this is for holding javascript data
Jake edited cuda_overview.tex
about 11 years ago
Commit id: 347b10ee9341ba6da51bdbeef2bb0f8c28906a32
deletions | additions
diff --git a/cuda_overview.tex b/cuda_overview.tex
index 9e9ed72..8727fc5 100644
--- a/cuda_overview.tex
+++ b/cuda_overview.tex
...
\subsection{CUDA Memory Model}
Similar to a CPU's architecture, the GPU also has multiple types of memory available to it. At the highest level
we have there are global and constant memory. When moving non-primitive values from the host to the GPU the developer must either copy into the GPU's global or constant memory. Constant memory is significantly
fast faster (quote to come) than global memory however it is immutable. Once the memory is on the GPU the developer can either access it directly from all threads and all blocks or subdivide the memory into local or shared memory. Local memory is accessible on a per thread basis and is the fastest type of memory available whereas shared memory is
accessible to all threads within a block.