p12346870
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!25762 Unified CPU thread pool 

Merge pull request !25762 from 范吉斌/unified_thread
This commit is contained in:
i-robot 2021-11-04 12:45:29 +00:00 committed by Gitee
parent eff89357a7 b6acbd1055
commit b6bf3cd641
44 changed files with 207 additions and 268 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mindspore/ccsrc/backend/kernel_compiler/cpu/adam_cpu_kernel.cc
View File

@ -60,7 +60,7 @@ void AdamCPUKernel::LaunchAdam(const std::vector<kernel::AddressPtr> &inputs, co
}
}
};
CPUKernelUtils::ParallelFor(task, lens);
ParallelLaunchAutoSearch(task, lens, this, &parallel_search_info_);
}
void AdamCPUKernel::LaunchAdamNnacl(const std::vector<kernel::AddressPtr> &inputs,

2
mindspore/ccsrc/backend/kernel_compiler/cpu/adam_delta_cpu_kernel.cc
View File

@ -54,7 +54,7 @@ void AdamDeltaCPUKernel::LaunchAdamDelta(T *delta, T *m, T *v, float lr, float b
}
};
}
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, this, &parallel_search_info_);
}
void AdamDeltaCPUKernel::InitKernel(const CNodePtr &kernel_node) {

2
mindspore/ccsrc/backend/kernel_compiler/cpu/adam_weight_decay_cpu_kernel.cc
View File

@ -61,7 +61,7 @@ void AdamWeightDecayCPUKernel::LaunchAdamWeightDecay(const std::vector<AddressPt
var[i] -= lr * update;
}
};
CPUKernelUtils::ParallelFor(task, lens);
ParallelLaunchAutoSearch(task, lens, this, &parallel_search_info_);
}
void AdamWeightDecayCPUKernel::LaunchAdamWeightDecayNnacl(const std::vector<AddressPtr> &inputs,

42
mindspore/ccsrc/backend/kernel_compiler/cpu/arithmetic_cpu_kernel.cc
View File

@ -62,18 +62,18 @@ void ElementRealDiv(const T *input1, const T *input2, T *out, size_t size, size_
} // namespace
template <typename T>
void ArithmeticCPUKernel<T>::AssignAdd(T *input1, const T *input2, T *out) const {
void ArithmeticCPUKernel<T>::AssignAdd(T *input1, const T *input2, T *out) {
auto task = [&input1, &input2, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = input1[i] + input2[i];
input1[i] = out[i];
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticCPUKernel<T>::Add(const T *input1, const T *input2, T *out) const {
void ArithmeticCPUKernel<T>::Add(const T *input1, const T *input2, T *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&input1, &input2, &out, &base_iter](size_t start, size_t end) {
auto iter = base_iter;
@ -83,7 +83,7 @@ void ArithmeticCPUKernel<T>::Add(const T *input1, const T *input2, T *out) const
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
@ -118,7 +118,7 @@ void ArithmeticCPUKernel<T>::Sub(const T *input1, const T *input2, T *out) {
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_, kMaxSubSerialSize);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
@ -152,7 +152,7 @@ void ArithmeticCPUKernel<T>::Mul(const T *input1, const T *input2, T *out) {
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
@ -203,11 +203,11 @@ void ArithmeticCPUKernel<T>::RealDiv(const T *input1, const T *input2, T *out) {
out[i] = dividend / divisor;
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticCPUKernel<T>::Div(const T *input1, const T *input2, T *out) const {
void ArithmeticCPUKernel<T>::Div(const T *input1, const T *input2, T *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&input1, &input2, &out, &base_iter](size_t start, size_t end) {
auto iter = base_iter;
@ -232,11 +232,11 @@ void ArithmeticCPUKernel<T>::Div(const T *input1, const T *input2, T *out) const
out[i] = dividend / divisor;
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticCPUKernel<T>::FloorDiv(const T *input1, const T *input2, T *out) const {
void ArithmeticCPUKernel<T>::FloorDiv(const T *input1, const T *input2, T *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&input1, &input2, &out, &base_iter](size_t start, size_t end) {
auto iter = base_iter;
@ -261,11 +261,11 @@ void ArithmeticCPUKernel<T>::FloorDiv(const T *input1, const T *input2, T *out)
out[i] = static_cast<T>(floor(static_cast<double>(dividend) / static_cast<double>(divisor)));
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticCPUKernel<T>::Mod(const T *input1, const T *input2, T *out) const {
void ArithmeticCPUKernel<T>::Mod(const T *input1, const T *input2, T *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&input1, &input2, &out, &base_iter](size_t start, size_t end) {
auto iter = base_iter;
@ -283,11 +283,11 @@ void ArithmeticCPUKernel<T>::Mod(const T *input1, const T *input2, T *out) const
out[i] = static_cast<T>(x - data_div_res * y);
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticCPUKernel<T>::FloorMod(const T *input1, const T *input2, T *out) const {
void ArithmeticCPUKernel<T>::FloorMod(const T *input1, const T *input2, T *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&input1, &input2, &out, &base_iter](size_t start, size_t end) {
auto iter = base_iter;
@ -300,11 +300,11 @@ void ArithmeticCPUKernel<T>::FloorMod(const T *input1, const T *input2, T *out)
out[i] = static_cast<T>((std::abs(res) > 1e-9) && ((res < 0.0) != (y < 0.0)) ? res + y : res);
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticCPUKernel<T>::Pow(const T *input1, const T *input2, T *out) const {
void ArithmeticCPUKernel<T>::Pow(const T *input1, const T *input2, T *out) {
if constexpr (std::is_same_v<T, float>) {
auto is_power_single = [this]() {
bool is_power_single = false;
@ -324,14 +324,14 @@ void ArithmeticCPUKernel<T>::Pow(const T *input1, const T *input2, T *out) const
auto task = [&](size_t start, size_t end) {
(void)Power(input1 + start, input2, out + start, end - start, 1, 0, true);
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
return;
}
if (is_power_single()) {
auto task = [&](size_t start, size_t end) {
(void)Power(input1 + start, input2 + start, out + start, end - start, 1, 0, false);
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
return;
}
}
@ -348,7 +348,7 @@ void ArithmeticCPUKernel<T>::Pow(const T *input1, const T *input2, T *out) const
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
} else {
base_iter.SetPos(0);
for (size_t i = 0; i < output_size_; i++) {
@ -376,7 +376,7 @@ void ArithmeticCPUKernel<T>::SquaredDifference(const T *input1, const T *input2,
}
template <typename T>
void ArithmeticCPUKernel<T>::Atan2(const T *input1, const T *input2, T *out) const {
void ArithmeticCPUKernel<T>::Atan2(const T *input1, const T *input2, T *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&input1, &input2, &out, &base_iter](size_t start, size_t end) {
auto iter = base_iter;
@ -387,7 +387,7 @@ void ArithmeticCPUKernel<T>::Atan2(const T *input1, const T *input2, T *out) con
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>

