AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
76 333 Commits 3 Branches 0 Tags
develop
Commit Graph

1845 Commits

Author SHA1 Message Date
Ioannis Assiouras a6a6f744ee SWDEV-380466 - Fixed typo in unsafe atomicAdd for doubles and gfx940 
Change-Id: I3b9ea4773f94bf6a9b9dfb655062f42aeb3b5eba


[ROCm/clr commit: 24d3d8216b]
 2023-02-07 10:06:17 -05:00
Matthew Arsenault 716ddd1d98 SWDEV-1 - Reapply "SWDEV-1 - Directly call __builtin_amdgcn_fence" 
This reverts commit 7b3cf2e9d7.

Resubmit after https://github.com/ROCmSoftwarePlatform/rocPRIM/commit/ba8a86166ec9c4cf3a40ecde7017feeb1484e7f6

Change-Id: I194559484a5a0d7f4443381fe77218ea73d2def9


[ROCm/clr commit: 8c7391398a]
 2023-02-03 10:54:27 -05:00
Matt Arsenault c77979a365 SWDEV-1 - Use proper builtins for math intrinsics 
Change-Id: If0e420332c718abe0e9f6316c467b6b29b80b183


[ROCm/clr commit: 14477c24d0]
 2023-02-01 07:19:45 -05:00
Rakesh Roy e8b7717abb SWDEV-375004 - Fix rocprim test failure 
- For !__HIPCC_RTC__ case, operator<<(std::ostream& os, const hip_bfloat16& bf16) calls itself in endless recursion
- Convert hip_bfloat16 to float to fix this

Change-Id: I252a656817550caf43c587cebf461474f12b8c0c


[ROCm/clr commit: 8b00f56577]
 2023-01-25 00:01:02 -05:00
Satyanvesh Dittakavi d96114fd22 SWDEV-372396 - Address the errors in hiprtc headers with -Werror 
Change-Id: Ied553216dfc2ff8b5c72de617cb47b6ca8f52063


[ROCm/clr commit: 0ccd41050b]
 2023-01-23 17:25:42 +00:00
Maneesh Gupta 7b3cf2e9d7 SWDEV-378321 - Revert "SWDEV-1 - Directly call __builtin_amdgcn_fence" 
This reverts commit 1de57c06b3.

Reason for revert: Root cause for regression SWDEV-378321

Change-Id: If3116c5ad1a23db1840e5fc019d2fe997b37d229


[ROCm/clr commit: 5b39c346ad]
 2023-01-19 13:01:27 -05:00
Satyanvesh Dittakavi f94a34e128 SWDEV-373231 - Support hip atomics header with HIPRTC 
Change-Id: Ic500dfb66ed5ef0c4b672dfd0595409d0e8caaf5


[ROCm/clr commit: 842b9d0b56]
 2023-01-17 00:31:07 -05:00
Jaydeep Patel c9fa0aad8b SWDEV-369961 - Add mappings for enum hipGraphInstantiateFlags and types. 
Change-Id: I03fa8221684b08a0c44e12aaf2eb7ce5281be629


[ROCm/clr commit: 8bd45ae5da]
 2023-01-15 12:17:21 +00:00
Matt Arsenault 967ad97993 SWDEV-1 - Use proper builtin for groupstaticsize 
Remove the now empty header for asm intrinsic wrappers.

Change-Id: I63495dc6ed899b1ea823062f2be2fb064af8d4f9


[ROCm/clr commit: 8615a89f24]
 2023-01-13 13:14:10 -05:00
German Andryeyev 9c811dc241 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


[ROCm/clr commit: eef47ca24a]
 2023-01-13 13:06:59 -05:00
Satyanvesh Dittakavi 6035b0e214 SWDEV-376386 - Support __hip_move_dpp with hipRTC 
Change-Id: If9a6fe23d6df143a7f522823fca7183416048c6a


[ROCm/clr commit: c193503722]
 2023-01-13 00:05:31 -05:00
Matt Arsenault 1de57c06b3 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


[ROCm/clr commit: 3e54bad5b3]
 2023-01-12 12:04:09 -05:00
Matt Arsenault ac1201f598 SWDEV-1 - Remove unused intrinsic declaration 
The uses have moved to using the proper __builtin_amdgcn_ds_swizzle.

