8618bf7e2c
minor fixes, debug output, comments, using env vars, dead code
...
Change-Id: I08ad73b561709c1818d78a9191c96d6ad141a609
2017-06-22 18:04:26 -04:00
08e0bca567
Support Perf Cntrs (PMC) and Thread Trace (SQTT) over AQL queues
...
Change-Id: I716b722895d90b46914c31377e791ad602acecc1
2017-06-15 12:58:31 -04:00
5b4df54b10
Revert "Implement memory fault analysis through context save area"
...
This reverts commit 75c9506f9d
2017-06-14 14:21:53 -04:00
35b376e2ee
GFX8 API
...
Change-Id: I9d0c430e4199f043226c8897f3320a7973cbdeda
2017-06-14 12:24:28 -04:00
75c9506f9d
Implement memory fault analysis through context save area
...
When a fatal memory fault occurs the scheduler context-saves all queues
in the process and notifies the runtime through the memory event. The
saved state contains all GPR/LDS data at the moment of the fault.
Retrieve this state and present it to the user if HSA_DEBUG_FAULT is set
to "analyze" and the wavefront caused the fault. If amdgcn-capable objdump
is in the PATH invoke this to disassemble code around the PC.
Queue lifetime is now managed by the runtime to allow querying the
context save state for all active queues.
Change-Id: I6fee662fad1c4f9aa125bf5c53d7d0ea1ab32f95
2017-06-13 23:12:28 -04:00
25035b8d09
Adding HSA extension AMD AQL profile library, see Readme.txt
...
Change-Id: Icbc1e0fb0185642eabbab411a2138ea030d22be8
2017-06-13 16:18:06 -04:00
da831502ab
Adding GFXIP and kernel code object
...
Change-Id: Ieb2dfea8d9e909efac583f541730d77b7d0c9679
2017-06-13 14:58:29 -05:00
d98e99949a
Update hsa_isa_t entries
...
- Add 7.0.2 (consumer hawaii)
- Add 9.0.1 (gfx900 with xnack)
- Add 9.0.2
- Add 9.0.3
Change-Id: I6a07797027c4eaf47038837c5ae51e05b2aba0e4
2017-06-12 14:34:11 -04:00
a0957bc679
The fallback path covers not just ARM64, need this for Power as well.
...
Change-Id: I7bbf76f77bd3ac47a0a0987c1e880e23834588e2
2017-06-07 14:45:29 -05:00
cd35fb280a
Patch target name in code object for future-proof
...
Change-Id: I6f12b5e5791bd1745ec3ab76d382fad50282e733
2017-06-05 19:08:27 -04:00
5db53ceda1
Enable SDMA on gfx9, disable on gfx8
...
gfx9 has passed qualification. gfx8 stability is under investigation.
Change-Id: Ia72211d47756399ecdfceafeb67c2ab34ebda834
2017-06-02 15:14:14 -05:00
c3e2a88ade
Add preferred agent info to pointer info struct.
...
Lookup blit agent via pointer info in memory_fill.
Change-Id: I02feaf68bb9726858e8cb0ede6bc5f2b3707f5af
2017-05-31 05:16:05 -04:00
77e5b30c41
remove finalizer usage from image ext
...
Change-Id: I282f02cedce790bf42f07c588fd50e346b9ba665
2017-05-29 20:44:52 -04:00
e38ff18990
Unmap GPUs when allow_access removes them from system pools.
...
Change-Id: Ib9eb88622fded43ebd9eddbf78ad6771a5b91e77
2017-05-17 20:58:05 -04:00
a777413400
Purge warning in amd_hsa_code.cpp
...
Change-Id: Iaa5d7af183af5e8c069365a1f0410365b46d53d5
2017-05-08 19:39:49 -04:00
001d43ce56
Change rpm preinstall script to post install
...
Change-Id: Iccc04902699bf0ba8b5269e1129b72cf69ef7f00
2017-05-07 14:02:54 -05:00
8aa19388a9
On GFX9+ amd_queue_t.scratch_backing_memory_location must store the queue's scratch backing store VA, not the offset.
...
Also fix permission in couple files.
Change-Id: I4203f8e5a36406b20562d8943ea5c341847f039a
2017-04-18 22:37:56 -05:00
617b6fa987
Separate gfx700 and AI architectures
...
