,4.70 ms,164.24 mW,811591564.70 pJ/it
+conv/input_224_7x7_stride2,arch-a,PASS,PASS,0.775 s,24.14 MiB,61.87 MiB,168,169,38.41 ms,185.26 mW,7116544212.12 pJ,1.142 s,46.43 MiB,73.41 MiB,126,153,27.30 samples/s,36.66 ms,177.05 mW,6915042527.00 pJ/it
+conv/kernel_2x2,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,1,0.00 ms,83.83 mW,360568.24 pJ,0.055 s,0.00 MiB,0.00 MiB,3,1,334000.00 samples/s,0.00 ms,51.45 mW,171905.91 pJ/it
+conv/kernel_3x3,arch-a,PASS,PASS,0.060 s,0.01 MiB,0.01 MiB,10,9,0.01 ms,123.80 mW,889640.16 pJ,0.063 s,0.01 MiB,0.01 MiB,12,9,219000.00 samples/s,0.00 ms,83.71 mW,382318.91 pJ/it
+conv/kernel_equals_input_spatial,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,2,2,0.00 ms,89.61 mW,415689.48 pJ,0.057 s,0.00 MiB,0.00 MiB,4,2,293000.00 samples/s,0.00 ms,59.39 mW,204713.48 pJ/it
+conv/large_input_channels_1x1,arch-a,PASS,PASS,0.096 s,0.01 MiB,0.02 MiB,9,8,0.01 ms,117.82 mW,901121.92 pJ,0.092 s,0.01 MiB,0.02 MiB,10,8,132000.00 samples/s,0.01 ms,59.24 mW,447909.92 pJ/it
+conv/large_output_channels_1x1,arch-a,PASS,PASS,0.089 s,0.01 MiB,0.02 MiB,17,8,0.01 ms,128.44 mW,1139415.92 pJ,0.095 s,0.01 MiB,0.02 MiB,18,8,123000.00 samples/s,0.01 ms,43.92 mW,355735.17 pJ/it
+conv/large_spatial,arch-a,PASS,PASS,0.059 s,0.01 MiB,0.04 MiB,37,36,0.02 ms,172.07 mW,2928344.64 pJ,0.078 s,0.01 MiB,0.04 MiB,39,36,88500.00 samples/s,0.01 ms,169.91 mW,1920027.89 pJ/it
+conv/multi_channel,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,105.68 mW,685040.72 pJ,0.060 s,0.00 MiB,0.00 MiB,4,3,146000.00 samples/s,0.01 ms,30.09 mW,205787.97 pJ/it
+conv/non_square_kernel_1x3,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,3,2,0.01 ms,99.35 mW,679752.48 pJ,0.059 s,0.00 MiB,0.00 MiB,3,2,141000.00 samples/s,0.01 ms,12.12 mW,85739.48 pJ/it
+conv/non_square_kernel_3x1,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.00 MiB,3,2,0.01 ms,95.89 mW,1292976.48 pJ,0.061 s,0.00 MiB,0.00 MiB,3,2,72900.00 samples/s,0.01 ms,8.83 mW,121109.48 pJ/it
+conv/non_uniform_stride,arch-a,PASS,PASS,0.061 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,104.05 mW,790874.72 pJ,0.059 s,0.00 MiB,0.00 MiB,4,3,131000.00 samples/s,0.01 ms,29.05 mW,221084.97 pJ/it
+conv/output_channel_grouping_minimal,arch-a,PASS,PASS,0.089 s,0.10 MiB,0.34 MiB,131,128,0.26 ms,170.73 mW,44125916.72 pJ,0.181 s,0.18 MiB,0.33 MiB,131,128,3910.00 samples/s,0.26 ms,181.50 mW,48146979.72 pJ/it
+conv/pointwise_1x1,arch-a,PASS,PASS,0.071 s,0.00 MiB,0.00 MiB,1,1,0.01 ms,80.24 mW,987244.24 pJ,0.084 s,0.00 MiB,0.00 MiB,3,1,131000.00 samples/s,0.01 ms,47.08 mW,380210.74 pJ/it
+conv/pointwise_tiled_chain,arch-a,PASS,PASS,0.819 s,0.01 MiB,0.04 MiB,20,80,0.04 ms,153.88 mW,6445455.20 pJ,0.777 s,0.05 MiB,0.08 MiB,22,80,12500.00 samples/s,0.08 ms,69.67 mW,5573378.45 pJ/it
+conv/real_asymmetric_padding,arch-a,PASS,PASS,0.074 s,0.01 MiB,0.03 MiB,29,28,0.01 ms,153.67 mW,2221606.72 pJ,0.087 s,0.00 MiB,0.03 MiB,31,28,104000.00 samples/s,0.01 ms,135.38 mW,1295814.97 pJ/it
+conv/relu_conv_store,arch-a,PASS,PASS,0.102 s,0.16 MiB,0.67 MiB,168,184,0.56 ms,183.08 mW,103057892.80 pJ,0.291 s,0.32 MiB,0.67 MiB,168,166,1640.00 samples/s,0.61 ms,182.39 mW,113644022.20 pJ/it
+conv/same_lower_3x3,arch-a,PASS,PASS,0.069 s,0.01 MiB,0.02 MiB,26,25,0.01 ms,166.15 mW,2215009.00 pJ,0.088 s,0.01 MiB,0.03 MiB,28,25,114000.00 samples/s,0.01 ms,134.46 mW,1180460.00 pJ/it
+conv/same_padding_3x3,arch-a,PASS,PASS,0.062 s,0.01 MiB,0.02 MiB,26,25,0.01 ms,166.15 mW,2215009.00 pJ,0.083 s,0.01 MiB,0.03 MiB,28,25,114000.00 samples/s,0.01 ms,134.46 mW,1180460.00 pJ/it
+conv/strategy_depthwise_16,arch-a,PASS,PASS,0.093 s,0.06 MiB,0.35 MiB,168,168,0.34 ms,197.94 mW,66331479.08 pJ,0.298 s,0.15 MiB,0.37 MiB,168,168,2890.00 samples/s,0.35 ms,196.87 mW,70672344.81 pJ/it
