Add clang pragma push and pop diagnostics for ignoring "-Weverything"
in the hiprtc builtins header. Otherwise this will ignore even the
geniune errors occurring in the hiprtc kernels.
Change-Id: I8c3dacf902732b2ea495d83e797369f8aebd75d6
[ROCm/clr commit: 912cc407a4]
- Remove newline from logging as log function internally inserts a new
line
Change-Id: I25eb2242a1f1e87cf811bcc373d1d485b2e027a8
[ROCm/clr commit: 058b2702db]
- Allow capture to be less rectrictive if we set the global thread
interaction mode for the thread.
Change-Id: I84f65d9418ac26ada0477c85a45a3831c2351ce4
[ROCm/clr commit: 59a6a6c12e]
If the compiler decides not to inline these functions, we might break ODR (one definition rule) due to this file being included in multiple files and being linked together
Change-Id: Iacbfdabb53f5b4e5db8c690b23f3730ec9af16c0
[ROCm/clr commit: 77c581a3eb]
This reverts commit 239fdc3bfd.
Reason for revert: This is considered a breaking change and requires
multiple apps to change their behavior. This will be reintroduced in later releases.
Change-Id: I3481627115af1872785585a155cc6a0ecfbe1372
[ROCm/clr commit: 7febad13be]
This reverts commit 6035b47801.
Reason for revert: This is considered a breaking change and requires
multiple apps to change their behavior. This will be reintroduced in later releases.
Change-Id: I0354ce4e0f5e6c402499a7a8c2aaf43bf5b1bfc7
[ROCm/clr commit: 270c6d48f1]
C++ does not allow const qualifier on function type, even if we add it it will get ignored and clang will fail with failed cast from const void* to func*. const_cast here is necessary to make it work.
Change-Id: I72cec8d9e715bdf9e163cb9b08393dd733dafaf2
[ROCm/clr commit: 5b5213adf5]
__HIP_CLANG_ONLY__ is not recognized in HIPRTC, due to which some
math functions like amd_mixed_dot were not included in hiprtc builtins.
Change-Id: I1fe41e1ddc8911f6a5b5b1405dd4730d0170a4f7
[ROCm/clr commit: f0010f4fdb]
Defining int64_t, uint64_t, int32_t, uint32_t in HIPRTC
seem to result in conflicts with some apps as they use
their own definitions for these types. NVRTC also doesn't
define these. Hence remove them to match the behavior.
Change-Id: I77ef70e846950698cb00375f5d0501b907f01fe3
[ROCm/clr commit: 629e279f72]
- Report kernel names for optimized graph path
- Refactor code so that we store profiling info in Accumulate command
Change-Id: Ib97735a0239aeb9fc3a50a4bb7126dd0bcadc8af
[ROCm/clr commit: b056686607]
__smid() needs to use both HW_ID and XCC_ID for gfx940, gfx941, and
gfx942. Previously, we only did this for gfx940 and thus XCC_ID
was incorrectly not passed back on the other two architectures.
Change-Id: I9fb13b6cef3280e15463443a180174629d03f8b2
[ROCm/clr commit: a0f29b454c]
Make hipExternalMemoryGetMappedMipmappedArray() accept
hipArraySurfaceLoadStore.
Make hipCreateSurfaceObject() check hipArraySurfaceLoadStore
flag. If flag is hipArrayDefault, hipCreateSurfaceObject() will
also pass to prevent failure of catch2/swissknife tests.
Change-Id: Ifb7db2db14e0c2208a9661cfa33887ec61ab26a5
[ROCm/clr commit: 1c442658ca]
Do not populate AMDGPU_TARGETS when there is no device
detected by amdgpu-arch on the machine
Change-Id: I87fd7081f9e0b72f057aab2eb639808d2f89cfb1
[ROCm/clr commit: e36020f339]
- Do not use extra barrier to detect graph end. If its a kernel node we
can use a completion signal for the last packet. Saves roughly 6us for
Phantom testcase per graph launch.
Change-Id: I5e0c2479d9964fbeda86ed97533f6718f49a7f91
[ROCm/clr commit: c3bd229f4f]
Compiler seem to be stricter in compiler staging builds related to
safe buffer programming when compared to other component staging builds.
This seem to result in additional errors when -Werror is enabled
in MIGraphX tests.
Removes all the clang pragmas to ignore several type of warnings in all
the headers and adds a single pragma which ignores all warnings using
#pragma clang diagnostic ignored "-Weverything" in hiprtc builtins.
Change-Id: I95f302bb285b2451b19dd5dfdb7df29164b0f750
[ROCm/clr commit: b5d286a6d3]
Set flag with hipCtxCreate so that get flags works.
Validate hipHostGetDevicePointer for flags!=0.
Validate mem cpy kind and accommodate new type hipMemcpyDeviceToDeviceNoCU.
Match error code for hipGetChannelDesc.
Change-Id: If09a635ac01bc53f1fe2b7df3f3f9c1b0d69a0ab
[ROCm/clr commit: 8e8fb993de]
Add __host__ and __device__ to bunch of operator/function matching CUDA
Fix some bugs seen in __hisinf
Change-Id: I9e67e3e3eb2083b463158f3e250e5221c89b2896
[ROCm/clr commit: 86bd518981]
- Track all captured commands under a new AccumulateCommand
- Add begin() and end() methods to capture commands
- Explicit TS object now passed to certain methods because
profilingBegin() and profilingEnd() now happen separately and thus can
run into threading issues
Change-Id: I171106bdcad72b057836cb2f3fc398db3533119f
[ROCm/clr commit: 40f41f4d0b]
- This matches the CUDA behavior
- The pitch and width checks removed are already covered in ihipmemcpy2D
Change-Id: I03a6921a78b5d89723830d8dde5865fdc6db0379
[ROCm/clr commit: 6d6465cb96]
Remove duplicated operators of hipComplexFloat and
hipComplexDouble.
If users need complex number multiplication and division,
they should call
hipCmulf() and hipCdivf() for hipComplexFloat,
hipCmul() and hipCdiv() for hipComplexComplex
SWDEV-428198 - Add missing operators
Add missing operators of vectors in host
Change-Id: Ie58d1642d579e7119997db49a9fd6a6641b666fd
[ROCm/clr commit: d4799b2a3f]
- Support graph with different types of nodes with single
branch when DEBUG_CLR_GRAPH_PACKET_CAPTURE flag is enabled
Change-Id: I149a8629769cd0d5849ffefb04f1352668a685b6
[ROCm/clr commit: 38d2c56784]
Todd tiantuo Li
Satyanvesh Dittakavi
Saleel Kudchadker
Ioannis Assiouras
Jatin Chaudhary
Anusha GodavarthySurya
Rahul Garg
jiabaxie
Jaydeep Patel
Joseph Greathouse
Tao Sang
sdashmiz