IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[CPU] Disable gather inPlace for out of range indices (#19159)

Browse Source
This commit is contained in:
Maksim Kutakov 2023-08-16 08:32:31 +02:00 committed by GitHub
parent 8a0a4df941
commit d13dff06f3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 62 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
src/plugins/intel_cpu/src/nodes/gather.cpp
View File

@ -140,18 +140,40 @@ void Gather::initSupportedPrimitiveDescriptors() {
// Let's check for the special inPlace memory use case
// in place only makes sense when we split by dense blocks since strided tensors are not supported by most nodes
const auto& parentdDims = inputShapes[0].getDims();
if (isAxisInputConst &&
0 == batchDims &&
1 == constIndices.size() &&
parentdDims[axis] != Shape::UNDEFINED_DIM &&
std::all_of(parentdDims.begin(), parentdDims.begin() + axis, [](size_t dim) { return dim == 1; })) {
addSupportedPrimDesc({{LayoutType::ncsp, dataPrecision},
{LayoutType::ncsp, Precision::I32},
{LayoutType::ncsp, Precision::I32, isAxisInputConst}},
{{LayoutType::ncsp, dataPrecision, false, GATHER_DATA}},
unknown);
if (!isAxisInputConst) {
return;
}
if (batchDims != 0) {
return;
}
if (constIndices.size() != 1) {
return;
}
const auto& parentDims = inputShapes[0].getDims();
const auto axisDim = parentDims[axis];
if (Shape::UNDEFINED_DIM == axisDim) {
return;
}
const auto indx = constIndices.front();
const auto normIndex = indx < 0 ? static_cast<int64_t>(axisDim) + indx : indx;
if (normIndex < 0 || normIndex >= static_cast<int64_t>(axisDim)) {
return;
}
if (std::any_of(parentDims.begin(), parentDims.begin() + axis, [](size_t dim) { return dim != 1; })) {
return;
}
addSupportedPrimDesc({{LayoutType::ncsp, dataPrecision},
{LayoutType::ncsp, Precision::I32},
{LayoutType::ncsp, Precision::I32, isAxisInputConst}},
{{LayoutType::ncsp, dataPrecision, false, GATHER_DATA}},
unknown);
}
void Gather::createPrimitive() {
@ -293,6 +315,9 @@ void Gather::prepareParams() {
}
void Gather::execute(dnnl::stream strm) {
if (isInPlace()) {
return;
}
#if defined(OPENVINO_ARCH_X86_64)
if (jitKernel && jitKernel->isSupportedConfiguration(afterAxisSize)) {
const void* srcIndices = getParentEdgeAt(GATHER_INDICES)->getMemoryPtr()->getData();
@ -349,6 +374,9 @@ void Gather::execute(dnnl::stream strm) {
}
void Gather::executeDynamicImpl(dnnl::stream strm) {
if (isInPlace()) {
return;
}
#if defined(OPENVINO_ARCH_X86_64)
if (jitKernel && jitKernel->isSupportedConfiguration(afterAxisSize)) {
const void* srcIndices = getParentEdgeAt(GATHER_INDICES)->getMemoryPtr()->getData();
@ -530,11 +558,11 @@ void Gather::resolveInPlaceEdges(Edge::LOOK look) {
auto& config = selected_pd->getConfig();
size_t inplaceInpIndx = selected_pd->getConfig().outConfs[outputPort].inPlace();
auto baseDim = inputShapes.front().getDims()[axis];
const auto baseDim = inputShapes.front().getDims()[axis];
IE_ASSERT(baseDim != Shape::UNDEFINED_DIM) << "Gather node: " << getName() << " can not use inPlace memory with splitting on dynamic dimention";
auto baseMemMngr = getParentEdgesAtPort(inplaceInpIndx).front()->getMemory().getMemoryMngr();
auto index = constIndices.at(0);
ptrdiff_t offset = index < 0 ? baseDim + index : index;
const auto index = constIndices.front();
const ptrdiff_t offset = index < 0 ? baseDim + index : index;
const auto& childEdges = getChildEdgesAtPort(outputPort);
for (auto& childEdge : childEdges) {
IE_ASSERT(childEdge->getStatus() == Edge::Status::NotAllocated) << " Unexpected edge status in node: " <<

2
src/plugins/intel_cpu/tests/functional/shared_tests_instances/skip_tests_config.cpp
View File