+conv/strategy_input_k_tiled,arch-a,PASS,PASS,0.079 s,0.08 MiB,0.27 MiB,109,108,0.35 ms,170.81 mW,60422605.92 pJ,0.120 s,0.16 MiB,0.30 MiB,85,101,3520.00 samples/s,0.28 ms,138.29 mW,40167697.42 pJ/it
+conv/strategy_output_channel_tiled,arch-a,PASS,PASS,0.079 s,0.03 MiB,0.16 MiB,74,72,0.09 ms,155.74 mW,14244739.28 pJ,0.146 s,0.08 MiB,0.25 MiB,111,72,12000.00 samples/s,0.08 ms,137.73 mW,12695085.91 pJ/it
+conv/strategy_streamed_packed,arch-a,PASS,PASS,0.168 s,3.34 MiB,7.89 MiB,168,168,9.35 ms,179.86 mW,1682364509.56 pJ,0.453 s,5.38 MiB,7.87 MiB,127,126,119.00 samples/s,8.39 ms,175.52 mW,1616768905.00 pJ/it
+conv/strategy_streamed_patch,arch-a,PASS,PASS,0.110 s,0.34 MiB,1.32 MiB,168,168,1.90 ms,181.91 mW,346476645.64 pJ,0.416 s,0.84 MiB,1.29 MiB,127,126,525.00 samples/s,1.90 ms,176.18 mW,359355537.30 pJ/it
+conv/strategy_tiled_2d,arch-a,PASS,PASS,0.170 s,0.11 MiB,0.44 MiB,168,168,0.42 ms,182.13 mW,75690907.84 pJ,0.235 s,0.28 MiB,0.45 MiB,130,168,3010.00 samples/s,0.33 ms,178.45 mW,62153061.01 pJ/it
+conv/stride_2,arch-a,PASS,PASS,0.060 s,0.01 MiB,0.00 MiB,5,4,0.01 ms,110.78 mW,580154.96 pJ,0.061 s,0.01 MiB,0.00 MiB,7,4,297000.00 samples/s,0.00 ms,48.26 mW,163092.63 pJ/it
+conv/with_bias_3x3,arch-a,PASS,PASS,0.069 s,0.00 MiB,0.01 MiB,4,3,0.01 ms,104.16 mW,776220.72 pJ,0.066 s,0.00 MiB,0.01 MiB,4,3,128000.00 samples/s,0.01 ms,28.71 mW,224217.97 pJ/it
+conv/with_constant,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.00 MiB,1,1,0.01 ms,81.74 mW,541270.24 pJ,0.067 s,0.00 MiB,0.00 MiB,4,1,138000.00 samples/s,0.01 ms,90.41 mW,664255.74 pJ/it
+conv/without_kernel_shape_attr,arch-a,PASS,PASS,0.064 s,0.01 MiB,0.01 MiB,10,9,0.01 ms,123.80 mW,889640.16 pJ,0.066 s,0.01 MiB,0.01 MiB,12,9,219000.00 samples/s,0.00 ms,83.71 mW,382318.91 pJ/it
+conv/yolo11n_depthwise_head,arch-a,PASS,PASS,2.447 s,8.66 MiB,34.24 MiB,168,255,42.70 ms,200.52 mW,8562449708.00 pJ,3.011 s,22.90 MiB,34.20 MiB,168,216,19.40 samples/s,51.59 ms,195.15 mW,10205156420.00 pJ/it
+conv/yolo11n_heavy,arch-a,PASS,PASS,0.585 s,4.82 MiB,19.10 MiB,161,800,8.54 ms,350.86 mW,2994764012.00 pJ,1.897 s,10.40 MiB,20.59 MiB,161,800,83.80 samples/s,11.93 ms,299.23 mW,3739084612.00 pJ/it
+conv/yolo11n_stem,arch-a,PASS,PASS,0.996 s,12.86 MiB,37.59 MiB,168,488,14.24 ms,301.23 mW,4289558753.00 pJ,1.726 s,22.34 MiB,32.79 MiB,168,362,23.80 samples/s,42.04 ms,214.78 mW,9030156087.00 pJ/it
+div/after_gemm,arch-a,PASS,PASS,0.065 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,104.70 mW,815012.96 pJ,0.071 s,0.01 MiB,0.01 MiB,6,4,145000.00 samples/s,0.01 ms,31.45 mW,216167.21 pJ/it
+div/basic,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.057 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+div/channel_broadcast_1024,arch-a,PASS,PASS,0.060 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.056 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
+div/leading_dimension_broadcast,arch-a,PASS,PASS,0.067 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.060 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+div/runtime_scalar_rhs,arch-a,PASS,PASS,0.057 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.055 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
+div/scalar_constant,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+gather/3d_input_axis1,arch-a,PASS,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.08 mW,45990.00 pJ,0.056 s,0.00 MiB,0.00 MiB,1,0,1700000.00 samples/s,0.00 ms,2.08 mW,1174.67 pJ/it
+gather/axis0_matrix_indices,arch-a,PASS,PASS,0.083 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.07 mW,54414.00 pJ,0.072 s,0.00 MiB,0.00 MiB,1,0,1440000.00 samples/s,0.00 ms,2.07 mW,1390.67 pJ/it
