0dcb288365
are more efficient and reduce the number of new/delete calls
arch/alpha/stacktrace.cc:
- Change the StackTrace code so that the class can more easily be
cleaned out and reused to avoid extra allocations.
- Allow trace() to accept a static instruction pointer so it can
determine if the instruction is worth tracing. This is moved from
the CPU.
- provide constants for special meaning PCs (user, console, unknown),
instead of magic numbers
- switch to using kernelSymtab instead of allSymtab which will be
going away
- if the stack adjustment doesn't make any sense, exit and push
unknown so we don't get into an infinite loop or record garbage.
- check to see if we've made too many iterations through the stack
and panic to avoid an infinite loop
arch/alpha/stacktrace.hh:
- Change the StackTrace code so that the class can more easily be
cleaned out and reused to avoid extra allocations.
- Allow trace() to accept a static instruction pointer so it can
determine if the instruction is worth tracing. This is moved from
the CPU.
- provide constants for special meaning PCs (user, console, unknown),
instead of magic numbers
cpu/base.cc:
only clear the profile if we have one
include profile.hh here since base.hh doesn't do it anymore
cpu/base.hh:
no need to include cpu/profile.hh here
cpu/profile.cc:
use ProfileNode pointers instead of objects in the ChildList
Consume a vector of addresses since that's really all we
care about.
cpu/profile.hh:
Keep pointers to ProfileNodes to reduce the size of these structures
keep a StackTrace around so that we may reuse it.
provide consume functions that use the new StackTrace trace interface
one consume function is inline and tries to fastpath the no trace
condition, it calls the outlined consume function if a trace is generated.
cpu/simple/cpu.cc:
include cpu/profile.hh here since base.hh no longer does
use the new FunctionProfile::consume interface
(which contains the tracing functions)
--HG--
extra : convert_revision : 5a1d9265289a75f67a497b322926be1f8c2d8eb3
This is release m5_1.1 of the M5 simulator. This file contains brief "getting started" instructions. For more information, see http://m5.eecs.umich.edu. If you have questions, please send mail to m5sim-users@lists.sourceforge.net. WHAT'S INCLUDED (AND NOT) ------------------------- The basic source release includes these subdirectories: - m5: the simulator itself - m5-test: regression tests - ext: less-common external packages needed to build m5 - alpha-system: source for Alpha console and PALcode To run full-system simulations, you will need compiled console, PALcode, and kernel binaries and one or more disk images. These files are collected in a separate archive, m5_system_1.1.tar.bz2. This file is included on the CD release, or you can download it separately from Sourceforge. M5 supports Linux 2.4/2.6, FreeBSD, and the proprietary Compaq/HP Tru64 version of Unix. We are able to distribute Linux and FreeBSD bootdisks, but we are unable to distribute bootable disk images of Tru64 Unix. If you have a Tru64 license and are interested in obtaining disk images, contact us at m5-dev@eecs.umich.edu. The CD release includes a few extra goodies, such as a tar file containing doxygen-generated HTML documentation (html-docs.tar.gz), a set of Linux source patches (linux_m5-2.6.8.1.diff), and the scons program needed to build M5. If you do not have the CD, the same HTML documentation is available online at http://m5.eecs.umich.edu/docs, the Linux source patches are available at http://m5.eecs.umich.edu/dist/linux_m5-2.6.8.1.diff, and the scons program is available from http://www.scons.org. WHAT'S NEEDED ------------- - GCC version 3.3 or newer - Python 2.3 or newer - SCons 0.96.1 or newer (see http://www.scons.org) WHAT'S RECOMMENDED ------------------ - MySQL (for statistics complex statistics storage/retrieval) - Python-MysqlDB (for statistics analysis) GETTING STARTED --------------- There are two different build targets and three optimizations levels: Target: ------- ALPHA_SE - Syscall emulation simulation ALPHA_FS - Full system simulation Optimization: ------------- m5.debug - debug version of the code with tracing and without optimization m5.opt - optimized version of code with tracing m5.fast - optimized version of the code without tracing and asserts Different targets are built in different subdirectories of m5/build. Binaries with the same target but different optimization levels share the same directory. Note that you can build m5 in any directory you choose;p just configure the target directory using the 'mkbuilddir' script in m5/build. The following steps will build and test the simulator. The variable "$top" refers to the top directory where you've unpacked the files, i.e., the one containing the m5, m5-test, and ext directories. If you have a multiprocessor system, you should give scons a "-j N" argument (like make) to run N jobs in parallel. To build and test the syscall-emulation simulator: cd $top/m5/build scons ALPHA_SE/test/opt/quick This process takes under 10 minutes on a dual 3GHz Xeon system (using the '-j 4' option). To build and test the full-system simulator: 1. Unpack the full-system binaries from m5_system_1.1.tar.bz2. (See above for directions on obtaining this file if you don't have it.) This package includes disk images and kernel, palcode, and console binaries for Linux and FreeBSD. 2. Edit the SYSTEMDIR search path in $top/m5-test/SysPaths.py to include the path to your local copy of the binaries. 3. In $top/m5/build, run "scons ALPHA_FS/test/opt/quick". This process also takes under 10 minutes on a dual 3GHz Xeon system (again using the '-j 4' option).