AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4,101 Commits 3 Branches 0 Tags
66c91b42e6d4f65c3ede3867da49c92c345d48b3
Commit Graph

1008 Commits

Author SHA1 Message Date
Laurent Morichetti 66c91b42e6 Fix a code object memory corruption 
The lifetime of the buffer given to
hsa_code_object_reader_create_from_memory must exceed that of the
code object reader. We need to create a copy of the code object
binary memory (file) that is kept allocated until the code object
reader is destroyed.
 2019-10-29 08:23:57 -07:00
Rahul Garg 14b870d1ce Add hipMemcpy2DfromArray (#1510) 
Adds hipMemcpy2DFromArray and hipMemcpy2DFromArrayAsync equivalent to cudaMemcpy2DFromArray and cudaMemcpy2DFromArrayAsync.
 2019-10-25 15:43:33 +05:30
satyanveshd 6c5fbf9b4a Fix occupany APIs (#1560) 
Addresses SWDEV-205006
 2019-10-24 17:44:47 +05:30
searlmc1 15a699688e Improve performance of v2 arg handling (#1539) 
* Improve performance of v2 arg handling

* Missing change to `std::string`
 2019-10-24 17:44:05 +05:30
Aryan Salmanpour 93c688a0c9 [hip] add support for implicit kernel argument for multi-grid sync (#1456) 
* [hip] add support for implicit kernel argument for multi-grid sync

* modified code for calculating the prev_sum

* change the impCoopArg type to size_t

* add memory clean up

* launch init_gws and main kernels into two separate loops
 2019-10-24 17:43:30 +05:30
Rahul Garg a21fe1443b Merge pull request #1544 from vsytch/master 
QoL changes to the hipMemset family
 2019-10-16 18:54:20 -07:00
Nick Curtis d16963c9d5 Guard against division by zero for no VGPR usage (e.g., in an empty kernel) (#1528) 
* guard against division by zero for no VGPR usage (e.g., in an empty kernel)

* fix bracket format

* clean up parenthesis
 2019-10-16 10:49:56 +05:30
Vladislav Sytchenko 0200aa3a21 Update the declarations of hipMemsetD8, hipMemsetD8Async, hipMemsetD16, hipMemsetD16Async. These functions are type aware and take in as their third argument the number of elements in the buffer, not the buffer size. Change the name of this argument from sizeBytes to count to align with the above description. 2019-10-15 14:18:42 -04:00
Evgeny ed29c10394 tracing layer unifying with hcc: removing API_ID_ANY 2019-10-08 19:09:43 -05:00
Rahul Garg e2260d82a6 Fix PCI Domain ID query (#1424) 
* Fix PCI Domain ID query

* Update BDF comment
 2019-10-07 14:11:52 +05:30
mhbliao 5fbb09fb39 [hip] Add the missing header <sstream>. (#1498) 2019-10-04 13:39:29 +05:30
Rahul Garg d5a61736d8 Add texref get APIs support (#1471) 
Added support for -
    hipTexRefGetArray
    hipTexRefGetAddressMode
    hipTexRefGetAddress
 2019-10-04 13:38:45 +05:30
ansurya 96890792b0 Added new Memory API's (#1399) 
Added new memory API's hipMemAllocPitch, hipMemAllocHost, hipMemsetD16, hipMemsetD16Async, hipMemsetD8Async
Modified to support all scenarios hipMemcpyParam2DAsync, hipMemcpyParam2D.
 2019-10-04 13:36:31 +05:30
Siu Chi Chan d8e09c4b70 fix kernel descriptor bug with code object v3 
Change-Id: I9306b2baf36d338e36c5ab1226f74373a61a5ae0
 2019-10-03 10:56:35 -04:00
satyanveshd 1ae4cbed4d Reimplement hipMemGetInfo (#1447) 
Addresses SWDEV-136570. hipMemGetInfo changed to compute free memory based on information from kfd instead of relying on hc::am_tracker.
 2019-10-01 12:40:36 +05:30
Jeff Daily 2a53299f07 hipModuleUnload should remove global variables from memtracker (#1464) 2019-09-30 10:41:20 +05:30
Sarbojit2019 db4c0c0811 [HIP] Add tccDriver info in hipDeviceProp 
Fixes #1433.
 2019-09-26 13:53:33 +05:30
satyanveshd 842e304a9c Fix checks in hipMemcpy[D/H]to[D/H]() (#1397) 
* SWDEV-202043 hipMemcpyDtoD() issue
 2019-09-16 08:32:38 +00:00
ansurya e2a934f377 Added new device attributes (#1377) 
* Added new device attributes

