Wykres commitów

1581 Commity

Autor SHA1 Wiadomość Data
Jatin Chaudhary f7f70a0880 SWDEV-400136 - change make_complex function name to make_hipComplex
Change-Id: Ia276610286df80ec35fe11f303eb9919eeda87dd
2023-06-15 09:02:38 -04:00
Ioannis Assiouras 4f5dfa77bd SWDEV-401852 - Do not define hipCreateChannelDesc for long types in LP64
Change-Id: I56881a229ea666269d575c6bdfde5081562ec009
2023-06-06 14:28:15 -04:00
Jaydeep Patel 9daf8e3177 SWDEV-404118 - Change to uint.
Change-Id: Ib9ced171a4330e868a584bfb86d7ee5418e784ed
2023-06-06 13:17:56 -04:00
Ajay 16c6b365c2 SWDEV-400515 - populate __HIP_NO_IMAGE_SUPPORT flag
MI300 does not support image APIs.
Apps to use __HIP_NO_IMAGE_SUPPORT instead of arch

Change-Id: I91178bfd27ea7b7188e7a958a876c0264f4469aa
2023-06-06 12:11:41 -04:00
Satyanvesh Dittakavi 287f607d2b SWDEV-395996 - Add double precision constants to math constants header
Fixes a typo and adds missing constants matching cuda

Change-Id: Iebf47d107af361cbd356c2a3b9cd6ef121d01363
2023-06-05 03:31:27 -04:00
Jaydeep Patel d576356505 SWDEV-401847 - Update atomicMin/Max for float and double.
Change-Id: Ib5be459b8a24f0739e299ed12c9f877f8baa02b1
2023-05-29 14:27:16 -04:00
Satyanvesh Dittakavi 586731c2cc SWDEV-401850 - Fix hipCreateChannelDescHalf APIs
- Address ChannelDescHalf1 and ChannelDescHalf2 APIs not returning
correct Channel Descriptors in amd headers
- Add missing hipCreateChannelDescHalf APIs in nvidia headers

Change-Id: I558847425c2459d3cde329ca2e926d882bb0a9dd
2023-05-25 04:36:24 -04:00
kjayapra-amd feb22250f3 SWDEV-393910 - Adding CAS expanders under gfx941 tag.
Change-Id: I2c4bcf56be419d1f037b8555ad254a2dc49d0c5b
2023-05-22 09:59:05 -04:00
sdashmiz 23e99dbb07 SWDEV-396533 - correct _shfl function to match cuda
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I311419fd25c055339f25fe0c7a132ec9ee225600
2023-05-17 14:19:46 -04:00
Jatin Chaudhary 15bafc9a93 SWDEV-395773 - Fix unordered compare functions in fp16 header
Change-Id: I9158420e37cd3151159182223c6645ed84c4fddd
2023-05-11 10:42:13 -04:00
Jatin Chaudhary 6c793ea206 SWDEV-367537 - Add __hip_bfloat16 and vector definitions to match __nv_bfloat16
Change-Id: I1c0f9f5f278c2c3b4e175d9f08831ba458ed856e
2023-05-11 04:45:13 -04:00
Satyanvesh Dittakavi a7041d15a7 SWDEV-399203 - Use clang pragma only with clang
Change-Id: I21d84ccde07e243b6bc06f1980c24b399e74d1c3
2023-05-10 04:19:51 -04:00
kjayapra-amd f14e8a2dba SWDEV-393910 - Port gfx94x changes to mainline.
Change-Id: Ibf727223bbe5230b132b47c39e0fc1d87cbd3b9c
2023-05-05 15:16:23 -04:00
Ajay 0aa70ee0e1 SWDEV-394488 - cudaStreamGetCaptureInfo_v2 is undefined in CUDA 12.0
hipStreamPerThrdCompilerOptn.cc test fails to build with cudaStreamGetCaptureInfo_v2
in CUDA 12.0.
fix was to change runtime API cudaStreamGetCaptureInfo_v2
to Driver cuStreamGetCaptureInfo_v2

Change-Id: I44a0110770d3246f5345092acae301c9a2f6d520
2023-05-05 10:10:07 -04:00
Jaydeep Patel a167abefe5 SWDEV-396277 - Offset and bit size correction, Considaration of SA ID for Navi.
Correct sm id formula for GFX10 and GFX11.

