Maneesh Gupta
b3779207c3
module_api sample: no longer need EXTERN_C workaround
...
Change-Id: Ida087d832df8e1f3620b38f920ec2853aad641c8
[ROCm/clr commit: 257774f8f0 ]
2016-09-04 13:49:43 +05:30
Maneesh Gupta
c32eca602d
hipgenisa.sh: handle extern C on HCC path
...
Change-Id: I2daf09d2cb323ab34653988b668e8bd89f6db94a
[ROCm/clr commit: 16c61fd6e2 ]
2016-09-04 13:48:44 +05:30
Maneesh Gupta
7974137a91
module_api: workaround to use vcpy_kernel.cpp for NV path
...
Change-Id: Ib4868bf02c64070e846c19427c39289609909466
[ROCm/clr commit: fa85974c47 ]
2016-09-04 12:35:08 +05:30
pensun
dd92a59939
For module_api sample, use vcpy_kernel.cu to generate ptx file for NV path.
...
Change-Id: Id0033678834288c4eaa56b12e7d447119be99deb
[ROCm/clr commit: 793dc2bce0 ]
2016-09-03 21:06:58 -05:00
Ben Sander
b47c7dc8aa
remove printf
...
Change-Id: I36510a7ff0425f05a6d0b9c65cda4397c9cc2d95
[ROCm/clr commit: 3c90766c70 ]
2016-09-02 17:50:31 -05:00
Ben Sander
2d662d866f
add hipStreamQuery on nvcc, fix hipStreamWaitEvent for nvcc
...
[ROCm/clr commit: 9466ab4fca ]
2016-09-02 17:26:16 -05:00
Evgeny Mankov
a65cc67602
[HIPIFY] CUDA Driver API porting to HIP : populate Replacer's rules with enum members.
...
enum members for:
CUdevice_attribute/hipDeviceAttribute_t
CUfunc_cache/hipFuncCache
CUsharedconfig/hipSharedMemConfig
[ROCm/clr commit: 7062586103 ]
2016-09-02 22:23:13 +03:00
Aditya Atluri
d864a28183
corrected offline kernel compilation on hipcc path
...
1. hipgenisa.sh now adds int main(){} during kernel compilation. User does not have to put it there
2. Renamed vcpy_isa.cpp to vcpy_kernel.cpp
3. Removed vcpy_isa.cu as the kernel code should be common for both paths
4. Changed Makefile and runkernel.cpp to work with above changes
Change-Id: I9f8c84706b44bb500bc493a68e959762b55a0142
[ROCm/clr commit: 8f536d8580 ]
2016-09-02 13:17:17 -05:00
Ben Sander
f3da27cd5a
Fix double-lock of stream on hipModuleLaunchKernel
...
Change-Id: I4ca164971c25f4eb8fbcca11d6258367bb3d2ab4
[ROCm/clr commit: 0fdb5bf517 ]
2016-09-02 12:47:49 -05:00
pensun
93c97069dd
Add deprecated information for threadfence() and threadfence_system() function.
...
Change-Id: I71793e9f48523776a87c91f3ed1eef7b9a9da88b
[ROCm/clr commit: 8ae5498f99 ]
2016-09-02 09:52:07 -05:00
Ben Sander
264d7fde03
Doc and test updates.
...
Change-Id: I44cbd2c0de7cb692d0194d1bb8b8ae25c58d4e00
[ROCm/clr commit: d882f4fb74 ]
2016-09-02 09:46:59 -05:00
Ben Sander
589f28547e
hipStreamWaitEvent update.
...
Add passed to hipStreamWaitEvent test.
Fix pointerAttrib test to work with new and old HCC versions.
Minor code touchup.
Change-Id: I139ba6ce9f6bf2b4bee89aebdec5981b4346ffc0
[ROCm/clr commit: 8e883ab666 ]
2016-09-02 09:46:59 -05:00
Ben Sander
98019e5f79
Only use ihipLogStatus from top-level HIP functions.
...
Change-Id: I07e9c088d5c16a79ed52cb008a798889a656016c
[ROCm/clr commit: 9ee9284306 ]
2016-09-02 09:46:59 -05:00
Ben Sander
b570732b0e
Add test for hipStreamWaitEvent
...
