Gabe Black [Sat, 16 Dec 2006 12:22:19 +0000 (07:22 -0500)]
Added a predicted NPC field, explicitly stored whether the instruction was predicted taken or not.
--HG--
extra : convert_revision :
ba668af302ca4d8a3a032e907d5058e1477f462a
Gabe Black [Sat, 16 Dec 2006 12:10:58 +0000 (07:10 -0500)]
Made changes to CWP be non speculative.
--HG--
extra : convert_revision :
43899bc97061c33e67a53179c23e46b079118117
Gabe Black [Sat, 16 Dec 2006 12:10:04 +0000 (07:10 -0500)]
Changes to the isa_parser and affected files to fix an indexing problem with split execute instructions and miscregs aliasing with integer registers.
src/arch/isa_parser.py:
Rearranged things so that classes with more than one execute function treat operands properly.
1. Eliminated the CodeBlock class
2. Created a SubOperandList
3. Redefined how InstObjParams is constructed
To define an InstObjParam, you can either pass in a single code literal which will be named "code", or you can pass in a dictionary of code snippets which will be substituted into the Templates. In order to get this to work, there is a new restriction that each template has only one function in it. These changes should only affect memory instructions which have regular and split execute functions.
Also changed the MiscRegs so that they use the instrunctions srcReg and destReg arrays.
src/arch/sparc/isa/formats/basic.isa:
src/arch/sparc/isa/formats/branch.isa:
src/arch/sparc/isa/formats/integerop.isa:
src/arch/sparc/isa/formats/mem/basicmem.isa:
src/arch/sparc/isa/formats/mem/blockmem.isa:
src/arch/sparc/isa/formats/mem/util.isa:
src/arch/sparc/isa/formats/nop.isa:
src/arch/sparc/isa/formats/priv.isa:
src/arch/sparc/isa/formats/trap.isa:
Rearranged to work with new InstObjParam scheme.
src/cpu/o3/sparc/dyn_inst.hh:
Added functions to access the miscregs using the indexes from instructions srcReg and destReg arrays. Also changed the names of the other accessors so that they have the suffix "Operand" if they use those arrays.
src/cpu/simple/base.hh:
Added functions to access the miscregs using the indexes from instructions srcReg and destReg arrays.
--HG--
extra : convert_revision :
c91e1073138b72bcf4113a721e0ed40ec600cf2e
Gabe Black [Tue, 12 Dec 2006 23:10:00 +0000 (18:10 -0500)]
Merge zizzer:/bk/newmem/
into zower.eecs.umich.edu:/eecshome/m5/newmem
--HG--
extra : convert_revision :
17d6c49ee15af5d192dedf82871159219d4277cd
Steve Reinhardt [Tue, 12 Dec 2006 17:58:40 +0000 (09:58 -0800)]
Rename the StaticInst-based (read|set)(Int|Float)Reg methods to (read|set)(Int|Float)RegOperand to distinguish from non-StaticInst version.
--HG--
extra : convert_revision :
b33ce0ebe2fee86cc791c00a35d8c6e395e1380c
Steve Reinhardt [Tue, 12 Dec 2006 17:54:59 +0000 (09:54 -0800)]
If no tests are specified for regression, just build the binaries
(instead of complaining and exiting).
--HG--
extra : convert_revision :
24ac0bab7fd92d9e74c80847a667f0affcd0473d
Steve Reinhardt [Tue, 12 Dec 2006 07:21:03 +0000 (02:21 -0500)]
Get rid of unused lock code.
--HG--
extra : convert_revision :
a8030132268662ca54f487b8d32d09ba224317a8
Kevin Lim [Tue, 12 Dec 2006 04:51:21 +0000 (23:51 -0500)]
Fix up in case a req hasn't yet been generated for this instruction (if there was a fault prior to translation).
--HG--
extra : convert_revision :
43f4ea5e6a234cc6071006eab72135c11b8523c8
Kevin Lim [Tue, 12 Dec 2006 04:47:30 +0000 (23:47 -0500)]
Fix for fetch to use the icache's block size to generate proper access size.
--HG--
extra : convert_revision :
0f292233ac05b584f527c32f80e3ca3d40a6a2c1
Steve Reinhardt [Sun, 10 Dec 2006 07:05:33 +0000 (02:05 -0500)]
Merge zizzer.eecs.umich.edu:/z/stever/bk/newmem-head
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-cache3
--HG--
extra : convert_revision :
c961d1bf2acaae6807870b78f444a4a606be65cc
Steve Reinhardt [Sun, 10 Dec 2006 07:04:53 +0000 (02:04 -0500)]
Reorder CacheTags members for better cache performance.
--HG--
extra : convert_revision :
cac6e9d447675805e3fcc4342e3bfdbef179fbf5
Steve Reinhardt [Sun, 10 Dec 2006 06:52:18 +0000 (01:52 -0500)]
Get rid of dummy 'hello world' outputs.