16
mindspore/ccsrc/backend/kernel_compiler/cpu/arithmetic_cpu_kernel.h
View File

@ -39,16 +39,16 @@ class ArithmeticCPUKernel : public CPUKernel {
private:
void InitComputeFunc();
void Sub(const T *input1, const T *input2, T *out);
void Add(const T *input1, const T *input2, T *out) const;
void Add(const T *input1, const T *input2, T *out);
void Mul(const T *input1, const T *input2, T *out);
void RealDiv(const T *input1, const T *input2, T *out);
void Div(const T *input1, const T *input2, T *out) const;
void FloorDiv(const T *input1, const T *input2, T *out) const;
void Mod(const T *input1, const T *input2, T *out) const;
void FloorMod(const T *input1, const T *input2, T *out) const;
void Pow(const T *input1, const T *input2, T *out) const;
void AssignAdd(T *input1, const T *input2, T *out) const;
void Atan2(const T *input1, const T *input2, T *out) const;
void Div(const T *input1, const T *input2, T *out);
void FloorDiv(const T *input1, const T *input2, T *out);
void Mod(const T *input1, const T *input2, T *out);
void FloorMod(const T *input1, const T *input2, T *out);
void Pow(const T *input1, const T *input2, T *out);
void AssignAdd(T *input1, const T *input2, T *out);
void Atan2(const T *input1, const T *input2, T *out);
void SquaredDifference(const T *input1, const T *input2, T *out);
using TypeComputeFunc = std::function<void(ArithmeticCPUKernel *, const T *in_x, const T *in_y, T *out)>;

32
mindspore/ccsrc/backend/kernel_compiler/cpu/arithmetic_logic_cpu_kernel.cc
View File

@ -32,7 +32,7 @@ constexpr size_t kOutputsNum = 1;
} // namespace
template <typename T>
void ArithmeticLogicCPUKernel<T>::Less(const T *input1, const T *input2, bool *out) const {
void ArithmeticLogicCPUKernel<T>::Less(const T *input1, const T *input2, bool *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
if (output_size_ > kMaxLessSerialSize) {
auto task = [&](size_t start, size_t end) {
@ -45,7 +45,7 @@ void ArithmeticLogicCPUKernel<T>::Less(const T *input1, const T *input2, bool *o
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
} else {
base_iter.SetPos(0);
for (size_t i = 0; i < output_size_; i++) {
@ -58,7 +58,7 @@ void ArithmeticLogicCPUKernel<T>::Less(const T *input1, const T *input2, bool *o
}
template <typename T>
void ArithmeticLogicCPUKernel<T>::Equal(const T *input1, const T *input2, bool *out) const {
void ArithmeticLogicCPUKernel<T>::Equal(const T *input1, const T *input2, bool *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&](size_t start, size_t end) {
auto iter = base_iter;
@ -70,11 +70,11 @@ void ArithmeticLogicCPUKernel<T>::Equal(const T *input1, const T *input2, bool *
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticLogicCPUKernel<T>::NotEqual(const T *input1, const T *input2, bool *out) const {
void ArithmeticLogicCPUKernel<T>::NotEqual(const T *input1, const T *input2, bool *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&](size_t start, size_t end) {
auto iter = base_iter;
@ -86,11 +86,11 @@ void ArithmeticLogicCPUKernel<T>::NotEqual(const T *input1, const T *input2, boo
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticLogicCPUKernel<T>::LogicalAnd(const T *input1, const T *input2, bool *out) const {
void ArithmeticLogicCPUKernel<T>::LogicalAnd(const T *input1, const T *input2, bool *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&](size_t start, size_t end) {
auto iter = base_iter;
@ -100,11 +100,11 @@ void ArithmeticLogicCPUKernel<T>::LogicalAnd(const T *input1, const T *input2, b
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticLogicCPUKernel<T>::LogicalOr(const T *input1, const T *input2, bool *out) const {
void ArithmeticLogicCPUKernel<T>::LogicalOr(const T *input1, const T *input2, bool *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&](size_t start, size_t end) {
auto iter = base_iter;
@ -114,11 +114,11 @@ void ArithmeticLogicCPUKernel<T>::LogicalOr(const T *input1, const T *input2, bo
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticLogicCPUKernel<T>::Greater(const T *input1, const T *input2, bool *out) const {
void ArithmeticLogicCPUKernel<T>::Greater(const T *input1, const T *input2, bool *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&](size_t start, size_t end) {
auto iter = base_iter;
@ -130,11 +130,11 @@ void ArithmeticLogicCPUKernel<T>::Greater(const T *input1, const T *input2, bool
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticLogicCPUKernel<T>::GreaterEqual(const T *input1, const T *input2, bool *out) const {
void ArithmeticLogicCPUKernel<T>::GreaterEqual(const T *input1, const T *input2, bool *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&](size_t start, size_t end) {
auto iter = base_iter;
@ -146,11 +146,11 @@ void ArithmeticLogicCPUKernel<T>::GreaterEqual(const T *input1, const T *input2,
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>
void ArithmeticLogicCPUKernel<T>::LessEqual(const T *input1, const T *input2, bool *out) const {
void ArithmeticLogicCPUKernel<T>::LessEqual(const T *input1, const T *input2, bool *out) {
BroadcastIterator base_iter(input_shape1_, input_shape2_, output_shape_);
auto task = [&](size_t start, size_t end) {
auto iter = base_iter;
@ -162,7 +162,7 @@ void ArithmeticLogicCPUKernel<T>::LessEqual(const T *input1, const T *input2, bo
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size_);
ParallelLaunchAutoSearch(task, output_size_, this, &parallel_search_info_);
}
template <typename T>

16
mindspore/ccsrc/backend/kernel_compiler/cpu/arithmetic_logic_cpu_kernel.h
View File

