There are a couple problems with this. First, llvm-dis is an unstable
llvm development tool and 3rd party users should generally not rely on
it. The text format is unstable, and the regex here isn't even
explicitly looking for the target triple field, so it could
accidentally find something else. Second, picking the target to
compile based on the library you are linking is a fundamentally
backwards decision. The target you're compiling for changes the
library you would want to link. The device libraries are only ever
compiled with amdgcn-amd-amdhsa. If we had a second triple, this
should be explicitly building for any it cares about.
Change-Id: I3bae8398f60f78df61ab2177aa9e83f47ec6dea4
The ROCR trap handler should check for all end program instructions
and not halt on them. Mask off the imm16 before comparing the
instruction to the s_endpgm opcode.
Change-Id: I669ffc7f5b699d7daf0c8ec5761ed7bb193f07a7
On Ubuntu 20.04, there is no more python or python2. Currently I get
this: /usr/bin/env: ‘python’: No such file or directory
Change-Id: Ib310b8aa7c1bd62973ef3cc8bcaf571831ad4435
This is needed to allow gdb to access the memory.
Change-Id: I96c084b714e952d7b7000f0dd41e1c530fdd092f
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
On newer kernels, it seems the group was changed from "video" to
"render". The check for video group misled me for quite some time, so
relax this check. Rather than specifically checking for video group
ownership, first see if /dev/kfd can be open as read-write. Then
diagnose whether the user belongs to the group that owns it, rather
than hardcoding the video group.
Change-Id: I9e65427363e9a5cdba802e09cee2f40fb80520ed
New trap handler ABI: Record in ttmp11[8:7] the event that caused the
trap handler to be entered. We currently record 2 events, trap_raised
if an s_trap instruction was executed, or excp_raised if an exception
(MEM_VIOL or ILLEGAL_INST) was raised.
Change-Id: Ie278c8277437b3b67c2737dcd1a12fe6511df428
This fixes a seg fault that would happen in release builds when
there are no KFD nodes on a system, which occurs when there are
not AMD gpus present in the system. This use case occurs
for higher application code that is meant to be gpu agnostic.
Change-Id: If374930bc2e62f9898f337349cde3ebb16091ff0
Remove the hard-coding of "SHARED" as the lib type, and move any
SO-specific linking to only happen if the .so exists in the first place
Change-Id: I3f0bfd5c03f19b2425423b4dc8eed8fd87acc1d6
Make the hsakmt library take the value from CMake regarding
static/shared
KFDTest automatically grabs the right one due to it checking the normal
shared folders. Tested locally (and via automation by the time that this
is merged)
Also set the default to building SOs if BUILD_SHARED_LIBS is not defined
Change-Id: I7f8b76a7e60f3b41e5981f472b388301ae09e2c6
Signed-off-by: Kent Russell <kent.russell@amd.com>
Changes in the compiler are being made to add controls for XNACK and SRAM ECC
for all targets which can support these features. By default the conservatively
correct settings of XNACK on and SRAM ECC on will be used. This change is to
facilitate these backend updates.
Change-Id: I2fd6b6bc1d32937737e7f56d8e08c70fe781c745
Using the building OS isn't guaranteed, as we can theoretically build
RPMs in Ubuntu or DEBs in CentOS. Use CPack's DEB/RPM-specific variables
to get around this issue
Change-Id: I404246c070eac2c74b45ae4b763c612891d66de1
Signed-off-by: Kent Russell <kent.russell@amd.com>
IPC create must only be used on whole ROCr allocations.
Fragments were allowing handle creation with offsets.
Change-Id: I1faa96d36bc7a6199bdc2e3ff1b8871d1a36a2fa
Chris Freehill
Matt Arsenault
Evgeny Shcherbakov
Rachida Kebichi
Laurent Morichetti
Felix Kuehling
Sean Keely
Ramesh Errabolu
Kent Russell
Austin Kerbow