Compilers: principles, techniques, and tools
Compilers: principles, techniques, and tools
Compilation of out-of-core data parallel programs for distributed memory machines
ACM SIGARCH Computer Architecture News - Special issue on input/output in parallel computer systems
Tuning the performance of I/O-intensive parallel applications
Proceedings of the fourth workshop on I/O in parallel and distributed systems: part of the federated computing research conference
Automatic compiler-inserted I/O prefetching for out-of-core applications
OSDI '96 Proceedings of the second USENIX symposium on Operating systems design and implementation
SIGPLAN '84 Proceedings of the 1984 SIGPLAN symposium on Compiler construction
High Performance Compilers for Parallel Computing
High Performance Compilers for Parallel Computing
Compiler support for out-of-core arrays on parallel machines
FRONTIERS '95 Proceedings of the Fifth Symposium on the Frontiers of Massively Parallel Computation (Frontiers'95)
Disk-directed I/O for MIMD Multiprocessors
Disk-directed I/O for MIMD Multiprocessors
Hi-index | 0.00 |
In compiling I/O intensive operations, it is important to pay attention to the operating system features available for enhancing I/O performance. One such useful feature implemented by several current operating system is the write-back facility, in which the output data is cached in main memory buffers and then slowly written to disks. Since the buffers are of limited size, this feature can be made much more effective if the compiler can transform very large output operations into a sequence of smaller operations. In this paper, we present a static analysis technique through which the compiler can perform such transformations automatically.