As part of Google's Summer of Code, I am porting libjit to the alpha 
architecture for the GNU Project. Please be aware that this is still 
very much a work in progress and isn't functional yet. You can follow my 
progress via my blog: http://mediumbagel.org/nucleus/index.php?catid=6

For the first iteration, the alpha port will not implement floating-
point arithmetic. This is done to reduce complexity and to get libjit
working on alpha sooner. Advanced features like prefetching, hints (for 
jmp, jsr, ret, and jsrco), and branch elimination with cmov are 
optimizations that will be implmented once the alpha port is functional.

-Thomas Cort <linuxgeek@gmail.com>

During the development of the alpha port, I found the following sources 
of information to be very useful:

	Alpha Architecture Handbook
	ftp://ftp.compaq.com/pub/products/alphaCPUdocs/alpha_arch_ref.pdf
	http://ftp.digital.com/pub/Digital/info/semiconductor/literature/alphaahb.pdf

	Compiler Writer's Guide for the 21264/21364
	ftp://ftp.compaq.com/pub/products/alphaCPUdocs/comp_guide_v2.pdf

	Assembly Language Programmer's Guide
	http://www.cs.arizona.edu/computer.help/policy/DIGITAL_unix/AA-PS31D-TET1_html/TITLE.html

	binutils source code
	binutils-2.16.1/opcodes/alpha-opc.c

	ffcall source code
	ffcall-1.10/avcall/avcall-alpha.c

	mono source code
	mono-.1.1.15/mono/arch/alpha/*

	gcc source code
	gcc-3.4.6/gcc/config/alpha/*

	ALPHA: Opcodes
	http://www.cs.arizona.edu/alto/Doc/local/alpha.opcode.html