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
a19b767e8a
SWDEV-319818 - Release restriction on hipResourceViewDesc
...
Let more types support hipResourceViewDesc.
Add missing symbols to fix cuda build failing.
Change-Id: Ife694cc6491427093863252e257e820b0bb4fa0f
2022-05-10 15:57:31 -04:00
f68149eafd
SWDEV-332811 - Clean up and extend HIP unsafe atomic add
...
Update HIP's unsafeAtomicAdd to:
- Compile properly even when not compiling for gfx90a
- Fall back to safe atomic add on non-gfx90a architectures
- use flat atomic add for FP64 on gfx90a, instead of dynamically
checking memory spaces.
In addition, when the compiler is passed -munsafe-fp-atomics, it
will define __AMDGCN_UNSAFE_FP_ATOMICS__. When this happens, the
compiler is requesting that the HIP headers force all HIP
atomicAdd() calls on floats or doubles to use their unsafe versions.
This patch thus causes unsafeAtomicAdd() calls when that define
is seen. This call to unsafeAtomicAdd() is also done for atomicSub(),
since that calls atomicAdd underneath. This is not done for
system-scope atomicAdd because, on gfx90a, system-scope atomic FP
add instructions would need to target fine-grained memory, which is
always unsafe.
This patch also creates safeAtomicAdd() functions for float and double.
These functions will create a standalone safe atomic, even when the
application is compiled with -munsafe-fp-atomics.
Finally, this patch adds wrappers in the Nvidia path of HIP so that
these HIP functions call through to atomicAdd there as well.
Change-Id: I8af0621d3d28ea30c9278bfeea7393d03bbdac6d
2022-04-29 07:19:58 -04:00
fc1f02bbed
SWDEV-323441 - support for default stream per thread
...
Change-Id: I0032da0357f5cffbf5e4ec4a02435d2a128a262b
2022-04-18 23:19:55 -04:00
cd447a5aaa
SWDEV-322620 - Virtual Memory Management APIs
...
Adding skeletons.
Implemented:
- hipMemGetAllocationGranularity with basic granularity
- hipMemGetAllocationPropertiesFromHandle
- hipMemCreate
Change-Id: I4bd2c75fae45d6a057efcad19d1d3c9715e9ae67
2022-04-08 11:38:51 -04:00
5f0f7ffe92
SWDEV-326789 - Mark texture reference APIs as deprecated
...
Change-Id: I7a39cc1f036cd185ac3aab6c5f44730f16225f69
2022-04-05 00:04:34 -04:00
539d264eb0
SWDEV-311271 - Initial mempool implementation
...
HIP_MEM_POOL_SUPPORT controls memory pool support in runtime.
Currently it's disabled by default. The initial change doesn't
include: IPC, MGPU, virtual memory alloc, suballoc, defragmentation,
internal dependencies.
Change-Id: Ibed8528ebec698b045ebb247e49c0ecd6e587ed7
2022-03-31 09:21:37 -04:00
1e77357c7f
SWDEV-326789 - Add Missing HIP API Functions For Nvidia Platform
...
Change-Id: I828028c5d893ca1487f33017a6902c3b7f786762
2022-03-25 01:34:57 -04:00
2fd90ec7a4
SWDEV-317716 - Add hipDeviceGetUuid API
...
Change-Id: I320c7bc11ddd7617e0246f6faf19135ad7363e73
2022-03-16 00:23:44 -04:00
3cc0a3fcaf
SWDEV-321656 - Address incorrect warp size with hiprtc
...
Change-Id: I97051d4e2cf27cb073c39663c62e43d5c19b1a12
2022-03-15 06:52:21 -04:00
2b86f24fda
SWDEV-323441 - New header for per-thread-default-stream
...
Change-Id: If74ea1464117abd2bfeadd543b94d26f9e934cbb
2022-03-14 01:13:01 -04:00
bed3995147
SWDEV-316128 - HIP surface API support
...
align with CUDA to support surf1DLayeredread/write,
surf2DLayeredread/write, surfCubemapread/write functions.
Change-Id: Ie3f6ca75e23accd97cb35cdc8362d88a1e5dbd54
2022-03-09 21:19:48 -05:00
1524c9515e
SWDEV-315118 - Add version check for hipGraphInstantiateWithFlags on nvidia path
...
Change-Id: I672b4a5287348bddf6eb8955decc9cce786275a2
2022-03-09 02:10:08 -05:00
1965dd5795
Revert "SWDEV-321698 - hipGraphNodeTypeMemcpy1D NVDIA build failure"
...
This reverts commit 74beb4583c
2022-03-08 15:08:31 -05:00
74beb4583c
SWDEV-321698 - hipGraphNodeTypeMemcpy1D NVDIA build failure
...
