Before this change, runtime hard code the device name, in this commit,
we will query the name from KFD. Will use codecvt to do UTF-16 to
UTF-8 transfer after GCC supports it.
Change-Id: I7c4dc32ef857296296c810d083888c5ba1c808b6
Have amd::MemoryRegion::Lock not assert if the alternate_va
is null but use the host_ptr instead because in the case where
the src/dst memory pointer is allocated via KFD, the host_ptr
is a GPUVA already.
Change-Id: If44368cc2854d4c0c477ae56e4eeabc37e54c1a5
Reduces the number of blit queues from 3 to 2, when SDMA is unavailable,
improving the availability of queue slots for applications.
Change-Id: I8860d2b6c6d6527494b9fc35d164099e1313886a
for the kernel args.
Most image-related HSA conformance tests pass now
Many more ocltst/oclperf image ones pass too.
Change-Id: I3f28d4ee7369f0ebc7af5128d3ffe1390957db98
Add performance counters for gfx70x. The reference is the gfx7 register spec.
The register being looked at is SQ_PERFCOUNTER0_SELECT.
Change-Id: I344bfb7452f6148f4dc268163d12c553c6be8424
Stepping 1 indicates higher double-precision float performance and
potentially other runtime workarounds needed for lack of PCIe atomics
on gfx70x.
Change-Id: I97185c1233e7d24caaf20a1eadea931d5a2bc664
In a NUMA system, topology should report NumCaches as the number of caches
within the node but current code reports the total caches in the system. This
patch fixes the error. This patch also uses cpuid to get cache information
instead of reading from sysfs files. See "Intel Corporation, Intel 64 and IA-32
Architectures Software Developer's Manual Volume 2(2A, 2B & 2C) Instruction
Set Reference" 3-179 for cpuid instruction features used in this patch.
Change-Id: I8ecece6c2b230741822620b44e66ddc201ff5112
max_single_fill_size_ overflowed the packet field size. Reduce by one dword.
[git-p4: depot-paths = "//depot/stg/hsa/drivers/hsa/runtime/": change = 1259263]
Since we include headers and not just a library anymore, we should be
considered a -dev package and not a lib package.
Change-Id: I220465ea4ffc8d66d8d76e6716e6c6c50cdacea1
Querying HSA_AMD_AGENT_MEMORY_POOL_INFO_LINK_INFO between a gpu agent
and its own local memory pool returns a wrong information.
Fix: return link with 0 hop count.
[git-p4: depot-paths = "//depot/stg/hsa/drivers/hsa/runtime/": change = 1257544]
Remove mutex and just make the thread spin again if the queue is wrapping.
Remove the wait for the queue to finish wrapping, and just check if there is enough space to recycle when reserving queue space.
[git-p4: depot-paths = "//depot/stg/hsa/drivers/hsa/runtime/": change = 1256713]
All files should go into /opt/rocm/$component
For developer convenience, a single include directory is created through
symlinks, from the component include directory to /opt/rocm/include.
Similarly, a unified linked directory is present in /opt/rocm/lib
The component lib directory should not include linker names (library
names without version numbers).
This commit also fixes 'make rpm' running correctly without the need for
sourcing build/envsetup.sh
Change-Id: I95a680f6d3e3bd1ae688d0694934a0577dbd007c
Build system/Package maintainer:
- BUILDID is specified at cmake.
- USAGE: cmake -DBUILDID=<ID> ../src
For developer builds the who typically don?t provide BUILDID, cmake will:
- Determine the last git commit when this tree was syncd
- Deteremine the build date
- Check if tree is clean when built
The idea of this embedded string is that later when you get a ROCR build, you can get some idea on the build origination by using: strings libhsa-runtime.so.1 | grep ?ROCR BUILD ID?
For eg:
- If it?s a Jenkins build 25, it returns: ?ROCR BUILD ID: 25?
- If it?s a developer build sync'd @ 06f5f2a with modifications, it returns: ?ROCR BUILD ID: 06f5f2a-2016-04-11-0"
[git-p4: depot-paths = "//depot/stg/hsa/drivers/hsa/runtime/": change = 1256588]
Intermediate size was stored in a 32-bit variable. This resulted in
4GB allocations to fail in KFD due to 0 size. Larger allocations
would allocate the wrong amount of memory.
Change-Id: If19dedf64952f1d2edd813793241e12c0362d220
Align with the rest of the driver stack on the new installation path
/opt/rocm/*
This mechanism for generating packages should be changed for something
nicer and more standards compliant in the future.
Change-Id: Ic31409b0d0b8f6ee4b25296d2580982a76aab564
HSA Finalizer: Add dumping of code object, ISA and executable to loader.
This is controlled by loader options -dump-all, -dump-isa, -dump-code, -dump-exec
The options can now also be set with env variable LOADER_OPTIONS_APPEND.
Added tests to finalizer_offline
Testing: smoke, dumping on hardware
Reviewed by: Konstantin Zhuravlyov
[git-p4: depot-paths = "//depot/stg/hsa/drivers/hsa/runtime/": change = 1255351]
Ramesh Errabolu
Fan Cao
James Edwards
Konstantin Zhuravlyov
Christophe Paquot
Jay Cornwall
Besar Wicaksono
shaoyunl
Amber Lin
Felix Kuehling
Shi, Aaron (en ye) (xN/A) TO
Andres Rodriguez
Hari Thangirala
Nikolay Haustov [TEXT]