When reset a port, we don't want to trigger a onChange().
Offer an option to bypass it and update state only.
Change-Id: Ia53b7a76d2a320ea67101096cdbfe2eafaf440d2
This patch fixes the buggy special path comparisons in
src/kern/linux/linux.cc Linux::openSpecialFile(), which only checked
for equality of path prefixes, but not equality of the paths
themselves. This patch replaces those buggy comparisons with
regular std::string::operator== string equality comparisons.
GitHub issue: https://github.com/gem5/gem5/issues/269
Change-Id: I216ff8019b9a6a3e87e364c2e197d9b991959ec1
Currently the MOESI_AMD_Base-directory transition for system level
atomics sends the response message before the atomic is performed. This
was likely done because atomics are supposed to return the value of the
data *before* the atomic is performed and by simply ordering the actions
this way that was taken care of.
With the new atomic log feature, the atomic values are pulled from the
log by the coalescer on the return path. Therefore, these actions can be
reordered. However, it is now necessary that the atomics be performed
before sending the response so that the log is populated and copied by
the response action. This should fix#253 .
Change-Id: Ie7e178f93990975367de2cc3e89e5ef9c9069241
The RM field of ModRM was printed as Reg field for several instructions.
For reference, this change fixes typos introduced by [1].
[1] https://gem5-review.googlesource.com/c/public/gem5/+/40339
Change-Id: I41eb58e6a70845c4ddd6774ccba81b8069888be5
Signed-off-by: Hoa Nguyen <hn@hnpl.org>
Starting with gfx900 (Vega) the LDS and scratch apertures can be queried
using a new s_getreg_b32 instruction. If the instruction is called with
the SH_MEM_BASES argument it returns the upper 16 bits of a 64 bit
address for the LDS and scratch apertures. The current addresses cannot
be encoded in this register, so that addresses are changed to have the
lower 48 bits be all zeros in addition to writing the bases register.
Change-Id: If20f262b2685d248afe31aa3ebb274e4f0fc0772
Augmenting the DataBlock class with a change log structure to record the
effects of atomic operations on a data block and service these changes
if the atomic operations require return values.
Although the operations are atomic, the coalescer need not send unique
memory requests for each operation. Atomic operations within a wavefront
to the same address are now coalesced into a single memory request. The
response of this request carries all the necessary information to
provide the requesting lanes unique values as a result of their
individual atomic operations. This helps reduce contention for request
and response queues in simulation.
Previously, only the final value of the datablock after all atomic ops
to the same address was visible to the requesting waves. This change
corrects this behavior by allowing each wave to see the effect of this
individual atomic op is a return value is necessary.
This patch allows a local JSON file to specify a local path in the JSON
object of a Resource, through the "url" field.
Local paths can be entered with the prefix "file:" in the "url" field.
If the local path exists, then the Resource from there is copied into
the resource directory defined in the
function earlier.
This behavior is the same as using specific Resource classes (ex.
BinaryResource) and passing a local_path into the function.
But, the above class does not allow simultaneous creation of local
Resources and Workloads of those local Resources.
With this patch, someone can use a local JSON, specify the location of
local Resources and create a Workload from those Resources and test both
together.
This patch allows a local JSON file to specify a local path
in the JSON object of a Resource, through the "url" field.
Local paths can be entered with the prefix "file:" in "url".
All File URI scheme formats are supported.
This behavior is the same as using specific Resource classes
(ex. BinaryResource) and passing a local_path into the function.
But, the above infrastructure does not allow simultaneous
creation of Resources and Workloads of those Resources.
With this patch, someone can use a local JSON, specify the location
of local Resources and create a Workload from those Resources and
test both together.
Also, this patch adds pyunit tests to check the functionality
of the function used to convert the "url" field into a path.
Change-Id: I1fa3ce33a9870528efd7751d7ca24c27baf36ad4
DCT must be disabled when handling a ReadUnique where the copy need to
be upgraded.