@ -190,6 +190,8 @@ std::vector<std::string> disabledTestPatterns() {
R"(.*(Auto|Multi|Hetero).*InferRequestPreprocessTest.*SetPreProcessToInferRequest.*)",
// TODO: for 22.2 (Issue 68949)
R"(.*smoke_AutoBatching_CPU/AutoBatching_Test_DetectionOutput.*)",
// Issue: 117837
R"(.*smoke_4D_out_of_range/GatherInPlaceLayerTestCPU.*_indices=\(\-15\).*)",
};
#if defined(OPENVINO_ARCH_X86)

27
src/plugins/intel_cpu/tests/functional/single_layer_tests/gather.cpp
View File

@ -148,7 +148,7 @@ protected:
typedef std::tuple<
InputShape, // Input shapes
std::vector<size_t>, // Indices
std::vector<int64_t>, // Indices
int, // Axis
ElementType, // Network precision
CPUSpecificParams // CPU specific params
@ -159,7 +159,7 @@ class GatherInPlaceLayerTestCPU : public testing::WithParamInterface<GatherInPla
public:
static std::string getTestCaseName(testing::TestParamInfo<GatherInPlaceLayerTestCPUParams> obj) {
InputShape inputShapes;
std::vector<size_t> indices;
std::vector<int64_t> indices;
int axis;
ElementType netPrecision;
CPUSpecificParams cpuParams;
@ -187,7 +187,7 @@ public:
protected:
void SetUp() override {
InputShape inputShapes;
std::vector<size_t> indices;
std::vector<int64_t> indices;
int axis;
ElementType netPrecision;
CPUSpecificParams cpuParams;
@ -924,32 +924,41 @@ INSTANTIATE_TEST_SUITE_P(smoke_static_4D_ref8_Bmax, GatherLayerTestCPU,
// InPlace
const std::vector<ov::test::InputShape> shapesInPlace4D_0 = {
{ {}, { {5, 4, 4, 19} } }, // Static shapes
{ {5, 4, -1, -1}, { {5, 4, 4, 19}, {5, 4, 4, 25}, {5, 4, 2, 19} } }, // Static shapes
{ {}, { {5, 4, 4, 19} } },
{ {5, 4, -1, -1}, { {5, 4, 4, 19}, {5, 4, 4, 25}, {5, 4, 2, 19} } },
};
INSTANTIATE_TEST_SUITE_P(smoke_inplace_4D_0, GatherInPlaceLayerTestCPU,
::testing::Combine(
::testing::ValuesIn(shapesInPlace4D_0),
::testing::Values(std::vector<size_t>{ 2 }),
::testing::Values(std::vector<int64_t>{ 2 }),
::testing::Values(0),
::testing::Values(ElementType::f32),
::testing::Values(CPUSpecificParams{{}, {}, {}, "unknown"})),
GatherInPlaceLayerTestCPU::getTestCaseName);
const std::vector<ov::test::InputShape> shapesInPlace4D_1 = {
{ {}, { {1, 9, 4, 19} } }, // Static shapes
{ {1, 9, -1, -1}, { {1, 9, 4, 19}, {1, 9, 4, 25}, {1, 9, 2, 19} } }, // Static shapes
{ {}, { {1, 9, 4, 19} } },
{ {1, 9, -1, -1}, { {1, 9, 4, 19}, {1, 9, 4, 25}, {1, 9, 2, 19} } },
};
INSTANTIATE_TEST_SUITE_P(smoke_inplace_4D_1, GatherInPlaceLayerTestCPU,
::testing::Combine(
::testing::ValuesIn(shapesInPlace4D_1),
::testing::Values(std::vector<size_t>{ 4 }),
::testing::Values(std::vector<int64_t>{ -4 }, std::vector<int64_t>{ 5 }),
::testing::Values(1),
::testing::Values(ElementType::f32),
::testing::Values(CPUSpecificParams{{}, {}, {}, "unknown"})),
GatherInPlaceLayerTestCPU::getTestCaseName);
INSTANTIATE_TEST_SUITE_P(smoke_4D_out_of_range, GatherInPlaceLayerTestCPU,
::testing::Combine(
::testing::ValuesIn(shapesInPlace4D_1),
::testing::Values(std::vector<int64_t>{ 10 }, std::vector<int64_t>{ -15 }),
::testing::Values(1),
::testing::Values(ElementType::f32),
::testing::Values(CPUSpecificParams{{}, {}, {}, "ref_any"})),
GatherInPlaceLayerTestCPU::getTestCaseName);
} // namespace
} // namespace CPULayerTestsDefinitions