mirrors/Bochs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
11,321 Commits 11 Branches 185 Tags 48 MiB
974c8d5124
Commit Graph

116 Commits

Author SHA1 Message Date
Stanislav Shwartsman
6ac7fa7106 MMX - modify masked write to RMW - faster execution 
CMPXCHG8B/16B - fixed possible problem. Instruction not allowed to fault after some part of it written to the memory
 2007-12-19 23:21:11 +00:00
Stanislav Shwartsman
c9932e97eb Fixes in resolve.cc -> reduce amount of resolve functions even more 2007-12-18 21:41:44 +00:00
Stanislav Shwartsman
8cfd17202a some simple SSE code optimizations 2007-11-27 22:12:45 +00:00
Stanislav Shwartsman
d9e58bd598 split11b on opcode tables level - split almost eevery splittable instruction 
will be continued
 2007-11-17 12:44:10 +00:00
Stanislav Shwartsman
f6ed95785f added cpu state param - for future use and for dbg info 
started to move debugger to info bx_param interface -> info sse and info mmx commands modified
 2007-10-11 18:12:00 +00:00
Stanislav Shwartsman
38d1f39c77 Converted CR0 bits to one register similar to CR4 - a bit slower but helps with other features implemntation 2007-07-09 15:16:14 +00:00
Stanislav Shwartsman
5189cfbf10 SSE4 support 2007-04-19 16:12:21 +00:00
Stanislav Shwartsman
26f08fdb2c Change my e-mail to #SF one 2007-03-23 21:27:13 +00:00
Stanislav Shwartsman
c24627c00f Implemented CLFLUSH instruction 
Set of minor fixes for correctness
 2007-01-28 21:27:31 +00:00
Stanislav Shwartsman
8221fa6838 - Fixed zero upper 32-bit part of GPR in x86-64 mode 
- CMOV_GdEd should zero upper 32-bit part of GPR register even if the
    'cmov' condition was false !
 2007-01-26 22:12:05 +00:00
Stanislav Shwartsman
acd1a05f6f Fixed bugs for SSE3E execution and decoding 2007-01-25 21:44:35 +00:00
Stanislav Shwartsman
f8003098b1 Rename SSE4 to SSE3E to match intel docs. SSE4 coming later ;) 
Fixed "last prefix" for REX in 64-bit mode
 2007-01-25 19:09:41 +00:00
Stanislav Shwartsman
16713b309d PALIGNR fixed 2006-05-16 16:20:26 +00:00
Stanislav Shwartsman
03eac64013 Added decoding of new SSE4 instructions (recently published in Intel docs) 
At least CPUID detects them correctly
The code is never tested (still) ! (but should work fine)
 2006-04-06 18:30:05 +00:00
Stanislav Shwartsman
7b6c2587a9 Now devices could be compiled separatelly from CPU 
Averything that required cpu.h include now has it explicitly and there are a lot of files not dependant by CPU at all which will compile a lot faster now ...
 2006-03-06 22:03:16 +00:00
Stanislav Shwartsman
0150904e9d Improve debug messages and optimize 2006-02-22 20:58:16 +00:00
Stanislav Shwartsman
5c58b22f44 Fixed opcode names according to Intel docs 
Fixed bug found during disasm validation
 2006-02-17 13:34:31 +00:00
Stanislav Shwartsman
d1c722211e Fix duplicate opcodes, fix opcode names and disasm bugs 2005-09-23 16:45:41 +00:00