@ -39,14 +39,14 @@ class ArithmeticLogicCPUKernel : public CPUKernel {
private:
void InitComputeFunc();
void Less(const T *input1, const T *input2, bool *out) const;
void Equal(const T *input1, const T *input2, bool *out) const;
void NotEqual(const T *input1, const T *input2, bool *out) const;
void Greater(const T *input1, const T *input2, bool *out) const;
void GreaterEqual(const T *input1, const T *input2, bool *out) const;
void LessEqual(const T *input1, const T *input2, bool *out) const;
void LogicalAnd(const T *input1, const T *input2, bool *out) const;
void LogicalOr(const T *input1, const T *input2, bool *out) const;
void Less(const T *input1, const T *input2, bool *out);
void Equal(const T *input1, const T *input2, bool *out);
void NotEqual(const T *input1, const T *input2, bool *out);
void Greater(const T *input1, const T *input2, bool *out);
void GreaterEqual(const T *input1, const T *input2, bool *out);
void LessEqual(const T *input1, const T *input2, bool *out);
void LogicalAnd(const T *input1, const T *input2, bool *out);
void LogicalOr(const T *input1, const T *input2, bool *out);
using TypeComputeFunc = std::function<void(ArithmeticLogicCPUKernel *, const T *, const T *, bool *)>;
TypeComputeFunc compute_func_{nullptr};

150
mindspore/ccsrc/backend/kernel_compiler/cpu/arithmetic_self_cpu_kernel.cc
View File

@ -33,17 +33,17 @@ constexpr size_t kInputsNum = 1;
constexpr size_t kOutputsNum = 1;
template <typename T>
void Square(const T *in, T *out, size_t size) {
void Square(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = in[i] * in[i];
}
};
ParallelLaunch(task, size, kMaxSquareSerialSize);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Sign(const T *in, T *out, size_t size) {
void Sign(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
if (in[i] < 0) {
@ -55,11 +55,11 @@ void Sign(const T *in, T *out, size_t size) {
}
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Neg(const T *in, T *out, size_t size) {
void Neg(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = -in[i];
@ -68,77 +68,77 @@ void Neg(const T *in, T *out, size_t size) {
ParallelLaunch(task, size, kMaxNegSerialSize);
}
void LogicalNot(const bool *in, bool *out, size_t size) {
void LogicalNot(ArithmeticSelfCPUKernel *content, const bool *in, bool *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = !in[i];
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void OnesLike(const T *, T *out, size_t size) {
void OnesLike(ArithmeticSelfCPUKernel *content, const T *, T *out, size_t size) {
auto task = [&out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(1);
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void ZerosLike(const T *, T *out, size_t size) {
void ZerosLike(ArithmeticSelfCPUKernel *content, const T *, T *out, size_t size) {
auto task = [&out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(0);
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Floor(const T *in, T *out, size_t size) {
void Floor(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(floor(in[i]));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Rint(const T *in, T *out, size_t size) {
void Rint(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(rint(in[i]));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Round(const T *in, T *out, size_t size) {
void Round(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(nearbyint(in[i]));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Reciprocal(const T *in, T *out, size_t size) {
void Reciprocal(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(1.0 / in[i]);
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Gelu(const T *in, T *out, size_t size) {
void Gelu(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
auto factor_a = static_cast<T>(0.7978845608);
auto factor_b = static_cast<T>(0.044715);
@ -149,137 +149,137 @@ void Gelu(const T *in, T *out, size_t size) {
out[i] = x * (static_cast<T>(1.0) + tanh_res) / static_cast<T>(2.0);
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Asin(const T *in, T *out, size_t size) {
void Asin(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(asin(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void ACos(const T *in, T *out, size_t size) {
void ACos(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(acos(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Atan(const T *in, T *out, size_t size) {
void Atan(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(atan(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Sin(const T *in, T *out, size_t size) {
void Sin(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(sin(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Cos(const T *in, T *out, size_t size) {
void Cos(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(cos(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Tan(const T *in, T *out, size_t size) {
void Tan(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(tan(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Sinh(const T *in, T *out, size_t size) {
void Sinh(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(sinh(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Cosh(const T *in, T *out, size_t size) {
void Cosh(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(cosh(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Asinh(const T *in, T *out, size_t size) {
void Asinh(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(asinh(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Acosh(const T *in, T *out, size_t size) {
void Acosh(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(acosh(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Atanh(const T *in, T *out, size_t size) {
void Atanh(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(atanh(static_cast<double>(in[i])));
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Abs(const T *in, T *out, size_t size) {
void Abs(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = abs(in[i]);
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
void Sqrt(const T *in, T *out, size_t size) {
void Sqrt(ArithmeticSelfCPUKernel *content, const T *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = sqrt(in[i]);
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename T>
@ -316,49 +316,49 @@ bool ArithmeticSelfCPUKernel::Launch(const std::vector<kernel::AddressPtr> &inpu
}
void ArithmeticSelfCPUKernel::LaunchLogicalNot(const std::vector<AddressPtr> &inputs,
const std::vector<AddressPtr> &outputs) const {
const std::vector<AddressPtr> &outputs) {
auto *input = reinterpret_cast<bool *>(inputs[0]->addr);
auto *output = reinterpret_cast<bool *>(outputs[0]->addr);
size_t lens = outputs[0]->size / sizeof(bool);
LogicalNot(input, output, lens);
LogicalNot(this, input, output, lens);
}
template <typename T>
void ArithmeticSelfCPUKernel::LaunchKernel(const std::vector<AddressPtr> &inputs,
const std::vector<AddressPtr> &outputs) const {
const std::vector<AddressPtr> &outputs) {
const auto *input = reinterpret_cast<T *>(inputs[0]->addr);
auto *output = reinterpret_cast<T *>(outputs[0]->addr);
const size_t lens = outputs[0]->size / sizeof(T);
static const std::unordered_map<std::string, std::function<void(const T *, T *, size_t)>> arithmeticSelfFuncMap{
{prim::kPrimSquare->name(), Square<T>},
{prim::kPrimSign->name(), Sign<T>},
{prim::kPrimNeg->name(), Neg<T>},
{prim::kPrimAtanh->name(), Atanh<T>},
{prim::kPrimAcosh->name(), Acosh<T>},
{prim::kPrimFloor->name(), Floor<T>},
{prim::kPrimSin->name(), Sin<T>},
{prim::kPrimGeLU->name(), Gelu<T>},
{prim::kPrimCos->name(), Cos<T>},
{prim::kPrimTan->name(), Tan<T>},
{prim::kPrimAsin->name(), Asin<T>},
{prim::kPrimACos->name(), ACos<T>},
{prim::kPrimAtan->name(), Atan<T>},
{prim::kPrimSinh->name(), Sinh<T>},
{prim::kPrimCosh->name(), Cosh<T>},
{prim::kPrimAsinh->name(), Asinh<T>},
{prim::kPrimZerosLike->name(), ZerosLike<T>},
{prim::kPrimOnesLike->name(), OnesLike<T>},
{prim::kPrimReciprocal->name(), Reciprocal<T>},
{prim::kPrimRint->name(), Rint<T>},
{prim::kPrimRound->name(), Round<T>},
{prim::kPrimAbs->name(), Abs<T>},
{prim::kPrimSqrt->name(), Sqrt<T>}};
static const std::unordered_map<std::string, std::function<void(ArithmeticSelfCPUKernel *, const T *, T *, size_t)>>
arithmeticSelfFuncMap{{prim::kPrimSquare->name(), Square<T>},
{prim::kPrimSign->name(), Sign<T>},
{prim::kPrimNeg->name(), Neg<T>},
{prim::kPrimAtanh->name(), Atanh<T>},
{prim::kPrimAcosh->name(), Acosh<T>},
{prim::kPrimFloor->name(), Floor<T>},
{prim::kPrimSin->name(), Sin<T>},
{prim::kPrimGeLU->name(), Gelu<T>},
{prim::kPrimCos->name(), Cos<T>},
{prim::kPrimTan->name(), Tan<T>},
{prim::kPrimAsin->name(), Asin<T>},
{prim::kPrimACos->name(), ACos<T>},
{prim::kPrimAtan->name(), Atan<T>},
{prim::kPrimSinh->name(), Sinh<T>},
{prim::kPrimCosh->name(), Cosh<T>},
{prim::kPrimAsinh->name(), Asinh<T>},
{prim::kPrimZerosLike->name(), ZerosLike<T>},
{prim::kPrimOnesLike->name(), OnesLike<T>},
{prim::kPrimReciprocal->name(), Reciprocal<T>},
{prim::kPrimRint->name(), Rint<T>},
{prim::kPrimRound->name(), Round<T>},
{prim::kPrimAbs->name(), Abs<T>},
{prim::kPrimSqrt->name(), Sqrt<T>}};
const auto func_pair = arithmeticSelfFuncMap.find(kernel_name_);
if (arithmeticSelfFuncMap.find(kernel_name_) == arithmeticSelfFuncMap.end()) {
MS_LOG(EXCEPTION) << "ArithmeticSelfCPUKernel does not support " << kernel_name_;
}
func_pair->second(input, output, lens);
func_pair->second(this, input, output, lens);
}
template <typename T>

