petites modifs

diff --git a/prng_gpu.tex b/prng_gpu.tex
index 23fc7769d9be3949932bfdcb8a2fb8856d42abe6..d95e87f0e69d9d47dab61d8e1e8cb708628cf177 100644 (file)
--- a/prng_gpu.tex
+++ b/prng_gpu.tex
@@ -906,17 +906,15 @@ tab1, tab2: Arrays containing permutations of size permutation\_size\;}
 
 \KwOut{NewNb: array containing random numbers in global memory}
 \If{threadId is concerned} {
 
 \KwOut{NewNb: array containing random numbers in global memory}
 \If{threadId is concerned} {

-  retrieve data from InternalVarXorLikeArray[threadId] in local variables\;
+  retrieve data from InternalVarXorLikeArray[threadId] in local variables including shared memory\;

   offset = threadIdx\%permutation\_size\;
   o1 = threadIdx-offset+tab1[offset]\;
   o2 = threadIdx-offset+tab2[offset]\;
   \For{i=1 to n} {
     t=xor-like()\;
   offset = threadIdx\%permutation\_size\;
   o1 = threadIdx-offset+tab1[offset]\;
   o2 = threadIdx-offset+tab2[offset]\;
   \For{i=1 to n} {
     t=xor-like()\;

-    shared\_mem[threadId]=(unsigned int)t\;
-    x = x $\oplus$ (unsigned int) t\;
-    x = x $\oplus$ (unsigned int) (t>>32)\;
-    x = x $\oplus$ shared[o1]\;
-    x = x $\oplus$ shared[o2]\;
+    t=t$\oplus$shmem[o1]$\oplus$shmem[o2]\;
+    shared\_mem[threadId]=t\;
+    x = x $\oplus$ t\;

 
     store the new PRNG in NewNb[NumThreads*threadId+i]\;
   }
 
     store the new PRNG in NewNb[NumThreads*threadId+i]\;
   }


@@ -930,9 +928,9 @@ version}
 
 \subsection{Theoretical Evaluation of the Improved Version}
 
 
 \subsection{Theoretical Evaluation of the Improved Version}
 

-A run of Algorithm~\ref{algo:gpu_kernel2} consists in four operations having 
+A run of Algorithm~\ref{algo:gpu_kernel2} consists in three operations having 

 the form of Equation~\ref{equation Oplus}, which is equivalent to the iterative
 the form of Equation~\ref{equation Oplus}, which is equivalent to the iterative

-system of Eq.~\ref{eq:generalIC}. That is, four iterations of the general chaotic
+system of Eq.~\ref{eq:generalIC}. That is, three iterations of the general chaotic

 iterations are realized between two stored values of the PRNG.
 To be certain that we are in the framework of Theorem~\ref{t:chaos des general},
 we must guarantee that this dynamical system iterates on the space 
 iterations are realized between two stored values of the PRNG.
 To be certain that we are in the framework of Theorem~\ref{t:chaos des general},
 we must guarantee that this dynamical system iterates on the space 


@@ -961,14 +959,15 @@ another one  equipped with  a less performant  CPU and  a GeForce GTX  280. Both
 cards have 240 cores.
 
 In Figure~\ref{fig:time_gpu}  we compare the number of  random numbers generated
 cards have 240 cores.
 
 In Figure~\ref{fig:time_gpu}  we compare the number of  random numbers generated

-per second.  In order to obtain the optimal performance we remove the storage of
-random numbers  in the GPU memory. This  step is time consumming  and slows down
-the random number  generation.  Moreover, if you are  interested by applications
-that consome random  numbers directly when they are  generated, their storage is
-completely useless. In this figure we can see that when the number of threads is
-greater than approximately  30,000 upto 5 millions the  number of random numbers
-generated per second is almost constant.   With the naive version, it is between
-2.5 and 3GSample/s.   With the optimized version, it  is approximately equals to
+per second. The xor-like prng  is a xor64 described in~\cite{Marsaglia2003}.  In
+order to obtain the optimal performance  we remove the storage of random numbers
+in the GPU memory. This step is time consumming and slows down the random number
+generation.  Moreover, if you are interested by applications that consome random
+numbers  directly   when  they  are  generated,  their   storage  is  completely
+useless. In this  figure we can see  that when the number of  threads is greater
+than approximately 30,000 upto 5 millions the number of random numbers generated
+per second  is almost constant.  With the  naive version, it is  between 2.5 and
+3GSample/s.   With  the  optimized   version,  it  is  approximately  equals  to

 20GSample/s. Finally  we can remark  that both GPU  cards are quite  similar. In
 practice,  the Tesla C1060  has more  memory than  the GTX  280 and  this memory
 should be of better quality.
 20GSample/s. Finally  we can remark  that both GPU  cards are quite  similar. In
 practice,  the Tesla C1060  has more  memory than  the GTX  280 and  this memory
 should be of better quality.