--HG--
extra : convert_revision :
e03634b5ec6b3c855c463618968984b5df7782f9
Steve Reinhardt [Sun, 10 Dec 2006 06:50:12 +0000 (01:50 -0500)]
Delete parser reference outputs so that test will no longer be run.
Runtimes are way too long with current inputs.
--HG--
extra : convert_revision :
19323308b40fb7de00c77ee552e39ca6558804b8
Steve Reinhardt [Sun, 10 Dec 2006 06:42:31 +0000 (01:42 -0500)]
Merge zizzer.eecs.umich.edu:/z/stever/bk/newmem-cache2
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-cache3
--HG--
extra : convert_revision :
7c78ae3298645aed2179ed4f2aa361619406f9de
Steve Reinhardt [Sun, 10 Dec 2006 06:42:16 +0000 (01:42 -0500)]
Add '-j' option directly to regress script (passed to scons).
--HG--
extra : convert_revision :
9776806b24da70b815280e47d2d5ec8674c82669
Steve Reinhardt [Sun, 10 Dec 2006 06:05:30 +0000 (22:05 -0800)]
Merge vm1.(none):/home/stever/bk/newmem-head
into vm1.(none):/home/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
e1ed5c8edb95e99200b4d26317f55f71338a96df
Gabe Black [Fri, 8 Dec 2006 00:00:46 +0000 (19:00 -0500)]
Fixed to take into account the misc regs that became int regs.
--HG--
extra : convert_revision :
b4f78f6e48fdd2f1774ba63b28615e0d2556b7b9
Gabe Black [Thu, 7 Dec 2006 23:49:10 +0000 (18:49 -0500)]
Compilation fixes
--HG--
extra : convert_revision :
974e91a960251a35d5ebb76c7e6c7ac330339896
Gabe Black [Thu, 7 Dec 2006 23:47:33 +0000 (18:47 -0500)]
Fix for squashing during a serializing instruction.
--HG--
extra : convert_revision :
04f9131258bfb7cca1654e00273edb29bde2366b
Gabe Black [Thu, 7 Dec 2006 23:45:30 +0000 (18:45 -0500)]
Make branches handle the lack of a symbol table or the lack of a symbol gracefully.
--HG--
extra : convert_revision :
7bb16405999b86f9fa082a6d44da43d346edc182
Gabe Black [Thu, 7 Dec 2006 23:43:55 +0000 (18:43 -0500)]
Change how Page Faults work in SPARC. It now prints the faulting address, and panics instead of fatals. This isn't technically what it should do, but it makes gdb stop at the panic rather than letting m5 exit.
--HG--
extra : convert_revision :
3b14c99edaf649e0809977c9579afb2b7b0d72e9
Steve Reinhardt [Thu, 7 Dec 2006 19:41:56 +0000 (14:41 -0500)]
Change detault regression build from opt to fast.
--HG--
extra : convert_revision :
b6db0254b73a97ab6e3685c90cc9cd30ea274d4f
Kevin Lim [Wed, 6 Dec 2006 19:23:31 +0000 (14:23 -0500)]
Fix for MIPS_SE/m5.fast compile.
--HG--
extra : convert_revision :
dbb893250974ac6db7b6c1ba67263fd35098ca43
Gabe Black [Wed, 6 Dec 2006 16:40:41 +0000 (11:40 -0500)]
Use the renamed register index, rather than the flattened one.
--HG--
extra : convert_revision :
599650c408667bb1b8db20a6847b9e697f7b49e4
Gabe Black [Wed, 6 Dec 2006 16:39:49 +0000 (11:39 -0500)]
Got rid of some typedefs and moved the tlbs into the base o3 cpu.
--HG--
extra : convert_revision :
dcd1d2a64fd91aded15c8c763a78b4eebf421870
Gabe Black [Wed, 6 Dec 2006 16:38:39 +0000 (11:38 -0500)]
Use the setSyscallReturn defined in arch rather than duplicating it here.
--HG--
extra : convert_revision :
862ece59aa253b52b6744a0a76738d5ee19561b3
Gabe Black [Wed, 6 Dec 2006 16:37:39 +0000 (11:37 -0500)]
Moved the RegIdx arrays to the base dyninst.
--HG--
extra : convert_revision :
d705cde25c2cf1add20669e99d086add49141518
Gabe Black [Wed, 6 Dec 2006 16:36:40 +0000 (11:36 -0500)]
Got rid of some typedefs, moved the tlbs to the base o3 cpu, and called the architecture defined setSyscallReturn function instead of a duplicate copy.
src/cpu/o3/alpha/cpu.hh:
Got rid of some typedefs, and moved the tlbs to the base o3 cpu.
src/cpu/o3/alpha/thread_context.hh:
src/cpu/o3/cpu.cc:
Moved the tlbs to the base o3 cpu.