Previously we were just asserting as it was assumed DCT is only enabled
for HNFs (which can "auto-upgrade"). However DCT may also be enabled for
intermediated levels of distributed shared caches above the HNFs.
Currently we generate these stats for all defined Events in the
protocol, which may generate too many stats that are never used. Though
these don't appear in the stats.txt file, they unnecessarily increases
simulation startup time and memory footprint.
This patch limits those stats to events with the "in_trans" and/or
"out_trans" properties. SLICC compiler then checks which combinations of
event+state are possible when generating the stats.
Also the possible level of detail for inTransLatHist was reduced.
Only the number of transactions for each event+initial+final state
combinations is now accounted. Latency histograms are only defined per
event type (similarly to outTransLatHist). This significantly reduces
the final file size for generated stats.
Flat scratch instructions (aka private) are the 3rd and final segment of
flat instructions in gfx9 (Vega) and beyond. These are used for things
like spills/fills and thread local storage. This commit enables two
forms of flat scratch instructions: (1) flat_load/flat_store
instructions where the memory address resolves to private memory and (2)
the new scratch_load/scratch_store instructions in Vega. The first are
similar to older generation ISAs where the aperture is unknown until
address translation. The second are instructions guaranteed to go to
private memory.
Since these are very similar to flat global instructions there are
minimal changes needed:
- Ensure a flat instruction is either regular flat, global, XOR scratch
- Rename the global op_encoding methods to GlobalScratch to indicate
they are for both and are intentionally used.
- Flat instructions in segment 1 output scratch_ in the disassembly
- Flat instruction executed as private use similar mem helpers as global
- Flat scratch cannot be an atomic
This was tested using a modified version of the 'square' application:
template <typename T>
__global__ void
scratch_square(T *C_d, T *A_d, size_t N)
{
size_t offset = (blockIdx.x * blockDim.x + threadIdx.x);
size_t stride = blockDim.x * gridDim.x ;
volatile int foo; // Volatile ensures scratch / unoptimized code
for (size_t i=offset; i<N; i+=stride) {
foo = A_d[i];
C_d[i] = foo * foo;
}
}
Change-Id: Icc91a7f67836fa3e759fefe7c1c3f6851528ae7d
According to the ABI documentation from LLVM, the *low* register of flat
scratch (maxSGPR - 4) is the offset and the high register (maxSGPR - 3)
is size. These are currently backwards, resulting in some gnarly
addresses being generated leading to page fault and/or incorrect data.
This commit fixes this by setting the order correctly.
Change-Id: I0b1d077c49c0ee2a4e59b0f6d85cdb8f17f9be61
Flat instructions may access memory locations in LDS (scratchpad) and
global (VRAM/framebuffer) and therefore increment both counters when
dispatched. Once the aperture is known, we decrement the counters of the
aperture that was *not* used. This is done incorrectly for scratch /
private flat instruction. Private memory is global and therefore local
memory counters should be decremented.
This commit fixes the counters by changing the global decrements to
local decrements.
Change-Id: I25890446908df72e5469e9dbaba6c984955196cf
The functional HSA signal read was a hack left in the gpu-compute code.
In full system, this functional read is causing problems occasionally
with the translation not yet being in the page table. The error message
output by gem5 was a fatal message on the readBlob method in port proxy.
Changing this to a timing DMA fixes this problem.
This commit adds the various timing DMA functions to send and receive
response and clean up. A helper method "sendCompletionSignal" is added
to the GPUCommandProcessor because the indentation level was getting too
deep. This change applies only to FS mode. Code for SE mode is
equivalent to what it was before this commit.
Change-Id: I1bfcaa0a52731cdf9532a7fd0eb06ab2f0e09d48
configs,dev-amdgpu: Add PCI express capability info
The ROCm stack requires PCI express atomics. Currently the first PCI
CapabilityPtr does not point to anything, which signals to the OS
(Linux) that this is an early generation PCI device. As PCI express
atomics were introduced later, the CapabilityPtr needs to point to at
least a PCI express capability structure. This capability is defined as
0x10 in Linux. We additionally set the PCI atomic based bits and
implement device specific PCI configuration space reads and writes to
the amdgpu device.