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I7aea11bf14adbeb7fea68eb862df74fcf6f13d75
2022-03-07 16:26:11 -05:00
27f102b167
SWDEV-323472 - Add hipThreadExchangeStreamCaptureMode
...
Also fix an issue in hip_prof_gen.py with GLenum.
Change-Id: Ib03fe9dae87b850c53b7d8aeb78b8dbdd01f794c
2022-02-24 15:24:22 -05:00
f3f11f4c7d
EXSWCPHIPT-13 - Fix Segfault on Nvidia Platform
...
Change-Id: Ib85bb0b0e91b7703afc4858c4a5ada0115ad68f4
2022-02-19 12:53:46 +00:00
aee5c48848
SWDEV-315981 - make nvidia hiprtc functions static
...
Change-Id: I945426c155ed9ce21c308745f384bbf8669d73c4
2022-02-15 23:38:19 -05:00
e5496b3159
SWDEV-314485 - Remove the older implementation of device-side malloc/free
...
Change-Id: I9ba3c6030a6dd7a5e064073d5c21223041282f61
2022-02-15 07:49:56 -05:00
087c0c25b2
SWDEV-315118 - Add version checks for few graph APIs on Nvidia path
...
HIP apps running on CUDA 11.0 are failing due to some graph APIs/enums
added only in CUDA 11.1 or CUDA 11.3
Change-Id: I0d32b412cb76c42c7b3a9c612d750990f9e89908
2022-02-15 02:03:49 -05:00
f371300933
SWDEV-315017 - Add missing graph error strings
...
Change-Id: I11b5a623756c5bef88cbc93e49c124d0caf62bd1
2022-02-15 01:41:44 -05:00
9c31a738c2
SWDEV-317135 - Fix mapping of hipStreamUpdateCaptureDependencies on cuda path
...
Change-Id: Ibbcf8136fa527a20684a377311bc76182345d17b
2022-02-14 09:10:46 -05:00
7d8c63cc34
SWDEV-294375 - Declares fns() functions static
...
Change-Id: Ife0150b8d6b9531522e61a82df6b88af3282f437
2022-02-13 23:35:46 -05:00
d7beddbfee
SWDEV-316128 - HIP surface API support
...
Change-Id: I5b98f86168e64b36588f5d7efb82191d895e27d7
2022-02-11 11:07:04 -05:00
0759f4ff81
SWDEV-314661 - Add hipGraphInstantiateWithFlags API mapping in nvidia path
...
Change-Id: Ibbf54ef18978448e92571f0535124844154726b6
2022-02-09 00:02:55 -05:00
523e5a007c
SWDEV-294375 - Adding coalesced_groups to ROCm CG
...
Change-Id: I4098e1970ae2c388171fa73deb5bc023ed1b7a68
2022-02-07 11:29:46 -05:00
760f275861
SWDEV-292714 - Added support for hipPointerGetAttribute and
...
hipDrvPointerGetAttributes
Change-Id: I44a0b5c5d9eb5a9a63406b11e8de83e5cb245a59
2022-02-02 05:33:07 -05:00
44e0c246f8
SWDEV-245531 - GLInterop adding register image
...
Change-Id: I075bec49b7ad5f78336586b9d55e259717c4c000
2022-01-23 14:59:18 -05:00
5f9d779324
SWDEV-245531 - GLInterop adding register image
...
Change-Id: Ib16b647e2a1b8f3c578a9689d3987121c984250b
2022-01-14 15:57:24 -05:00
c8103470d5
Fix missing system-scope for CAS in atomic[Min|Max]_system
...
Change-Id: Ieb0ca79eaeba3a0ae56739246e08135a25a8d6dd
2022-01-12 22:53:11 -05:00
0f94653447
SWDEV-315924 - align with CUDA to define vector3 data type
...
Change-Id: I7654fb757b4c387a762f384ccdd3f2c8555d149f
2022-01-06 17:35:56 -05:00
78de8cd672
SWDEV-315590 - Fix texture vector issue
...
Apply mapFrom() to related texture device functions.
Change-Id: Ifed918c87373b784780b2180320ccb746845daff
2022-01-04 19:26:14 -05:00
7de480760b
SWDEV-315590 - Fix texture fetch issue
...
Add mapFrom() to map "float __attribute__((ext_vector_type(4)))"
of output of low-level device function to right vector.
Change-Id: Ifed915c87273b784780b2180320ccb746845dafb
2022-01-04 13:38:57 -05:00
8a8581edf5
SWDEV-316052 - fix HIP_Directed tests build error
...
Change-Id: I782c68859f77934f2cf672ee53378e51b1cb1ddd
2021-12-21 03:21:53 -05:00
a8b30291c3
SWDEV-303956 - add make_int2/3/4 and make_float2/3/4 function support
...