+gather/axis1,arch-a,PASS,PASS,0.064 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.06 mW,62526.00 pJ,0.066 s,0.00 MiB,0.00 MiB,1,0,1250000.00 samples/s,0.00 ms,2.06 mW,1598.67 pJ/it
+gather/negative_axis,arch-a,PASS,PASS,0.078 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.03 mW,112134.00 pJ,0.064 s,0.00 MiB,0.00 MiB,1,0,697000.00 samples/s,0.00 ms,2.03 mW,2870.67 pJ/it
+gather/negative_indices,arch-a,PASS,PASS,0.062 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.13 mW,29376.00 pJ,0.062 s,0.00 MiB,0.00 MiB,1,0,2670000.00 samples/s,0.00 ms,2.12 mW,748.67 pJ/it
+gemm/alpha_beta,arch-a,PASS,PASS,0.068 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,105.27 mW,784908.96 pJ,0.070 s,0.01 MiB,0.01 MiB,6,4,153000.00 samples/s,0.01 ms,32.18 mW,210663.21 pJ/it
+gemm/bias_rank2_broadcast,arch-a,PASS,PASS,0.063 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,105.98 mW,749484.96 pJ,0.063 s,0.01 MiB,0.01 MiB,6,4,168000.00 samples/s,0.01 ms,33.68 mW,200469.21 pJ/it
+gemm/dynamic,arch-a,PASS,PASS,0.065 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.48 mW,221475.00 pJ,0.062 s,0.00 MiB,0.00 MiB,5,0,471000.00 samples/s,0.00 ms,20.30 mW,43105.75 pJ/it
+gemm/dynamic_alpha,arch-a,PASS,PASS,0.064 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.42 mW,298198.00 pJ,0.063 s,0.00 MiB,0.00 MiB,5,0,337000.00 samples/s,0.00 ms,20.28 mW,60117.75 pJ/it
+gemm/dynamic_beta,arch-a,PASS,PASS,0.070 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.32 mW,398595.00 pJ,0.059 s,0.00 MiB,0.00 MiB,5,0,246000.00 samples/s,0.00 ms,20.21 mW,82201.75 pJ/it
+gemm/dynamic_bias,arch-a,PASS,PASS,0.066 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.45 mW,243703.00 pJ,0.063 s,0.00 MiB,0.00 MiB,5,0,422000.00 samples/s,0.00 ms,20.28 mW,48009.75 pJ/it
+gemm/dynamic_bias_alpha_beta,arch-a,PASS,PASS,0.061 s,0.00 MiB,0.00 MiB,5,0,0.01 ms,91.28 mW,513811.00 pJ,0.077 s,0.00 MiB,0.00 MiB,5,0,188000.00 samples/s,0.01 ms,20.20 mW,107673.75 pJ/it
+gemm/dynamic_transpose_b,arch-a,PASS,PASS,0.064 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.38 mW,118883.00 pJ,0.065 s,0.00 MiB,0.00 MiB,5,0,781000.00 samples/s,0.00 ms,20.51 mW,26151.50 pJ/it
+gemm/huge_1024,arch-a,PASS,PASS,0.182 s,0.01 MiB,0.10 MiB,73,64,0.02 ms,215.04 mW,3767885.36 pJ,0.220 s,0.03 MiB,0.10 MiB,73,64,36900.00 samples/s,0.03 ms,148.63 mW,4053069.50 pJ/it
+gemm/large,arch-a,PASS,PASS,0.074 s,0.02 MiB,0.03 MiB,17,16,0.01 ms,140.15 mW,1573768.84 pJ,0.082 s,0.02 MiB,0.03 MiB,17,16,88800.00 samples/s,0.01 ms,84.59 mW,942235.51 pJ/it
+gemm/large_k_small_n,arch-a,PASS,PASS,0.142 s,0.01 MiB,0.01 MiB,9,8,0.00 ms,133.48 mW,633769.92 pJ,0.119 s,0.01 MiB,0.01 MiB,9,8,194000.00 samples/s,0.01 ms,76.91 mW,390598.09 pJ/it
+gemm/non_square,arch-a,PASS,PASS,0.069 s,0.00 MiB,0.01 MiB,5,4,0.00 ms,118.96 mW,419565.96 pJ,0.069 s,0.00 MiB,0.01 MiB,5,4,270000.00 samples/s,0.00 ms,46.78 mW,172713.46 pJ/it
+gemm/scalar_bias,arch-a,PASS,PASS,0.062 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,105.98 mW,749484.96 pJ,0.066 s,0.01 MiB,0.01 MiB,6,4,168000.00 samples/s,0.01 ms,33.68 mW,200469.21 pJ/it
+gemm/small,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.00 MiB,2,2,0.00 ms,90.14 mW,398436.48 pJ,0.059 s,0.00 MiB,0.00 MiB,4,2,327000.00 samples/s,0.00 ms,61.13 mW,188023.48 pJ/it
+gemm/small_k_large_n,arch-a,PASS,PASS,0.112 s,0.01 MiB,0.02 MiB,17,8,0.01 ms,131.01 mW,1043061.92 pJ,0.100 s,0.01 MiB,0.02 MiB,18,8,141000.00 samples/s,0.01 ms,47.48 mW,336507.17 pJ/it
+gemm/square_weights,arch-a,PASS,PASS,0.080 s,0.03 MiB,0.08 MiB,42,40,0.02 ms,151.77 mW,3284393.60 pJ,0.100 s,0.03 MiB,0.09 MiB,44,40,51800.00 samples/s,0.02 ms,115.71 mW,2278356.60 pJ/it