--HG--
extra : convert_revision :
1805613aa230b8974a226ee3d2584c85f7a578aa
Gabe Black [Wed, 6 Dec 2006 16:33:37 +0000 (11:33 -0500)]
Made the alpha setSyscallReturn take a ThreadContext pointer instead of a RegFile *.
--HG--
extra : convert_revision :
021a1fe6760df1daf6299d46060371a5310f008a
Gabe Black [Wed, 6 Dec 2006 16:30:41 +0000 (11:30 -0500)]
Added a flattenIntIndex function for Alpha.
--HG--
extra : convert_revision :
5ed79ed18e443118a28d6890327c55a6a3fcd325
Gabe Black [Wed, 6 Dec 2006 11:05:28 +0000 (06:05 -0500)]
Merge zizzer:/bk/newmem
into zower.eecs.umich.edu:/eecshome/m5/newmem
src/cpu/o3/commit_impl.hh:
Hand Merge
--HG--
extra : convert_revision :
6984db90d5b5ec71c31f1c345f5a77eed540059e
Gabe Black [Wed, 6 Dec 2006 11:02:13 +0000 (06:02 -0500)]
Added a DPRINTF to print out the actual value pulled from memory.
--HG--
extra : convert_revision :
18780f753a7e98f8de3047dd6781b944b0826b4e
Gabe Black [Wed, 6 Dec 2006 11:00:04 +0000 (06:00 -0500)]
Flattening and syscallReturn fixes
src/cpu/o3/thread_context_impl.hh:
Use flattened indices
src/cpu/simple_thread.hh:
Use flattened indices, and pass a thread context to setSyscallReturn rather than a register file.
src/cpu/thread_context.hh:
The SyscallReturn class is no longer in arch/syscallreturn.hh
--HG--
extra : convert_revision :
ed84bb8ac5ef0774526ecd0d7270b0c60cd3708e
Gabe Black [Wed, 6 Dec 2006 10:58:07 +0000 (05:58 -0500)]
Don't panic, but this needs to be fixed.
--HG--
extra : convert_revision :
7a4aed238d437dbb2cc5946b3045d53697070a27
Gabe Black [Wed, 6 Dec 2006 10:56:34 +0000 (05:56 -0500)]
Make syscalls flatten their register indices, and also call into the ISA's setSyscallReturn function rather than having a duplicated one.
--HG--
extra : convert_revision :
1e83ef629a7fd143f2e35e68abaa56f81d6b9d9e
Gabe Black [Wed, 6 Dec 2006 10:55:23 +0000 (05:55 -0500)]
Change rename to rename the flattened register index instead of the architectural one.
--HG--
extra : convert_revision :
757866ad7a3c8be7382e1ffa71c60bc00c861f6f
Gabe Black [Wed, 6 Dec 2006 10:54:16 +0000 (05:54 -0500)]
Added in endianness conversion on memory accesses as the data goes out. This will break the checker!
--HG--
extra : convert_revision :
b8191cab09ab8f3ced05693293f058382319ed8e
Gabe Black [Wed, 6 Dec 2006 10:51:18 +0000 (05:51 -0500)]
Change how optional delay slot instructions are detected and squashed.
--HG--
extra : convert_revision :
ffd019d4adc2fbbc0a663d8dc6ef73edce12511b
Gabe Black [Wed, 6 Dec 2006 10:48:59 +0000 (05:48 -0500)]
Get rid of some typedefs which were hardly used, and move some stuff back here that shouldn't be in the architecture specific DynInst classes.
--HG--
extra : convert_revision :
dad0d7191acf773c16dc3ed9dd911f5e8bfc08b3
Gabe Black [Wed, 6 Dec 2006 10:47:19 +0000 (05:47 -0500)]
Change to use -return_value.value like other implementations.
--HG--
extra : convert_revision :
513422c1c8c24f3662e6a423d13ee033424aa44b
Gabe Black [Wed, 6 Dec 2006 10:46:44 +0000 (05:46 -0500)]
Some changes for misc regs which were changed into unofficial integer registers, and moved the flattenIndex function into the register file.
--HG--
extra : convert_revision :
6b797c793a6c12c61a23f0f78a1ea1c88609553e
Gabe Black [Wed, 6 Dec 2006 10:45:18 +0000 (05:45 -0500)]
Reorganize the includes and add an include for misc.hh.
--HG--
extra : convert_revision :
484b2d07a1e8b3879c35d80bf16b73fd0cc9be1f
Gabe Black [Wed, 6 Dec 2006 10:44:31 +0000 (05:44 -0500)]
Added some debug output, and made sure not to accidentally ask for the result of a store conditional.
--HG--
extra : convert_revision :
d36ff9e2343fdf78a3bc16a1348975fdba5c55e2
Gabe Black [Wed, 6 Dec 2006 10:43:25 +0000 (05:43 -0500)]
Some basic fix ups, and CWP is no longer set explicitly.