Change-Id: I0260d1a9d2ac66e84dc31a80b0995616ef78b0fe
2021-12-15 14:57:36 -08:00
937415141c
SWDEV-303956 - align with CUDA to define float4 data type
...
Change-Id: I9ad1315e5899a8c0cf1812302b27010d88015f88
2021-12-14 15:22:43 -05:00
f3c5f12d26
SWDEV-311744 - Update floating point max/min atomic implementation
...
Clang builtins doesnt yet support max/min atomics with float/double
parameters, Hence modify atomicMax/Min to use compare and swap
implementation
Change-Id: Ia351f9b136129fe25f0eddcbbb17549553247182
2021-12-07 13:29:44 -05:00
5acc8b5102
SWDEV-303204 - Disable texture/image Apis on some devices
...
If the target device doesn't support image,
compiler will send out unavailable error if device texture apis
are called; and host texture apis will return hipErrorNotSupported.
Remove useless include/hip/amd_detail/texture_functions.h.
Add hipDeviceAttributeImageSupport attribute to check image
support in runtime.
Add __HIP_NO_IMAGE_SUPPORT(=1) macro in device code to indicate
texture apis not supported.
Change-Id: Ia891493e681a61980a2444859a90e046a9ebea39
2021-12-04 08:14:08 -05:00
69117705c8
SWDEV-309292 - add hipPos definition in CUDA path
...
Change-Id: Ia81d5db77d7403cafb583fda8083d0f4dbe33835
2021-12-04 04:40:34 -05:00
5b08779b25
SWDEV-307407 - Add hiprtc's type traits function to match implementation of libcxx
...
Change-Id: I0a10eca329f817bbe31bdc47869b2de104d12d38
2021-12-02 23:32:23 -05:00
e90cb3b07b
SWDEV-305766 - Added new debug APIs to get build information
...
Change-Id: Ibbf0c010cd8f7e6e659f2c4ba932cc8436574431
2021-12-02 12:20:51 -05:00
a6bf18791e
SWDEV-240808 - Added nvidia handling for few graph APIs
...
Change-Id: I8edee87ea75d80152418f76cc8a521b2ba58f139
2021-11-22 07:17:34 -08:00
17cc99c05d
SWDEV-306947 Enable hipAddressModeBorder
...
Enable hipAddressModeBorder.
Fix default of height of hipMallocArray().
Some code improvement.
Change-Id: I57045118e7adf915074c547cbe76349a4cfd72d8
2021-10-27 10:05:53 -04:00
1c51d82dd5
SWDEV-240806 - Added few Graph API Implementation
...
hipGraph APIs clone, childGraph, RemoveDependencies, GetEdges,GetDependencies, GetDependentNodes, GetType and DestroyNode
hipStream APIs GetCaptureInfo, GetCaptureInfo_v2, UpdateCaptureDependencies.
Change-Id: Ib0f4cb8ea335698eecdd6d744ffab1e954153673
2021-10-05 07:44:54 -07:00
1111468b49
SWDEV-240806 - Added few more Graph APIs
...
Change-Id: I028a1fdf30232b0c47443685e03d7ca410d2a0d0
2021-10-05 07:37:11 -04:00
4cd4d2d280
SWDEV-304552 - Add default to return the last error value
...
Change-Id: Ia399033e30aaa454a454067f5afc6f7d1e5ff8dd
2021-10-04 07:23:10 -04:00
70e1fb6a5b
SWDEV-304076 - Fix for Cuda build error
...
Change-Id: Ibca63a08b8d6d1235b51a06c0bc024cd284cee97
2021-09-27 23:55:52 -04:00
7aaad05910
SWDEV-298667 - fix stream operation for Cuda
...
Change-Id: Ida91712e678e324b54293ba48dfca442be390783
2021-09-21 15:07:15 -04:00
673c2deed1
SWDEV-302147 - fix __hip_ds_permutef device function to return float
...
Change-Id: Ie452e90a7f7410401df4a66de468ad850403953c
2021-09-14 02:15:53 -04:00
b25e6d3716
SWDEV-301330 - Remove the hard coded driver version on HIP CUDA platform
...
Change-Id: I0eb10781acc7524174c7ae6fc552c824b7c94b0a
2021-09-02 09:03:04 +00:00
Satyanvesh Dittakavi
Tao Sang
Joseph Greathouse
Sarbojit Sarkar
Christophe Paquot
Rakesh Roy
German Andryeyev
haoyuan2
Shadi Dashmiz
Sourabh Betigeri
pghafari
Payam
Nick Curtis
cjatin
anusha GodavarthySurya