4
mindspore/ccsrc/backend/kernel_compiler/cpu/arithmetic_self_cpu_kernel.h
View File

@ -37,9 +37,9 @@ class ArithmeticSelfCPUKernel : public CPUKernel {
private:
template <typename T>
void LaunchKernel(const std::vector<AddressPtr> &inputs, const std::vector<AddressPtr> &outputs) const;
void LaunchKernel(const std::vector<AddressPtr> &inputs, const std::vector<AddressPtr> &outputs);
void LaunchLogicalNot(const std::vector<AddressPtr> &inputs, const std::vector<AddressPtr> &outputs) const;
void LaunchLogicalNot(const std::vector<AddressPtr> &inputs, const std::vector<AddressPtr> &outputs);
TypeId dtype_{kTypeUnknown};
};

3
mindspore/ccsrc/backend/kernel_compiler/cpu/boundingbox_decode_cpu_kernel.cc
View File

@ -141,8 +141,7 @@ bool BoundingBoxDecodeCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr>
bboxes[right_y] = y2;
}
};
CPUKernelUtils::ParallelFor(task, elem_num);
ParallelLaunchAutoSearch(task, elem_num, this, &parallel_search_info_);
return true;
}
} // namespace kernel

2
mindspore/ccsrc/backend/kernel_compiler/cpu/boundingbox_encode_cpu_kernel.cc
View File

@ -113,7 +113,7 @@ bool BoundingBoxEncodeCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr>
deltas[right_y] = (dh - static_cast<T>(means_[H_INDEX])) / static_cast<T>(stds_[H_INDEX]);
}
};
CPUKernelUtils::ParallelFor(task, elem_num);
ParallelLaunchAutoSearch(task, elem_num, this, &parallel_search_info_);
return true;
}

6
mindspore/ccsrc/backend/kernel_compiler/cpu/cast_cpu_kernel.cc
View File

@ -30,13 +30,13 @@ constexpr size_t kCastOutputsNum = 1;
} // namespace
template <typename S, typename T>
void Cast(const S *in, T *out, size_t size) {
void Cast(CastCPUKernel<S, T> *content, const S *in, T *out, size_t size) {
auto task = [&in, &out](size_t start, size_t end) {
for (size_t i = start; i < end; i++) {
out[i] = static_cast<T>(in[i]);
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, content, &content->parallel_search_info_);
}
template <typename S, typename T>
@ -59,7 +59,7 @@ bool CastCPUKernel<S, T>::Launch(const std::vector<kernel::AddressPtr> &inputs,
const auto *input = reinterpret_cast<S *>(inputs[0]->addr);
auto *output = reinterpret_cast<T *>(outputs[0]->addr);
MS_LOG(DEBUG) << "Type source: " << typeid(S).name() << "; target: " << typeid(T).name();
Cast<S, T>(input, output, outputs[0]->size / sizeof(T));
Cast<S, T>(this, input, output, outputs[0]->size / sizeof(T));
return true;
}
} // namespace kernel

3
mindspore/ccsrc/backend/kernel_compiler/cpu/check_valid_cpu_kernel.cc
View File

@ -64,8 +64,7 @@ bool CheckValidCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &input
output[i] = !valid_flag;
}
};
CPUKernelUtils::ParallelFor(task, elem_num);
ParallelLaunchAutoSearch(task, elem_num, this, &parallel_search_info_);
return true;
}

3
mindspore/ccsrc/backend/kernel_compiler/cpu/cpu_kernel.h
View File

@ -141,12 +141,13 @@ class CPUKernel : public kernel::KernelMod {
void InitDynamicKernel(const CNodePtr &cnode_ptr) { dynamic_kernel_ = std::make_shared<CpuDynamicKernel>(cnode_ptr); }
device::DynamicKernelPtr DynamicKernel() const { return dynamic_kernel_; }
ParallelSearchInfo parallel_search_info_;
protected:
virtual void InitInputOutputSize(const CNodePtr &kernel_node);
std::vector<size_t> input_size_list_;
std::vector<size_t> output_size_list_;
std::vector<size_t> workspace_size_list_;
ParallelSearchInfo parallel_search_info_;
CNodeWeakPtr cnode_ptr_;
device::DynamicKernelPtr dynamic_kernel_;

2
mindspore/ccsrc/backend/kernel_compiler/cpu/crop_and_resize_cpu_kernel.cc
View File

@ -214,7 +214,7 @@ bool CropAndResizeCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &in
}
}
};
CPUKernelUtils::ParallelFor(task, IntToSize(output_size_));
ParallelLaunchAutoSearch(task, IntToSize(output_size_), this, &parallel_search_info_);
return true;
}
} // namespace kernel

