cpu/cpu_exec_context.cc:
Be sure to switch over the kernel stats so things don't get messed up. This may lead to weird stats files for sampling runs (detailed stats should be correct, regardless of which kernel stats this is defined on).
cpu/o3/cpu.cc:
Updates for switching out. Also include a bunch of debug info if needed.
cpu/o3/fetch_impl.hh:
Switch out properly.
cpu/o3/inst_queue.hh:
cpu/o3/inst_queue_impl.hh:
Comment out unused stats (they made the stats file huge).
cpu/o3/lsq_unit.hh:
cpu/o3/lsq_unit_impl.hh:
Add in new stat.
cpu/o3/rename.hh:
Fix up for switching out.
cpu/o3/rename_impl.hh:
Fix up for switching out. Be sure to mark any Misc regs as ready if their renamed inst got squashed from being switched out.
cpu/ozone/cpu_impl.hh:
cpu/simple/cpu.cc:
Switch out fixup.
sim/eventq.hh:
Make CPU switching more immediate.
Also comment out the assertion, as it doesn't apply if we're putting it on an inst-based queue.
--HG--
extra : convert_revision : f40ed40604738993f061e0c628810ff37a920562
cpu/checker/cpu.cc:
Print better error messages.
cpu/checker/cpu.hh:
Fix up small bug (similar to Ozone's DynInsts with FPs and float/doubles), output better messages.
--HG--
extra : convert_revision : 0e199b3dbbcdb5917cdfbebb4c5c18e4b9056c86
cpu/base.cc:
Be sure to deschedule the profile event so it doesn't take profiles while the CPU is switched out.
Also include the option to reset stats at a specific instruction.
cpu/base.hh:
Include the option to reset stats at a specific instruction.
cpu/checker/cpu_builder.cc:
Handle stats reset inst.
cpu/o3/alpha_cpu_builder.cc:
Handle stats reset inst, allow for profiling.
cpu/ozone/cpu_builder.cc:
Handle profiling, stats reset event, slightly different parameters.
python/m5/objects/BaseCPU.py:
Add in stats reset.
--HG--
extra : convert_revision : e27a78f7fb8fd19c53d9f2c1e6edce4a98cbafdb
arch/alpha/freebsd/system.cc:
arch/alpha/isa/decoder.isa:
arch/alpha/linux/system.cc:
arch/alpha/system.cc:
arch/alpha/tru64/system.cc:
Let symbol files be read in so that profiling can happen on the binaries as well.
python/m5/objects/System.py:
Add in symbol files.
sim/pseudo_inst.cc:
Load in a specified symbol file.
sim/pseudo_inst.hh:
Allow for symbols to be loaded.
sim/system.hh:
Support symbol file.
util/m5/m5.c:
util/m5/m5op.S:
Add support to m5 util for loading symbols (and readfile).
--HG--
extra : convert_revision : f10c1049bcd7b22b98c73052c0666b964aff222b
Working on pulling out the changes in the cache so that it remains working.
src/mem/bus.cc:
Changes for multi-phase snoop
Some code for registering snoop ranges (a version that compiles and runs, but does nothing)
src/mem/bus.hh:
Changes for multi-phase snoop
src/mem/packet.hh:
Flag for multi-phase snoop
src/mem/port.hh:
Status for multi-phase snoop
--HG--
extra : convert_revision : 4c2e5263bba16e3bcf03aabe36ff45ec36de4720
Add checks for swig & libz, version check for swig.
Factor out version check code into function, use for mysql too.
SConstruct:
Add checks for swig & libz, version check for swig.
Factor out version check code into function, use for mysql too.
--HG--
extra : convert_revision : a077d961ae52011141fbf5021b167485f8638139
Added in the filename parameter which is provided for the user space linker.
Fix the ordering and alignment of stack elements.
Made mmap start with the address it has been seen starting with "in the wild"
--HG--
extra : convert_revision : 8734753145f59a6cb433e4f92f43cb28a44b56d4
1. alignaddr wrote it's address to a floating point register rather than a gpr.
2. sethi was sign extending it's immediate value.