Stanislav Shwartsman
3d9ee328fb PMOVMSKB and PEXTRW instruction should zero-extend dest when in 64-bit mode 2005-09-12 18:08:35 +00:00
Stanislav Shwartsman
80c895498e Fixed comments for code 2005-08-10 18:40:38 +00:00
Stanislav Shwartsman
a66b45e024 Fixed bug for masked writes in 64-bit mode 2005-08-10 18:34:00 +00:00
Stanislav Shwartsman
d10731f162 Update my e-mail in source files 
Update committed SF patches in changes
 2005-05-12 18:07:48 +00:00
Stanislav Shwartsman
3074078297 Added CVS version header to all the files. 
One more small change in APIC
 2005-03-19 20:44:01 +00:00
Stanislav Shwartsman
33b50ec4c4 For spammers o 2004-04-08 17:17:47 +00:00
Stanislav Shwartsman
1706beda30 fixed bug in floatx80_class function 
mmx code optimizations
 2004-03-03 21:09:08 +00:00
Stanislav Shwartsman
ecdbf40aac fixed compilation error for case when 3dnow! enabled and sse not 2004-01-31 17:13:05 +00:00
Stanislav Shwartsman
9120961241 update checking for pending FPU exceptions code 2004-01-31 13:43:26 +00:00
Stanislav Shwartsman
56beb4110c Little code optimization 2003-09-26 19:20:17 +00:00
Stanislav Shwartsman
1616539667 additional FPU changes 2003-08-01 09:32:33 +00:00
Stanislav Shwartsman
1d45167e5b Merged NEW-INSTRUCTIONS branch 2003-05-15 16:41:17 +00:00
Volker Ruppert
79b811f23f - fixed warnings in these files: 
cpu/fetchdecode.cc
  cpu/mmx.cc
  cpu/proc_ctrl.cc
  iodev/virt_timer.cc
  plugin.cc
 2003-05-02 12:22:48 +00:00
Stanislav Shwartsman
fa623fda74 FPU tag word is 16bit only 2003-04-25 18:43:48 +00:00
Stanislav Shwartsman
88d433bb73 Implemented MASKMOVQ 2003-04-23 18:57:57 +00:00
Stanislav Shwartsman
40bd4f138b Little style changes 
Elliminated i387_t alimit field (not used in FPU)
 2003-04-16 18:38:53 +00:00
Stanislav Shwartsman
aa9152129c Changes in i387 register file definition. Define common FPU/MMX register file. 2003-04-12 21:02:08 +00:00
Stanislav Shwartsman
216124c6c3 Send #MF exception for MMX instructions if there is a pending FPU exception 2003-04-05 12:49:14 +00:00
Stanislav Shwartsman
8193a710ad Changed MMX/SSE/SSE2 diagnostic messages to be more informative 2003-03-21 20:33:23 +00:00
Christophe Bothamy
50efc3b8c7 - apply Conn Clark's patch.perf-regparm-cclark : 
- it works only on x86 with gcc2.95+
  - uses the GCC function atribute "regparm(n)" to declare that certain
    functions use the register calling convention
  - performance improvement is about 6%
 2003-03-02 23:59:12 +00:00
Stanislav Shwartsman
513db033ab fixed compilation error and a logic bug together 2003-01-09 05:21:22 +00:00
Stanislav Shwartsman
e6eacd984f Implemented MOVD 64bit extensions 2003-01-08 20:33:28 +00:00
Stanislav Shwartsman
e1d5cddc6d Fixed a problem with zero-count shift in following instructions: 
PSRAW_PqQq    (MMX)
PSRAD_PqQq    (MMX)
PSRAW_PqIb    (MMX)
PSRAD_PqIb    (MMX)