+gemm/transpose_a,arch-a,PASS,PASS,0.063 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,109.14 mW,628868.96 pJ,0.062 s,0.00 MiB,0.01 MiB,6,4,212000.00 samples/s,0.00 ms,38.03 mW,179501.21 pJ/it
+gemm/transpose_a_and_b,arch-a,PASS,PASS,0.070 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,109.14 mW,628868.96 pJ,0.080 s,0.00 MiB,0.01 MiB,6,4,212000.00 samples/s,0.00 ms,38.03 mW,179501.21 pJ/it
+gemm/transpose_b,arch-a,PASS,PASS,0.065 s,0.00 MiB,0.01 MiB,5,4,0.00 ms,118.96 mW,419565.96 pJ,0.069 s,0.00 MiB,0.01 MiB,5,4,270000.00 samples/s,0.00 ms,46.78 mW,172713.46 pJ/it
+gemm/transpose_b_with_bias,arch-a,PASS,PASS,0.064 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,110.55 mW,557818.96 pJ,0.071 s,0.01 MiB,0.01 MiB,5,4,191000.00 samples/s,0.01 ms,38.98 mW,203117.46 pJ/it
+gemm/with_bias,arch-a,PASS,PASS,0.064 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,108.77 mW,604966.96 pJ,0.062 s,0.01 MiB,0.01 MiB,5,4,175000.00 samples/s,0.01 ms,37.33 mW,213443.71 pJ/it
+gemv/all_constant,arch-a,PASS,PASS,0.071 s,0.00 MiB,0.00 MiB,0,0,0.00 ms,2.00 mW,0.00 pJ,0.061 s,0.00 MiB,0.00 MiB,0,0,0.00 samples/s,0.00 ms,2.00 mW,0.00 pJ/it
+gemv/constant_weight,arch-a,PASS,PASS,0.100 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,111.15 mW,573535.96 pJ,0.079 s,0.00 MiB,0.01 MiB,8,4,235000.00 samples/s,0.00 ms,68.14 mW,293181.96 pJ/it
+gemv/non_uniform_bias,arch-a,PASS,PASS,0.080 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,109.82 mW,609371.96 pJ,0.081 s,0.00 MiB,0.01 MiB,8,4,215000.00 samples/s,0.00 ms,66.23 mW,310779.96 pJ/it
+gemv/scalar_bias,arch-a,PASS,PASS,0.092 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,109.82 mW,609371.96 pJ,0.095 s,0.00 MiB,0.01 MiB,8,4,215000.00 samples/s,0.00 ms,66.23 mW,310779.96 pJ/it
+gemv/uniform_bias,arch-a,PASS,PASS,0.090 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,109.82 mW,609371.96 pJ,0.149 s,0.00 MiB,0.01 MiB,8,4,215000.00 samples/s,0.00 ms,66.23 mW,310779.96 pJ/it
+matmul/basic,arch-a,PASS,PASS,0.089 s,0.00 MiB,0.00 MiB,2,2,0.00 ms,90.14 mW,398436.48 pJ,0.071 s,0.00 MiB,0.00 MiB,4,2,327000.00 samples/s,0.00 ms,61.13 mW,188023.48 pJ/it
+matmul/batched_3d,arch-a,PASS,PASS,0.099 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,108.59 mW,646972.96 pJ,0.086 s,0.00 MiB,0.01 MiB,6,4,207000.00 samples/s,0.00 ms,37.52 mW,181507.21 pJ/it
+matmul/batched_3d_dynamic,arch-a,PASS,PASS,0.065 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,92.19 mW,167975.00 pJ,0.065 s,0.00 MiB,0.00 MiB,5,0,736000.00 samples/s,0.00 ms,17.42 mW,23971.67 pJ/it
+matmul/batched_left_constant,arch-a,PASS,PASS,0.069 s,0.00 MiB,0.02 MiB,9,8,0.01 ms,114.39 mW,1009105.92 pJ,0.070 s,0.01 MiB,0.02 MiB,11,8,133000.00 samples/s,0.01 ms,58.19 mW,441494.75 pJ/it
+matmul/batched_lhs_broadcast,arch-a,PASS,PASS,0.065 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,109.39 mW,621440.96 pJ,0.071 s,0.00 MiB,0.01 MiB,6,4,217000.00 samples/s,0.00 ms,38.52 mW,177665.21 pJ/it
+matmul/batched_rhs_broadcast,arch-a,PASS,PASS,0.065 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,108.59 mW,646972.96 pJ,0.065 s,0.00 MiB,0.01 MiB,6,4,207000.00 samples/s,0.00 ms,37.52 mW,181507.21 pJ/it
+matmul/dynamic,arch-a,PASS,PASS,0.061 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.42 mW,148195.00 pJ,0.080 s,0.00 MiB,0.00 MiB,5,0,628000.00 samples/s,0.00 ms,20.41 mW,32505.75 pJ/it
+matmul/huge_1024,arch-a,PASS,PASS,0.188 s,0.01 MiB,0.10 MiB,73,64,0.02 ms,215.04 mW,3767885.36 pJ,0.224 s,0.03 MiB,0.10 MiB,73,64,36900.00 samples/s,0.03 ms,148.63 mW,4053069.50 pJ/it