--HG--
extra : convert_revision :
1dde5594a2bcfd9fb5ad974360b3dc035f1624e5
Gabe Black [Wed, 6 Dec 2006 10:42:09 +0000 (05:42 -0500)]
Changed the integer register file to work with flattened indices.
--HG--
extra : convert_revision :
c5153c3c712e5d18b5233e1fd205806adcb30654
Gabe Black [Wed, 6 Dec 2006 10:41:08 +0000 (05:41 -0500)]
Change MIPS's setSyscallReturn to use a thread context.
--HG--
extra : convert_revision :
618f8404ec5380615e28170d761b2fcdf9c07d96
Gabe Black [Wed, 6 Dec 2006 10:40:11 +0000 (05:40 -0500)]
Added basic flatten function for mips.
--HG--
extra : convert_revision :
2c32851584001734d139f36c4d58c5e61067fcfc
Kevin Lim [Tue, 5 Dec 2006 16:12:18 +0000 (11:12 -0500)]
Override default SConscript options and only build the SimpleCPUs.
--HG--
extra : convert_revision :
cfcfb787d8442cb76ed766aa5bc947636f067209
Steve Reinhardt [Tue, 5 Dec 2006 15:24:13 +0000 (07:24 -0800)]
Merge zizzer.eecs.umich.edu:bk/newmem-cache2
into vm1.(none):/home/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
0a7d17460f17c96fe869124f54f9c92409495003
Steve Reinhardt [Tue, 5 Dec 2006 15:23:20 +0000 (10:23 -0500)]
Merge zizzer.eecs.umich.edu:/z/stever/bk/newmem-head
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
a5569cef10ab22da1865e368f0bb5e7532772227
Steve Reinhardt [Tue, 5 Dec 2006 15:18:35 +0000 (10:18 -0500)]
Merge zizzer.eecs.umich.edu:/z/stever/bk/newmem-head
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
ca78bf2fc1ddefd56b98a90eaffab57d93026626
Steve Reinhardt [Tue, 5 Dec 2006 15:16:36 +0000 (07:16 -0800)]
Don't compress data on writebacks unless it's actually necessary.
--HG--
extra : convert_revision :
7a068e28f9ea2f6aab57be7133b47bda72d10302
Gabe Black [Tue, 5 Dec 2006 06:55:02 +0000 (01:55 -0500)]
Move the SyscallReturn class into sim/syscallreturn.hh. Also move some miscregs into the integer register file so they get renamed.
src/arch/alpha/syscallreturn.hh:
src/arch/mips/syscallreturn.hh:
src/sim/syscallreturn.hh:
Move the SyscallReturn class into sim/syscallreturn.hh
src/arch/sparc/faults.cc:
src/arch/sparc/isa/operands.isa:
src/arch/sparc/isa_traits.hh:
src/arch/sparc/miscregfile.cc:
src/arch/sparc/miscregfile.hh:
src/arch/sparc/process.cc:
src/arch/sparc/sparc_traits.hh:
Move some miscregs into the integer register file so they get renamed.
--HG--
extra : convert_revision :
df5b94fa1e7fdca34816084e0a423d6fdf86c79b
Steve Reinhardt [Tue, 5 Dec 2006 05:35:48 +0000 (21:35 -0800)]
Merge vm1.(none):/home/stever/bk/newmem-head
into vm1.(none):/home/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
e456687d940c833d8255a88633555778480f7825
Steve Reinhardt [Tue, 5 Dec 2006 00:10:50 +0000 (16:10 -0800)]
Merge zizzer.eecs.umich.edu:/bk/newmem
into vm1.(none):/home/stever/bk/newmem-head
--HG--
extra : convert_revision :
df2b33a629ae4298c4da33383b491e3cbefab92d
Steve Reinhardt [Tue, 5 Dec 2006 00:07:00 +0000 (19:07 -0500)]
Update SPEC CPU2000 tests with actual benchmark output.
