The CorePairs in MOESI_AMD_Base round up the number of CPUs when
creating CPU sequencers. If the CPU count is an odd number, this was
causing the Disjoint_VIPER config to connect a sequencer that does not
exist. As a result the crossbar was waiting for a range change from the
sequencer but it never arrived, causing an assert.
This patch fixes this by conditionally connecting CPU sequencers to the
PIO port only if the ID is less than the number of CPUs.
Change-Id: I2280c0048492d43528429a947a726871f1c23ca7
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/57531
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The driver will check this bit is set after initializing IPs. Currently
the MMIO trace will cause this bit to be set at the correct time,
however this is not portable access different ROCm versions. Therefore
we modify the value to always set the bit indicating interrupts are
enabled.
Change-Id: Iae0baf1936720fbe9835ae4acadbf1b3bdc52896
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/57530
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Currently if a Ruby functional access fails to find an address in the
caches, it gives up. For functional page table walks we need to be able
to go all the way to memory. This adds a pointer to the system object
which allows the walker to get a pointer to device memory which can be
used to do a functional access directly to memory bypassing Ruby.
Change-Id: I0ead6e5e130a0d53021c44ae9221b167c6316ab2
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/57529
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Make the necessary changes to connect Vega pagetable walkers for
full-system mode. Previously the CP and HSA packet processor could only
read AQL packets from system/host memory using proxy port. This allows
for AQL to be read from device memory which is used for non-blit
kernels.
Change-Id: If28eb8be68173da03e15084765e77e92eda178e9
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/53077
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The classes defined by the ISA description are actually just descriptors
which are used to make more specialized Operand classes, and then those
classes are instantiated to represent actual operands in a given
instruction. There they encode the actual index of the register, any
extensions used, etc.
To make defining operand types in the ISA more flexible and to take less
explicit machinery, this change defines a mechanism to allow overriding
individual methods of the operand class. This should for instance make
the read_code and write_code members of those classes unnecessary.
Change-Id: I1a1f787970ba56bd2884a80df4618a77eb454605
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/49740
Tested-by: kokoro <noreply+kokoro@google.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
This patch is fixing the redirectRegVHE method in the following
ways:
* Redirect AArch32 version of timer/counter registers
* Redirect _EL12 registers to _EL1
* Redirect _EL02 registers to _EL0
* Redirect CNTV_*_EL0 and CNTP_*_EL0 registers to
the Secure/Non-secure _EL2
* Redirect CNTVCT_EL0 to CNTPCT_EL0
Change-Id: I34eb317045b2d5a304a29ccf6e6440df68b2a279
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58117
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The disjoint VIPER configuration creates completely disconnected CPU and
GPU Ruby networks which can communicate only via the PCI bus. Either
garnet or simple network can be used. This copies most of the Ruby setup
from Ruby.py's create_system since creating disjoint networks is not
possible using Ruby.py.
Change-Id: Ibc23aa592f56554d088667d8e309ecdeb306da68
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/53072
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
At the moment those operands are using uint32_t (uw) variables,
therefore losing the content of the 32 most significant bits
This is not a problem for some of them (like CPTR_EL2, CPTR_EL3)
as [63:32] bits are RES0 for now.
HCR_EL2 on the other hand holds meaningful bits in [63:32],
HCR_EL.E2H being a notable example. With this patch we
are then fixing a bug in VHE (which relies on E2H)
Change-Id: I3e31009ad3dec8d8ea1c1057a189f7dcc2c3a54c
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58113
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Presumably, these are fixed for whatever protocol that gets selected. We
don't need to accumulate includes, we need to set includes to something
in particular. If there is a common include which always needs to be
used, we can handle that in the SConscript separately from
SLICC_INCLUDES.
Change-Id: I996d08566944e38e388dc287f644c40366ebba0d
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/56754
Tested-by: kokoro <noreply+kokoro@google.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Reviewed-by: Yu-hsin Wang <yuhsingw@google.com>
The Arm Architecture Reference Manual has moved from
"Armv7-oriented" names for generic timer interrupts to
names more consistent with Armv8 (Exception Levels based).
We are therefore renaming those interrupts as follows:
int_phys_s -> int_el3_phys
int_phys_ns -> int_el1_phys
int_virt -> int_el1_virt
int_hyp -> int_el2_ns_phys
Change-Id: Id6e34a0e4311953938b25bca168a34357e3c8643
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58109
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Connect the --second-disk option in GPUFS. Typically this is used as a
benchmarks disk image. If the disk is unmounted at the time of
checkpoint, a new disk image can be mounted after restoring the
checkpoint for a simple way to add new benchmarks without recreating a
checkpoint.
Change-Id: I57b31bdf8ec628006d774feacff3fde6f533cd4b
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/53071
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
A valid CPU vendor string (i.e., not "M5 Simulator") needs to be passed
to CPUID in order for Linux to create the sysfs files needed for ROCm's
Thunk interface to initialize properly. If these are no created
hipDeviceProperties and other basic GPU code APIs will error out.
Change-Id: I6e3f459162e4673860a8f0a88473e38d5d7be237
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/53070
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The PM4 packet processor is handling all non-HSA GPU packets such
as packets for (un)mapping HSA queues. This commit pulls many
Linux structs and defines out into their own files for clarity.
Finally, it implements the VMID related functions in AMDGPU device.