The second commit, output of simulation when loading the amdgpu
driver no longer outputs "PCIE atomics not supported". Further, an
application which uses PCIe atomics (PyTorch with a reduce_sum kernel)
now makes further progress.
First commit is a minor typo fix changing PCI capability struct to
union.
In the RISC-V system, we need to VecClassReg to run RISC-V vector
instruction, and VecElemReg is not applicable because the element length
of vector can be resizable via vset\*vl\* instruction.
The change will seperate the reg_index for VecReg and VecElemReg to
ensure that have the space for VecReg when VecElemReg is not applicable.
When an Evict request is received from upstream for a shared line and
the line is no longer cached locally (or on any other upstream cache),
we need to also send an Evict downstream. In this case we need to wait
until our outgoing Evict completes before completing the Evict from
upstream in order be able to resolve race conditions with incoming
snoops. E.g.: while our outgoing Evict is pending we may receive a snoop
requesting data, but we won't be able to complete this snoop if we have
already completed all upstream Evicts and we no longer have the line.
The ROCm stack requires PCI express atomics. Currently the first PCI
CapabilityPtr does not point to anything, which signals to the OS
(Linux) that this is an early generation PCI device. As PCI express
atomics were introduced later, the CapabilityPtr needs to point to at
least a PCI express capability structure. This capability is defined as
0x10 in Linux. We additionally set the PCI atomic based bits and
implement device specific PCI configuration space reads and writes to
the amdgpu device.
With this commit, the output of simulation when loading the amdgpu
driver no longer outputs "PCIE atomics not supported". Further, an
application which uses PCIe atomics (PyTorch with a reduce_sum kernel)
now makes further progress.
Change-Id: I5e3866979659a2657f558941106ef65c2f4d9988
In the RISC-V system, we need to VecClassReg to run RISC-V vector
instruction, and VecElemReg is not applicable because the element
length of vector can be resizable via vset*vl* instruction.
The change will seperate the reg_index for VecReg and VecElemReg to
ensure that have the space for VecReg when VecElemReg is not
applicable.
Change-Id: I99a82dec273baeee31df89a0ee0f5e87f3ff187c
The capabilities for PCI express is a struct, instead of a union, like
the other capability unions. A union is used here to provide access to
the ordinal data values when reading/writing an offset while
simultaneously providing human readable field values that can be set
when writing the code.
This commit changes it to union which is likely should be. Nothing
appears to be using this union yet so it is likely an oversight.
Change-Id: I85fe7cc62914525c70fd7a5946d725ed308f8775
There are a few LDS instructions that perform local ALU operations and
writeback which are marked as loads. These are marked as loads because
they fit in the pipeline logic better, according to a several year old
comment. In the VEGA ISA these instructions (swizzle, permute, bpermute)
are not decrementing the LDS load counter. As a result, the counter will
gradually increase over time. Since wavefront slots are persistent, this
can cause applications with a few thousand kernels to eventually hang
thinking there are not enough resources.
This changeset fixes this by decrementing the LDS load counter for these
instructions. This fix was already integrated in the GCN3 ISA in the
exact same way. This changeset moves it near a similar comment about
scheduling register file writes.
Change-Id: Ife5237a2cae7213948c32ef266f4f8f22917351c
Marks which events signal the beginning of incoming and outgoing
transactions for generating inTransLatHist and outTransLatHist stats.
Change-Id: I90594a27fa01ef9cfface309971354b281308d22
Signed-off-by: Tiago Mück <tiago.muck@arm.com>
Generating these stats for all defined Events may generate too many
stats that are never used, which unnecessarily increases simulation
startup time and memory consumption.
This patch limits those stats to events with the "in_trans" and/or
"out_trans" properties. SLICC compiler then checks which combinations
of event+state are possible when generating the stats.
Also the possible level of detail for inTransLatHist was reduced.
