Skip to content

[CPU] Enable one shot weights packing for Convolution and Deconvolution #32941

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[CPU] Enable one shot weights packing for Convolution and Deconvolution #32941

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions src/plugins/intel_cpu/src/graph_optimizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,7 @@ void GraphOptimizer::ApplyCommonGraphOptimizations(Graph& graph) {
graph.RemoveDroppedNodes();

OV_ITT_SCOPE_NEXT(FIRST_INFERENCE, taskChain, "FuseFCAndConvertOnWeights");
FuseFCAndConvertOnWeights(graph);
FuseConvDeconvFCAndConvertOnWeights(graph);
graph.RemoveDroppedNodes();

OV_ITT_SCOPE_NEXT(FIRST_INFERENCE, taskChain, "FuseFCAndTransposeOnWeights");
Expand Down Expand Up @@ -832,7 +832,7 @@ void GraphOptimizer::MergeConvertAndEltwise(Graph& graph) {
}
}

void GraphOptimizer::FuseFCAndConvertOnWeights(Graph& graph) {
void GraphOptimizer::FuseConvDeconvFCAndConvertOnWeights(Graph& graph) {
#if defined(OV_CPU_WITH_SHL)
return;
#endif
Expand All @@ -851,7 +851,7 @@ void GraphOptimizer::FuseFCAndConvertOnWeights(Graph& graph) {

const auto& graphNodes = graph.GetNodes();
for (const auto& fullyConnected : graphNodes) {
if (fullyConnected->getType() != Type::FullyConnected) {
if (none_of(fullyConnected->getType(), Type::FullyConnected, Type::Convolution, Type::Deconvolution)) {
continue;
}

Expand Down
2 changes: 1 addition & 1 deletion src/plugins/intel_cpu/src/graph_optimizer.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ class GraphOptimizer {
static void FuseMultiplyAndAdd(Graph& graph);
static void MergeEltwiseAndConvert(Graph& graph);
static void MergeConvertAndEltwise(Graph& graph);
static void FuseFCAndConvertOnWeights(Graph& graph);
static void FuseConvDeconvFCAndConvertOnWeights(Graph& graph);
static void FuseFCAndTransposeOnWeights(Graph& graph);
static void FuseFullyConnectedAndSimpleOperation(Graph& graph);
static void FuseMatMulAndSimpleOperation(Graph& graph);
Expand Down
5 changes: 4 additions & 1 deletion src/plugins/intel_cpu/src/transformations/transformation_pipeline.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -555,7 +555,10 @@ void Transformations::PreLpt(const std::vector<ov::element::Type>& defaultPrecis
[](const_node_ptr& node) -> bool {
const auto consumers = node->get_output_target_inputs(0);
return std::all_of(consumers.begin(), consumers.end(), [](const ov::Input<ov::Node>& consumer) {
return !ov::is_type<ov::op::v0::MatMul>(consumer.get_node());
// @todo cover RNN type of ops as well
return !is_type_any_of<ov::op::v0::MatMul,
ov::op::v1::Convolution,
ov::op::v1::ConvolutionBackpropData>(consumer.get_node());
});
},
ov::pass::KeepConstAndDecompression);
Expand Down
Loading