PSRAW_VdqWdq  (SSE)
PSRAD_VdqWdq  (SSE)
PSRAW_PdqIb   (SSE)
PSRAD_PdqIb   (SSE)

When register was shifted by 0 bits the result produced was incorrect.

Now Bochs fully passes MMX test provided by
Hentai Yagi [hentai_yagi@yahoo.com.au] !
 2002-12-29 21:14:25 +00:00
Stanislav Shwartsman
8909ce442c Fixed problem in PSRLD_PqIb instruction 2002-12-28 20:18:56 +00:00
Stanislav Shwartsman
6ccd2fb7fa Fixed bug in following MMX instructions: 
void BX_CPU_C::PUNPCKLBW_PqQd(bxInstruction_c *i)
void BX_CPU_C::PUNPCKLWD_PqQd(bxInstruction_c *i)
void BX_CPU_C::PUNPCKLDQ_PqQd(bxInstruction_c *i)

Thanks to Hentai Yagi [hentai_yagi@yahoo.com.au]
that provided nessesary test application.
 2002-12-28 19:06:29 +00:00
Stanislav Shwartsman
04c7d9301b implemented 
PINSRW_VdqEdIb
PEXTRW_VdqEdIb
PINSRW_PqEdIb
PEXTRW_PqEdIb

instructions
 2002-12-02 21:24:09 +00:00
Stanislav Shwartsman
57fd94744d Implemented MOVQ2DQ/MOVDQ2Q instructions 
Small fixes with MMX environment
 2002-11-30 14:42:41 +00:00
Bryce Denney
9b14101a05 - rewrite typecast of temp to Bit64u to keep VC++ happy. I don't really 
know what it thought was wrong.
 2002-11-19 05:53:47 +00:00
Stanislav Shwartsman
3217759a75 Implemented 
PSHUFLW_VqWqIb, PSHUFHW_VqWqIb instructions
 2002-11-15 17:34:47 +00:00
Stanislav Shwartsman
da8a2a71b1 Fixed bug PSHUFW instruction 2002-11-15 17:02:06 +00:00
Stanislav Shwartsman
62e362afc2 just typo 2002-11-15 15:55:36 +00:00
Stanislav Shwartsman
34dd74fe6c Fixed BUG in PMADDWD instruction 2002-11-15 15:51:12 +00:00
Stanislav Shwartsman
65b8712d04 More tuning of SSE 2002-11-14 19:59:29 +00:00
Stanislav Shwartsman
5803e20240 Changed policy of SSE/SSE2 checking 2002-11-13 21:00:05 +00:00
Stanislav Shwartsman
0df9c9af85 Implemented integer SSE2 instructions: 
PSRLW_PdqIb
PSRLD_PdqIb
PSRLQ_PdqIb
PSLLW_PdqIb
PSLLD_PdqIb
PSLLQ_PdqIb
PSRAW_PdqIb
PSRAD_PdqIb
PSRLW_VdqWdq
PSRLD_VdqWdq
PSRLQ_VdqWdq
PSRAW_PdqWdq
PSRAD_PdqWdq
PSLLW_VdqWdq
PSLLD_VdqWdq
PSLLQ_VdqWdq
PMOVMSKB_GdVRdq
PMULUDQ_VdqWdq
PMINUB_VdqWdq
PMINSW_VdqWdq
PMAXUB_VdqWdq
PMAXSW_VdqWdq

