Vector Pascal is a language targeted at SIMD multi-core instruction-sets such as the AVX and SSE2 or x86-64-v3. It has a SIMD compiler which supports parallel vector operations, loop unrolling, common sub expression removal etc. It is implemented in Java.
FastFlow is a C/C++ programming framework supporting the development of pattern-based parallel programs on multi/many-core, GPUs and distributed platforms. FastFlow run-time is built upon non-blocking threads and lock-free queues. Thanks to its very efficient CAS-free communication/synchronization support (e.g. few clock cycles core-to-core latency), FastFlow effectively supports the exploitation of fine grain parallelism, e.g. parallel codes managing very high frequency streams on commodity multi-core.
...
Freemat is an interpreted, matrix-oriented development environment for engineering and scientific applications, similar to the commercial package MATLAB. Freemat provides visualization, image manipulation, and plotting as well as parallel programming.
Here are asm source codes for parallel port dma and fifo fast transfer of data. They are command line programs for dos and Win95/98. With winio they can be used in WinNT/2000/XP. Transfer rates up to 750 kbytes/sec. Recurrences directories.
Parallel Events and Asynchronous tasKing Library. Originally combining multi-threading with an efficient I/O event model, it's now more a lightweight object-oriented framework for event-based applications.