Each SE must be assigned equal numbers of slots and slots
must be assigned in units of whole groups.
Change-Id: I8f3677237fa6f2e2d25e3e78210c5a7a0ad792f3
- Remove gfx800, gfx804 and gfx901 as they do not exist.
- Map the V2 note record of "AMD:AMDGPU:8:0:0" to gfx802 as they are
the same target just connected to a differnt motherboard.
- Correct typo for supporting gfx902:xnack+.
- Support agent names with a minor or stepping version greater than 9.
Change-Id: Ife933449f60ab4687e2aaab9baf4c9fc5b86339d
Add missing target names and make all parts consistent with which
targets are supported.
- Add gfx805 as a supported target.
- Add all ELF targets to genric code.
- Make offline loader match supported targets.
Change-Id: Idab4d69edc71645aecaa83aa55e29c1aeee4c1d6
Code object V2 had the ability to support the following queries:
- HSA_CODE_SYMBOL_INFO_KERNEL_KERNARG_SEGMENT_SIZE
- HSA_EXECUTABLE_SYMBOL_INFO_KERNEL_KERNARG_SEGMENT_SIZE
- HSA_CODE_SYMBOL_INFO_KERNEL_KERNARG_SEGMENT_ALIGNMENT
- HSA_EXECUTABLE_SYMBOL_INFO_KERNEL_KERNARG_SEGMENT_ALIGNMENT
However code object V3 onwards cannot support these as the kernel
descriptor changed. These queries need to be deprecated.
Until then return more reasonable values:
- For kernarg alignment return 16 which is the minimum alignment
required by the HSA standard.
- For kernarg size return the field from the kernel descriptor which
is a hint. If it is 0 then the compiler is not specifying the kernarg
size, or the kernel has no kernarg.
Change-Id: I19ce6cd0f3658a2bf62277492f39100ea5ab4256
The modern meaning of the construct if( NOT ON ) was added in CMake 2.8,
but when the cmake_minimum_required not set in user code and no policy
level is set in the CMake config, then CMake 2.8 features cannot be
used. In old CMake (the default), ON is interpreted as a variable, and
because it is not defined, it is considered false. The same is true of
OFF.
This change sets a variable as ON, so that old CMake interpretation is
correct, and the if works as expected regardless of policy version.
Change-Id: I67d7ed4ceaf8248eeb5a1c7f54009d72313f3f5d
Names test good:
hsa-rocr-dev_1.2.0.30900-crdnnv.415_amd64.deb
hsa-rocr-dev-1.2.0.30900-crdnnv.415.el7.x86_64.rpm
hsa-rocr-dev-1.2.0.30900-crdnnv.sles151.415.x86_64.rpm
http://confluence.amd.com/display/GPUCPT/Package+File+Naming
Note: rpm requires 'devel' instead of 'dev', to be a subsequent
patchset.
Change-Id: Id6a422f3c335448b52c70c77ed39c9041114b80f
Signed-off-by: Cole Nelson <cole.nelson@amd.com>
The error checking macro IS_OPEN returns an hsa_signal_t.
This conflicts with the return type of uint32_t.
Add an assert and rely on spurious return rule to return zero
when rocr is not initialized.
Change-Id: Ifc9bb75e22ecdd675273de59b31e5026a69c62e0
For small copies cache flush latency is larger than data transfer
latency in local VRAM. Select SDMA for small copies.
Environment key HSA_FORCE_SDMA_SIZE is added for easy adjustment
of the small copy size. This may be removed after tuning is done.
Change-Id: I733fa0ae01c616617c5de50e71226b51fd589ef2
We want wraparound behavior here but we don't want to trigger sanitizer
warnings. Converting to int64_t and then wraping around by cast to
uint64_t avoids the UB issue that triggers the sanitizer warning.
Change-Id: I9400b988dce7899e9ba42cab3e35c7ffedec8fe1
Enables standards compliant package naming for debian and rpm.
Change-Id: Iad86bf942b4e2938516ef46cda6fa2e4bb3744cc
Signed-off-by: Cole Nelson <cole.nelson@amd.com>
Make explicit reference to hsa_api_trace.cpp from
initialization of hsa_table_interface.cpp. Breaks
the ability to use hsa_table_interface.cpp in plugins.
Change-Id: I22a42d3a132512b0d9ec7a1ca629b169e7f8eba7
Rather than manually linking to the device libraries, the compiler
can now handle linking with them. Allow the build to continue using
old layout if the build system still uses it. Therefore maintain
compatibility with ROCm 3.7 and earlier.
Change-Id: Ida81775da3d0f7c2c67386a71cb057ede31a1545
The excess declarations mark implemenation functions as default
visibility. Normally this is not an issue since our linker script
will specify which visible symbols will be permitted into the dynamic
symbol table. However, for static linking methods which apply linker
directives during incremental linking symbol visibility must be correct
in the (non-dynamic) symbol table.
Change-Id: I13dc8dd1019368e8943920d36335a91f0c555a92
The size of the m0 payload for MSG_INTERRUPT has changed in gfx10. It is
now 23bit wide instead of 24bit wide in gfx9.
Since we are generating different binaries for gfx9 and gfx10, we can
conditionally set DEBUG_INTERRUPT_CONTEXT_ID_BIT to 23 for gfx9 and
22 for gfx10.
Change-Id: Ifc15a9fa4399d35328ab58b742f791f1660bcd9a
- Make code object reader use mmap when loading from a file on Linux.
- Support computing code object URI for memory either fro the loaded
host executables, or from all mmapped files. Define the environment
variable HSA_LOADER_ENABLE_MMAP_URI to non 0 to search the mmap
files, otherwise only the loaded executables will be seatched.
- For mmap search, determine file size and ommit offset and size URI
fragment when the code object is the whole file even when specifying
a file size explicitly or specifying memory that has been mmaped.
- Always return a non-empty code object URI.
- When a code object reader is created, complete all fields to ensure
it can be used in a multi-threaded manner using only const
operations.
- Add missing exception handlers in the AMD vendor extentions.
- More rigorous checking for errors.
Change-Id: I07797b1dc60c5c64245142d77becf9f7c9643395
We should preserve the queue address and queue size when suspending a
queue. The ROCdbgapi gets all its information from the KFD, and if we
reset the queue properties, a call to queue snapshot will not return
the correct information.
Change-Id: I646ed4a779cada55b0c1b4342ec140d3678beb67
Sean Keely
Tony Tye
Cordell Bloor
Cole Nelson
Pruthvi Madugundu
Konstantin Zhuravlyov
Evgeny
Chris Freehill
Aaron Enye Shi
Laurent Morichetti
Ramesh Errabolu
Vlad Sytchenko