tests/long/00.gzip/ref/alpha/linux/o3-timing/config.ini:
tests/long/00.gzip/ref/alpha/linux/o3-timing/config.out:
tests/long/00.gzip/ref/alpha/linux/o3-timing/m5stats.txt:
tests/long/00.gzip/ref/alpha/linux/o3-timing/stderr:
tests/long/00.gzip/ref/alpha/linux/o3-timing/stdout:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/config.ini:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/config.out:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/stderr:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/stdout:
tests/long/00.gzip/ref/alpha/linux/simple-timing/config.ini:
tests/long/00.gzip/ref/alpha/linux/simple-timing/config.out:
tests/long/00.gzip/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/00.gzip/ref/alpha/linux/simple-timing/stderr:
tests/long/00.gzip/ref/alpha/linux/simple-timing/stdout:
tests/long/30.eon/ref/alpha/linux/simple-atomic/config.ini:
tests/long/30.eon/ref/alpha/linux/simple-atomic/config.out:
tests/long/30.eon/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/30.eon/ref/alpha/linux/simple-atomic/stderr:
tests/long/30.eon/ref/alpha/linux/simple-atomic/stdout:
tests/long/30.eon/ref/alpha/linux/simple-timing/config.ini:
tests/long/30.eon/ref/alpha/linux/simple-timing/config.out:
tests/long/30.eon/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/30.eon/ref/alpha/linux/simple-timing/stderr:
tests/long/30.eon/ref/alpha/linux/simple-timing/stdout:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/config.ini:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/config.out:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/stderr:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/stdout:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/config.ini:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/config.out:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/stderr:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/stdout:
tests/long/50.vortex/ref/alpha/linux/o3-timing/config.ini:
tests/long/50.vortex/ref/alpha/linux/o3-timing/config.out:
tests/long/50.vortex/ref/alpha/linux/o3-timing/m5stats.txt:
tests/long/50.vortex/ref/alpha/linux/o3-timing/stderr:
tests/long/50.vortex/ref/alpha/linux/o3-timing/stdout:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/config.ini:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/config.out:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/stderr:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/stdout:
tests/long/50.vortex/ref/alpha/linux/simple-timing/config.ini:
tests/long/50.vortex/ref/alpha/linux/simple-timing/config.out:
tests/long/50.vortex/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/50.vortex/ref/alpha/linux/simple-timing/stderr:
tests/long/50.vortex/ref/alpha/linux/simple-timing/stdout:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/config.ini:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/config.out:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/m5stats.txt:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/stderr:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/stdout:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/config.ini:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/config.out:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/stderr:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/stdout:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/config.ini:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/config.out:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/stderr:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/stdout:
tests/long/70.twolf/ref/alpha/linux/o3-timing/config.ini:
tests/long/70.twolf/ref/alpha/linux/o3-timing/config.out:
tests/long/70.twolf/ref/alpha/linux/o3-timing/m5stats.txt:
tests/long/70.twolf/ref/alpha/linux/o3-timing/stderr:
tests/long/70.twolf/ref/alpha/linux/o3-timing/stdout:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.ini:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.out:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/stderr:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/stdout:
tests/long/70.twolf/ref/alpha/linux/simple-timing/config.ini:
tests/long/70.twolf/ref/alpha/linux/simple-timing/config.out:
tests/long/70.twolf/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/70.twolf/ref/alpha/linux/simple-timing/stderr:
tests/long/70.twolf/ref/alpha/linux/simple-timing/stdout:
Update with actual benchmark output.
--HG--
extra : convert_revision :
12e8de58172dd717d9cc8c5c27dd926a7257153c
Steve Reinhardt [Tue, 5 Dec 2006 00:05:09 +0000 (19:05 -0500)]
Only update stderr, stdout, m5stats.txt, and config.* on update_ref,
since we don't know which of the other files are outputs and which
are inputs.
--HG--
extra : convert_revision :
b038bd15930721ab9fceb0a18ab5c895aacb5309
Steve Reinhardt [Mon, 4 Dec 2006 23:57:17 +0000 (18:57 -0500)]
Clean up SPEC CPU2000 reference files.
Get rid of reference files for o3-atomic (non-existent configuration)
and mcf (doesn't seem to be working).
Left in empty refs for parser/simple-timing... this appears to be
dying because it's running out of memory, so maybe it will be OK
once we get the memory leak fixed.
--HG--
extra : convert_revision :
ae3bc8dfec44d09a2a084da5041ec386fe16be8b
Steve Reinhardt [Mon, 4 Dec 2006 17:10:53 +0000 (09:10 -0800)]
Turn cache MissQueue/BlockingBuffer into virtual object
instead of template parameter.
--HG--
extra : convert_revision :
fce0fbd041149b9c781eb23f480ba84fddbfd4a0
Steve Reinhardt [Mon, 4 Dec 2006 17:09:36 +0000 (09:09 -0800)]
Better handling of scons -u targets.
--HG--
extra : convert_revision :
7bf0688a1c83d8385b77a59a1c75040e9624c0ae
Steve Reinhardt [Mon, 4 Dec 2006 16:59:53 +0000 (08:59 -0800)]
SConstruct:
Couple minor fixes.
SConstruct:
Couple minor fixes.
--HG--
extra : convert_revision :
25f3c12570287334c2cbd1cf9b8227043a57e7d1
Steve Reinhardt [Mon, 4 Dec 2006 16:55:06 +0000 (08:55 -0800)]
import os.path.join as joinpath
--HG--
extra : convert_revision :
200612675e49908b9ff9c965aede35a657241391
Steve Reinhardt [Sun, 3 Dec 2006 06:26:40 +0000 (22:26 -0800)]
Merge vm1.(none):/home/stever/bk/newmem-head
into vm1.(none):/home/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
321f7fcc8bd6c6aaaab92d10172814f4d07d5e65
Steve Reinhardt [Sun, 3 Dec 2006 06:24:52 +0000 (22:24 -0800)]
Support better param conversions to/from numeric subclasses.
