14deacf86egpu-compute: fix segfault when constructing GPUExecContext
Tony Gutierrez
2016-11-21 15:40:03 -0500
a0d4019abdgpu-compute: init valid field of GpuTlbEntry in default ctor
Tony Gutierrez
2016-11-21 15:38:30 -0500
f82418acefruby: add default ctor for MachineID type
Tony Gutierrez
2016-11-21 15:37:07 -0500
0799600686x86: fix issue with casting in Cvtf2i
Tony Gutierrez
2016-11-21 15:35:56 -0500
29d38e7576ruby: init MessageSizeType of SequencerMsg to Request_Control
Sooraj Puthoor
2016-11-19 12:39:04 -0500
ae55cba281x86: fix loading/storing of Float80 types
Tony Gutierrez
2016-11-19 12:35:14 -0500
af934452afext: Update fputils to rev 13589cd
Andreas Sandberg
2016-11-18 18:08:20 +0000
b8a162087dstats, alpha: Update ALPHA stats
Andreas Hansson
2016-11-17 04:54:18 -0500
4cf7f6c4catests, ruby: Move rubytests from ALPHA (linux) to NULL (none)
Andreas Hansson
2016-11-17 04:54:16 -0500
6ed567d600alpha: Remove ALPHA tru64 support and associated tests
Andreas Hansson
2016-11-17 04:54:14 -0500
74249f80dfhsail,gpu-compute: fixes to appease clang++
Tony Gutierrez
2016-10-26 22:48:45 -0400
dc16c1ceb8dev: Add m5 op to toggle synchronization for dist-gem5. This patch adds the ability for an application to request dist-gem5 to begin/ end synchronization using an m5 op. When toggling on sync, all nodes agree on the next sync point based on the maximum of all nodes' ticks. CPUs are suspended until the sync point to avoid sending network messages until sync has been enabled. Toggling off sync acts like a global execution barrier, where all CPUs are disabled until every node reaches the toggle off point. This avoids tricky situations such as one node hitting a toggle off followed by a toggle on before the other nodes hit the first toggle off.
Michael LeBeane
2016-10-26 22:48:40 -0400
48e43c9ad1ruby: Allow multiple outstanding DMA requests DMA sequencers and protocols can currently only issue one DMA access at a time. This patch implements the necessary functionality to support multiple outstanding DMA requests in Ruby.
Michael LeBeane
2016-10-26 22:48:37 -0400
96905971f2dev: Add 'simLength' parameter in EthPacketData Currently, all the network devices create a 16K buffer for the 'data' field in EthPacketData, and use 'length' to keep track of the size of the packet in the buffer. This patch introduces the 'simLength' parameter to EthPacketData, which is used to hold the effective length of the packet used for all timing calulations in the simulator. Serialization is performed using only the useful data in the packet ('length') and not necessarily the entire original buffer.
mlebeane
2016-10-26 22:48:33 -0400
de72e36619gpu-compute: support in-order data delivery in GM pipe
Tony Gutierrez
2016-10-26 22:48:28 -0400
b63eb1302bgpu-compute, hsail: pass GPUDynInstPtr to getRegisterIndex()
Tony Gutierrez
2016-10-26 22:47:49 -0400
aa7364276fgpu-compute: use System cache line size in the GPU
Tony Gutierrez
2016-10-26 22:47:47 -0400
844fb845a5gpu-compute, hsail: make the PC a byte address, not an instruction index
Tony Gutierrez
2016-10-26 22:47:43 -0400
d327cdba07gpu-compute: add gpu_isa.hh to switch hdrs, add GPUISA to WF
Tony Gutierrez
2016-10-26 22:47:38 -0400
98d8a7051dgpu-compute: add instruction mix stats for the gpu
Tony Gutierrez
2016-10-26 22:47:30 -0400
c7a79c9a42gpu-compute, hsail: call discardFetch() from the WF
Tony Gutierrez
2016-10-26 22:47:27 -0400
8c5df4be2edev, arm: Make GenericTimer param handling more robust
Andreas Sandberg
2016-10-07 14:14:44 +0100
22e6f65d72ruby: Add M5_VAR_USED before variables used only inside assert in garnet2.0. This removes errors when building gem5.fast
Tushar Krishna
2016-10-06 21:06:00 -0400
dbe8892b76ruby: garnet2.0 Revamped version of garnet with more optimized single-cycle routers, more configurability, and cleaner code.
Tushar Krishna
2016-10-06 14:35:22 -0400
b512f4bf71ruby: remove the original garnet code. Only garnet2.0 will be supported henceforth.
Tushar Krishna
2016-10-06 14:35:21 -0400
0962d76827config: add port directions and per-router delay in topology. This patch adds port direction names to the links during topology creation, which can be used for better printed names for the links or for users to code up their own adaptive routing algorithms. It also adds support for every router to have an independent latency value to support heterogeneous topologies with the subsequent garnet2.0 patch.
Tushar Krishna
2016-10-06 14:35:20 -0400
003c08fa90config: make internal links in network topology unidirectional. This patch makes the internal links within the network topology unidirectional, thus allowing any deadlock-free routing algorithms to be specified from the topology itself using weights. This patch also renames Mesh.py and MeshDirCorners.py to Mesh_XY.py and MeshDirCorners_XY.py (Mesh with XY routing). It also adds a Mesh_westfirst.py and CrossbarGarnet.py topologies.
Tushar Krishna
2016-10-06 14:35:18 -0400
b9e23a6d74config: add a separate config file for the network. This patch adds a new file configs/network/Network.py to setup the network, instead of doing that within Ruby.py.
Tushar Krishna
2016-10-06 14:35:17 -0400
Brandon Potter
Gabor Dozsa
Andreas Hansson
Nikos Nikoleris
Tony Gutierrez
Matthew Poremba
Jason Lowe-Power
Alec Roelke
Sophiane Senni
Michael LeBeane
Joe Gross
Andreas Sandberg
Rekai Gonzalez Alberquilla
Jieming Yin
Sooraj Puthoor
Shawn Rosti
Bjoern A. Zeeb
Nicolas Derumigny
Fernando Endo
Jason Lowe-Power
Curtis Dunham
Omar Naji
Wendy Elsasser
Mitch Hayenga
Tushar Krishna