* updated comment

* updated with new device attributes supported
 2019-09-16 08:31:30 +00:00
Aryan Salmanpour 6c7da60e28 [hip] add initial support for hipLaunchCooperativeKernelMultiDevice API (#1368) 
* [hip] add initial support for hipLaunchCooperativeKernelMultiDevice API

* fix formatting
 2019-09-16 08:31:17 +00:00
Rahul Garg d9179cbe70 Fix typo and colon in comment 2019-09-13 03:09:01 +05:30
Rahul Garg 2e9b8e9d0d [HACK] Temporary fix for hipFree for hipManagedMalloc 2019-09-13 02:10:21 +05:30
Jeff Daily 3d7c146296 fix bug where HIP_DB=1 seg faults at startup (#1388) 2019-09-05 10:04:19 +00:00
Rahul Garg d433f6fb58 Revert "Using HSA API for hipMemsetAsync (#1346)" (#1381) 
This reverts commit 9bbd09b04f.
 2019-09-03 05:13:46 +00:00
Sarbojit2019 b5ff9e71ed Updated hipErrorString and CUDAErrorTohipError (#1365) 2019-08-29 01:02:59 +00:00
Sarbojit2019 1ae43cbeba [HIP] Reclaiming hipLaunchKernel API (#1353) 
* [HIP] Reclaiming hipLaunchKernel API

* Reclaiming hipLaunchKernel : Incorporated review comments

* Incorporated review comments

* Removed hipLaunchKernel Macro from nvcc path
 2019-08-29 01:02:41 +00:00
Aryan Salmanpour 32ce882d6e [hip] add initial implementation for hipLaunchCooperativeKernel API (#1339) 
* [hip] add initial implementation for hipLaunchCooperativeKernel API

* [hip] use total number of work groups to initialize the GWS resource

* [hip] use only one argument for init_gws kernel

* [hip] use the device associated with the stream for checking the device properties
 2019-08-23 09:19:35 +00:00
Rahul Garg a786728939 Fix memcpy with IPC slowness (#1321) 
* Fix memcpy with IPC slowness

* Make early erroneous returns

* Real Clean up

* Real Clean up++
 2019-08-23 09:19:18 +00:00
Jatin Chaudhary 9bbd09b04f Using HSA API for hipMemsetAsync (#1346) 2019-08-21 10:00:10 +00:00
Rahul Garg a0cc627c42 Fix build issues seen with hip-clang path (#1331) 2019-08-16 02:13:45 +00:00
Rahul Garg fbc9f7e20a Add hipMemcpy3DAsync (#1320) 
* Add hipMemcpy3DAsync

* Fix CI build error

* Move back stream resolution to internal function

* Remove stream redefinition and check
 2019-08-16 02:13:16 +00:00
Rahul Garg 7f9de881cb Fix undefined identifier issue for hipExtModuleLaunchKernel 2019-08-14 16:46:32 -04:00
Rahul Garg 569f35a258 Add hipMemcpyParam2DAsync (#1296) 
* Add hipMemcpyParam2DAsync

* Add NVCC path changes

* Clean up

* Fix build issue

* Fix else use in both sync and async apis
 2019-08-09 11:50:37 +00:00
Siu Chi Chan 3cf2d7d385 Compile HIP runtime with hidden visibility by default (#1303) 
* add default visibility to most APIs in program_state

* remove unwanted C++ headers

* Add symbol visibility pragmas and compiler flags

* Add visibility attribute to APIs in channel_descriptor and hip_hcc

* remove unused headers

* simplify build flags with hcc

* add pragma visibility hidden to functional_grid_launch

* [CMake] add gfx908 back
 2019-08-08 08:33:04 +00:00
Rahul Garg 8b6317d041 Add support for hipFuncGetAttribute (#1279) 
* Add support for hipFunGetAttribute

* Support NVCC path

* Test using sample module_api_global

* Try fixing CI build failure due to hip_prof_gen scan

* Fix for CI build issue

* Resolve conflict

* Rebase and resolve conflicts with master

* Fix build error

* Fix NVCC path build error
 2019-08-08 08:27:41 +00:00
Alex Voicu e24df75cc1 Fix hip_throw. (#1285) 
* Fix hip_throw.