Change-Id: I157b33a78a0fc125b4b85f611f32f3b492f1b4d9
[ROCm/clr commit: 8ec453a8c1 ]
2016-09-02 09:46:59 -05:00
Ben Sander
5e8149a783
Add hipEvent_t to vim syn
...
Change-Id: Iade4aa123e72ada39028543890957cec03dd7a2e
[ROCm/clr commit: fca1b367da ]
2016-09-02 09:46:59 -05:00
Ben Sander
f575ad7396
Fix av::copy in dialects to use capture-by-value
...
Change-Id: Ibce1488a1326f66b92b4d5b351230666b691ed31
[ROCm/clr commit: 43e9932196 ]
2016-09-02 09:46:59 -05:00
Ben Sander
fe85edad3f
Use create_blocking_marker for WaitEvent implementation
...
Change-Id: Ib3113f69a14e48b9fe0558d7b455148e478d8eed
[ROCm/clr commit: 9a99000a62 ]
2016-09-02 09:46:59 -05:00
Ben Sander
5d87b2f50d
improve debug for event
...
Change-Id: If6c0e25729d9964cbe5967833247a6d791d575a0
[ROCm/clr commit: 8a4900b679 ]
2016-09-02 09:46:59 -05:00
Ben Sander
938933ca2f
Refactor for stream->_av.
...
- move _av into stream critical section. ( HCC accelerator_view is not
thread-safe but HIP steram is. )
- Refactored many places in code that need to acquire critical section.
some were previously thread races, ie enqueueing marker.
-remove support for GRID_LAUNCH_VERSION < 20
-Enable USE_AV_COPY based on HCC work-week.
- Review hipModule docs, some calrity/editing.
Change-Id: I3ce7c25ece048c3504f55ecd4683e506bb1fc8b6
[ROCm/clr commit: 02f65a483c ]
2016-09-02 09:46:59 -05:00
Ben Sander
61a5a53512
enable hc_am example in hcc_ddialects example
...
Change-Id: Iec2f9eb05f95cb025c157fee8fd284aab844d1a2
[ROCm/clr commit: 27b3706a72 ]
2016-09-02 09:46:59 -05:00
Ben Sander
704b269d28
enable dynamic shared always
...
Change-Id: Idc246546f583a82489ef34d1fe22d0e118b1e0ed
[ROCm/clr commit: 6a8ae733cc ]
2016-09-02 09:46:59 -05:00
Aditya Atluri
1e6aa52868
added logger for return status
...
Change-Id: Ib93012a15b1cfa90714a6ebd5153cc40e28e6566
[ROCm/clr commit: 3fbe062008 ]
2016-09-02 09:44:00 -05:00
Aditya Atluri
40d824337e
fixed code according to convention
...
Change-Id: Ib90c84a30ea6da3531e8b7c3e281dd4b31915198
[ROCm/clr commit: af86d28187 ]
2016-09-02 09:31:37 -05:00
Ben Sander
d322ce516d
Documentation review and update
...
Change-Id: If40d096646014d70a198db3532758028abe6a93f
[ROCm/clr commit: bc489dd902 ]
2016-09-02 09:15:49 -05:00
Evgeny Mankov
6e2480b3af
[HIPIFY] CUDA Driver API porting to HIP : types are added.
...
CUdevice -> hipDevice_t // Yet under discussion
CUdevice_attribute -> hipDeviceAttribute_t
CUdevprop -> hipDeviceProp_t
CUfunction -> hipFunction_t
CUfunc_cache -> hipFuncCache
CUsharedconfig -> hipSharedMemConfig
CUcontext -> hipCtx_t
CUmodule -> hipModule_t
CUevent -> hipEvent_t
CUstream -> hipStream_t
[ROCm/clr commit: 000f0f8114 ]
2016-09-02 16:31:46 +03:00
Rahul Garg
04a3cdb846
Removed Doxygen return codes from source file
...
Change-Id: Iaf9f13df73a9c17c494c9ff67203b836ee90648d
[ROCm/clr commit: 093569e611 ]
2016-09-02 18:37:26 +05:30
Rahul Garg
bb03a2274d
Added hipDeviceTotalMem
...