Change-Id: I2883c139b8e684e0334ccc81f703a09e3ddec588
2023-05-05 01:04:42 -04:00
Ioannis Assiouras 633e720da4 SWDEV-393199 - Added new include file for opengl interop mappings for nvidia
Change-Id: I2e955a9dd06539939188a5f2e1dde4f173af1202
2023-05-03 19:43:24 -04:00
taosang2 381e6520d0 SWDEV-396574 – Refactor texture channel type checking
Create __hip_is_tex_surf_channel_type to replace
__hip_is_tex_channel_type
__hip_is_itex_channel_type
__hip_is_surf_channel_type .

Change-Id: I1692b92d417bad742d562679f218ebf8ca532e31
2023-05-02 10:01:13 -04:00
Jaydeep Patel cbd91bdc19 SWDEV-395559 - Move unsigned short up.
Change-Id: I3373a7bc22e632dc10b94b93ff023444d456b2b7
2023-05-02 00:43:36 -04:00
taosang2 2f2d02649f SWDEV-396574 – Refactor device mapping functions
Refactor mapFrom(), mapTo(), mapElem(),
__hip_is_surf_channel_type() and
__hip_is_itex_channel_type()

Change-Id: I1692b92d407bad742d562678f218ebf8ca532e91
2023-05-01 13:57:10 -04:00
Satyanvesh Dittakavi a67f354cec SWDEV-395413 - Fix fp16 header errors with -Werror in hiprtc
Change-Id: I7875b91758e826b439c67ac9f211a20f9b6133f0
2023-04-26 13:05:20 -04:00
taosang2 650b6767c4 SWDEV-390626 - Fix wrong mapping functions
Remove wrong functions
__hipMapFromNativeFloat4()
__hipMapToNativeFloat4()

Replace them with mapFrom() and mapTo()

Change-Id: I1692b92d397bfd732d562778f918ebf8ca532e93
2023-04-25 13:19:00 -04:00
Ajay 9ca5e71127 SWDEV-390170 - guard deprecated runtime apis on CUDA 12.0
Change-Id: I4ab967c276dfa98f75d508b9484e8d1324b4e4a7
2023-04-05 16:36:53 +00:00
Julia Jiang 0442501849 SWDEV-389033 - Update header for cooperate group
Change-Id: Ica8f99c644a32835bf480b52a6a2af861f1526c0
2023-04-05 10:58:04 +00:00
Ioannis Assiouras 1d6c40b569 SWDEV-387173 - Added cuda mappings for hipGraphMemAttr* enums
Change-Id: Ie5485ec518c6d107901a429ac3614e22caa9196b
2023-03-09 08:08:06 -05:00
Anusha GodavarthySurya b689c56107 SWDEV-330658 - Added flag hipHostRegisterReadOnly
Change-Id: Idb59dc6187e99512546dfeafde44c08ae85f6057
2023-03-09 00:20:24 -05:00
Satyanvesh Dittakavi a8c2375fe1 SWDEV-384714 - Add hipRTC support for amd_hip_fp16
Change-Id: Ib6e2b46908d740909dfc15253965590f496a7068
2023-03-01 06:57:57 -05:00
Jatin Chaudhary a7049bf7a0 SWDEV-372153 - Add hipStreamGetDevice Implementation
Change-Id: Ifd1f13e311e8221ca6d94cf27f9131eb97678067
2023-03-01 04:35:49 -05:00
Sarbojit Sarkar d0920c5959 SWDEV-293749 - Fix for operator mixup
Change-Id: I61d1fea5a6ed2176dd92050c6d96cee1af3a39fb
2023-02-23 04:45:23 -05:00
Anusha GodavarthySurya 32a9249d3e SWDEV-345571 - Added support for half/half2 data types for warp shuffle functions
Change-Id: I276a55129d6527b73292d75eb18403acd2623c8a
2023-02-22 22:40:01 -05:00
Jaydeep Patel 0ad47eb3e5 SWDEV-319526 - SE ID size incresed.
Change-Id: Ia7df94d172102b321f12c8caa821e3a7e4447a21
2023-02-21 22:13:57 -05:00
Ioannis Assiouras aaf1c19609 SWDEV-384362 - Added explicit cast from __fp16 to _Float16 in rcph
Change-Id: Ibbb11e928a80126ed7a8c7cd8bddebc74c38986d
2023-02-21 17:32:59 -05:00
Ajay fc6a77a09f SWDEV-384100 - HIP support for CUDA 12.0
Apps are failing to build due to undefined deprecated texture APIs