Registers are different and it's cleaner to do as such
Change-Id: I36eee4c9c74deb43ca4666baa87894765a5f27b8
2017-04-07 00:14:22 -04:00
f0a1c7c4c6
Fix gfx9 trap handler to retrieve correct return address
...
The trap protocol changed between gfx8 and gfx9. The return address
is in trap temporaries [0,1] on gfx9 rather than [4,5] on gfx8.
Unfortunately SP3 changes the meaning of the ttmp register aliases
in gfx9, further confusing the issue.
Clean up later when LLVM assembly build is introduced to the runtime.
Change-Id: I84ea9bf3736f060dd95d0361f9d5a0f9a3576178
2017-04-05 17:33:49 -05:00
8a5ff78be6
Remove comments, no functional change.
...
Change-Id: I923c037803a847352c2c50d9d47460cb0f01f22c
2017-03-28 18:22:49 -05:00
7dfeee5074
Support async. queue errors and dynamic scratch without KFD events.
...
Change-Id: I4e9e7a37aa7b9c96b28ce79f562760283e02b1e0
2017-03-28 19:18:18 -04:00
c4544906b9
Refactor signal_wait timing code and respect small timeouts.
...
Optimized for Gromacs and SHOC.
Change-Id: Ib674710268b41003259711a0e42d3e770a82018d
2017-03-23 23:55:48 -05:00
ba3f1cb476
We should be using the "used" gcc attribute.
...
Change-Id: I1589273740ae66e8d7d8186a88e2c411a2e0425c
See: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#Common-Variable-Attributes
2017-03-20 11:57:39 -04:00
6c750f479d
Fix the comment to specify the right type of allocation required.
...
Change-Id: I8bda8d64010d466d6ca5e779d2042cca3f494ecf
2017-03-20 11:56:54 -04:00
7c6cde1871
Disable SDMA only on gfx900 until it is validated.
...
Change-Id: Ib960be3ca6d3fc4b664ba047243964b8c7a33f24
2017-03-20 11:55:22 -04:00
a08d760c70
[Loader] Fix memory allocations for code objects that
...
are larger than swap space available
Change-Id: I321487f96fe0a18998301a9058430c19427e5a94
2017-03-11 00:57:25 -05:00
5f50e97d18
Support async error code 256, invalid vendor specific packet.
...
Change-Id: I491f34def4c3d54403864fa42670f7847a6141cc
2017-03-10 16:20:27 -05:00
2824786b3b
Relax signal assertion.
...
Informs, in debug mode only, that a signal wait violated the HSA
spec with regard to the consuming agents list. This list is used
for optimized signal type selection.
Change-Id: I5879f8f822d01af504ab913482b2532feb00be98
2017-03-10 16:05:34 -05:00
05d587ef79
Add inc/ to some include
...
Change-Id: Id027b015c8785a132835a422d97a23b0bbce208a
2017-03-09 19:45:01 -08:00
426d41e27c
Adjust signal sleep to reflect null kernel latency. Performance tested on Gromacs.
...
Change-Id: I3851148ee8544b15d840f2c26ca73a83f8d0df2e
2017-03-09 15:20:53 -05:00
29894df0b5
Update addrlib for gfx900.
...
Change-Id: I2b7b6093406c5498e9a551327701ad8973f1cf3a
2017-03-07 14:41:16 -08:00
470750cc3c
Update readme regarding CMAKE_PREFIX_PATH.
...
Change-Id: I322789f38b1984b2527554c10cb0f3be886d3e91
2017-02-20 14:33:53 -06:00
57ac399652
Modify packaging cmake files to use BUILD_VERSION* instead of RELEASE_VERSION*.
...
Change-Id: I6f1b83c9faf0d40c1ac27d8998f4651341971b1b
2017-02-16 16:40:20 -06:00
42e751519b
Enable code for Perf Cntrs for gfx900 - AI family device
...
Change-Id: I4659da1a8db17392016fc90c8ea19b5805b5d3aa
2017-02-15 21:50:23 -06:00
900f272622
Fixes to HSA CMakeList.txt files
...
