petites modifs

diff --git a/prng_gpu.tex b/prng_gpu.tex
index f21f19e817e2590d6e96c48bf88b3257b4c37b8c..c646316ef6549811294655cd3dbb38366f54663f 100644 (file)
--- a/prng_gpu.tex
+++ b/prng_gpu.tex
@@ -877,18 +877,18 @@ unsigned int CIPRNG() {
 
 
 
 
 
 

-In Listing~\ref{algo:seqCIPRNG}  a sequential version of  the proposed PRNG based on chaotic iterations
- is  presented.  The xor operator is  represented by \textasciicircum.
-This  function uses  three classical  64-bits PRNGs, namely the  \texttt{xorshift}, the
-\texttt{xor128},  and  the  \texttt{xorwow}~\cite{Marsaglia2003}.   In  the following,  we  call  them
-``xor-like PRNGs''. 
-As
-each xor-like PRNG  uses 64-bits whereas our proposed generator works with 32-bits,
-we use the command \texttt{(unsigned int)}, that selects the 32 least significant bits of a given integer, and the code
-\texttt{(unsigned int)(t3$>>$32)}  in order to obtain the 32 most significant  bits of \texttt{t}.   
-
-So producing a  pseudorandom number needs  6 xor operations
-with 6 32-bits  numbers that are provided by 3 64-bits PRNGs.   This version successfully passes the
+In Listing~\ref{algo:seqCIPRNG} a sequential  version of the proposed PRNG based
+on  chaotic  iterations  is  presented.   The xor  operator  is  represented  by
+\textasciicircum.  This function uses  three classical 64-bits PRNGs, namely the
+\texttt{xorshift},         the          \texttt{xor128},         and         the
+\texttt{xorwow}~\cite{Marsaglia2003}.  In the following, we call them ``xor-like
+PRNGs''.   As each  xor-like PRNG  uses 64-bits  whereas our  proposed generator
+works with 32-bits, we use the command \texttt{(unsigned int)}, that selects the
+32 least  significant bits  of a given  integer, and the  code \texttt{(unsigned
+  int)(t$>>$32)} in order to obtain the 32 most significant bits of \texttt{t}.
+
+So producing a pseudorandom number needs 6 xor operations with 6 32-bits numbers
+that  are provided by  3 64-bits  PRNGs.  This  version successfully  passes the

 stringent BigCrush battery of tests~\cite{LEcuyerS07}.
 
 \section{Efficient PRNGs based on Chaotic Iterations on GPU}
 stringent BigCrush battery of tests~\cite{LEcuyerS07}.
 
 \section{Efficient PRNGs based on Chaotic Iterations on GPU}


@@ -982,12 +982,14 @@ thread uses the result of which other  one, we can use a combination array that
 contains  the indexes  of  all threads  and  for which  a combination has  been
 performed. 
 
 contains  the indexes  of  all threads  and  for which  a combination has  been
 performed. 
 

-In Algorithm~\ref{algo:gpu_kernel2}, two combination arrays are used.
-The    variable   \texttt{offset}    is    computed   using    the   value    of
+In  Algorithm~\ref{algo:gpu_kernel2},  two  combination  arrays are  used.   The
+variable     \texttt{offset}    is     computed    using     the     value    of

 \texttt{combination\_size}.   Then we  can compute  \texttt{o1}  and \texttt{o2}
 \texttt{combination\_size}.   Then we  can compute  \texttt{o1}  and \texttt{o2}

-representing the indexes of the  other threads whose results are used
-by the  current one. In  this algorithm, we  consider that a  64-bits xor-like
-PRNG has been chosen, and so its two 32-bits parts are used.
+representing the  indexes of  the other  threads whose results  are used  by the
+current one.   In this algorithm, we  consider that a 32-bits  xor-like PRNG has
+been chosen. In practice, we  use the xor128 proposed in~\cite{Marsaglia2003} in
+which  unsigned longs  (64 bits)  have been  replaced by  unsigned  integers (32
+bits).

 
 This version also can pass the whole {\it BigCrush} battery of tests.
 
 
 This version also can pass the whole {\it BigCrush} battery of tests.
 


@@ -996,14 +998,14 @@ This version also can pass the whole {\it BigCrush} battery of tests.
 \KwIn{InternalVarXorLikeArray: array with internal variables of 1 xor-like PRNGs
 in global memory\;
 NumThreads: Number of threads\;
 \KwIn{InternalVarXorLikeArray: array with internal variables of 1 xor-like PRNGs
 in global memory\;
 NumThreads: Number of threads\;

-tab1, tab2: Arrays containing combinations of size combination\_size\;}
+array\_comb1, array\_comb2: Arrays containing combinations of size combination\_size\;}

 
 \KwOut{NewNb: array containing random numbers in global memory}
 \If{threadId is concerned} {
   retrieve data from InternalVarXorLikeArray[threadId] in local variables including shared memory and x\;
   offset = threadIdx\%combination\_size\;
 
 \KwOut{NewNb: array containing random numbers in global memory}
 \If{threadId is concerned} {
   retrieve data from InternalVarXorLikeArray[threadId] in local variables including shared memory and x\;
   offset = threadIdx\%combination\_size\;

-  o1 = threadIdx-offset+tab1[offset]\;
-  o2 = threadIdx-offset+tab2[offset]\;
+  o1 = threadIdx-offset+array\_comb1[offset]\;
+  o2 = threadIdx-offset+array\_comb2[offset]\;

   \For{i=1 to n} {
     t=xor-like()\;
     t=t $\wedge$ shmem[o1] $\wedge$ shmem[o2]\;
   \For{i=1 to n} {
     t=xor-like()\;
     t=t $\wedge$ shmem[o1] $\wedge$ shmem[o2]\;


@@ -1293,15 +1295,17 @@ variable for BBS number 8 is stored in place 1.
 \KwIn{InternalVarBBSArray: array with internal variables of the 8 BBS
 in global memory\;
 NumThreads: Number of threads\;
 \KwIn{InternalVarBBSArray: array with internal variables of the 8 BBS
 in global memory\;
 NumThreads: Number of threads\;

-tab: 2D Arrays containing 16 combinations (in first dimension)  of size combination\_size (in second dimension)\;}
+array\_comb: 2D Arrays containing 16 combinations (in first dimension)  of size combination\_size (in second dimension)\;
+
+}

 
 \KwOut{NewNb: array containing random numbers in global memory}
 \If{threadId is concerned} {
   retrieve data from InternalVarBBSArray[threadId] in local variables including shared memory and x\;
   we consider that bbs1 ... bbs8 represent the internal states of the 8 BBS numbers\;
   offset = threadIdx\%combination\_size\;
 
 \KwOut{NewNb: array containing random numbers in global memory}
 \If{threadId is concerned} {
   retrieve data from InternalVarBBSArray[threadId] in local variables including shared memory and x\;
   we consider that bbs1 ... bbs8 represent the internal states of the 8 BBS numbers\;
   offset = threadIdx\%combination\_size\;

-  o1 = threadIdx-offset+tab[bbs1\&7][offset]\;
-  o2 = threadIdx-offset+tab[8+bbs2\&7][offset]\;
+  o1 = threadIdx-offset+array\_comb[bbs1\&7][offset]\;
+  o2 = threadIdx-offset+array\_comb[8+bbs2\&7][offset]\;

   \For{i=1 to n} {
     t<<=4\;
     t|=BBS1(bbs1)\&15\;
   \For{i=1 to n} {
     t<<=4\;
     t|=BBS1(bbs1)\&15\;