Access/execute architectures have several advantages over more traditional architectures. Because address generation and memory access are decoupled from operand use, memory laten...
Multiprocessor memory reference traces provide a wealth of information on the behavior of parallel programs. We have used this information to explore the relationship between kern...
William J. Bolosky, Michael L. Scott, Robert P. Fi...
We demonstrate Spiral, a domain-specific library generation system. Spiral generates high performance source code for linear transforms (such as the discrete Fourier transform and ...
Many hardware optimizations rely on collecting information about program behavior at runtime. This information is stored in lookup tables. To be accurate and effective, these opti...
Ioana Burcea, Stephen Somogyi, Andreas Moshovos, B...
Abstract. Lightweight bytecode verification uses stack maps to annotate Java bytecode programs with type information in order to reduce the verification to type checking. This pape...