I'll push it some time today.
--
Nilay
On Wed, 30 Oct 2013, Lluc Alvarez wrote:
On Oct. 30, 2013, 1:17 p.m., Nilay Vaish wrote:
Ship It!
I cannot push the change to the repository, no permissions I guess...
- Lluc
-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/2073/#review4796
-----------------------------------------------------------
On Oct. 29, 2013, 4:18 p.m., Lluc Alvarez wrote:
-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/2073/
-----------------------------------------------------------
(Updated Oct. 29, 2013, 4:18 p.m.)
Review request for Default.
Repository: gem5
Description
-------
Add missing initializations of the SenderMachine field of out_msg's when thery
are created in the L2 cache controller of the MOESI_CMP_directory coherence
protocol. When an out_msg is created and this field is left uninitialized, it
is set to the default value MachineType_NUM. This causes a panic in the
MachineType_to_string function when gem5 is executed with the Ruby debug flag
on and it tries to print the message.
Diffs
-----
src/mem/protocol/MOESI_CMP_directory-L2cache.sm cd0a9c975c8c
Diff: http://reviews.gem5.org/r/2073/diff/
Testing
-------
Simple OpenMP vector addition microbenchmark running with the following command:
./build/X86/gem5.debug --debug-flags=Ruby --redirect-stdout --redirect-stderr
configs/example/se.py --output=/tmp/bench.out --errout=/tmp/bench.err --ruby
--cpu-type=detailed --num-cpus=4 --num-l2caches=4 --l2_size=1MB --num-dirs=4
--topology=Mesh -c /home/lluc/NAS/bin/vecadd -o "-numthreads 4"
Thanks,
Lluc Alvarez
_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev
