lxdream.org :: lxdream/src/sh4/

tree revision 934:3acd3b3ee6d1 lxdream-mem

/src/sh4/

[parent directory]
cache.c	933:880c37bb1909	15 years	nkeynes	Start putting cache together	log
dmac.c	929:fd8cb0c82f5f	15 years	nkeynes	First pass experiment using cached decoding.	log
dmac.h	736:a02d1475ccfd	15 years	nkeynes	Re-indent everything consistently	log
ia32abi.h	930:07e5b11419db	15 years	nkeynes	Remove pointer cache and add full address-space map. Much better	log
ia64abi.h	930:07e5b11419db	15 years	nkeynes	Remove pointer cache and add full address-space map. Much better	log
intc.c	929:fd8cb0c82f5f	15 years	nkeynes	First pass experiment using cached decoding.	log
intc.h	736:a02d1475ccfd	15 years	nkeynes	Re-indent everything consistently	log
mmu.c	934:3acd3b3ee6d1	15 years	nkeynes	Change RAM regions to use static arrays rather than mmap regions, for a 2-3% performance gain.	log
mmu.h	931:430048ea8b71	15 years	nkeynes	More refactoring and general cleanup. Most things should be working again now.	log
pmm.c	929:fd8cb0c82f5f	15 years	nkeynes	First pass experiment using cached decoding.	log
scif.c	929:fd8cb0c82f5f	15 years	nkeynes	First pass experiment using cached decoding.	log
sh4.c	934:3acd3b3ee6d1	15 years	nkeynes	Change RAM regions to use static arrays rather than mmap regions, for a 2-3% performance gain.	log
sh4.def	359:c588dce7ebde	16 years	nkeynes	Commit decoder generator	log
sh4.h	930:07e5b11419db	15 years	nkeynes	Remove pointer cache and add full address-space map. Much better	log
sh4core.h	934:3acd3b3ee6d1	15 years	nkeynes	Change RAM regions to use static arrays rather than mmap regions, for a 2-3% performance gain.	log
sh4core.in	927:17b6b9e245d8	15 years	nkeynes	Add return-address-modifying exception return code to mmu TLB lookups (a little bit faster)	log
sh4dasm.h	736:a02d1475ccfd	15 years	nkeynes	Re-indent everything consistently	log
sh4dasm.in	873:cb3a8c502727	15 years	nkeynes	Fix typo in FCMP/GT disassembly	log
sh4mem.c	934:3acd3b3ee6d1	15 years	nkeynes	Change RAM regions to use static arrays rather than mmap regions, for a 2-3% performance gain.	log
sh4mmio.c	929:fd8cb0c82f5f	15 years	nkeynes	First pass experiment using cached decoding.	log
sh4mmio.h	929:fd8cb0c82f5f	15 years	nkeynes	First pass experiment using cached decoding.	log
sh4stat.h	905:4c17ebd9ef5e	15 years	nkeynes	Use regparam calling conventions for all functions called from translated code,	log
sh4stat.in	905:4c17ebd9ef5e	15 years	nkeynes	Use regparam calling conventions for all functions called from translated code,	log
sh4trans.c	914:72abecf5a315	15 years	nkeynes	Fix (extremely boneheaded) failure to convert pc to physical address before	log
sh4trans.h	926:68f3e0fe02f1	15 years	nkeynes	Setup a 'proper' stackframe in translated blocks. This doesn't affect performance noticeably,	log
sh4x86.in	930:07e5b11419db	15 years	nkeynes	Remove pointer cache and add full address-space map. Much better	log
timer.c	929:fd8cb0c82f5f	15 years	nkeynes	First pass experiment using cached decoding.	log
x86op.h	930:07e5b11419db	15 years	nkeynes	Remove pointer cache and add full address-space map. Much better	log
xltcache.c	922:8a8361264b1e	15 years	nkeynes	Disable the generational translation cache - I've got no evidence that it	log
xltcache.h	906:268ea359f884	15 years	nkeynes	Change xlat_get_native_pc to pass in the expected code region - this lets the Mac	log