Only the number of transactions for each event+initial+final state
combinations is now accounted. Latency histograms are only defined
per event type (similarly to outTransLatHist). This significantly
reduces the final file size for generated stats.
Change-Id: I29aaeb771436cc3f0ce7547a223d58e71d9cedcc
Signed-off-by: Tiago Mück <tiago.muck@arm.com>
Do not respond with SnpRespData_I when the line is still present
upstream.
Change-Id: I2592e5c6637cfc0e83042169a245837648276e61
Signed-off-by: Tiago Mück <tiago.muck@arm.com>
DCT must be disabled when handling a ReadUnique where the copy
need to be upgraded.
Previously we were just asserting as it was assumed DCT is only enabled
for HNFs (which can "auto-upgrade"). However DCT may also be enabled
for intermediated levels of distributed shared caches above the HNFs.
Change-Id: I9e29142a8d2f59ea61c1d90cda6b00c19435d6b7
Signed-off-by: Tiago Mück <tiago.muck@arm.com>
When an Evict request is received from upstream for a shared line
and the line is no longer cached locally (or on any other upstream
cache), we need to also send an Evict downstream. In this case we need
to wait until our outgoing Evict completes before completing the Evict
from upstream in order be able to resolve race conditions with incoming
snoops. E.g.: while our outgoing Evict is pending we may receive a
snoop requesting data, but we won't be able to complete this snoop if
we have already completed all upstream Evicts and we no longer have the
line.
Change-Id: I23ac4f0a9c4ddd81e2425376c8d1e1c7fb66d107
Signed-off-by: Tiago Mück <tiago.muck@arm.com>
Augmenting the DataBlock class with a change log structure to
record the effects of atomic operations on a data block and
service these changes if the atomic operations require return
values.
Although the operations are atomic, the coalescer need not
send unique memory requests for each operation. Atomic
operations within a wavefront to the same address are now
coalesced into a single memory request. The response of this
request carries all the necessary information to provide the
requesting lanes unique values as a result of their individual
atomic operations. This helps reduce contention for request
and response queues in simulation.
Previously, only the final value of the datablock after all
atomic ops to the same address was visible to the requesting
waves. This change corrects this behavior by allowing each wave
to see the effect of this individual atomic op is a return value
is necessary.
Change-Id: I639bea943afd317e45f8fa3bff7689f6b8df9395
1. The current SignalSinkPort and SignalSourcePort have no
ways to assign the init value of the state. Add a new constructor
for them with the param init_state
2. After the source and sink are bound, the state at both side should
be the same. Set the the state of sink to the state of source in the
bind() function.
Change-Id: Idde0a12aa0ddd0c9c599ef47059674fb12aa5d68
Compilation bug found on:
https://github.com/gem5/gem5/actions/runs/5899831222/job/16002984553
In gcc Version 8 and below the following error is received:
```
src/base/bitfield.hh: In function ‘constexpr int gem5::findLsbSet(uint64_t)’:
src/base/bitfield.hh:365:34: error: call to non-‘constexpr’ function ‘int gem5::{anonymous}::findLsbSetFallback(uint64_t)’
return findLsbSetFallback(val);
~~~~~~~~~~~~~~~~~~^~~~~
scons: *** [build/ALL/kern/linux/events.o] Error 1
```
`findLsbSet` cannot be `constexr` as it calls non-constexpr function
`findLsbSetFallback`. `findLsbSetFallback`. The problematic function is
the `count` on the std::bitset.
This patch changes this to a constexpr.
Compilation bug found on:
https://github.com/gem5/gem5/actions/runs/5899831222/job/16002984553
In gcc Version 8 and below the following error is received:
```
src/base/bitfield.hh: In function ‘constexpr int gem5::findLsbSet(uint64_t)’:
src/base/bitfield.hh:365:34: error: call to non-‘constexpr’ function ‘int gem5::{anonymous}::findLsbSetFallback(uint64_t)’
return findLsbSetFallback(val);
~~~~~~~~~~~~~~~~~~^~~~~
scons: *** [build/ALL/kern/linux/events.o] Error 1
```
`findLsbSet` cannot be `constexr` as it calls non-constexpr function
`findLsbSetFallback`. `findLsbSetFallback`. The problematic function is
the `count` on the std::bitset.