Change-Id: Idd176d24dfd22bd9a6a8860ab035fd5d1aca756d
2017-02-15 08:26:30 -06:00
b7e06b471c
Fix TeamCity builds using utils.cmake.
...
Change-Id: Id15a911dad06643d9457cc4d8c907fc5796772ee
2017-02-14 15:36:21 -06:00
73e942cd8a
Modify hsa CMakeList.txt file to use PREFIX_PATH and git describe versioning.
...
Change-Id: I08668df07725369ecf8a2f35e74dd7d64c8ca94b
2017-02-14 08:39:16 -05:00
9887c26113
Bring loader in sync with stg/sc
...
Change-Id: Iccce07b8fa03d37c4267a2a9bd343e6614dc43e7
2017-02-10 11:21:15 -05:00
4d62b9482a
Implement code cache invalidation for Gfx9
...
When a new enough microcode build is running use a vendor AQL packet
to submit the PM4 IB.
Change-Id: Icd3e2b322c418477420ba4a29f4455ce340ef0d2
2017-02-09 14:15:21 -05:00
e91970a39b
Support Gfx9 and Pre-Gfx9 Thread Trace Drivers
...
Change-Id: Ic3fea4006d76d1e3f58dde6f64c343a1261abe39
2017-02-07 15:39:59 -06:00
505d722b7d
Fix Api table copy operation and tools version checking.
...
Change-Id: Ia76d16f3ea6d0abb931813f90bc3bc2119da5999
2017-02-07 14:26:20 -05:00
bc43f97964
Use fixed size type for queue type arguments.
...
Change-Id: I81b605c9cc9b18bcef043a4f0292212241ce5987
2017-02-07 01:22:30 -05:00
74e3a49b20
Refactor Thread Trace Service as an independent library
...
Change-Id: Ia7579bc16626f3e21c8df50f8a35cb4b82f6bda9
2017-02-06 17:04:07 -05:00
28f51d5808
Fix Gfx9 write pointer setup
...
Should point directly to amd_queue_t.write_dispatch_id. Only noticeable
with HWS enabled which is not yet stable.
Change-Id: I169906d45225379a3ca2729ff04d298fdbb9a9fb
2017-02-06 14:06:12 -05:00
7755bd5487
Refactor Device Id to Asic Type Mapping Service
...
Change-Id: I8969b41f7c4de9fdeee5131e2049053a486f64fb
2017-02-03 14:22:32 -05:00
9e575ea96a
Add support for ARM
...
- Build system fixes
- No user-mode high-precision timer by default, use clock_gettime
- Use C11 aligned_alloc pending C++17 std::aligned_alloc
Change-Id: I268365bdfd11d1e817a89584b9e086ee5b86e1dc
2017-01-31 16:43:49 -08:00
7e0a5f9c00
Add support for gfx900
...
- Route AQL doorbell directly to HW doorbell
- Reuse precompiled Gfx8 shaders on Gfx9 (ISA is compatible)
- Add a warning for unimplemented code cache invalidation
Change-Id: I92096584a1404e35779c96ae6bdc3e0e7fd04721
2017-01-30 16:36:28 -06:00
796d31d94d
Remove old names from API table interfaces.
...
Change-Id: I41ca38b596e1dac85e871f583e3ffe7078b790e7
2017-01-27 17:45:26 -06:00
9ae1e15750
Adding the new APIs to the .def files and fixed a couple of things
...
Change-Id: I247a60b8cdbd4acfed72fb6d78ac7faf69d8a556
2017-01-27 16:51:50 -05:00
1cd46afe6d
Implement SDMA path for Gfx9
...
Gfx9 requires monotonic write pointer and doorbell.
Cound fields are 1-based compared with 0-based pre-Gfx9.
- Restructure implementation to use monotonic ring indices
- Remove redundant submission size checks (handled by AcquireWriteAddress)
- Unify copy/fill per-command limit (documentation is unclear)
Change-Id: I57c1675221d2e63aa319fee700d9951671e1bd65
2017-01-26 13:11:21 -05:00
Evgeny
Ramesh Errabolu
Kenny Ho
Jay Cornwall
Konstantin Zhuravlyov
hthangir
Qingchuan Shi
Sean Keely
James Edwards
Christophe Paquot
Konstantin Zhuravlyov