--HG--
extra : convert_revision : 9aa30a6485bc4cba916367973b986d439b7c7588
Arg to m5.simulate() is a delta, not an absolute curTick value.
I didn't test this change, but I'm not convinced the previous
example was tested either, so I don't feel too badly about it.
configs/example/fs.py:
Arg to m5.simulate() is a delta, not an absolute curTick value.
I didn't test this change, but I'm not convinced the previous
example was tested either, so I don't feel too badly about it.
--HG--
extra : convert_revision : ef7df7b83b3e2b5da02408c674169ccbed75a441
rename build/*/test dir to build/*/tests for consistency
SConstruct:
rename build/*/test dir to build/*/tests for consistency
--HG--
extra : convert_revision : 6af3cf6b2d6582b2c4d2bc9211e44767e0fa494f
also, update all the rcS files so that they are in sync with the new linux-dist build system.
configs/boot/devtime.rcS:
configs/boot/iscsi-client.rcS:
configs/boot/iscsi-server.rcS:
configs/boot/micro_memlat.rcS:
configs/boot/micro_stream.rcS:
configs/boot/micro_tlblat.rcS:
configs/boot/nat-netperf-maerts-client.rcS:
configs/boot/nat-netperf-server.rcS:
configs/boot/nat-netperf-stream-client.rcS:
configs/boot/nat-spec-surge-client.rcS:
configs/boot/nat-spec-surge-server.rcS:
configs/boot/natbox-netperf.rcS:
configs/boot/natbox-spec-surge.rcS:
configs/boot/netperf-rr.rcS:
configs/boot/netperf-server.rcS:
configs/boot/netperf-stream-client.rcS:
configs/boot/netperf-stream-nt-client.rcS:
configs/boot/nfs-client-nhfsstone.rcS:
configs/boot/nfs-client-tcp-smallb.rcS:
configs/boot/nfs-client-tcp.rcS:
configs/boot/nfs-client.rcS:
configs/boot/nfs-server-nhfsstone.rcS:
configs/boot/nfs-server.rcS:
configs/boot/ping-client.rcS:
configs/boot/ping-server.rcS:
configs/boot/spec-surge-client.rcS:
configs/boot/spec-surge-server.rcS:
configs/boot/surge-client.rcS:
configs/boot/surge-server.rcS:
make tree rcS files reflect what we've been actually using in /dist.
--HG--
extra : convert_revision : 48fe4fe71938ef9d029e428028a271242c8d2faa
src/python/m5/objects/BaseCPU.py:
Make mem parameter a MemObject, not just a PhysicalMemory
Fix a reference not using self
tests/configs/simple-atomic.py:
Set the mem paramter
tests/configs/simple-timing.py:
Set the mem parameter
--HG--
extra : convert_revision : 6bd9df36831a1c5bafc9e88ab945c2ebe91db785
Kinda port DRAM to new memory system. The code is *really* ugly (not my fault) and right now something about the stats it uses
causes a simulator segfault.
src/SConscript:
Add dram.cc to sconscript
src/mem/physical.cc:
src/mem/physical.hh:
Add params struct to physical memory, use params, make latency function be virtual
src/python/m5/objects/PhysicalMemory.py:
Add DRAMMemory python class
--HG--
extra : convert_revision : 5bd9f2e071c62da89e8efa46fa016f342c01535d
Get rid of caches in simple-timing config for now.
tests/SConscript:
another line for diff to ignore
tests/configs/simple-timing.py:
turn off caches for now
tests/quick/00.hello/ref/mips/linux/simple-atomic/m5stats.txt:
tests/quick/00.hello/ref/mips/linux/simple-atomic/stdout:
tests/quick/00.hello/ref/sparc/linux/simple-atomic/m5stats.txt:
tests/quick/00.hello/ref/sparc/linux/simple-atomic/stdout:
update for inst/tick rate (old one was debug?)
tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini:
tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.out:
tests/quick/20.eio-short/ref/alpha/eio/simple-timing/m5stats.txt:
tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stderr:
tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stdout:
works now (no caches)
--HG--
extra : convert_revision : 472030f63297346976db6274a78235c93d4eef8e