29
mindspore/ccsrc/backend/kernel_compiler/cpu/cumsum_cpu_kernel.cc
View File

@ -225,35 +225,16 @@ void CumSumCPUKernel::LaunchCumSum(const T *input, T *output, T *workspace, size
template <typename T>
void CumSumCPUKernel::LaunchKernel(const std::vector<kernel::AddressPtr> &inputs,
const std::vector<kernel::AddressPtr> &workspace,
const std::vector<kernel::AddressPtr> &outputs) const {
const std::vector<kernel::AddressPtr> &outputs) {
const auto *input = reinterpret_cast<T *>(inputs[0]->addr);
auto *ws = reinterpret_cast<T *>(workspace[0]->addr);
auto output = reinterpret_cast<T *>(outputs[0]->addr);
// multithreading
size_t lens = inputs[0]->size > 0 ? static_cast<size_t>(inputs[0]->size / sizeof(T)) : 1;
auto max_thread_num = std::thread::hardware_concurrency();
size_t thread_num = lens < 128 * max_thread_num ? std::ceil(lens / 128.0) : max_thread_num;
MS_LOG(INFO) << "Lens=" << lens << "; use thread_num=" << thread_num << "; max_thread_num: " << max_thread_num;
std::vector<std::thread> threads;
threads.reserve(thread_num);
size_t start = 0;
if (thread_num < 1) {
MS_LOG(ERROR) << "Invalid value: thread_num " << thread_num;
return;
}
size_t once_compute_size = (lens + thread_num - 1) / thread_num;
if (once_compute_size < 1) {
MS_LOG(ERROR) << "Invalid value: once_compute_size " << once_compute_size;
return;
}
while (start < lens) {
size_t end = (start + once_compute_size) > lens ? lens : (start + once_compute_size);
(void)threads.emplace_back(std::thread(&CumSumCPUKernel::LaunchCumSum<T>, this, input, output, ws, start, end));
start += once_compute_size;
}
for (size_t i = 0; i < threads.size(); ++i) {
threads[i].join();
}
auto task = [this, &input, &output, &ws](size_t start, size_t end) {
LaunchCumSum<T>(input, output, ws, start, end);
};
ParallelLaunchAutoSearch(task, lens, this, &parallel_search_info_);
}
} // namespace kernel
} // namespace mindspore

2
mindspore/ccsrc/backend/kernel_compiler/cpu/cumsum_cpu_kernel.h
View File

@ -65,7 +65,7 @@ class CumSumCPUKernel : public CPUKernel {
template <typename T>
void LaunchKernel(const std::vector<AddressPtr> &inputs, const std::vector<AddressPtr> &workspace,
const std::vector<AddressPtr> &outputs) const;
const std::vector<AddressPtr> &outputs);
template <typename T>
void LaunchCumSum(const T *input_addr, T *output_addr, T *ws_addr, size_t start, size_t end) const;

2
mindspore/ccsrc/backend/kernel_compiler/cpu/depthtospace_cpu_kernel.cc
View File

@ -73,7 +73,7 @@ bool DepthToSpaceCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inp
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, this, &parallel_search_info_);
return true;
}
} // namespace kernel

5
mindspore/ccsrc/backend/kernel_compiler/cpu/elu_grad_cpu_kernel.cc
View File

@ -51,8 +51,7 @@ bool EluGradCPUKernel::Launch(const std::vector<kernel::AddressPtr> &inputs, con
}
template <typename T>
void EluGradCPUKernel::LaunchKernel(const std::vector<AddressPtr> &inputs,
const std::vector<AddressPtr> &outputs) const {
void EluGradCPUKernel::LaunchKernel(const std::vector<AddressPtr> &inputs, const std::vector<AddressPtr> &outputs) {
const auto *input0 = reinterpret_cast<T *>(inputs[0]->addr);
const auto *input1 = reinterpret_cast<T *>(inputs[1]->addr);
auto *output = reinterpret_cast<T *>(outputs[0]->addr);
@ -64,7 +63,7 @@ void EluGradCPUKernel::LaunchKernel(const std::vector<AddressPtr> &inputs,
output[i] = (input1[i] < static_cast<T>(0)) ? input0[i] * (input1[i] + alpha) : input0[i];
}
};
CPUKernelUtils::ParallelFor(task, lens);
ParallelLaunchAutoSearch(task, lens, this, &parallel_search_info_);
}
} // namespace kernel
} // namespace mindspore

2
mindspore/ccsrc/backend/kernel_compiler/cpu/elu_grad_cpu_kernel.h
View File

@ -34,7 +34,7 @@ class EluGradCPUKernel : public CPUKernel {
bool Launch(const std::vector<AddressPtr> &inputs, const std::vector<AddressPtr> &workspace,
const std::vector<AddressPtr> &outputs) override;
template <typename T>
void LaunchKernel(const std::vector<AddressPtr> &inputs, const std::vector<AddressPtr> &outputs) const;
void LaunchKernel(const std::vector<AddressPtr> &inputs, const std::vector<AddressPtr> &outputs);
private:
TypeId dtype_{kTypeUnknown};

2
mindspore/ccsrc/backend/kernel_compiler/cpu/hsigmoid_cpu_kernel.cc
View File

@ -59,7 +59,7 @@ bool HSigmoidCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inputs,
}
}
};
CPUKernelUtils::ParallelFor(task, tensor_size_);
ParallelLaunchAutoSearch(task, tensor_size_, this, &parallel_search_info_);
return true;
}
} // namespace kernel

2
mindspore/ccsrc/backend/kernel_compiler/cpu/hsigmoid_grad_cpu_kernel.cc
View File

@ -58,7 +58,7 @@ bool HSigmoidGradCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inp
}
}
};
CPUKernelUtils::ParallelFor(task, tensor_size_);
ParallelLaunchAutoSearch(task, tensor_size_, this, &parallel_search_info_);
return true;
}
} // namespace kernel

2
mindspore/ccsrc/backend/kernel_compiler/cpu/hswish_cpu_kernel.cc
View File

@ -57,7 +57,7 @@ bool HSwishCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inputs, c
}
}
};
CPUKernelUtils::ParallelFor(task, tensor_size_);
ParallelLaunchAutoSearch(task, tensor_size_, this, &parallel_search_info_);
return true;
}
} // namespace kernel

2
mindspore/ccsrc/backend/kernel_compiler/cpu/hswish_grad_cpu_kernel.cc
View File

@ -61,7 +61,7 @@ bool HSwishGradCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &input
}
}
};
CPUKernelUtils::ParallelFor(task, tensor_size_);
ParallelLaunchAutoSearch(task, tensor_size_, this, &parallel_search_info_);
return true;
}
} // namespace kernel