--HG--
extra : convert_revision :
2ccb75b0912a384789458710fd9bbb65626f839e
Steve Reinhardt [Sun, 3 Dec 2006 06:23:46 +0000 (22:23 -0800)]
Fix help strings on GenRepl params.
--HG--
extra : convert_revision :
520814e193b9e86b6410f3ab98d62ed131d295aa
Steve Reinhardt [Sun, 3 Dec 2006 06:22:58 +0000 (22:22 -0800)]
Make cache compression policy a runtime virtual thing
instead of a template policy.
--HG--
extra : convert_revision :
6a4ac7a189a950390a973fdfce94f56190de92db
Steve Reinhardt [Sun, 3 Dec 2006 06:12:26 +0000 (22:12 -0800)]
Merge zizzer.eecs.umich.edu:/bk/newmem
into vm1.(none):/home/stever/bk/newmem-head
--HG--
extra : convert_revision :
4a077b463b938c54b546b00e586d8609c24ae465
Steve Reinhardt [Sun, 3 Dec 2006 06:11:24 +0000 (01:11 -0500)]
Delete src/oldmem.
util/make_release.py:
src/oldmem gone from repo, no need to delete here.
--HG--
extra : convert_revision :
570fa1b8d7144376cf13a010160a39d1c1cccbc2
Steve Reinhardt [Sun, 3 Dec 2006 03:52:26 +0000 (19:52 -0800)]
Merge zizzer.eecs.umich.edu:/bk/newmem
into vm1.(none):/home/stever/bk/newmem-head
--HG--
extra : convert_revision :
4c8de6e4c6f729c83e92abd81ea6c1347e647756
Kevin Lim [Sat, 2 Dec 2006 18:33:46 +0000 (13:33 -0500)]
Fixes for MIPS_SE compiling. Regressions seem to work, but Korey should make sure these changes (commit especially) work okay.
src/cpu/o3/commit_impl.hh:
src/cpu/o3/fetch_impl.hh:
Fixes for MIPS_SE compile.
--HG--
extra : convert_revision :
fde9616f8e72b397c5ca965774172372cff53790
Lisa Hsu [Sat, 2 Dec 2006 16:11:58 +0000 (11:11 -0500)]
stats update
--HG--
extra : convert_revision :
b47d3817d204a43e0afb89aafc8dacf619c3f910
Nathan Binkert [Sat, 2 Dec 2006 06:33:18 +0000 (22:33 -0800)]
don't blow away the whole destination directory
--HG--
extra : convert_revision :
7370bad15cc30e75ebb0c8685324d8db06fc2936
Lisa Hsu [Fri, 1 Dec 2006 18:51:49 +0000 (13:51 -0500)]
change this to be a quick one so that it's in the regressions every night - it's only maybe 15 min. long.
tests/configs/twosys-tsunami-simple-atomic.py:
don't need this import
--HG--
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.ini => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.ini
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.out => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.out
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.drivesys.sim_console => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.drivesys.sim_console
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.testsys.sim_console => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.testsys.sim_console
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/m5stats.txt => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/m5stats.txt
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stderr => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stderr
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stdout => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stdout
rename : tests/long/80.netperf-stream/test.py => tests/quick/80.netperf-stream/test.py
extra : convert_revision :
68497b2ef8b21590cb6c636485703e46dc616513
Lisa Hsu [Fri, 1 Dec 2006 06:24:16 +0000 (01:24 -0500)]
Merge zizzer:/bk/newmem
into zed.eecs.umich.edu:/z/hsul/work/m5/newmem
--HG--
extra : convert_revision :
b62ca8009105aad7173bdbc5d528de243d21a82c
Lisa Hsu [Fri, 1 Dec 2006 06:24:01 +0000 (01:24 -0500)]
add a simple netperf-stream test to the long tests.
tests/SConscript:
add a new configuration for two-system tests (atomic simple only)
--HG--
extra : convert_revision :
16c260ab16f38779fe17b1cab18f36d5c7a70846
Nathan Binkert [Fri, 1 Dec 2006 04:53:30 +0000 (20:53 -0800)]
Merge zizzer.eecs.umich.edu:/bk/newmem
into iceaxe.:/Volumes/work/m5/incoming
--HG--
extra : convert_revision :
05060a06e0b6d66a9c1e7005c233047c6e8ba15f
Nathan Binkert [Fri, 1 Dec 2006 04:50:47 +0000 (20:50 -0800)]
Get rid of the old release-edits script and create make_release.py
which takes care of almost everything needed for putting together
a release.