Change-Id: I82159ebf41fb91ac6a9d07b33311e569dce5e754


[ROCm/clr commit: 91b851fad7]
 2023-01-12 12:04:09 -05:00
Ioannis Assiouras bfa0b9f844 SWDEV-374405 - Added OpenGL interoperability APIs for nvidia 
Change-Id: I1d6ad5c610ab6ee805bd07dacea316b3242ed129


[ROCm/clr commit: e97dcfbe48]
 2023-01-12 05:22:14 -05:00
Rakesh Roy 87db95fad7 SWDEV-368881 - Implement hipModuleLaunchCooperative* APIs 
- Add implementation for hipModuleLaunchCooperativeKernel, hipModuleLaunchCooperativeKernelMultiDevice APIs

Change-Id: I2a80264e458549211c34b413397a08b57d021147


[ROCm/clr commit: b321e2afc6]
 2023-01-10 13:50:20 -05:00
Maneesh Gupta 4f5f6a3696 SWDEV-345571 - Revert changes for warp shuffle functions 
This reverts commit 609598cd15 and 149afa9444.

Change-Id: I548f15055417453a7fd323a481ed410598830521


[ROCm/clr commit: 6c53a670c1]
 2023-01-09 22:56:52 -05:00
kjayapra-amd 5057429e7a SWDEV-361374 - Adding support for hipPointerSetAttributes 
Change-Id: I56710b808854acefca07b3b5898deebee38063e9


[ROCm/clr commit: 0c8c08cf51]
 2023-01-09 12:36:57 -05:00
Jaydeep Patel 149afa9444 SWDEV-375137 - Bypass defination of half and half2 alias for internal include of hip_fp16.h 
Change-Id: I5258a487d4c2d93e889a523fde81f1b3906d9318


[ROCm/clr commit: 695533d435]
 2023-01-06 21:34:51 -05:00
pghafari bb765cafaf SWDEV-369042 - updating to GetError to match cuda 
Change-Id: I0ec2330443b26cb1c8cedba942f31fb1267cd09d


[ROCm/clr commit: 335a24d1a0]
 2023-01-06 05:33:41 -05:00
Anusha GodavarthySurya 609598cd15 SWDEV-345571 - Added support for half/half2 data types for warp shuffle functions 
Change-Id: Ia0791760c1b0a35bbbf0b1f8435aa924af205169


[ROCm/clr commit: ad1fae7df4]
 2022-12-26 01:24:06 -05:00
Satyanvesh Dittakavi 42766fde8b SWDEV-372767 - Fix hipCUB and rocWMMA build failures 
Change-Id: If3672fd50075c67cfce4d94e73b1376c4aa8d2ae


[ROCm/clr commit: e90721435b]
 2022-12-16 03:08:18 -05:00
Satyanvesh Dittakavi a17cc5c6ba SWDEV-372032 - Support cooperative groups header with HIPRTC 
Change-Id: Ia64652fd52b210a4eeee9d38fdfdfa6fdc7163ff


[ROCm/clr commit: 91291e48db]
 2022-12-09 04:45:59 -05:00
Satyanvesh Dittakavi 63d37c8ae7 SWDEV-369955 - Support hipDrvGetErrorString and hipDrvGetErrorName on Nvidia headers 
Change-Id: I54cfa8faed2f45f310682625f94952aa3c2ee27f


[ROCm/clr commit: d413375d51]
 2022-12-02 11:52:07 -05:00
Satyanvesh Dittakavi f6d130cfd7 SWDEV-287842 - Add int8_t and int16_t support in hiprtc 
Change-Id: I03bb967068f1a29e85ce8d9410f78de4af9589c4


