Gabe Black
69f0bf743c
X86: (Re)implement XORPS and XORPD.
2009-08-17 18:22:37 -07:00
Gabe Black
982b3ad1f0
X86: Implement a media xor microop.
2009-08-17 18:22:33 -07:00
Gabe Black
f3fb444af4
X86: Implement PUNPCKLQDQ.
2009-08-17 18:21:46 -07:00
Gabe Black
cfaeb5eaf7
X86: Implement PUNPCKHQDQ.
2009-08-17 18:21:09 -07:00
Gabe Black
aabbb22cca
X86: Implement PUNPCKHDQ.
2009-08-17 18:20:50 -07:00
Gabe Black
535ba241f8
X86: Implement PUNPCKHWD.
2009-08-17 18:19:43 -07:00
Gabe Black
093b5b3274
X86: Implement PUNPCKHBW.
2009-08-17 18:19:19 -07:00
Gabe Black
3ae2f03927
X86: Implement PUNPCKLDQ.
2009-08-17 18:19:01 -07:00
Gabe Black
673b19f5d4
X86: Implement PUNPCKLWD.
2009-08-17 18:18:40 -07:00
Gabe Black
ae4ee21ecd
X86: Implement the versions of PUNPCKLBW that use XMM registers.
2009-08-17 18:18:19 -07:00
Gabe Black
24496060e5
X86: Implement the MOVQ instruction.
2009-08-17 18:17:29 -07:00
Gabe Black
f1bfa9d6e4
X86: Implement the lfpimm microop.
2009-08-17 18:17:26 -07:00
Gabe Black
fca7cb83f0
X86: Implement the versions of MOVD that have an MMX source.
2009-08-17 18:16:07 -07:00
Gabe Black
247ed2379d
X86: Implement the versions of PUNPCKLBW that use MMX registers.
2009-08-17 18:15:42 -07:00
Gabe Black
ecc62e750e
X86: Implement an unpack microop.
2009-08-17 18:15:39 -07:00
Gabe Black
6457fb7003
X86: Implement the versions of MOVD that have an MMX destination.
2009-08-17 18:15:24 -07:00
Gabe Black
191590bcc4
X86: Ignore the size part of XMM/MMX operands. The instructions know what they want.
2009-08-17 18:15:23 -07:00
Gabe Black
33cb4c2f09
X86: Use suffixes to differentiate XMM/MMX/GPR operands.
2009-08-17 18:15:21 -07:00
Gabe Black
3a4438a868
X86: Add microcode assembler symbols for mmx registers.
2009-08-17 18:15:19 -07:00
Gabe Black
2f1001e95c
X86: Set up a media microop framework and create mov2int and mov2fp microops.
2009-08-17 18:15:18 -07:00
Gabe Black
cec4e3b39e
X86: Create base classes for use with media/SIMD microops.
2009-08-17 18:15:16 -07:00
Gabe Black
0b68fbdbe1
X86: Turn the DIV and IDIV microcode into templates and generate all the variants.
2009-08-17 18:15:14 -07:00
Gabe Black
a9b2bf5119
X86: Remove some FIXMEs from IDIV that have been fixed.
2009-08-17 18:15:13 -07:00
Gabe Black
3f2f3bede8
X86: Turn the CMPXCHG8B microcode into a template and generate each variant.
2009-08-17 18:15:00 -07:00
Polina Dudnik
c438b2e431
Branch Merge
2009-08-17 11:33:32 -05:00
Gabe Black
a43ae579dd
Merge with head.
2009-08-17 00:21:57 -07:00
Gabe Black
32c8514b45
X86: Fix a bug introduced to IDIV in a recent attempt to fix another bug.
2009-08-17 00:20:03 -07:00
Nathan Binkert
a6b39c07d9
code_formatter: Add a python class for writing code generator templates
2009-08-16 13:40:03 -07:00
Nathan Binkert
2ecaa99025
ply: add a base class called Grammar that encapsulates a ply grammar
2009-08-16 13:40:01 -07:00
Nathan Binkert
2334e6fdd5
orderdict: Use DictMixin and add orderdict to m5.util
2009-08-16 13:40:00 -07:00
Nathan Binkert
06c7ecb207
python: Make it possible to import the parts of m5 that are pure python
2009-08-16 13:39:59 -07:00
Nathan Binkert
e1270f81bd
ply: update PLY to version 3.2
2009-08-16 13:39:58 -07:00
Polina Dudnik
6654fe02da
Made servicing_atomic a counter and added started writes:
...
a function for setting the flag to indicate that
the rmw_writes started issuing
2009-08-15 12:45:11 -05:00
Polina Dudnik
a8e11cf3bb
Bug fix: indicate when writes started coming in
2009-08-14 17:57:54 -05:00
Polina Dudnik
ee3226d973
Merge with current branch
2009-08-14 15:30:25 -05:00
Polina Dudnik
0b0f47ec16
Added proc_id to CacheMsg for SMT.
...
Not yet necessary, but in case each of the threads
is allowed to initiate an atomic, will come in handy
2009-08-14 15:30:07 -05:00
Polina Dudnik
de25decf37
Multi-line RMW handling
2009-08-14 14:24:15 -05:00
Polina Dudnik
4b924fd16c
SMT atomics modifications:
...
don't allow enquing from other threads if servicing and atomic for a thread
2009-08-14 14:06:14 -05:00
Derek Hower
bcaf93d182
Automated merge with ssh://hg@m5sim.org/m5
2009-08-13 10:37:37 -05:00
Derek Hower
db40cb8f51
ruby: config bugfix
2009-08-13 10:37:09 -05:00
Tushar Krishna
35082a67b6
ruby/network data_msg_size bug fix with updated stats
2009-08-11 15:19:04 -07:00
Brad Beckmann
b89add1e3f
merged Tushar's bug fix with public repository changes
2009-08-11 12:22:41 -07:00
Derek Hower
1c3efb48ad
Automated merge with ssh://hg@m5sim.org/m5
2009-08-09 13:59:14 -05:00
Derek Hower
1a452d228b
protocol: added recycle actions to MOESI DMA events
2009-08-09 13:58:40 -05:00
Gabe Black
33b063a2a7
X86: Update the stats on the ruby x86 regressions for the new CMOVcc implementation.
2009-08-09 04:01:56 -07:00
Gabe Black
c5fae51774
X86: Implement the CMPXCHG8B/CMPXCHG16B instruction.
2009-08-09 01:01:41 -07:00
Gabe Black
bbf117b20e
X86: Don't clobber the original dividend when doing signed divide.
2009-08-09 01:01:18 -07:00
Gabe Black
3b07a5829d
X86: Decode byte sized singed divide as byte sized.
2009-08-09 01:00:47 -07:00
Gabe Black
bcfc4178f5
X86: Update the stats for the slightly lengthened cmov.
2009-08-08 17:23:25 -07:00
Gabe Black
6e97feb8a5
X86: Make not taken conditional moves leave the destination alone. Adjust CMOVcc.
...
The manuals from both AMD and Intel say that when writing to a 32 bit
destination in 64 bit mode, the upper 32 bits of the register are filled with
zeros. They also both say that the CMOV instructions leave their destination
alone when their condition fails. Unfortunately, it seems that CMOV will zero
extend its destination register whether or not it was supposed to actually do
a move on both platforms. This seems to be the only case where this happens,
but it would be hard to say for sure.
2009-08-08 17:23:19 -07:00