This patch changes this to a constexpr.
Change-Id: I48bd15d03e4615148be6c4d926a3c9c2f777dc3c
When a linux kernel changes a page property, it flushes the related cache
lines. The kernel might change the page property before flushing the
cache lines. This results in the clflush might occur in an uncacheable region.
Currently, an uncacheable request must be a read or a write. However,
clflush request is neither of them.
This change aims to allow clflush requests to work on uncacheable regions.
Since there is no straightforward way to check if a packet is from a clflush
instruction, this change permits all Clean Invalidate Requests, which is
the type of request produced by clflush, to work on uncacheable regions.
Change-Id: Ib3ec01d9281d3dfe565a0ced773ed912edb32b8f
Signed-off-by: Hoa Nguyen <hn@hnpl.org>
In this case the function is turned into a generator with the
"yield" of the generator the return the function's execution.
Change-Id: I4b06d64c5479638712a11e3c1a2f7bd30f60d188
On RISC-V when trap occurs the contents of PC register contains the
address of instruction that caused that trap (as opposed to the address
of instruction following it in instruction stream). Therefore this commit
does not advance the PC before reporting trap in SE mode.
Change-Id: I83f3766cff276312cefcf1b4ac6e78a6569846b9
Due to inverted logic in POWER fault handlers, unimplemented opcode and
trap faults did not report trap to GDB (if connected). This commit fixes
the problem.
While at it, I opted to use `if (! ...) { panic(...) }` rather than
`panic_if(...)`. I find it easier to understand in this case.
Change-Id: I6cd5dfd5f6546b8541d685e877afef21540d6824
The mem instructions usually executed from initiateAcc. We also need
to check vector required in those instructions
Change-Id: I97b4fec7fada432abb55ca58050615e12e00d1ca
Detected via this failing workload:
https://github.com/gem5/gem5/actions/runs/5861958237
Ir caused the following compilation error to be thrown:
```
src/arch/x86/kvm/x86_cpu.cc:1462:22: error: unused variable ‘rv’ [-Werror=unused-variable]
1462 | bool rv = isa->cpuid->doCpuid(tc, function, idx, cpuid);
| ^~
```
`rv` is unused in the .fast compilation as it's only used in the
`assert` statement immediately after.
To fix this, the `[[maybe_unused]]` annotation is used.
Detected via this failing workload:
https://github.com/gem5/gem5/actions/runs/5861958237
It caused the following compilation error to be thrown:
```
src/arch/x86/kvm/x86_cpu.cc:1462:22: error: unused variable ‘rv’ [-Werror=unused-variable]
1462 | bool rv = isa->cpuid->doCpuid(tc, function, idx, cpuid);
| ^~
```
`rv` is unused in the .fast compilation as it's only used in the
`assert` statement immediately after.
To fix this, the `[[maybe_unused]]` annotation is used
Change-Id: Ib98dd859c62f171c8eeefae93502f92a8f133776
The previous exit event occurs when the dispatcher sends a completion
signal for a kernel, but gem5 does some kernel-based stats updates after
the signal is sent. Therefore, if these exit events are used as a way to
dump per-kernel stats, some of the stats for the kernel that just ended
will be in the next kernel's stat dump which is misleading.
This patch moves the exit event to where the stats are updated and only
exits if the dispatcher has requested a stat dump to prevent situations
where stats are updated mid-kernel.
Change-Id: I74dc1cad5fc90382a2a80564764b3e7c9fb65521
We're seeing some occasional connection timeouts in CI, possibly when we
aggressively hit the license server, so let's add a parameter to retry
the connection a few times.
Also, print the time required to connect to the server to help debug
issues.