Change-Id: I877fbc9e4767bbd70ecd0184f5123c9bc6cbd06f
[ROCm/clr commit: 302f6c1e3a ]
2016-09-02 15:12:50 +05:30
Maneesh Gupta
02b799c3a7
hip_base package: bundle cmake folder in package
...
Change-Id: I7f30469242a0357c68b9a27b7b18bbe1f1f15fc1
[ROCm/clr commit: 672e8772a2 ]
2016-09-02 15:09:05 +05:30
Maneesh Gupta
f39307c6a6
CMakeLists.txt: install cmake folder
...
Change-Id: I5367281c62529b4b832c77ea93e3994a5f9133f4
[ROCm/clr commit: 6396f07835 ]
2016-09-02 15:08:36 +05:30
Maneesh Gupta
58a2e6086b
FindHIP: First version of re-implementation
...
Change-Id: I84332a0f7d89271bf9370dbcd19d893119e738f9
[ROCm/clr commit: de24b6d228 ]
2016-09-02 15:07:33 +05:30
Rahul Garg
c60fc14dcd
Added hipDeviceComputeCapability, hipDeviceGetPCIBusId and hipDeviceGetName
...
Change-Id: Ibe2d975df796712633900ddc7b0734ec2b8ab4ec
[ROCm/clr commit: 392860bf20 ]
2016-09-02 14:45:53 +05:30
Rahul Garg
86cef27391
Added hipDeviceGet function
...
Change-Id: I7c25bc24680589682af1b199072807523fc37f50
[ROCm/clr commit: 2b2ffaf599 ]
2016-09-02 12:25:50 +05:30
Ben Sander
db79cd18c2
add hipStreamWaitEvent on nvcc
...
[ROCm/clr commit: af2dee92ab ]
2016-09-01 13:28:27 -05:00
pensun
65ce463726
Modify hipMalloc to take size of 0 and return NULL pointer for it.
...
Modify hipMemoryAllocate test for this change.
Change-Id: I884aee0cd5fe0c60aebb4cb37cdbb4833c5bd0c7
[ROCm/clr commit: 4ed2035dd2 ]
2016-09-01 13:08:30 -05:00
Evgeny Mankov
c676ecdbc9
[HIPIFY] CUDA Driver API porting to HIP : CUresult enum.
...
enum CUresult was merged with enum cudaError_t into single hipError_t.
Thus a majority of HIP error codes has a reflection to Driver's and RT's corresponding error code at the same time. For instance:
cuda2hipRename["CUDA_SUCCESS"] = {"hipSuccess", CONV_ERR, API_DRIVER};
cuda2hipRename["cudaSuccess"] = {"hipSuccess", CONV_ERR, API_RUNTIME};
There are a few CUDA return error codes which are RT or Driver specific. For instance:
cuda2hipRename["CUDA_ERROR_INVALID_CONTEXT"] = {"hipErrorInvalidContext", CONV_ERR, API_DRIVER};
cuda2hipRename["cudaErrorInvalidMemcpyDirection"] = {"hipErrorInvalidMemcpyDirection", CONV_ERR, API_RUNTIME};
Matchers were changed from "cuda.* | cublas.*" to "cu.*" as CUDA API functions/types starts with 'cu'.
[ROCm/clr commit: 22dca6794d ]
2016-09-01 18:54:03 +03:00
Aditya Atluri
8bbd449f9f
Fixed offline kernel compilation
...
1. Removed vcpy_isa.ptx as it should be generated during make
2. Made argument padding specific to hcc path
3. Renamed --gencodeobject to --genco
4. Changed Makefile to work on both nvcc and hcc path
Change-Id: Ifd053d541085d9ce4fd37bc21b07674786c7163e
[ROCm/clr commit: f22fda1291 ]
2016-09-01 10:39:14 -05:00
Maneesh Gupta
11f6cc4c4a
Fixed module_api/Makefile to set flags based on HIP_PLATFORM
...
Change-Id: I2fa9a556e0c4f25f4963ecef1d25eb922f9af1b9
[ROCm/clr commit: b7b78d3b86 ]
2016-09-01 15:11:12 +05:30
Maneesh Gupta
30c04a4f28
Updates to gencodeobject generation logic
...
