correct ch18

[book_gpu.git] / BookGPU / Chapters / chapter11 / code4.cu

diff --git a/BookGPU/Chapters/chapter11/code4.cu b/BookGPU/Chapters/chapter11/code4.cu
index 6eb646d78094667b6d227474d26923f41b4afa3a..2a091d369708782b1fc85c742e06253628d9323b 100644 (file)
--- a/BookGPU/Chapters/chapter11/code4.cu
+++ b/BookGPU/Chapters/chapter11/code4.cu
@@ -1,9 +1,11 @@
 template<typename Tx>   
 template<typename Tx>   

-__device__ Tx Aver(Tx z,int i,int j, Tx *z) {return (z-z[j+1])/(j-i+1);}
+__device__ Tx Aver(Tx z,int i,int j, Tx *z) 
+         { return (z-z[j+1])/(j-i+1); }

 
 template<typename Tx>
 __global__ void monotonizekernel(Tx *y, Tx *z, Tx *u, int *key, int n)  
 
 template<typename Tx>
 __global__ void monotonizekernel(Tx *y, Tx *z, Tx *u, int *key, int n)  

-{ int i = threadIdx.x + blockIdx.x * blockDim.x;
+{ 
+   int i = threadIdx.x + blockIdx.x * blockDim.x;

    if(i<n) {
       int smallestJ = i;
       Tx curP, smallestP, curz=z[i];
    if(i<n) {
       int smallestJ = i;
       Tx curP, smallestP, curz=z[i];


@@ -26,7 +28,8 @@ __global__ void monotonizekernel(Tx *y, Tx *z, Tx *u, int *key, int n)
 }
 
 template< typename Tx >
 }
 
 template< typename Tx >

-void MonotonizeData(Tx *y, int n, Tx *u) {
+void MonotonizeData(Tx *y, int n, Tx *u) 
+{

     thrust::less_equal<int> binary_pred;
     thrust::maximum<Tx>     binary_op2;
     thrust::device_vector<Tx> z_d(n+1);
     thrust::less_equal<int> binary_pred;
     thrust::maximum<Tx>     binary_op2;
     thrust::device_vector<Tx> z_d(n+1);


@@ -35,9 +38,9 @@ void MonotonizeData(Tx *y, int n, Tx *u) {
     thrust::fill(u_d, u_d+n, -1e100);
     thrust::fill(keys_d.begin(), keys_d.end(), 0);
 
     thrust::fill(u_d, u_d+n, -1e100);
     thrust::fill(keys_d.begin(), keys_d.end(), 0);
 

-    thrust::reverse_iterator< typename thrust::device_vector<Tx>::iterator >  y_reverse_b(y_d+n), y_reverse_end(y_d), z_reverse_b(z_d.end());
+    thrust::reverse_iterator< typename thrust::device_vector<Tx>::iterator>  y_reverse_b(y_d+n), y_reverse_end(y_d), z_reverse_b(z_d.end());

        
        

-    thrust::inclusive_scan(y_reverse_b, y_reverse_end, z_reverse_b+1);
+    thrust::inclusive_scan(y_reverse_b,y_reverse_end,z_reverse_b+1);

 
     monotonizekernel<<<grid, block>>>(y, thrust::raw_pointer_cast(&z_d[0]), u, thrust::raw_pointer_cast(&keys_d[0]), n );
 
 
     monotonizekernel<<<grid, block>>>(y, thrust::raw_pointer_cast(&z_d[0]), u, thrust::raw_pointer_cast(&keys_d[0]), n );