8615a89f24
SWDEV-1 - Use proper builtin for groupstaticsize
...
Remove the now empty header for asm intrinsic wrappers.
Change-Id: I63495dc6ed899b1ea823062f2be2fb064af8d4f9
2023-01-13 13:14:10 -05:00
eef47ca24a
SWDEV-353281 - Initial support of memalloc in graph
...
Add memory allocation support in graph. Current implementation uses
cache from mempool to hold the allocations which belong to the graph.
Also the resource tracking is disabled at this moment because mempool
operates with hip::Stream objects, but graph has execution with
amd::HostQueue objects.
Change-Id: I54fe3250126d24f5a26ada975f37d429bb4ef17b
2023-01-13 13:06:59 -05:00
c193503722
SWDEV-376386 - Support __hip_move_dpp with hipRTC
...
Change-Id: If9a6fe23d6df143a7f522823fca7183416048c6a
2023-01-13 00:05:31 -05:00
3e54bad5b3
SWDEV-1 - Directly call __builtin_amdgcn_fence
...
The device libraries provide hip.bc, which only contains
__atomic_work_item_fence. This is identical to OpenCL's
atomic_work_item_fence, except prefixed with __. This only existed to
switch over the unknown values the OpenCL function provides. There's
no need to go through the wrapper here since it's using constant
values, and without it we can drop one of the bitcode libraries. I'm
guessing this was a holdover from before the fence builtin existed.
Change-Id: I8b04614f96194eafddeba295215c12c3856e6c42
2023-01-12 12:04:09 -05:00
91b851fad7
SWDEV-1 - Remove unused intrinsic declaration
...
The uses have moved to using the proper __builtin_amdgcn_ds_swizzle.
Change-Id: I82159ebf41fb91ac6a9d07b33311e569dce5e754
2023-01-12 12:04:09 -05:00
b321e2afc6
SWDEV-368881 - Implement hipModuleLaunchCooperative* APIs
...
- Add implementation for hipModuleLaunchCooperativeKernel, hipModuleLaunchCooperativeKernelMultiDevice APIs
Change-Id: I2a80264e458549211c34b413397a08b57d021147
2023-01-10 13:50:20 -05:00
6c53a670c1
SWDEV-345571 - Revert changes for warp shuffle functions
...
This reverts commit ad1fae7df4695533d435
2023-01-09 22:56:52 -05:00
0c8c08cf51
SWDEV-361374 - Adding support for hipPointerSetAttributes
...
Change-Id: I56710b808854acefca07b3b5898deebee38063e9
2023-01-09 12:36:57 -05:00
695533d435
SWDEV-375137 - Bypass defination of half and half2 alias for internal include of hip_fp16.h
...
Change-Id: I5258a487d4c2d93e889a523fde81f1b3906d9318
2023-01-06 21:34:51 -05:00
ad1fae7df4
SWDEV-345571 - Added support for half/half2 data types for warp shuffle functions
...
Change-Id: Ia0791760c1b0a35bbbf0b1f8435aa924af205169
2022-12-26 01:24:06 -05:00
e90721435b
SWDEV-372767 - Fix hipCUB and rocWMMA build failures
...
Change-Id: If3672fd50075c67cfce4d94e73b1376c4aa8d2ae
2022-12-16 03:08:18 -05:00
91291e48db
SWDEV-372032 - Support cooperative groups header with HIPRTC
...
Change-Id: Ia64652fd52b210a4eeee9d38fdfdfa6fdc7163ff
2022-12-09 04:45:59 -05:00
1deee433d0
SWDEV-287842 - Add int8_t and int16_t support in hiprtc
...
Change-Id: I03bb967068f1a29e85ce8d9410f78de4af9589c4
2022-12-01 11:58:46 -05:00
f7ca4b8fb9
SWDEV-365299 - update implementation __float2half_{rd,ru,rz} to call __ocml_cvt{rtn, rtp, rtz}_f16_f32
...
Change-Id: I6cd711fbeb0e02a1caa03ac7f3dd9c8f8fdbac01
2022-11-25 16:27:02 +00:00
c5b08c621f
SWDEV-364950 - Remove Scalar_accessors from HIP_vector_type
...
Change-Id: I13ecc213c98a1c7b5febcd43c0a21ee6db725f60
2022-11-24 09:40:54 -05:00
a312c0a956
Fix atomicInc/dec scope to "agent"
...
Addresses leftover comment of Icd1d9b9438cac4bef0f7c52d4cd341ac76500890
Change-Id: If9c395335497d634e4c702433d6e3681583bedef
2022-11-24 06:56:49 -05:00
432f5fbc97
SWDEV-364950 - Add trivial copy assignment for HIP_vector_type under HIP_CLANG_ONLY path
...