* Fix typo

* No, really fix typo
 2019-08-05 09:52:22 +00:00
Jeff Daily f337ae1edb consolidate thread local storage (#915) 
* all thread local access now through single struct

* clean up old commented-out code, more use of GET_TLS()

* fewer calls to GET_TLS by passing tls as a funtion argument

* revert unnecessary change to printf

* fix failing tests due to TLS change

* fix merge conflicts in ihipOccupancyMaxActiveBlocksPerMultiprocessor
 2019-08-05 09:51:02 +00:00
Maneesh Gupta a489877153 Merge pull request #1278 from gargrahul/fix_hipfuncGetAttribute_logstatus 
Fix missing logstatus in hipFuncGetAttributes
 2019-08-02 10:00:38 +00:00
wkwchau ed04e96e2d Added CooperativeLaunch and CooperativeMultiDeviceLaunch flag and property for hipDeviceGetAttribute() and hipGetDeviceProperties() (#1247) 2019-08-02 10:00:25 +00:00
Rahul Garg 20e9aba94e Fix missing logstatus in hipFuncGetAttributes 2019-08-02 11:51:34 +05:30
wkwchau abe6776677 Added query of hipDeviceAttributeHdpMemFlushCntl and hipDeviceAttribu… (#1238) 
* Added query of hipDeviceAttributeHdpMemFlushCntl and hipDeviceAttributeHdpRegFlushCntl

* Added NVCC blocker for the hip*FlushCntl test cases
 2019-08-01 16:03:35 +00:00
Maneesh Gupta 3de3f57468 Merge pull request #1243 from jeffdaily/master-stream-lock-fix 
remove stream locks where it is safe to do so
 2019-08-01 08:59:13 +00:00
wkwchau 7b9801fe9a Added support of hipOccupancyMaxActiveBlocksPerMultiprocessor & hipOc… (#1240) 
* Added support of hipOccupancyMaxActiveBlocksPerMultiprocessor & hipOccupancyMaxActiveBlocksPerMultiprocessorWithFlags APIs

* Taking into account of SGPR usage to determine the max active blocks in hipOccupancyMaxActiveBlocksPerMultiprocessor()
 2019-08-01 08:58:48 +00:00
Maneesh Gupta e0397d3d1f Merge pull request #1269 from gargrahul/fix_ptr_attr_unkonwn_to_invalid 
hipPointerGetAttributes- Change hipErrorUnknown to hipErrorInvalidValue
 2019-07-31 15:43:06 +00:00
Rahul Garg 8df47255c5 Add hip init in hipExtLaunchMultiKernelMultiDevice (#1263) 
* Add hip init in hipExtLaunchMultiKernelMultiDevice

* Add more logstatus for multiple return paths

* Fix missing i in function name
 2019-07-31 15:42:29 +00:00
Rahul Garg c610159b85 Add HIP init in hipFuncGetAttributes (#1262) 
* Add HIP init in hipFuncGetAttributes

* [dtest]Remove explicit hip init call in hipFuncGetAttributes dtest
 2019-07-31 15:42:08 +00:00
Rahul Garg 1c49943ac3 Change hipErrorUnknown to hipErrorInvalidValue 2019-07-31 00:28:30 +05:30
Jeff Daily 734c4b92c3 remove stream locks where it is safe to do so 2019-07-22 17:38:51 +00:00
cdevadas fc0aca2a7d Increased the number of implicit-kernarg bytes to 56 (#1217) 2019-07-19 04:45:34 +00:00
wkwchau 6ec476e50a Fixed bug of determine max block size in hipOccupancyMaxPotentialBlockSize (#1235) 2019-07-18 03:19:29 +00:00