front&excuter:sqrt,pow,powscalar,log,exp

Author: miaobyte

doc/excuter/op-mem-cuda/list.md

@@ -5,11 +5,15 @@
 | Operation | Author | Func Def | Math Formula | IR Instruction |
 |-----------|--------|------------|--------------|----------------|
 | matmul | cublas | matmul(tensor<any> A, tensor<any> B)->(tensor<any> C) | T3=T1 @ T2 | matmul(tensor<any> A, tensor<any> B)->(tensor<any> C) |
+| exp | miaobyte | exp(tensor<any> A)->(tensor<any> C) | T3=exp(T1) | exp(tensor<any> A)->(tensor<any> C) |
+| pow | miaobyte | pow(tensor<any> A, tensor<any> B)->(tensor<any> C) | T3=pow(T1, T2) | pow(tensor<any> A, tensor<any> B)->(tensor<any> C) |
+| powscalar | miaobyte | powscalar(tensor<any> A, var<any> scalar)->(tensor<any> C) | T3=pow(T1, scalar) | powscalar(tensor<any> A, var<any> scalar)->(tensor<any> C) |
 | rdivscalar | miaobyte | rdivscalar(var<any> scalar, tensor<any> A)->(tensor<any> C) | T3=scalar/T1 | rdivscalar(var<any> scalar, tensor<any> A)->(tensor<any> C) |
 | div | miaobyte | div(tensor<any> A, tensor<any> B)->(tensor<any> C) | T3=T1/T2 | div(tensor<any> A, tensor<any> B)->(tensor<any> C) |
 | sub | miaobyte | sub(tensor<any> A, tensor<any> B)->(tensor<any> C) | T3=T1-T2 | sub(tensor<any> A, tensor<any> B)->(tensor<any> C) |
 | argset |  none  | argset(var<any> value)->(var<any> name) | var argname = argvalue | argset(var<any> value)->(var<any> name) |
 | mulscalar | miaobyte | mulscalar(tensor<any> A, var<any> b)->(tensor<any> C) | T3=T1*scalar | mulscalar(tensor<any> A, var<any> b)->(tensor<any> C) |
+| sqrt | miaobyte | sqrt(tensor<any> A)->(tensor<any> C) | T3=sqrt(T1) | sqrt(tensor<any> A)->(tensor<any> C) |
 | vecset |  none  | vecset(vector<any> value)->(vector<any> name) | shape = [3  4  5] | vecset(vector<any> value)->(vector<any> name) |
 | newtensor |  none  | newtensor(vector<int32> shape)->(tensor<any> tensor1) | T1 = zeros(shape) | newtensor(vector<int32> shape)->(tensor<any> tensor1) |
 | newtensor |  none  | newtensor(var<string> shape)->(tensor<any> tensor1) | T1 = zeros(shape) | newtensor(var<string> shape)->(tensor<any> tensor1) |
@@ -19,6 +23,7 @@
 | constant | miaobyte | constant(tensor<any> t, var<any> value)->() | constant(T1) | constant(tensor<any> t, var<any> value)->() |
 | arange | miaobyte | arange(tensor<any> t, var<any> start, var<any> step)->() | arange(T1,start,step) | arange(tensor<any> t, var<any> start, var<any> step)->() |
 | subscalar | miaobyte | subscalar(tensor<any> A, var<any> b)->(tensor<any> C) | T3=T1-scalar | subscalar(tensor<any> A, var<any> b)->(tensor<any> C) |
+| log | miaobyte | log(tensor<any> A)->(tensor<any> C) | T3=log(T1) | log(tensor<any> A)->(tensor<any> C) |
 | uniform | miaobyte | uniform(tensor<any> t, var<any> low, var<any> high, var<int32> seed)->() | uniform(T1,low,high,seed) | uniform(tensor<any> t, var<any> low, var<any> high, var<int32> seed)->() |
 | add | cublas | add(tensor<any> a, tensor<any> b)->(tensor<any> c) | T3=T1+T2 | add(tensor<any> a, tensor<any> b)->(tensor<any> c) |
 | add | miaobyte | add(tensor<any> a, tensor<any> b)->(tensor<any> c) | T3=T1+T2 | add(tensor<any> a, tensor<any> b)->(tensor<any> c) |

