ForwardProgram is :
{
 (%0) = "pd_op.data" () {dtype:(pd_op.DataType)float32,name:"_jst.0.x.0",place:(pd_op.Place)Place(undefined:0),shape:(pd_op.IntArray)[64,128],stop_gradient:[false]} : () -> pd_op.tensor<64x128xf32>
 (%1) = "pd_op.exp" (%0) {stop_gradient:[false]} : (pd_op.tensor<64x128xf32>) -> pd_op.tensor<64x128xf32>
 (%2) = "pd_op.subtract" (%1, %0) {stop_gradient:[false]} : (pd_op.tensor<64x128xf32>, pd_op.tensor<64x128xf32>) -> pd_op.tensor<64x128xf32>
 () = "builtin.set_parameter" (%2) {parameter_name:"output_0"} : (pd_op.tensor<64x128xf32>) -> 
}

{
 (%0) = "pd_op.data" () {dtype:(pd_op.DataType)float32,name:"_jst.0.x.0",place:(pd_op.Place)Place(undefined:0),shape:(pd_op.IntArray)[64,128],stop_gradient:[false]} : () -> pd_op.tensor<64x128xf32>
 (%1) = "cinn_runtime.jit_kernel" (%0) {jit_info:(0x46aa1f90)} : (pd_op.tensor<64x128xf32>) -> pd_op.tensor<64x128xf32>
 () = "builtin.set_parameter" (%1) {parameter_name:"output_0"} : (pd_op.tensor<64x128xf32>) -> 
}

{
 (%0) = "data(phi_kernel)" () {dtype:(pd_op.DataType)float32,kernel_key:<backend:Undefined|layout:Undefined(AnyLayout)|dtype:float32>,kernel_name:"data",name:"_jst.0.x.0",op_name:"pd_op.data",place:(pd_op.Place)Place(undefined:0),shape:(pd_op.IntArray)[64,128],stop_gradient:[false]} : () -> undefined_tensor<64x128xf32>
 (%1) = "shadow_feed(phi_kernel)" (%0) {kernel_key:<backend:GPU|layout:Undefined(AnyLayout)|dtype:float32>,kernel_name:"shadow_feed",op_name:"pd_op.shadow_feed"} : (undefined_tensor<64x128xf32>) -> gpu_tensor<64x128xf32>
 (%2) = "cinn_runtime.jit_kernel" (%1) {jit_info:(0x46aa1f90)} : (gpu_tensor<64x128xf32>) -> gpu_tensor<64x128xf32>
 () = "(phi_kernel)" (%2) {kernel_key:<backend:GPUDNN|layout:Undefined(AnyLayout)|dtype:float32>,kernel_name:"",op_name:"builtin.set_parameter",parameter_name:"output_0"} : (gpu_tensor<64x128xf32>) -> 
}