Change-Id: I56a1003ba32c748631c7751b2e6a49e12e48afcb
2022-11-23 16:56:39 +00:00
78eef7f173
SWDEV-366653 - Added new graph APIs - Fix windows build
...
Change-Id: I580133bddcbab5529aecfb70bc9776e8c40de697
2022-11-23 08:57:49 +00:00
93ce12c90d
SWDEV-325711 - Added Graph APIs hipGraphDebugDotPrint, hipGraphKernelNodeCopyAttributes
...
hipGraphNodeGetEnabled, hipGraphNodeSetEnabled and hipGraphUpload
Change-Id: Ib5a58fbc0a9b3f134eb56d42cd945f3d7f4922d8
2022-11-22 23:20:25 -05:00
5f4aa2e994
SWDEV-366306 - SWDEV-366314 - Support hip vector types and hip_bfloat16 with hiprtc
...
Also, moves the hip_bfloat16 header implemenation from hip
to hipamd
Change-Id: I9980126fa1ee8160ff9f5f8241f64699a9702c95
2022-11-18 06:58:31 -05:00
30c43056c1
SWDEV-340754 - Update coordinates in coperatative helper
...
Change-Id: Ibf4e833d10ea5c317900e83f020c9c23f55f3951
2022-11-17 14:17:58 -05:00
834d9d3a3c
make header intel-compatible
...
Change-Id: I8f8b68ba23e8f86dfeaf7c7b464f2b6ca6999971
2022-11-14 17:59:01 -05:00
5ff27faa04
SWDEV-337452 - Adding__ockl_steadyctr_u64 option for wall_clock64.
...
Change-Id: I4ee6fd4d40d500363ef84975078185093dab5ddd
2022-11-07 08:47:30 -05:00
c974cbcb3d
SWDEV-366153 - Fix __ocml_isnan_f16 to pass _Float16
...
Change-Id: I7628f21d000cec490f5fb2c91f1b99ca61fb46cf
2022-11-06 21:57:23 -05:00
07b3070e25
SWDEV-362611 - Added hmax and hmin
...
Change-Id: I133a80e997e39357693df7ab969425c0d5585607
2022-10-31 00:23:57 -04:00
dcb5d29f1e
Replace LLVM atomic.inc intrinsics with Clang builtins
...
With opaque pointers, the suffix of those intrinsics changed. This caused
build failures that should be solved by just using the corresponding
Clang builtins instead of using intrinsics directly
See SWDEV-356581
Change-Id: Icd1d9b9438cac4bef0f7c52d4cd341ac76500890
2022-10-27 10:17:21 -04:00
19107858d6
SWDEV-361847 - Print 'char' parameters as 'integer'
...
When printing HIP API function parameters, use the integer format to
print 'char' arguments to avoid printing invalid ASCII characters
(value > 127).
Make sure the roctracer::hip_support::detail operator<< overloads are
used when printing arguments.
Change-Id: Id072c2ed19b1b4166108599e393d1cae6c54b6b0
2022-10-21 14:55:33 -04:00
47a29c748a
SWDEV-359838 - Add a phase data pointer to the hip_api_data_t
...
To avoid using the thread local std::stack to remember the phase enter
timestamp, the tracer tool uses the phase data to store the timestamp.
Change-Id: I9e95637b41d6f0b2bd61016062ca07d6ba897652
2022-09-30 14:55:01 -07:00
835b7578dc
Revert "SWDEV-351980 - Update hip_prof_str.h"
...
This reverts commit f296e42803
2022-09-21 13:04:38 -04:00
f296e42803
SWDEV-351980 - Update hip_prof_str.h
...
Change-Id: Ied27c137aff54e69dc14129e6daad9196479edf9
2022-09-21 11:38:59 +00:00
2801e4fe63
SWDEV-357334 - hipEventRecord_spt() to take optional stream arg
...
Change-Id: I19540c577e2c3635a00379f814350ada41020af2
2022-09-19 20:28:13 +00:00
df278887fe
SWDEV-301667 - Pass all params to API Init
...
- Correct return for ihipLaunchKernel
Change-Id: I66e81fa635473e6e728936e4cfba9f1bc7f018ad
2022-09-15 22:20:02 -07:00
52a22a1263
SWDEV-350025 - Added hipLaunchHostFunc functionality
...
Change-Id: I6b9d547f7ddf84e617e35ff5d5a490ff458272ef
2022-09-07 17:53:26 +00:00
3b530b5676
SWDEV-354138 - Fixed SPT functions linking issue
...