Change-Id: I5f0057209305404df58aff2c4cd07762d1a31690
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/53068
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Add the devices that have been added in previous changesets to the
config file. Forward MMIO writes to the appropriate device based
on the MMIO address. Connect doorbells and forward rings to the
appropriate device based on queue type.
Change-Id: I44110c9a24559936102a246c9658abb84a8ce07e
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/53065
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
SDMAEngine handles copies to device memory. This commit
updates sdma_packets.hh style as well. Added several methods needed by
SDMAEngine to GPU device including GART table, various getters, and
aperture range checkers. Move the MMIO interface from GPUController to
SDMAEngine. Create an SDMA MMIO and commands header with only the macros
we use so that we don't need to check in multi-thousand line header
files from the linux kernel. Keep SOC15 IH client ID macros as that file
is small.
Change-Id: I986fede90cc1bc16ee56d4e8598cf9283bde034e
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/53064
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Create a VM class to reduce clutter in the amdgpu_device.* files. This
new file is in charge of reading/writting MMIOs related to VM contexts
and apertures. It also provides ranges checks for various apertures and
breaks out the MMIO interface so that there are not overloaded macro
definitions in the device MMIO methods.
The new translation generator classes for the various apertures are also
added to this class.
Change-Id: Ic224c1aa485685685b1136a46eed50bcf99d2350
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/53066
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
* The value of build environment variable KVM_ISA is serialized into
the generated file `kvm_isa.hh'. This value should be a string, but on
hosts where the KVM headers are not available, the default `None` is
inserted. Changed the default value to the string `""` in this case.
* Added missing include for `std::array`.
Change-Id: I651122cc46fc9c0757f592b05f4b4cab285cb91f
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/57889
Reviewed-by: Gabe Black <gabe.black@gmail.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Current implementation prevents customers from performing zero
initialize on BitUnion class. Customers would get unexpected results
when writing `BitUnion{}`. Changing the default constructor to default
can solve this issue.
After changing the default constructor, the test failed with unused
variable. I also change one with zero initializer and make the other
with maybe_unused label.
```
tests/build/ARM/base/bitunion.test.cc:133:14: error: 'emptySixteen' defined but not used [-Werror=unused-variable]
133 | EmptySixteen emptySixteen;
| ^~~~~~~~~~~~
tests/build/ARM/base/bitunion.test.cc:132:16: error: 'emptyThirtyTwo' defined but not used [-Werror=unused-variable]
132 | EmptyThirtyTwo emptyThirtyTwo;
| ^~~~~~~~~~~~~~
```
Change-Id: Icbed36b3fa6751cbda63e84443eaab6d865d9bd6
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/57730
Reviewed-by: Gabe Black <gabe.black@gmail.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
There have been failures on the weekly tests during the decoding of the
downloaded resources.json base64 file. These errors suggested an
incomplete download or some form of file corruption. These errors only
ever seem to occur when multiple threads of gem5 are running. It has
therefore been proposed that perhaps, in some cases, the cached
downloaded file was bring re-downloaded while also being read by
another thread. For this reason this patch adds a filelock so only one
instance of gem5, at any one time, can download and read the
resources.json file. Even if this is not the cause of the weekly test
errors, it still adds some additional safeguards.
Change-Id: I7c6e1c1786c1919e8519587e53b6a77f4aafa932
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/57789
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
In a dGPU configuration, vector and scalar loads/stores can either be
requests to device memory or host memory depending on if the system bit
is set in the PTE when the request's virtual address is translated. This
object is used to send/receive those requests to the host via DMA.
This object will be used in a later changeset by the compute unit and
fetch units to issue data and instruction loads from the GPU which
translate to physical addresses on the host/cpu memory.
Change-Id: I4537059f90ebc03f3b2e6b8b631b4c452841f83f
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/51851
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Sometimes a library is needed to support particular functionality in
gem5, and that functionality is only used (or even desirable) in
certain binaries SCons can build. We can currently filter sources to
include in a particular executable using tags, but libraries have been
added to the environment globally using the LIBS variable which applies
to all Executables.
This change adds a SourceLib() mechanism which is a new category of
source which represents libraries. This is independent from classes
which inherit from SourceFile which represent actual files, as opposed
to more abstract libraries.
When gem5 builds an executable, the filters it provides are used to
select both Source()-es, aka c/c++ files, and libraries. If something
like a unit test does not need all the libraries gem5 proper does,
then those won't be picked up by its filter, and it won't include them.
Change-Id: I003e029eb82f7800a7ecff698c260e2d18ea2900
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/58069
Reviewed-by: Yu-hsin Wang <yuhsingw@google.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This was defined in the Micro_Container base class, and then again in
each subclass. The base definition was different and less complete than
the others, but the others were identical. Replace the base class
definition with the definition in the subclasses, and delete the ones in
the subclasses.
Change-Id: Ib2d1ce72958ec299115efb6efced2bd14c08467c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/56330
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Maintainer: Gabe Black <gabe.black@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The current default GPU register allocator is the "simple" policy,
which only allows 1 wavefront to run at a time on each CU. This is
not very realistic and also means the tester (when not specifically
choosing the dynamic policy) is less rigorous in terms of validating
correctness.
To resolve this, this commit changes the default to the "dynamic"
register allocator, which runs as many waves per CU as there are
space in terms of registers and other resources -- thus it is more
realistic and does a better job of ensuring test coverage.
Change-Id: Ifca915130bb4f44da6a9ef896336138542b4e93e
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/57537
Maintainer: Matt Sinclair <mattdsinclair@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