--HG--
extra : convert_revision :
b05d418a1002633b1286591eb8a8588ba33f5df1
Ron Dreslinski [Thu, 30 Nov 2006 20:01:49 +0000 (15:01 -0500)]
Update stats to match writeback fix that was made
--HG--
extra : convert_revision :
3e0ed2b374d8d96798ea9b3416c9e5579cafacda
Lisa Hsu [Thu, 30 Nov 2006 16:53:33 +0000 (11:53 -0500)]
netperf-maerts-client.rcS:
change /netperf/netperf to /netperf-bin/netperf
nat-netperf-maerts-client.rcS:
bad comment that went with the file - accidentally committed but probably doesn't matter, i ust eliminated an ivlb in the script.
configs/boot/nat-netperf-maerts-client.rcS:
replace netperf/netperf with netperf-bin/netperf
configs/boot/netperf-maerts-client.rcS:
change /netperf/netperf to /netperf-bin/netperf
--HG--
extra : convert_revision :
32fed0042e267f315d3e688ebc4b66d7002b85f0
Steve Reinhardt [Wed, 29 Nov 2006 21:17:41 +0000 (13:17 -0800)]
cscope-find.py:
Write directly to 'cscope.files' and run 'cscope -b' .
Now this script does everything automatically.
cscope-index.py:
Rename: util/cscope-find.py -> util/cscope-index.py
util/cscope-find.py:
Write directly to 'cscope.files' and run 'cscope -b' .
Now this script does everything automatically.
--HG--
rename : util/cscope-find.py => util/cscope-index.py
extra : convert_revision :
cd6fa5cc0c2146f7184c9213956aff67c7cb9341
Kevin Lim [Wed, 29 Nov 2006 21:08:19 +0000 (16:08 -0500)]
Merge ktlim@zizzer:/bk/newmem
into zamp.eecs.umich.edu:/z/ktlim2/clean/tmp/test-regress
--HG--
extra : convert_revision :
3142f68356458ecd2677c30e9cf0a65005b782c2
Kevin Lim [Wed, 29 Nov 2006 21:07:55 +0000 (16:07 -0500)]
Change the connecting of the physPort and virtPort to the memory object below the CPU to happen every time activateContext is called. The overhead is probably a little higher than necessary, but allows these connections to properly be made when there are CPUs that are inactive until they are switched in.
Right now this introduces a minor memory leak as old physPorts and virtPorts are not deleted when new ones are created. A flyspray task has been created for this issue. It can not be resolved until we determine how the bus will handle giving out ID's to functional ports that may be deleted.
src/cpu/o3/cpu.cc:
src/cpu/simple/atomic.cc:
src/cpu/simple/timing.cc:
Change the setup of the physPort and virtPort to instead happen every time the CPU has a context activated. This is a little high overhead, but keeps it working correctly when the CPU does not have a physical memory attached to it until it switches in (like the case of switch CPUs).
src/cpu/o3/thread_context.hh:
Change function from being called at init() to just being called whenever the memory ports need to be connected.
src/cpu/o3/thread_context_impl.hh:
Update this to not delete the port if it's the same as the virtPort.
src/cpu/thread_context.hh:
Change function from being called at init() to whenever the memory ports need to be connected.
src/cpu/thread_state.cc:
Instead of initializing the ports, simply connect them, deleting any old ports that might exist. This allows these functions to be called multiple times.
src/cpu/thread_state.hh:
Ports are no longer initialized, but rather connected at context activation time.
--HG--
extra : convert_revision :
e399ce5dfbd6ad658c953a7c9c7b69b89a70219e
Kevin Lim [Wed, 29 Nov 2006 16:50:03 +0000 (11:50 -0500)]
Add in O3CPU to default CPU list.
--HG--
extra : convert_revision :
4aaaae058cb763580ea0b9019d4a9346938121d4
Ali Saidi [Tue, 28 Nov 2006 21:02:13 +0000 (16:02 -0500)]
add 2.0b2 release notes
--HG--
extra : convert_revision :
ce34f8086f682cc732bf868f6b9700e42c604ca3
Kevin Lim [Tue, 28 Nov 2006 16:41:17 +0000 (11:41 -0500)]
Merge ktlim@zizzer:/bk/newmem
into zamp.eecs.umich.edu:/z/ktlim2/clean/tmp/test-regress
--HG--
extra : convert_revision :
ffc7931d7da153b421b3c838a0968e484fd182ec
Kevin Lim [Tue, 28 Nov 2006 16:41:08 +0000 (11:41 -0500)]
Remove assertion. It's not needed and messes up writebacks when a 2 level cache is used in a uniprocessor setting.