Fixed bug in the PMINUB_PqQq and PMAXUB_PqQq SSE instructions
 2002-11-08 17:47:46 +00:00
Stanislav Shwartsman
4363745725 Implemented SSE2 integer instructions: 
PACKSSDW_VdqWdq
PUNPCKHDQ_VdqWq
PUNPCKHWD_VdqWq
PUNPCKHBW_VdqWq
PUNPCKHQDQ_VdqWq
MOVD_EdVd
MOVD_VdqEd
 2002-11-08 12:47:24 +00:00
Stanislav Shwartsman
b200ff2058 Implemented several integer SSE2 instructions (similar to the MMX): 
PACKSSWB_VdqWq
PCMPGTB_VdqWq
PCMPGTW_VdqWq
PCMPGTD_VdqWdq
PACKUSWB_VdqWdq
PCMPEQB_VdqWdq
PCMPEQW_VdqWdq
PCMPEQD_VdqWdq
PADDQ_VdqWdq
PSUBUSB_VdqWdq
PSUBUSW_VdqWdq
PAND_VdqWdq
PANDN_VdqWdq
PAVGB_VdqWdq
PAVGW_VdqWdq
POR_VdqWdq
PXOR_VdqWdq
PSUBB_VdqWdq
PSUBW_VdqWdq
PSUBD_VdqWdq
PSUBQ_VdqWdq
PADDB_VdqWdq
PADDW_VdqWdq
PADDD_VdqWdq
PADDQ_VdqWdq
 2002-11-07 22:41:34 +00:00
Stanislav Shwartsman
0e60aa8232 We will need integer saturation functions also in SSE2 instructions 2002-11-02 12:35:33 +00:00
Stanislav Shwartsman
277f14dd76 Implemented PMOVMSKB_GdPRq instruction (SSE) 2002-10-19 21:46:07 +00:00
Stanislav Shwartsman
63ac78d496 Implemented MOVNTQ instruction 2002-10-19 21:28:50 +00:00
Stanislav Shwartsman
21201bc237 Add opcode name to the information message in case of MMX/SSE/SSE2 instruction is not supported 2002-10-19 20:16:42 +00:00
Stanislav Shwartsman
194952a53d Merged BOCHS-SSE branch 2002-10-16 17:37:35 +00:00
Kevin Lawton
66452e9898 Replaced tabs in cpu/*.{cc,h} files with spaces. 2002-10-04 17:04:33 +00:00
Kevin Lawton
402d02974d Moved the EFLAGS.RF check and clearing of inhibit_mask code 
in cpu.cc out of the main loop, and into the asynchronous
events handling.  I went through all the code paths, and
there doesn't seem to be any reason for that code to be
in the hot loop.

Added another accessor for getting instruction data, called
modC0().  A lot of instructions test whether the mod field
of mod-nnn-rm is 0xc0 or not, ie., it's a register operation
and not memory.  So I flag this in fetchdecode{,64}.cc.
This added on the order of 1% performance improvement for
a Win95 boot.

Macroized a few leftover calls to Write_RMV_virtual_xyz()
that didn't get modified in the x86-64 merge.  Really, they
just call the real function for now, but I want to have them
available to do direct writes with the guest2host TLB pointers.
 2002-09-20 03:52:59 +00:00
Kevin Lawton
6723ca9bf4 Moved more separate fields in the bxInstruction_c into bitfields 
with accessors.  Had to touch a number of files to update the
access using the new accessors.

Moved rm_addr to the CPU structure, to slim down bxInstruction_c
and to prevent future instruction caching from getting sprayed
with writes to individual rm_addr fields.  There only needs to
be one.  Though need to deal with instructions which have
static non-modrm addresses, but which are using rm_addr since
that will change.

bxInstruction_c is down to about 40 bytes now.  Trying to
get down to 24 bytes.
 2002-09-18 05:36:48 +00:00
Kevin Lawton
07b0df2a8a Updated accessing of modrm/sib addressing information to 
use accessors.  This lets me work on compressing the
size of fetch-decode structure (now called bxInstruction_c).

I've reduced it down to about 76 bytes.  We should be able
to do much better soon.  I needed the abstraction of the
accessors, so I have a lot of freedom to re-arrange things
without making massive future changes.

Lost a few percent of performance in these mods, but my
main focus was to get the abstraction.
 2002-09-17 22:50:53 +00:00
Kevin Lawton
1e22357b06 Very small #ifdef mods so that all the static functions would 
be compiled out, when MMX is not enabled for a compile.  Eliminates
the unused warnings from the compiler.
 2002-09-09 17:13:13 +00:00
Bryce Denney
be659a09b3 - check in Stanislav Shwartsman's patch "bochs-mmx.patch-endian-support". 
He writes: Detailed description: MMX instruction set support.
  Also supports BIG_ENDIAN systems. Tested on Solaris and HP1100.
- modified files:
    configure.in cpu/Makefile.in cpu/cpu.h cpu/fetchdecode.cc
    cpu/proc_ctrl.cc fpu/fpu_system.h fpu/wmFPUemu_glue.cc
- added files: cpu/i387.h cpu/mmx.cc
 2002-09-09 16:11:25 +00:00