PandA 0.9.1 released

PandA 0.9.1 new features introduced:
– complete support of CHSTone benchmarks synthesis and verification (http://www.ertl.jp/chstone/),
– better support of multi-ported memories,
– local memory exploitation,
– read-only-memory exploitation,
– support of multi-bus for parallel memory accesses,
– support of unaligned memory accesses,
– better support of pipelined resources,
– improved module binding algorithms (e.g., slack-based module binding),
– support of resource constraints through user xml file,
– support of libc primitives: memcpy, memcmp, memset and memmove,
– better support of printf primitive for RTL debugging purposes,
– support of dynamic memory allocation,
– synthesis of libm builtin primitives such as sin, cos, acosh, etc,
– better integration with FloPoCo library (http://flopoco.gforge.inria.fr/),
– soft-float based HW synthesis,
– support of Vivado Xilinx backend,
– support of Diamond Lattice backend,
– support of XSIM Xilinx simulator,
– synthesis and testbench generation of WISHBONE B4 Compliant Accelerators (see http://cdn.opencores.org/downloads/wbspec_b4.pdf for details on the WISHBONE specification),
– synthesis of AXI4LITE Compliant Accelerators (experimental),
– inclusion of GCC regression tests to test HLS synthesis (tested HLS synthesis and RTL simulation),
– inclusion of libm regression tests to test HLS synthesis of libm (tested HLS synthesis and RTL simulation),
– support of multiple versions of GCC compiler: v4.5, v4.6 and v4.7.
– support of GCC vectorizing capability (experimental).

For any information or bug report, please write to panda-info@elet.polimi.it