+matmul/left_constant,arch-a,PASS,PASS,0.076 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,108.86 mW,637168.96 pJ,0.068 s,0.00 MiB,0.01 MiB,6,4,208000.00 samples/s,0.00 ms,37.62 mW,180976.21 pJ/it
+matmul/matrix_vector,arch-a,PASS,PASS,0.120 s,0.52 MiB,0.78 MiB,168,173,0.38 ms,202.13 mW,77751814.88 pJ,0.384 s,0.97 MiB,0.72 MiB,127,173,2250.00 samples/s,0.44 ms,193.72 mW,92630594.79 pJ/it
+matmul/vector_matrix,arch-a,PASS,PASS,0.099 s,0.01 MiB,0.01 MiB,9,8,0.01 ms,118.68 mW,879301.92 pJ,0.104 s,0.01 MiB,0.01 MiB,9,8,132000.00 samples/s,0.01 ms,45.10 mW,342617.42 pJ/it
+matmul/yolo_attention,arch-a,PASS,PASS,0.526 s,1.02 MiB,43.44 MiB,168,0,8.15 ms,170.00 mW,1385775865.00 pJ,0.796 s,13.76 MiB,43.56 MiB,136,0,65.40 samples/s,15.29 ms,166.46 mW,2545338467.00 pJ/it
+mul/after_conv,arch-a,PASS,PASS,0.072 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,107.64 mW,586955.72 pJ,0.072 s,0.00 MiB,0.00 MiB,4,3,183000.00 samples/s,0.01 ms,32.66 mW,178132.97 pJ/it
+mul/after_conv_scalar_constant,arch-a,PASS,PASS,0.120 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,107.64 mW,586955.72 pJ,0.160 s,0.00 MiB,0.00 MiB,4,3,183000.00 samples/s,0.01 ms,32.66 mW,178132.97 pJ/it
+mul/basic,arch-a,PASS,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.086 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+mul/channel_broadcast_1024,arch-a,PASS,PASS,0.063 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.061 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
+mul/leading_dimension_broadcast,arch-a,PASS,PASS,0.064 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.059 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+mul/scalar_constant,arch-a,PASS,PASS,0.065 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.066 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+pool/avg_basic,arch-a,PASS,PASS,0.062 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,931506.00 pJ,0.063 s,0.00 MiB,0.00 MiB,1,0,84000.00 samples/s,0.01 ms,2.02 mW,24067.00 pJ/it
+pool/avg_ceil_mode,arch-a,PASS,PASS,0.062 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.03 mW,340146.00 pJ,0.057 s,0.00 MiB,0.00 MiB,1,0,230000.00 samples/s,0.00 ms,2.03 mW,8810.67 pJ/it
+pool/avg_explicit_padding,arch-a,PASS,PASS,0.125 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.03 mW,688356.00 pJ,0.077 s,0.00 MiB,0.00 MiB,1,0,114000.00 samples/s,0.01 ms,2.03 mW,17809.00 pJ/it
+pool/avg_include_pad,arch-a,PASS,PASS,0.064 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,663612.00 pJ,0.059 s,0.00 MiB,0.00 MiB,1,0,118000.00 samples/s,0.01 ms,2.02 mW,17081.00 pJ/it
+pool/avg_large_channels,arch-a,PASS,PASS,0.069 s,0.04 MiB,0.02 MiB,1,0,0.24 ms,78.00 mW,18399156.00 pJ,0.067 s,0.04 MiB,0.02 MiB,1,0,4250.00 samples/s,0.24 ms,2.00 mW,471428.00 pJ/it
+pool/avg_non_uniform_stride,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,1132254.00 pJ,0.060 s,0.00 MiB,0.00 MiB,1,0,69100.00 samples/s,0.01 ms,2.02 mW,29191.00 pJ/it
+pool/avg_real_asymmetric_padding,arch-a,PASS,PASS,0.070 s,0.00 MiB,0.00 MiB,1,0,0.03 ms,78.02 mW,1966692.00 pJ,0.073 s,0.00 MiB,0.00 MiB,1,0,39700.00 samples/s,0.03 ms,2.02 mW,50961.00 pJ/it
+pool/max_after_conv,arch-a,PASS,PASS,0.069 s,0.00 MiB,0.00 MiB,5,4,0.01 ms,99.12 mW,1210689.96 pJ,0.074 s,0.00 MiB,0.00 MiB,5,4,81600.00 samples/s,0.01 ms,28.10 mW,344619.71 pJ/it
+pool/max_basic,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.06 mW,324744.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,241000.00 samples/s,0.00 ms,2.06 mW,8532.67 pJ/it
+pool/max_ceil_mode,arch-a,PASS,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.07 mW,151464.00 pJ,0.059 s,0.00 MiB,0.00 MiB,1,0,516000.00 samples/s,0.00 ms,2.07 mW,3972.67 pJ/it