--HG--
extra : convert_revision :
020a9799cd7177fdb85a767701d6fcb8cf018827
Steve Reinhardt [Mon, 27 Nov 2006 07:16:24 +0000 (02:16 -0500)]
Add TRACING_ON setting for m5.prof.
--HG--
extra : convert_revision :
ebda49bff30d76d3209acce55458d3f4e29594d3
Kevin Lim [Sun, 26 Nov 2006 16:46:58 +0000 (11:46 -0500)]
Include check for making sure caches are enabled.
--HG--
extra : convert_revision :
e3902b065db524ebe5bf762e44a840133ccb8d75
Gabe Black [Sat, 25 Nov 2006 03:06:33 +0000 (22:06 -0500)]
Initial changes to get O3 working with SPARC
src/arch/sparc/process.cc:
MachineBytes doesn't exist any more.
src/arch/sparc/regfile.cc:
Add in the miscRegFile for good measure.
src/cpu/o3/isa_specific.hh:
Add in a section for SPARC
src/cpu/o3/sparc/cpu.cc:
src/cpu/o3/sparc/cpu.hh:
src/cpu/o3/sparc/cpu_builder.cc:
src/cpu/o3/sparc/cpu_impl.hh:
src/cpu/o3/sparc/dyn_inst.cc:
src/cpu/o3/sparc/dyn_inst.hh:
src/cpu/o3/sparc/dyn_inst_impl.hh:
src/cpu/o3/sparc/impl.hh:
src/cpu/o3/sparc/params.hh:
src/cpu/o3/sparc/thread_context.cc:
src/cpu/o3/sparc/thread_context.hh:
Sparc version of this file.
--HG--
extra : convert_revision :
34bb5218f802d0a1328132a518cdd769fb59b6a4
Gabe Black [Fri, 24 Nov 2006 19:08:44 +0000 (14:08 -0500)]
Merge zower:/eecshome/m5/newmem
into ewok.(none):/home/gblack/m5/newmemo3
--HG--
extra : convert_revision :
e8d6ce19a83fe526112c1dd61c48196eb8c0951f
Gabe Black [Fri, 24 Nov 2006 19:08:43 +0000 (14:08 -0500)]
Merge zizzer:/bk/newmem
into zower.eecs.umich.edu:/eecshome/m5/newmem
--HG--
extra : convert_revision :
7dbd30ce5579dd62d5f54bb5d75cf12346bc5d1d
Gabe Black [Fri, 24 Nov 2006 19:01:18 +0000 (14:01 -0500)]
Rename this function.
--HG--
extra : convert_revision :
57ea1e1d3b75e35abb3310d392ec70086fff699a
Gabe Black [Fri, 24 Nov 2006 19:00:45 +0000 (14:00 -0500)]
Fix weird type modifier.
--HG--
extra : convert_revision :
7372b7a92b3c9d05388acb43ba58ada18464fa24
Gabe Black [Fri, 24 Nov 2006 19:00:00 +0000 (14:00 -0500)]
Fix an include problem.
--HG--
extra : convert_revision :
89be55bd3f4f9b452a680a98b69ce42b80546769
Steve Reinhardt [Fri, 24 Nov 2006 17:32:33 +0000 (12:32 -0500)]
Add no-op versions of ivlb and ivle back in for backwards compatibility.
--HG--
extra : convert_revision :
383b72c130b20f3d7cde4e08fa36a481f3c0bf7c
Steve Reinhardt [Thu, 23 Nov 2006 15:46:24 +0000 (10:46 -0500)]
Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/newmem
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-head
--HG--
extra : convert_revision :
154bc605c62b1e51c32e65916d4c2eda3a3f22fd
Gabe Black [Thu, 23 Nov 2006 06:27:41 +0000 (01:27 -0500)]
Use the right constant.
--HG--
extra : convert_revision :
f93182ed41057025cc10df443b24e82fbe783df6
Gabe Black [Thu, 23 Nov 2006 05:36:42 +0000 (00:36 -0500)]
Fixes to the isa description.
src/arch/sparc/isa/base.isa:
Fix a constant.
src/arch/sparc/isa/decoder.isa:
Made carry calculation more consistent.
src/arch/sparc/isa/operands.isa:
Use the right constant.
--HG--
extra : convert_revision :
25b3a09ff20d4b8e1a95ee8a983d14ef3cfe73bb
Gabe Black [Thu, 23 Nov 2006 04:49:44 +0000 (23:49 -0500)]
Moved some constants from isa_traits.hh to the reg file headers.
--HG--
extra : convert_revision :
378b2d9791e6282539900a2261ad2275d726b4be
Gabe Black [Thu, 23 Nov 2006 04:09:27 +0000 (23:09 -0500)]
Added a parameter to set memory to zero. This is to support Legion, and once we can make our own hypervisor binary, we probably won't need it.
--HG--
extra : convert_revision :
168883e4a5d3760962cd9759a6f41c66f5a6402a