- hipcc honors HIPCC_VERBOSE for gencodeobject too
- fixed gencodeobject generation logic for nvcc path
- hipgenisa.sh is no longer passed the --gencodeobject flag
Change-Id: Iab83c18a6decef445fda8468ba5de10cd7935046
[ROCm/clr commit: 1446ad3b92 ]
2016-09-01 15:06:36 +05:30
Rahul Garg
96fd13305a
Added doxygen documentation for hipCtxXXX APIs
...
Change-Id: Id9cf3491e9a8c78cb7bfeb9976c36d6fe565628f
[ROCm/clr commit: 25f3032328 ]
2016-09-01 12:22:37 +05:30
Maneesh Gupta
cc302c9729
hipgenisa.sh looks for hipcc relative to itself
...
Change-Id: Iac63fb5a87db1d735dbfa9697ce1f769a36b4d4a
[ROCm/clr commit: adcc0e32d2 ]
2016-09-01 12:13:11 +05:30
Maneesh Gupta
0b63bdc501
Fix typo in hipcc
...
Change-Id: I35817c08b503f438f412d4bfe84afc11b671dc77
[ROCm/clr commit: 9eeb6c31ae ]
2016-09-01 12:11:11 +05:30
Maneesh Gupta
291db23ec2
module_api/Makefile: Use gencodeobject instead of genisa
...
Change-Id: I7e3523810f5603ad727b1fda7ff2d0dc53ec72d7
[ROCm/clr commit: 7c24b08284 ]
2016-09-01 12:10:31 +05:30
Rahul Garg
ae64721cbb
Added context related difference note in hip_porting_driver_api.md
...
Change-Id: I5bd2884a16db51871baa7c19fa2bd63a0bd3adad
[ROCm/clr commit: 8de15914ae ]
2016-09-01 11:35:42 +05:30
Rahul Garg
f2e8d2c976
Added HIP_INIT_API to hipDeviceSynchronize()
...
Change-Id: I9bd6bf206905621b17e1999994b5ea09b7382180
[ROCm/clr commit: a949060b12 ]
2016-09-01 11:00:30 +05:30
Aditya Atluri
606a27d2d7
added device code offline compilation for nvcc
...
Change-Id: I1f77131778b4dcfcf720b4367dd9f18ffaf1cbb3
[ROCm/clr commit: 6cd10125e9 ]
2016-08-31 20:36:36 -05:00
Aditya Atluri
207f9f7434
corrected path to hipgenisa.sh and fixed its working
...
Change-Id: I140055d5e800cd4b23253171ba889db5e63b637b
[ROCm/clr commit: bcbf2973a3 ]
2016-08-31 20:16:48 -05:00
Aditya Atluri
3011696544
added sample for how-to-use pre-compiled kernels1. Corrected the exit output of kernel compilation by hipcc
...
2. Added sample which loads/run kernel binary during runtime?
Change-Id: I26ccaca1f844fee317592e26c9e654ce548b96a8
[ROCm/clr commit: 667ec7cbe2 ]
2016-08-31 13:56:07 -05:00
Aditya Atluri
786127a91f
added how to use hipcc for kernel compilation
...
Change-Id: If652316272f21b90516f5a5ed88c17f4f4e77fb0
[ROCm/clr commit: 6754587ed2 ]
2016-08-31 13:22:28 -05:00
Aditya Atluri
f97eec0d3b
added kernel only compilation feature for hipcc
...
1. Added hipgenisa.sh file to compile kernel code to hsa code object
2. Changed hipcc to call hipgenisa.sh, making hipcc compiling the kernels
Change-Id: I976459c1ebb24343e1b1fe38b4c3a203f1adffa9
[ROCm/clr commit: 2f8b2fca6b ]
2016-08-31 13:05:57 -05:00
Aditya Atluri
df6f400a8e
added doxygen comments for hipModuleLaunchKernel
...
Change-Id: I8a52d2e62f4b7eea8e05d779b9fda49f0ac45130
[ROCm/clr commit: 6bfbf17fb6 ]
2016-08-31 10:18:46 -05:00