Change-Id: I1fb64adc4bc0ba6ee6ecaa65d54b34da0327e6a3
2023-02-21 12:23:48 -05:00
Rakesh Roy 287d07ccd4 SWDEV-338733 - Implement hipArrayGet* APIs
- Add implementation for hipArrayGetInfo, hipArrayGetDescriptor &
  hipArray3DGetDescriptor APIs

Change-Id: I181a472066006bc3bd0d987408ea67e218310983
2023-02-16 23:04:29 -05:00
Matt Arsenault eacf63673b SWDEV-1 - Use proper __builtin_amdgcn_rcph builtin
Change-Id: Ic0b1b25a5ab7d132cb51425f2a17bc779c762668
2023-02-07 10:58:48 -05:00
Matt Arsenault bebbf3c4ec SWDEV-1 - Eliminate rcp_2f16 pseudo intrinsic
No such wrapper or intrinsic would ever exist because there is no such
underlying instruction.

Change-Id: I6c3f64cd2df2a58edf32037da8f5712868f296ea
2023-02-07 10:58:31 -05:00
Ioannis Assiouras 6704f3d0f0 SWDEV-380687 - Fixed typo in safe atomicAdd for gfx90a
Change-Id: I87bc6d9e0ef1f564d679c6280c71c4633d3aa619
2023-02-07 10:14:34 -05:00
Ioannis Assiouras 24d3d8216b SWDEV-380466 - Fixed typo in unsafe atomicAdd for doubles and gfx940
Change-Id: I3b9ea4773f94bf6a9b9dfb655062f42aeb3b5eba
2023-02-07 10:06:17 -05:00
Matthew Arsenault 8c7391398a SWDEV-1 - Reapply "SWDEV-1 - Directly call __builtin_amdgcn_fence"
This reverts commit 5b39c346ad.

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

Change-Id: I194559484a5a0d7f4443381fe77218ea73d2def9
2023-02-03 10:54:27 -05:00
Matt Arsenault 14477c24d0 SWDEV-1 - Use proper builtins for math intrinsics
Change-Id: If0e420332c718abe0e9f6316c467b6b29b80b183
2023-02-01 07:19:45 -05:00
Rakesh Roy 8b00f56577 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
2023-01-25 00:01:02 -05:00
Satyanvesh Dittakavi 0ccd41050b SWDEV-372396 - Address the errors in hiprtc headers with -Werror
Change-Id: Ied553216dfc2ff8b5c72de617cb47b6ca8f52063
2023-01-23 17:25:42 +00:00
Maneesh Gupta 5b39c346ad SWDEV-378321 - Revert "SWDEV-1 - Directly call __builtin_amdgcn_fence"
This reverts commit 3e54bad5b3.

Reason for revert: Root cause for regression SWDEV-378321

Change-Id: If3116c5ad1a23db1840e5fc019d2fe997b37d229
2023-01-19 13:01:27 -05:00
Satyanvesh Dittakavi 842b9d0b56 SWDEV-373231 - Support hip atomics header with HIPRTC
Change-Id: Ic500dfb66ed5ef0c4b672dfd0595409d0e8caaf5
2023-01-17 00:31:07 -05:00
Jaydeep Patel 8bd45ae5da SWDEV-369961 - Add mappings for enum hipGraphInstantiateFlags and types.
Change-Id: I03fa8221684b08a0c44e12aaf2eb7ce5281be629
2023-01-15 12:17:21 +00:00
Matt Arsenault 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
German Andryeyev 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
Satyanvesh Dittakavi c193503722 SWDEV-376386 - Support __hip_move_dpp with hipRTC
Change-Id: If9a6fe23d6df143a7f522823fca7183416048c6a
2023-01-13 00:05:31 -05:00
Matt Arsenault 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
Matt Arsenault 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
Ioannis Assiouras e97dcfbe48 SWDEV-374405 - Added OpenGL interoperability APIs for nvidia
Change-Id: I1d6ad5c610ab6ee805bd07dacea316b3242ed129
2023-01-12 05:22:14 -05:00