doc/excuter/op-mem-ompsimd/list.md

@@ -7,11 +7,15 @@
 | concat |  none  | concat()->() | Tresult = concat([T1, T2...], axis=3) | concat()->() |
 | matmul | cblas | matmul(tensor<float64|float32> A, tensor<float64|float32> B)->(tensor<float64|float32> C) | T3=T1 @ T2 | matmul(tensor<float64|float32> A, tensor<float64|float32> B)->(tensor<float64|float32> C) |
 | matmul | miaobyte | matmul(tensor<any> A, tensor<any> B)->(tensor<any> C) | T3=T1 @ T2 | matmul(tensor<any> A, tensor<any> B)->(tensor<any> C) |
+| exp | miaobyte | exp(tensor<any> A)->(tensor<any> C) | T3=exp(T1) | exp(tensor<any> A)->(tensor<any> C) |
+| pow | miaobyte | pow(tensor<any> A, tensor<any> B)->(tensor<any> C) | T3=T1^T2 | pow(tensor<any> A, tensor<any> B)->(tensor<any> C) |
+| powscalar | miaobyte | powscalar(tensor<any> A, var<any> scalar)->(tensor<any> C) | T3=T1^scalar | powscalar(tensor<any> A, var<any> scalar)->(tensor<any> C) |
 | rdivscalar | miaobyte | rdivscalar(var<any> scalar, tensor<any> A)->(tensor<any> C) | T3=scalar/T1 | rdivscalar(var<any> scalar, tensor<any> A)->(tensor<any> C) |
 | div | miaobyte | div(tensor<any> A, tensor<any> B)->(tensor<any> C) | T3=T1/T2 | div(tensor<any> A, tensor<any> B)->(tensor<any> C) |
 | sub | miaobyte | sub(tensor<any> a, tensor<any> b)->(tensor<any> c) | T3=T1-T2 | sub(tensor<any> a, tensor<any> b)->(tensor<any> c) |
 | argset |  none  | argset(var<any> value)->(var<any> name) | var argname = argvalue | argset(var<any> value)->(var<any> name) |
 | mulscalar | miaobyte | mulscalar(tensor<any> A, var<any> b)->(tensor<any> C) | T3=T1*scalar | mulscalar(tensor<any> A, var<any> b)->(tensor<any> C) |
+| sqrt | miaobyte | sqrt(tensor<any> A)->(tensor<any> C) | T3=sqrt(T1) | sqrt(tensor<any> A)->(tensor<any> C) |
 | vecset |  none  | vecset(vector<any> value)->(vector<any> name) | shape = [3  4  5] | vecset(vector<any> value)->(vector<any> name) |
 | newtensor |  none  | newtensor(vector<int32> shape)->(tensor<any> tensor1) | T1 =Tensor(shape=[...]) | newtensor(vector<int32> shape)->(tensor<any> tensor1) |
 | newtensor |  none  | newtensor(var<string> shape)->(tensor<any> tensor1) | T1 =Tensor(shape=[...]) | newtensor(var<string> shape)->(tensor<any> tensor1) |
@@ -21,6 +25,7 @@
 | constant | miaobyte | constant(tensor<any> t, var<any> value)->() | constant(T1,value) | constant(tensor<any> t, var<any> value)->() |
 | arange | miaobyte | arange(tensor<any> t, var<any> start, var<any> step)->() | arange(T1,start,step) | arange(tensor<any> t, var<any> start, var<any> step)->() |
 | subscalar | miaobyte | subscalar(tensor<any> a, var<any> scalar)->(tensor<any> c) | T3=T1-scalar | subscalar(tensor<any> a, var<any> scalar)->(tensor<any> c) |
+| log | miaobyte | log(tensor<any> A)->(tensor<any> C) | T3=log(T1) | log(tensor<any> A)->(tensor<any> C) |
 | uniform | miaobyte | uniform(tensor<any> t, var<any> low, var<any> high, var<int32> seed)->() | uniform(T1,low,high,seed) | uniform(tensor<any> t, var<any> low, var<any> high, var<int32> seed)->() |
 | add | cblas | add(tensor<float64|float32> a, tensor<float64|float32> b)->(tensor<float64|float32> c) | T3=T1+T2 | add(tensor<float64|float32> a, tensor<float64|float32> b)->(tensor<float64|float32> c) |
 | add | miaobyte | add(tensor<any> a, tensor<any> b)->(tensor<any> c) | T3=T1+T2 | add(tensor<any> a, tensor<any> b)->(tensor<any> c) |

excuter/cpp-common/src/deepx/tensorfunc/elementwise.hpp

@@ -195,7 +195,7 @@ namespace deepx::tensorfunc
         divaddbetaDispatcher<Author, T>::divaddbeta(A, B, alpha, C, beta, D);
     }
 
-    template <typename Author, typename T>
+    template <typename Author, typename T,typename = void>
     struct sqrtDispatcher
     {
         static void sqrt(const Tensor<T> &input, Tensor<T> &output) = delete;