Change-Id: I738ccdfd6db8cfa8c29f93bb6061e83795df382b
2022-09-05 06:22:08 -04:00
8ac20e5e38
SWDEV-351980 - Fix hip_prof_str.h generation
...
Fixed an error in the CMakeLists.txt USE_PERF_API option declaration
that was making it always disabled. Fixing this exposed an issue with
the hip_prof_gen.py script's handling of function variants (for example,
_spt functions) and new HIP_INIT_API_* macros.
Also switched the python interpreter to python3 as python2 may not be
available by default on the build system.
Change-Id: I971fc9edcc746ca63a2bdf4f540e755f9a80fe69
2022-08-18 23:15:27 -07:00
2c010dec17
SWDEV-325711: Add userobject functions for graph
...
- add user obj APIs for creating release and retain of user onbjects
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I0bf2999c77e44269565b27c31c7c1461f8a160a2
2022-08-17 14:31:43 -04:00
638f9a7c0e
SWDEV-348565 - Support for += operator.
...
Change-Id: I29045733de3906849e68b89c22e01badc9bd2b24
2022-08-05 02:59:39 -04:00
e1f1e38d79
SWDEV-1 - cleanup
...
Change-Id: Ib50424c87cfc76317eb0c114b5dd3553d8ebd9eb
2022-08-01 00:05:58 -04:00
9f9fd859db
SWDEV-286739 - Support hipDeviceAttributeWallClockRate
...
Part 3: Add missing declaration of wall_clock64() to fix
compiling issue in device code.
Add querying hipDeviceAttributeWallClockRate.
Change-Id: Ie54771c2f58eeaacdc0248bc116ef193f99eb9b9
2022-07-28 13:02:42 -04:00
b96ff76989
SWDEV-342896 - fix incorrect format setting
...
Change-Id: I1fa72eefa3b550d41db6a4cc0812771fb0035bdc
2022-07-22 11:17:50 -04:00
9b18e404ae
SWDEV-327563 - catch2 deviceLib build failure
...
Change-Id: I82f95d61f64018a761e45dc8f424af032953fc51
2022-07-15 21:11:20 -04:00
a47887aa0d
SWDEV-343278 - fix conversion functions
...
Change-Id: Ib93f886363314e980462ef562c998981bb958569
2022-07-15 16:00:58 -04:00
4375b9f5b9
SWDEV-333033 - add safe and unsafe atomic min and max including gfx940 and add missing nvidia support
...
Change-Id: I829a0a5fd49c510e77eabbcb92d1a415ef6b5a4c
2022-07-14 10:22:42 -04:00
9eb45dd1e0
SWDEV-345188 - hipamd: warnings treated as errors for catch tests
...
Change-Id: I8981a530da2e0213c60f7a81b09d9c36e27e9025
2022-07-12 15:34:39 -04:00
e9961fedd8
SWDEV-323441 - Phase-II : per thread default stream
...
Change-Id: I3c796ddaebcf0223d7faf50c425c1674de215f9d
2022-07-11 12:22:23 -04:00
1074b22c48
SWDEV-333073 - HIP_INIT_API to handle no return case
...
Change-Id: I78d43e88cc196047a4cb5d6fcf756339c0e46e80
2022-06-24 12:53:18 -04:00
7f92a98a3c
SWDEV-331066- Added hipDeviceSetLimit
...
Change-Id: I4de099387ad34ca7c195588274b546649038e2aa
2022-06-21 06:06:05 +00:00
8d464a2e83
SWDEV-322688 - Added hip math constants header.
...
Change-Id: I9363f82159a53c6822e943c4950fc7f6c350b326
2022-06-16 23:56:45 -04:00
e8194dca76
SWDEV-325711 - add Graph memory APIs skeleton
...
- hipDeviceGet/SetGraphMemAttr
- hipDeviceGraphMemTrim
- there is no memory pool for graphs currently
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I11db76ea7ea1c7732175fc93264448052357e8dc
2022-06-15 14:47:16 -04:00
8dfa7e7f98
SWDEV-334908 - Guard the __noinline__ macro as it is also supported as keyword by clang
...
Change-Id: I314b3ac463ea63132a5107f4f24ce769d8112b9b
2022-05-18 05:51:32 -04:00
Matt Arsenault
German Andryeyev
Satyanvesh Dittakavi
Rakesh Roy
Maneesh Gupta
kjayapra-amd
Jaydeep Patel
Anusha GodavarthySurya
Ioannis Assiouras
Pierre van Houtryve
Julia Jiang
Daria Materikina
Laurent Morichetti
Ajay
Saleel Kudchadker
Sarbojit Sarkar
sdashmiz
Tao Sang
haoyuan2
Brian Sumner