[ROCm/clr commit: 1deee433d0]
 2022-12-01 11:58:46 -05:00
Your Name dd18b3b01b SWDEV-368477 - hipOccupancyMaxPotentialBlockSizeVariableSMemWithFlags nvidia mapping 
SWDEV-369618 - hipOccupancyMaxPotentialBlockSizeVariableSMemWithFlags invalid flag scenario
Change-Id: I2edbab5d3eeacf80bc215f0a77a46d733f4b4ec9


[ROCm/clr commit: 3e47c052e0]
 2022-11-29 12:38:39 -05:00
Rakesh Roy ff8d9d3c77 SWDEV-348820 - Fix hipPointerAttribute_t incompatibility 
- Use hipPointerAttribute_t.type instead of hipPointerAttribute_t.memoryType

Change-Id: I3bf1c0758bdae987213ba7de62247dd420ef4cc9


[ROCm/clr commit: cbc3a0a652]
 2022-11-29 00:53:24 -05:00
Ioannis Assiouras 312b9e13ed SWDEV-369557 - Added enum mapping for external[Semaphore/Memory]HandleType 
Change-Id: If1b95b084f7fa312e6cdad4ccf433127671a35ce


[ROCm/clr commit: 33cb388101]
 2022-11-28 13:32:31 -05:00
Anusha GodavarthySurya 65d01b5347 SWDEV-365299 - update implementation __float2half_{rd,ru,rz} to call __ocml_cvt{rtn, rtp, rtz}_f16_f32 
Change-Id: I6cd711fbeb0e02a1caa03ac7f3dd9c8f8fdbac01


[ROCm/clr commit: f7ca4b8fb9]
 2022-11-25 16:27:02 +00:00
Anusha GodavarthySurya bb6872fa86 SWDEV-325711 - Added few graph API support for nvidia path 
Change-Id: I4eb6e77220e201c85fdaa3a004590c4c5d5ea6c6


[ROCm/clr commit: 766c40aab8]
 2022-11-25 09:08:32 -05:00
Ioannis Assiouras 26a1c72182 SWDEV-364950 - Remove Scalar_accessors from HIP_vector_type 
Change-Id: I13ecc213c98a1c7b5febcd43c0a21ee6db725f60


[ROCm/clr commit: c5b08c621f]
 2022-11-24 09:40:54 -05:00
Pierre van Houtryve 64e080a99d Fix atomicInc/dec scope to "agent" 
Addresses leftover comment of Icd1d9b9438cac4bef0f7c52d4cd341ac76500890

Change-Id: If9c395335497d634e4c702433d6e3681583bedef


[ROCm/clr commit: a312c0a956]
 2022-11-24 06:56:49 -05:00
Ioannis Assiouras bee5fcc4b6 SWDEV-364950 - Add trivial copy assignment for HIP_vector_type under HIP_CLANG_ONLY path 
Change-Id: I56a1003ba32c748631c7751b2e6a49e12e48afcb


[ROCm/clr commit: 432f5fbc97]
 2022-11-23 16:56:39 +00:00
Anusha GodavarthySurya 0645ad4576 SWDEV-366653 - Added new graph APIs - Fix windows build 
Change-Id: I580133bddcbab5529aecfb70bc9776e8c40de697


[ROCm/clr commit: 78eef7f173]
 2022-11-23 08:57:49 +00:00
Anusha Godavarthy Surya ed6595bc41 SWDEV-325711 - Added Graph APIs hipGraphDebugDotPrint, hipGraphKernelNodeCopyAttributes 
hipGraphNodeGetEnabled, hipGraphNodeSetEnabled and hipGraphUpload

Change-Id: Ib5a58fbc0a9b3f134eb56d42cd945f3d7f4922d8


[ROCm/clr commit: 93ce12c90d]
 2022-11-22 23:20:25 -05:00
Satyanvesh Dittakavi 243d4dacd1 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


[ROCm/clr commit: 5f4aa2e994]
 2022-11-18 06:58:31 -05:00
Julia Jiang d5a8c3fbf9 SWDEV-340754 - Update coordinates in coperatative helper 
Change-Id: Ibf4e833d10ea5c317900e83f020c9c23f55f3951


