new

[prng_gpu.git] / prng_gpu.tex

diff --git a/prng_gpu.tex b/prng_gpu.tex
index 00752c7ebacafd738aea10ba6c2c603c0fc8e26a..d7e466407e9fe071e2c8a0e602d893884d8cdf09 100644 (file)
--- a/prng_gpu.tex
+++ b/prng_gpu.tex
@@ -996,9 +996,9 @@ tab1, tab2: Arrays containing combinations of size combination\_size\;}
   o2 = threadIdx-offset+tab2[offset]\;
   \For{i=1 to n} {
     t=xor-like()\;
-    t=t$\oplus$shmem[o1]$\oplus$shmem[o2]\;
+    t=t $\hat{ }$ shmem[o1] $\hat{ }$ shmem[o2]\;
     shared\_mem[threadId]=t\;
-    x = x $\oplus$ t\;
+    x = x $\hat{ }$ t\;
 
     store the new PRNG in NewNb[NumThreads*threadId+i]\;
   }
@@ -1082,7 +1082,7 @@ As a  comparison,   Listing~\ref{algo:seqCIPRNG}  leads   to the  generation of
 
 In Figure~\ref{fig:time_bbs_gpu}  we highlight the performances  of the optimized
 BBS-based  PRNG on GPU. On the  Tesla C1060 we
-obtain approximately 1.8GSample/s and on the GTX 280 about 1.6GSample/s, which is
+obtain approximately 700MSample/s and on the GTX 280 about 670MSample/s, which is
 obviously slower than the xorlike-based PRNG on GPU. However, we will show in the 
 next sections that 
 this new PRNG has a strong level of security, which is necessary paid by a speed
@@ -1305,9 +1305,9 @@ tab: 2D Arrays containing 16 combinations (in first dimension)  of size combinat
     t|=BBS1(bbs1)\&7\;
      t<<=BBS7(bbs7)\&3\;
     t|=BBS2(bbs2)\&7\;
-    t=t$\oplus$shmem[o1]$\oplus$shmem[o2]\;
+    t=t $\hat{ }$ shmem[o1] $\hat{ }$ shmem[o2]\;
     shared\_mem[threadId]=t\;
-    x = x $\oplus$ t\;
+    x = x $\hat{ }$ t\;
 
     store the new PRNG in NewNb[NumThreads*threadId+i]\;
   }