gem5/src/mem
Ali Saidi 0c29a97ba9 Prefetch: Don't prefetch if address is in the write queue.
Check that we're not currently writing back an address the prefetcher is trying
to prefetch before issuing it. We previously checked the mshrQueue and the cache
itself, but forgot to check the writeBuffer. This fixes a memory corrucption
issue with an L2 prefetcher.
2011-09-13 12:06:13 -05:00
..
cache Prefetch: Don't prefetch if address is in the write queue. 2011-09-13 12:06:13 -05:00
config Fixes to get prefetching working again. 2009-02-16 08:56:40 -08:00
protocol Functional Accesses: Update states to support Broadcast/Snooping protocols. 2011-09-01 11:41:44 -07:00
ruby Functional Accesses: Update states to support Broadcast/Snooping protocols. 2011-09-01 11:41:44 -07:00
slicc Functional Accesses: Update states to support Broadcast/Snooping protocols. 2011-09-01 11:41:44 -07:00
bridge.cc trace: reimplement the DTRACE function so it doesn't use a vector 2011-04-15 10:44:32 -07:00
bridge.hh includes: sort all includes 2011-04-15 10:44:06 -07:00
Bridge.py DMA: Add IOCache and fix bus bridge to optionally only send requests one 2007-08-10 16:14:01 -04:00
bus.cc trace: reimplement the DTRACE function so it doesn't use a vector 2011-04-15 10:44:32 -07:00
bus.hh includes: sort all includes 2011-04-15 10:44:06 -07:00
Bus.py bus: clean up default responder code. 2010-08-17 05:06:21 -07:00
dram.cc Replace curTick global variable with accessor functions. 2011-01-07 21:50:29 -08:00
dram.hh stats: Fix all stats usages to deal with template fixes 2009-03-05 19:09:53 -08:00
mem_object.cc params: Get rid of the remnants of the old style parameter configuration stuff. 2008-08-11 12:22:17 -07:00
mem_object.hh params: Get rid of the remnants of the old style parameter configuration stuff. 2008-08-11 12:22:17 -07:00
MemObject.py Major changes to how SimObjects are created and initialized. Almost all 2007-07-23 21:51:38 -07:00
mport.cc Replace curTick global variable with accessor functions. 2011-01-07 21:50:29 -08:00
mport.hh Create a message port for sending messages as apposed to reading/writing a memory range. 2008-10-12 12:08:51 -07:00
packet.cc Ruby: Add support for functional accesses 2011-06-30 19:49:26 -05:00
packet.hh Ruby: Add support for functional accesses 2011-06-30 19:49:26 -05:00
packet_access.hh arch: nuke arch/isa_specific.hh and move stuff to generated config/the_isa.hh 2009-09-23 08:34:21 -07:00
page_table.cc trace: reimplement the DTRACE function so it doesn't use a vector 2011-04-15 10:44:32 -07:00
page_table.hh Faults: Pass the StaticInst involved, if any, to a Fault's invoke method. 2010-09-13 19:26:03 -07:00
physical.cc Mem: Use sysconf to get the page size instead of the PAGE_SIZE macro. 2011-06-08 00:57:50 -07:00
physical.hh SE: Fix simulating more than 4GB of RAM in SE mode 2010-11-19 18:01:01 -06:00
PhysicalMemory.py Make default PhysicalMemory latency slightly more realistic. 2008-08-03 18:13:29 -04:00
port.cc trace: reimplement the DTRACE function so it doesn't use a vector 2011-04-15 10:44:32 -07:00
port.hh types: clean up types, especially signed vs unsigned 2009-06-04 23:21:12 -07:00
port_impl.hh arch: nuke arch/isa_specific.hh and move stuff to generated config/the_isa.hh 2009-09-23 08:34:21 -07:00
request.hh Spelling: Fix the a spelling error by changing mmaped to mmapped. 2011-03-01 23:18:47 -08:00
SConscript scons: rename TraceFlags to DebugFlags 2011-06-02 17:36:21 -07:00
tport.cc trace: reimplement the DTRACE function so it doesn't use a vector 2011-04-15 10:44:32 -07:00
tport.hh includes: sort all includes 2011-04-15 10:44:06 -07:00
translating_port.cc Stack: Tidy up some comments, a warning, and make stack extension consistent. 2011-09-09 01:01:43 -07:00
translating_port.hh fix the translating ports so it can add a page on a fault 2007-05-09 15:37:46 -04:00
vport.cc arch: nuke arch/isa_specific.hh and move stuff to generated config/the_isa.hh 2009-09-23 08:34:21 -07:00
vport.hh includes: sort all includes 2011-04-15 10:44:06 -07:00