[ROCm/clr commit: 30c43056c1]
 2022-11-17 14:17:58 -05:00
Jaydeep Patel b7318ab24c SWDEV-366088 - Default case returns -1 as enum value. 
Change-Id: I8dd5cac254c99e4de9f6d492e71060e39b069507


[ROCm/clr commit: c800d2126d]
 2022-11-15 22:12:12 -05:00
Daria Materikina d388a7fad7 make header intel-compatible 
Change-Id: I8f8b68ba23e8f86dfeaf7c7b464f2b6ca6999971


[ROCm/clr commit: 834d9d3a3c]
 2022-11-14 17:59:01 -05:00
kjayapra-amd a72344ad67 SWDEV-337452 - Adding__ockl_steadyctr_u64 option for wall_clock64. 
Change-Id: I4ee6fd4d40d500363ef84975078185093dab5ddd


[ROCm/clr commit: 5ff27faa04]
 2022-11-07 08:47:30 -05:00
Anusha GodavarthySurya 3a482da878 SWDEV-366153 - Fix __ocml_isnan_f16 to pass _Float16 
Change-Id: I7628f21d000cec490f5fb2c91f1b99ca61fb46cf


[ROCm/clr commit: c974cbcb3d]
 2022-11-06 21:57:23 -05:00
pghafari d9eb49726f SWDEV-362199 - add vulkan interop apis in nvidia 
Change-Id: I6c5de6174a80be862b6d869927ed704dd1421b41


[ROCm/clr commit: ac2948651e]
 2022-11-04 16:49:21 -04:00
Anusha GodavarthySurya c9f30dcdd6 SWDEV-362611 - Added hmax and hmin 
Change-Id: I133a80e997e39357693df7ab969425c0d5585607


[ROCm/clr commit: 07b3070e25]
 2022-10-31 00:23:57 -04:00
Pierre van Houtryve 6d160e5a69 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


[ROCm/clr commit: dcb5d29f1e]
 2022-10-27 10:17:21 -04:00
Laurent Morichetti bec405981e 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


[ROCm/clr commit: 19107858d6]
 2022-10-21 14:55:33 -04:00
Satyanvesh Dittakavi c0c8aa5eb6 SWDEV-349226 - Add the hipDataTypes mapping to cudaDataTypes 
Change-Id: Iadeb2675adf314c02dcc5d722581678ec36f8632


[ROCm/clr commit: 1c68c74bb7]
 2022-10-14 06:44:30 -04:00
Jaydeep Patel fc3f04fa7d SWDEV-356551 - Add support for device attributes. 
Change-Id: Ic0f2b9cb510b027e0b8d1b3fb6d984e0d2600b15


[ROCm/clr commit: 7ef4eada54]
 2022-10-11 12:06:44 -04:00
Satyanvesh Dittakavi f664f42443 SWDEV-360001 - Add hipLaunchHostFunc in Nvidia path 
Change-Id: I5c733b416642174a089a86c420b03e8775e206d6


[ROCm/clr commit: 0d67bd3f09]
 2022-10-11 06:18:52 -04:00
Laurent Morichetti 08d7b38b0f 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


[ROCm/clr commit: 47a29c748a]
 2022-09-30 14:55:01 -07:00
kjayapra-amd 32838b0613 SWDEV-356651 - Merge hipJit options between hiprtc and hip runtime. 
Change-Id: I73b66eaf081ce63b6b7ce45f71880877953cf81c


[ROCm/clr commit: ab89a70f5d]
 2022-09-22 12:53:58 -04:00
Maneesh Gupta 12c48303c8 Revert "SWDEV-351980 - Update hip_prof_str.h" 
This reverts commit c878ce02f6.

Reason for revert: Incorrect patch

Change-Id: I9adba47d0ab18f621b599295bd9d0fd98887f5d3


[ROCm/clr commit: 835b7578dc]
 2022-09-21 13:04:38 -04:00