+pool/max_global_style_kernel_equals_input,arch-a,PASS,PASS,0.066 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.01 mW,658626.00 pJ,0.063 s,0.00 MiB,0.00 MiB,1,0,119000.00 samples/s,0.01 ms,2.01 mW,16871.00 pJ/it
+pool/max_non_square_kernel,arch-a,PASS,PASS,0.070 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,1063068.00 pJ,0.063 s,0.00 MiB,0.00 MiB,1,0,73600.00 samples/s,0.01 ms,2.02 mW,27417.00 pJ/it
+pool/max_real_asymmetric_padding,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.03 mW,814992.00 pJ,0.060 s,0.00 MiB,0.00 MiB,1,0,96100.00 samples/s,0.01 ms,2.03 mW,21173.00 pJ/it
+pool/max_same_upper,arch-a,PASS,PASS,0.066 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.04 mW,625068.00 pJ,0.067 s,0.00 MiB,0.00 MiB,1,0,125000.00 samples/s,0.01 ms,2.04 mW,16233.00 pJ/it
+pool/max_stride2_multichannel,arch-a,PASS,PASS,0.067 s,0.00 MiB,0.00 MiB,1,0,0.02 ms,78.02 mW,1247274.00 pJ,0.074 s,0.00 MiB,0.00 MiB,1,0,62700.00 samples/s,0.02 ms,2.02 mW,32153.00 pJ/it
+reduce_mean/4d_spatial,arch-a,PASS,PASS,0.068 s,0.00 MiB,0.00 MiB,3,0,0.00 ms,92.45 mW,29676.00 pJ,0.068 s,0.00 MiB,0.00 MiB,3,0,2310000.00 samples/s,0.00 ms,4.54 mW,1959.17 pJ/it
+reduce_mean/4d_spatial_keepdims_0,arch-a,PASS,PASS,0.072 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,94.35 mW,61801.00 pJ,0.070 s,0.00 MiB,0.00 MiB,4,0,1210000.00 samples/s,0.00 ms,19.43 mW,16020.25 pJ/it
+reduce_mean/after_conv,arch-a,PASS,PASS,0.071 s,0.00 MiB,0.00 MiB,5,3,0.01 ms,106.95 mW,571332.72 pJ,0.075 s,0.00 MiB,0.00 MiB,5,3,183000.00 samples/s,0.01 ms,19.71 mW,107526.72 pJ/it
+reduce_mean/all_axes_keepdims_0,arch-a,PASS,PASS,0.059 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.24 mW,30982.00 pJ,0.063 s,0.00 MiB,0.00 MiB,2,0,2530000.00 samples/s,0.00 ms,3.31 mW,1260.00 pJ/it
+reduce_mean/all_axes_keepdims_1,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.067 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
+reduce_mean/basic,arch-a,PASS,PASS,0.068 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,93.51 mW,34881.00 pJ,0.061 s,0.00 MiB,0.00 MiB,4,0,2600000.00 samples/s,0.00 ms,5.85 mW,2235.67 pJ/it
+reduce_mean/channel_axis_nchw,arch-a,PASS,PASS,0.061 s,0.03 MiB,0.02 MiB,4,0,0.16 ms,93.60 mW,15436518.00 pJ,0.062 s,0.03 MiB,0.08 MiB,4,0,12900.00 samples/s,0.08 ms,5.00 mW,388853.50 pJ/it
+reduce_mean/keepdims_0,arch-a,PASS,PASS,0.067 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.40 mW,68368.00 pJ,0.056 s,0.00 MiB,0.00 MiB,5,0,1300000.00 samples/s,0.00 ms,20.71 mW,16115.50 pJ/it
+reduce_mean/large_dimension_1024,arch-a,PASS,PASS,0.057 s,0.01 MiB,0.00 MiB,1,0,0.00 ms,78.02 mW,217278.00 pJ,0.056 s,0.01 MiB,0.00 MiB,1,0,359000.00 samples/s,0.00 ms,2.02 mW,5274.00 pJ/it
+reduce_mean/legacy_axes_1_2_keepdims_1,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.35 mW,21505.00 pJ,0.058 s,0.00 MiB,0.00 MiB,2,0,3620000.00 samples/s,0.00 ms,3.45 mW,898.00 pJ/it
+reduce_mean/legacy_axis1_keepdims_0,arch-a,PASS,PASS,0.062 s,0.00 MiB,0.00 MiB,9,0,0.00 ms,92.50 mW,183708.00 pJ,0.065 s,0.00 MiB,0.00 MiB,9,0,679000.00 samples/s,0.00 ms,38.84 mW,57998.17 pJ/it
+reduce_mean/legacy_axis1_keepdims_1,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,8,0,0.00 ms,94.56 mW,129830.00 pJ,0.066 s,0.00 MiB,0.00 MiB,8,0,1340000.00 samples/s,0.00 ms,10.15 mW,7594.50 pJ/it
+reduce_mean/legacy_empty_axes_noop,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
+reduce_mean/legacy_nchw_spatial,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.00 MiB,3,0,0.00 ms,92.45 mW,29676.00 pJ,0.058 s,0.00 MiB,0.00 MiB,3,0,1720000.00 samples/s,0.00 ms,4.40 mW,2552.75 pJ/it