2
mindspore/ccsrc/backend/kernel_compiler/cpu/iou_cpu_kernel.cc
View File

@ -93,7 +93,7 @@ bool IOUCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inputs, cons
}
}
};
CPUKernelUtils::ParallelFor(task, iou_size_);
ParallelLaunchAutoSearch(task, iou_size_, this, &parallel_search_info_);
return true;
}
} // namespace kernel

4
mindspore/ccsrc/backend/kernel_compiler/cpu/l2_normalize_cpu_kernel.cc
View File

@ -90,7 +90,7 @@ void L2NormalizeCPUKernel<T>::CalcDenominator(const T *input_addr, const size_t
(*denominator_addr)[i] = sqrt(denominator);
}
};
CPUKernelUtils::ParallelFor(task, reduce_size);
ParallelLaunchAutoSearch(task, reduce_size, this, &parallel_search_info_);
}
template <typename T>
@ -120,7 +120,7 @@ void L2NormalizeCPUKernel<T>::CalcOutput(const T *input_addr, const std::vector<
iter.GenNextPos();
}
};
CPUKernelUtils::ParallelFor(task, output_size);
ParallelLaunchAutoSearch(task, output_size, this, &parallel_search_info_);
}
template <typename T>

2
mindspore/ccsrc/backend/kernel_compiler/cpu/l2normalize_grad_cpu_kernel.cc
View File

@ -65,7 +65,7 @@ bool L2NormalizeGradCPUKernel<T>::Launch(const std::vector<AddressPtr> &inputs,
GetOutput(input_x_vector, y_vector, dout_vector, high_dim_index, &output[i]);
}
};
CPUKernelUtils::ParallelFor(task, output_size);
ParallelLaunchAutoSearch(task, output_size, this, &parallel_search_info_);
return true;
}

4
mindspore/ccsrc/backend/kernel_compiler/cpu/mkldnn/addn_cpu_kernel.cc
View File

@ -86,11 +86,11 @@ bool AddNCPUKernel::Launch(const std::vector<kernel::AddressPtr> &inputs, const
const auto input_1 = reinterpret_cast<int *>(inputs[1]->addr);
auto output = reinterpret_cast<int *>(outputs[0]->addr);
auto task_0 = std::bind(AddInt, input_0, input_1, output, std::placeholders::_1, std::placeholders::_2);
CPUKernelUtils::ParallelFor(task_0, elements_num);
ParallelLaunchAutoSearch(task_0, elements_num, this, &parallel_search_info_);
for (size_t index = 2; index < input_num_; ++index) {
const auto input = reinterpret_cast<int *>(inputs[index]->addr);
auto task = std::bind(AddInt, input, output, output, std::placeholders::_1, std::placeholders::_2);
CPUKernelUtils::ParallelFor(task, elements_num);
ParallelLaunchAutoSearch(task, elements_num, this, &parallel_search_info_);
}
} else if (dtype_ == kNumberTypeFloat64) {
size_t elements_num = outputs[0]->size / sizeof(double);

14
mindspore/ccsrc/backend/kernel_compiler/cpu/nms_with_mask_cpu_kernel.cc
View File

@ -49,7 +49,7 @@ void NMSWithMaskCPUKernel<T>::NmsBitonicSortByKeyKernel(const int inner, const s
index_buff[i] = i;
}
};
CPUKernelUtils::ParallelFor(task1, ceil_power2);
ParallelLaunchAutoSearch(task1, ceil_power2, this, &parallel_search_info_);
for (size_t i = 2; i <= ceil_power2; i <<= 1) {
for (size_t j = (i >> 1); j > 0; j >>= 1) {
@ -71,7 +71,7 @@ void NMSWithMaskCPUKernel<T>::NmsBitonicSortByKeyKernel(const int inner, const s
}
}
};
CPUKernelUtils::ParallelFor(task2, ceil_power2);
ParallelLaunchAutoSearch(task2, ceil_power2, this, &parallel_search_info_);
}
}
}
@ -84,7 +84,7 @@ void NMSWithMaskCPUKernel<T>::MaskInit(size_t numSq, bool *row_mask) {
row_mask[mat_pos] = true;
}
};
CPUKernelUtils::ParallelFor(task, numSq);
ParallelLaunchAutoSearch(task, numSq, this, &parallel_search_info_);
}
// copy data from input to output array sorted by indices returned from bitonic sort
@ -122,7 +122,7 @@ void NMSWithMaskCPUKernel<T>::PopulateOutput(const T *data_in, T *data_out, cons
}
}
};
CPUKernelUtils::ParallelFor(task, IntToSize(num));
ParallelLaunchAutoSearch(task, IntToSize(num), this, &parallel_search_info_);
}
// populated return mask (init to all true) and return index array
@ -134,7 +134,7 @@ void NMSWithMaskCPUKernel<T>::Preprocess(const int num, int *sel_idx, bool *sel_
sel_boxes[box_num] = true;
}
};
CPUKernelUtils::ParallelFor(task, IntToSize(num));
ParallelLaunchAutoSearch(task, IntToSize(num), this, &parallel_search_info_);
}
template <typename T>
@ -175,7 +175,7 @@ void NMSWithMaskCPUKernel<T>::NmsPass(const int num, const float IOU_value, cons
}
}
};
CPUKernelUtils::ParallelFor(task, IntToSize(num * num));
ParallelLaunchAutoSearch(task, IntToSize(num * num), this, &parallel_search_info_);
}
// Reduce pass runs on 1 block to allow thread sync
@ -192,7 +192,7 @@ void NMSWithMaskCPUKernel<T>::ReducePass(const int num, bool *sel_boxes, const b
sel_boxes[j] = sel_boxes[j] && row_mask[i * num + j];
}
};
CPUKernelUtils::ParallelFor(task, IntToSize(num));
ParallelLaunchAutoSearch(task, IntToSize(num), this, &parallel_search_info_);
}
}

24
mindspore/ccsrc/backend/kernel_compiler/cpu/pack_cpu_kernel.cc
View File

@ -61,28 +61,8 @@ bool PackCpuFwdKernel<T>::Launch(const std::vector<AddressPtr> &inputs, const st
// multi-threading
size_t input_size = output_size_;
size_t max_thread_num = std::max(std::thread::hardware_concurrency(), static_cast<unsigned int>(1));
size_t use_thread_num =
input_size < 128 * max_thread_num ? std::ceil(static_cast<float>(input_size / 128.0)) : max_thread_num;
std::vector<std::thread> threads;
if (use_thread_num < 1) {
use_thread_num = 1;
}
threads.reserve(use_thread_num);
size_t start = 0;
size_t batch_size = (input_size + use_thread_num - 1) / use_thread_num;
while (start < input_size) {
size_t end = (start + batch_size) > input_size ? input_size : (start + batch_size);
(void)threads.emplace_back(std::thread(&PackCpuFwdKernel::PackTensor, this, output, start, end));
start += batch_size;
}
for (auto &it : threads) {
it.join();
}
auto task = [this, &output](size_t start, size_t end) { PackTensor(output, start, end); };
ParallelLaunchAutoSearch(task, input_size, this, &parallel_search_info_);
return true;
}

33
mindspore/ccsrc/backend/kernel_compiler/cpu/random_cpu_kernel.cc
View File

@ -34,35 +34,16 @@ void StandardNormal(float *output, std::normal_distribution<float> distribution,
}
}
void LaunchStandardNormal(unsigned int seed, const std::vector<AddressPtr> &outputs) {
void LaunchStandardNormal(RandomCPUKernel *content, unsigned int seed, const std::vector<AddressPtr> &outputs) {
auto output = reinterpret_cast<float *>(outputs[0]->addr);
// multithreading
size_t lens = outputs[0]->size / sizeof(float);
auto max_thread_num = std::thread::hardware_concurrency();
size_t thread_num = lens < 128 * max_thread_num ? std::ceil(lens / 128.0) : max_thread_num;
if (thread_num < 1) {
MS_LOG(ERROR) << "Invalid value: thread_num " << thread_num;
return;
}
std::vector<std::thread> threads;
threads.reserve(thread_num);
size_t start = 0;
size_t once_compute_size = (lens + thread_num - 1) / thread_num;
if (once_compute_size < 1) {
MS_LOG(ERROR) << "Invalid value: once_compute_size " << once_compute_size;
return;
}
std::normal_distribution<float> distribution;
while (start < lens) {
// avoid different threads using the same seed to generate the same random number
auto task = [&seed, &output](size_t start, size_t end) {
std::normal_distribution<float> distribution;
std::default_random_engine random_generator(++seed);
size_t end = (start + once_compute_size) > lens ? lens : (start + once_compute_size);
(void)threads.emplace_back(std::thread(StandardNormal, output, distribution, random_generator, start, end));
start += once_compute_size;
}
for (size_t i = 0; i < threads.size(); ++i) {
threads[i].join();
}
StandardNormal(output, distribution, random_generator, start, end);
};
ParallelLaunchAutoSearch(task, lens, content, &content->parallel_search_info_);
}
void LaunchUniformInt(unsigned int seed, const std::vector<AddressPtr> &inputs,
@ -138,7 +119,7 @@ bool RandomCPUKernel::Launch(const std::vector<kernel::AddressPtr> &inputs, cons
if (random_op_type_ == RANDOM_OP_NORMAL) {
CHECK_KERNEL_OUTPUTS_NUM(outputs.size(), kStandardNormalOutputsNum, kernel_name_);
LaunchStandardNormal(RNG_seed, outputs);
LaunchStandardNormal(this, RNG_seed, outputs);
} else if (random_op_type_ == RANDOM_OP_UNIFORM_INT) {
CHECK_KERNEL_INPUTS_NUM(inputs.size(), kUniformIntInputsNum, kernel_name_);
CHECK_KERNEL_OUTPUTS_NUM(outputs.size(), kUniformIntOutputsNum, kernel_name_);

4
mindspore/ccsrc/backend/kernel_compiler/cpu/reduce_cpu_kernel.cc
View File

@ -176,7 +176,7 @@ bool ReduceCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inputs, c
}
}
};
CPUKernelUtils::ParallelFor(task, output_size);
ParallelLaunchAutoSearch(task, output_size, this, &parallel_search_info_);
}
return true;
}
@ -204,7 +204,7 @@ void ReduceCPUKernel<T>::AccelerateLongVector(T *input_addr, T *output_addr, siz
reduce_func_(&block_output, 0, output_addr);
}
};
CPUKernelUtils::ParallelFor(task, input_size);
ParallelLaunchAutoSearch(task, input_size, this, &parallel_search_info_);
if (reduce_type_ == kReduceMean) {
*output_addr /= input_size;
}

2
mindspore/ccsrc/backend/kernel_compiler/cpu/rl/buffer_append_cpu_kernel.h
View File

@ -88,7 +88,7 @@ class BufferCPUAppendKernel : public CPUKernel {
}
}
};
CPUKernelUtils::ParallelFor(task, element_nums_);
ParallelLaunchAutoSearch(task, element_nums_, this, &parallel_search_info_);
return true;
}

2
mindspore/ccsrc/backend/kernel_compiler/cpu/rl/buffer_get_cpu_kernel.h
View File

@ -77,7 +77,7 @@ class BufferCPUGetKernel : public CPUKernel {
}
}
};
CPUKernelUtils::ParallelFor(task, element_nums_);
ParallelLaunchAutoSearch(task, element_nums_, this, &parallel_search_info_);
return true;
}

2
mindspore/ccsrc/backend/kernel_compiler/cpu/rl/buffer_sample_cpu_kernel.h
View File

@ -104,7 +104,7 @@ class BufferCPUSampleKernel : public CPUKernel {
}
}
};
CPUKernelUtils::ParallelFor(task, batch_size_);
ParallelLaunchAutoSearch(task, batch_size_, this, &parallel_search_info_);
return true;
}

4
mindspore/ccsrc/backend/kernel_compiler/cpu/rmsprop_cpu_kernel.cc
View File

@ -44,7 +44,7 @@ void RMSPropCPUKernel<T>::LaunchRMSPropUnuseCenter(T *variable, T *mean_square,
}
};
}
CPUKernelUtils::ParallelFor(task, size_);
ParallelLaunchAutoSearch(task, size_, this, &parallel_search_info_);
}
template <typename T>
@ -70,7 +70,7 @@ void RMSPropCPUKernel<T>::LaunchRMSPropUseCenter(T *variable, T *mean_square, T
}
};
}
CPUKernelUtils::ParallelFor(task, size_);
ParallelLaunchAutoSearch(task, size_, this, &parallel_search_info_);
}
template <typename T>

3
mindspore/ccsrc/backend/kernel_compiler/cpu/roi_align_cpu_kernel.cc
View File

@ -109,8 +109,7 @@ bool ROIAlignCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inputs,
out_data[thread_idx] = accumulate_val;
}
};
CPUKernelUtils::ParallelFor(task, elem_num);
ParallelLaunchAutoSearch(task, elem_num, this, &parallel_search_info_);
return true;
}

4
mindspore/ccsrc/backend/kernel_compiler/cpu/roi_align_grad_cpu_kernel.cc
View File