+reduce_mean/legacy_negative_axis,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,6,0,0.00 ms,93.52 mW,51717.00 pJ,0.060 s,0.00 MiB,0.00 MiB,6,0,1760000.00 samples/s,0.00 ms,8.07 mW,4588.50 pJ/it
+reduce_mean/legacy_reduce_all_keepdims_1,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.054 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
+reduce_mean/negative_axis,arch-a,PASS,PASS,0.059 s,0.00 MiB,0.00 MiB,6,0,0.00 ms,93.52 mW,51717.00 pJ,0.058 s,0.00 MiB,0.00 MiB,6,0,1760000.00 samples/s,0.00 ms,8.07 mW,4588.50 pJ/it
+relu/4d,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.18 mW,40734.00 pJ,0.053 s,0.00 MiB,0.00 MiB,1,0,1930000.00 samples/s,0.00 ms,2.18 mW,1014.00 pJ/it
+relu/after_conv,arch-a,PASS,PASS,0.063 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,107.89 mW,577437.72 pJ,0.067 s,0.00 MiB,0.00 MiB,4,3,187000.00 samples/s,0.01 ms,32.91 mW,176189.97 pJ/it
+relu/after_gemm,arch-a,PASS,PASS,0.069 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,105.16 mW,790056.96 pJ,0.074 s,0.01 MiB,0.01 MiB,6,4,151000.00 samples/s,0.01 ms,32.04 mW,211536.21 pJ/it
+relu/basic,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.057 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
+reshape/4d_to_2d_flatten,arch-a,PASS,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.28 mW,20196.00 pJ,0.061 s,0.00 MiB,0.00 MiB,1,0,3910000.00 samples/s,0.00 ms,2.28 mW,488.00 pJ/it
+reshape/infer_dim_minus_one,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,12684.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,6250000.00 samples/s,0.00 ms,2.30 mW,308.00 pJ/it
+reshape/same_rank,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,12684.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,6250000.00 samples/s,0.00 ms,2.30 mW,308.00 pJ/it
+reshape/zero_copies_input_dim,arch-a,PASS,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,12684.00 pJ,0.056 s,0.00 MiB,0.00 MiB,1,0,6250000.00 samples/s,0.00 ms,2.30 mW,308.00 pJ/it
+resize/height_only,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,93.55 mW,64833.00 pJ,0.063 s,0.00 MiB,0.00 MiB,4,0,1880000.00 samples/s,0.00 ms,5.60 mW,2986.00 pJ/it
+resize/nearest_2x,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,93.57 mW,109761.00 pJ,0.059 s,0.00 MiB,0.00 MiB,4,0,1450000.00 samples/s,0.00 ms,5.46 mW,3776.00 pJ/it
+resize/nearest_downsample,arch-a,PASS,PASS,0.059 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.45 mW,33925.00 pJ,0.059 s,0.00 MiB,0.00 MiB,2,0,2330000.00 samples/s,0.00 ms,3.28 mW,1360.50 pJ/it
+resize/non_uniform_scales,arch-a,PASS,PASS,0.063 s,0.00 MiB,0.00 MiB,6,0,0.00 ms,93.58 mW,164037.00 pJ,0.069 s,0.00 MiB,0.00 MiB,6,0,1250000.00 samples/s,0.00 ms,7.76 mW,6207.25 pJ/it
+resize/width_only,arch-a,PASS,PASS,0.062 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.50 mW,53029.00 pJ,0.059 s,0.00 MiB,0.00 MiB,2,0,1700000.00 samples/s,0.00 ms,3.20 mW,1833.50 pJ/it
+resize/with_sizes,arch-a,PASS,PASS,0.061 s,0.00 MiB,0.00 MiB,3,0,0.00 ms,92.54 mW,73756.00 pJ,0.068 s,0.00 MiB,0.00 MiB,3,0,1700000.00 samples/s,0.00 ms,4.39 mW,2586.75 pJ/it
+sigmoid/4d,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.18 mW,40734.00 pJ,0.060 s,0.00 MiB,0.00 MiB,1,0,1930000.00 samples/s,0.00 ms,2.18 mW,1014.00 pJ/it
+sigmoid/after_gemm,arch-a,PASS,PASS,0.063 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,105.16 mW,790056.96 pJ,0.062 s,0.01 MiB,0.01 MiB,6,4,151000.00 samples/s,0.01 ms,32.04 mW,211536.21 pJ/it
+sigmoid/basic,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.060 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
+slice/2d_basic,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,18948.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,4170000.00 samples/s,0.00 ms,2.30 mW,491.67 pJ/it
+slice/after_conv,arch-a,PASS,PASS,0.067 s,0.00 MiB,0.01 MiB,7,6,0.01 ms,118.19 mW,1335082.88 pJ,0.074 s,0.00 MiB,0.01 MiB,7,6,87400.00 samples/s,0.01 ms,47.90 mW,547806.13 pJ/it
+slice/default_axes,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,18948.00 pJ,0.054 s,0.00 MiB,0.00 MiB,1,0,4170000.00 samples/s,0.00 ms,2.30 mW,491.67 pJ/it
+slice/large_channel_1024,arch-a,PASS,PASS,0.059 s,0.01 MiB,0.00 MiB,1,0,0.00 ms,78.14 mW,221304.00 pJ,0.052 s,0.01 MiB,0.00 MiB,1,0,353000.00 samples/s,0.00 ms,2.14 mW,5058.00 pJ/it
+slice/nchw_spatial_crop,arch-a,PASS,PASS,0.062 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.24 mW,101868.00 pJ,0.060 s,0.00 MiB,0.00 MiB,1,0,769000.00 samples/s,0.00 ms,2.24 mW,2851.67 pJ/it
+slice/negative_axis,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,44004.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,1790000.00 samples/s,0.00 ms,2.30 mW,1227.67 pJ/it
+slice/negative_indices,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,25212.00 pJ,0.054 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.30 mW,675.67 pJ/it
+slice/step2,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.29 mW,159876.00 pJ,0.053 s,0.00 MiB,0.00 MiB,1,0,490000.00 samples/s,0.00 ms,2.29 mW,4619.67 pJ/it
+softmax/3d_last_axis,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.056 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
+softmax/basic,arch-a,PASS,PASS,0.062 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.058 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
+softmax/channel_axis,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.067 s,0.00 MiB,0.00 MiB,3,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
+softmax/large_dimension_1024,arch-a,PASS,PASS,0.059 s,0.01 MiB,0.01 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.054 s,0.01 MiB,0.01 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
+softmax/negative_axis,arch-a,PASS,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.060 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
+split/basic,arch-a,PASS,PASS,0.114 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,31554.00 pJ,0.067 s,0.00 MiB,0.00 MiB,1,0,2490000.00 samples/s,0.00 ms,2.30 mW,861.67 pJ/it
+split/equal_three_way,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,44160.00 pJ,0.073 s,0.00 MiB,0.00 MiB,1,0,1780000.00 samples/s,0.00 ms,2.30 mW,1231.67 pJ/it
+split/negative_axis,arch-a,PASS,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.29 mW,84786.00 pJ,0.059 s,0.00 MiB,0.00 MiB,1,0,925000.00 samples/s,0.00 ms,2.29 mW,2413.67 pJ/it
+split/uneven_channel_axis_4d,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,18948.00 pJ,0.060 s,0.00 MiB,0.00 MiB,1,0,4170000.00 samples/s,0.00 ms,2.30 mW,491.67 pJ/it
+sub/after_gemm,arch-a,PASS,PASS,0.065 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,104.70 mW,815012.96 pJ,0.065 s,0.01 MiB,0.01 MiB,6,4,145000.00 samples/s,0.01 ms,31.45 mW,216167.21 pJ/it
+sub/basic,arch-a,PASS,PASS,0.062 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+sub/broadcast_row,arch-a,PASS,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.077 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
+sub/channel_broadcast_1024,arch-a,PASS,PASS,0.064 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.058 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
+sub/constant_lhs_broadcast,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25188.00 pJ,0.061 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,656.67 pJ/it
+sub/leading_dimension_broadcast,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.057 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it