@ -117,7 +117,7 @@ bool ROIAlignGradCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inp
dx[thread_idx] = ZERO;
}
};
CPUKernelUtils::ParallelFor(task1, IntToSize(size_init));
ParallelLaunchAutoSearch(task1, IntToSize(size_init), this, &parallel_search_info_);
int elem_num = roi_rows_ * channels_ * pooled_height_ * pooled_width_;
auto task2 = [this, &dy, &rois, &dx](size_t start, size_t end) {
@ -176,7 +176,7 @@ bool ROIAlignGradCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inp
}
}
};
CPUKernelUtils::ParallelFor(task2, IntToSize(elem_num));
ParallelLaunchAutoSearch(task2, IntToSize(elem_num), this, &parallel_search_info_);
return true;
}

9
mindspore/ccsrc/backend/kernel_compiler/cpu/scatter_nd_cpu_kernel.cc
View File

@ -27,7 +27,8 @@ constexpr size_t kScatterNdOutputSize = 1;
constexpr size_t kMinIndiceRank = 2;
template <typename S, typename T>
void Compute(const ComputeParams<S, T> *params, const size_t start, const size_t end) {
void Compute(ScatterNdCPUKernel<S, T> *content, const ComputeParams<S, T> *params, const size_t start,
const size_t end) {
T *target = params->target_;
S *indices = params->indices_;
T *updates = params->updates_;
@ -47,7 +48,7 @@ void Compute(const ComputeParams<S, T> *params, const size_t start, const size_t
target[IntToSize(offset) + idx] += updates[IntToSize(params->unit_size_) * i + idx];
}
};
CPUKernelUtils::ParallelFor(task, IntToSize(params->unit_size_));
ParallelLaunchAutoSearch(task, IntToSize(params->unit_size_), content, &content->parallel_search_info_);
}
}
} // namespace
@ -113,10 +114,10 @@ bool ScatterNdCPUKernel<S, T>::Launch(const std::vector<kernel::AddressPtr> &inp
auto task = [this, &params](size_t start, size_t end) {
for (size_t idx = start; idx < end; idx++) {
Compute<S, T>(&params, idx, idx + 1);
Compute<S, T>(this, &params, idx, idx + 1);
}
};
CPUKernelUtils::ParallelFor(task, num_units_);
ParallelLaunchAutoSearch(task, num_units_, this, &parallel_search_info_);
return true;
}

4
mindspore/ccsrc/backend/kernel_compiler/cpu/searchsorted_cpu_kernel.cc
View File

@ -70,7 +70,7 @@ bool SearchSortedCPUKernel<S, T>::Launch(const std::vector<kernel::AddressPtr> &
output[i] = static_cast<T>(result);
}
};
CPUKernelUtils::ParallelFor(task, elem_num);
ParallelLaunchAutoSearch(task, elem_num, this, &parallel_search_info_);
return true;
}
@ -96,7 +96,7 @@ void SearchSortedCPUKernel<S, T>::CheckParam(const std::vector<AddressPtr> &inpu
}
}
};
CPUKernelUtils::ParallelFor(task, IntToSize(list_count));
ParallelLaunchAutoSearch(task, IntToSize(list_count), this, &parallel_search_info_);
}
} // namespace kernel
} // namespace mindspore

2
mindspore/ccsrc/backend/kernel_compiler/cpu/sgd_cpu_kernel.cc
View File

@ -72,7 +72,7 @@ bool SGDCPUKernel<T>::Launch(const std::vector<AddressPtr> &inputs, const std::v
output_param[i] = param[i];
}
};
CPUKernelUtils::ParallelFor(task, elem_num);
ParallelLaunchAutoSearch(task, elem_num, this, &parallel_search_info_);
return true;
}
} // namespace kernel

2
mindspore/ccsrc/backend/kernel_compiler/cpu/smooth_l1_loss_cpu_kernel.cc
View File

@ -63,7 +63,7 @@ bool SmoothL1LossCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inp
}
}
};
CPUKernelUtils::ParallelFor(task, tensor_size_);
ParallelLaunchAutoSearch(task, tensor_size_, this, &parallel_search_info_);
return true;
}
} // namespace kernel

2
mindspore/ccsrc/backend/kernel_compiler/cpu/spacetodepth_cpu_kernel.cc
View File

@ -84,7 +84,7 @@ bool SpaceToDepthCPUKernel<T>::Launch(const std::vector<kernel::AddressPtr> &inp
}
};
CPUKernelUtils::ParallelFor(task, size);
ParallelLaunchAutoSearch(task, size, this, &parallel_search_info_);
return true;
}
} // namespace kernel

19
mindspore/ccsrc/runtime/framework/actor/actor_common.cc
View File

@ -23,23 +23,22 @@ namespace runtime {
void ComputeThreadNums(size_t *actor_thread_num, size_t *actor_and_kernel_thread_num) {
MS_EXCEPTION_IF_NULL(actor_thread_num);
MS_EXCEPTION_IF_NULL(actor_and_kernel_thread_num);
size_t cpu_core_num = std::thread::hardware_concurrency() - 1;
// Compute the actor thread num.
const size_t kActorThreadMaxNum = 5;
const size_t cpu_core_num = std::thread::hardware_concurrency() - 1;
// The MemoryManagerActor binds single thread, and the other actors share one thread at least, so the min num is 2.
const size_t kActorThreadMinNum = 2;
// Compute the actor thread num.
const size_t kActorThreadMaxNum = 5;
// a machine may run multiple process, a process should not use all CPUs. default run 5 process in the same time.
const size_t kParallelNum = 5;
const size_t kThreadMaxNum = cpu_core_num / kParallelNum;
auto context_ptr = MsContext::GetInstance();
MS_EXCEPTION_IF_NULL(context_ptr);
*actor_thread_num = cpu_core_num < kActorThreadMinNum ? kActorThreadMinNum : cpu_core_num;
*actor_thread_num = *actor_thread_num > kActorThreadMaxNum ? kActorThreadMaxNum : *actor_thread_num;
// Compute the actor and kernel thread num.
const size_t kActorAndKernelThreadMaxNum = 23;
*actor_and_kernel_thread_num = cpu_core_num > *actor_thread_num ? cpu_core_num : (*actor_thread_num + 1);
*actor_and_kernel_thread_num = *actor_and_kernel_thread_num > kActorAndKernelThreadMaxNum
? kActorAndKernelThreadMaxNum
: *actor_and_kernel_thread_num;
// Compute the actor and kernel thread num. 1 thread is useless for kernel, so kernel thread num should at least 2.
*actor_and_kernel_thread_num = kThreadMaxNum > (*actor_thread_num + 2) ? kThreadMaxNum : (*actor_thread_num + 2);
}
bool IsDeviceQueueDSActor(const AnfNodePtr &node, GraphExecutionStrategy strategy) {