c2482d1255
This switches HIP from its currently convoluted macro + pfe based dispatch mechanism to a more natural one partially based on the existing module API. The basic idea is that HCC will always correctly emit __global__ functions: as empty-bodied stubs, on host, and as kernels, on device. It then becomes trivial to obtain the mangled name on host, at dispatch, from the function's address, and then to use the mangled name to retrieve the kernel. This should address all problems stemming from serialisation, dubious mismatches due to the manufactured functor, macro-isms et al. It also immediately enables support for generalised globals as a consequence of that being available in the module API. Finally, it will make debug much easier, since the actual names of the __global__ functions will automatically be used in traces etc. One detail is that due to how dispatch works now (hipLaunchKernel and hipLaunchKernelGGL are themselves variadic function templates which deduce the function type of the callee), in certain cases it may be necesssary to insert explicit casts to ensure that the variadic argument list selects a viable overload - this can be observed in some unit tests. Eventually we may be able to remove this limitation, but for now it does not appear terribly onerous. The code is not extremely HIPpie, nor is it fully optimised, but rather is intended as a starting point for the HIP team to make its own.
2017-11-01 15:09:59 +00:00
2e8ec71e40
Merge pull request #222 from bensander/fix_device_prop
...
Fix device prop
2017-10-30 17:58:48 +01:00
f8bdb9f688
add a printf device function
2017-10-23 18:30:08 -04:00
acf89b43d4
Update device properties.
...
- clear properties to defined initial state.
- enable some property flags which are now supported.
2017-10-20 15:52:13 +00:00
68c2146dc3
Fix math ordering for --genco mode.
2017-10-02 21:52:16 +00:00
83d9e889a9
ensure the condition is evaluated before applying the negation operator
2017-09-20 01:38:28 -04:00
40ff42e555
Device side assert support
2017-09-07 20:45:27 +05:30
1a9e588932
Update docs.
...
- Review unsupported comments and refresh.
- Review experimental tag in API.
2017-08-28 15:44:38 -05:00
96e79f97e2
implement __threadfence_system
2017-08-02 08:50:18 +00:00
4f93b99f23
Merge pull request #100 from weixingzhang/texture
...
HIP Texture Support
2017-07-26 19:28:15 -05:00
7a446dcbc5
Renable frexp(f) device math function
...
Change-Id: I53c022b8ddf38cd17ddb42eba457b9020db66395
2017-07-20 14:41:30 +05:30
e671cec367
HIP Texture Support
2017-07-17 15:16:12 -04:00
30ee797dd4
Remove explicit address spaces declarations
2017-07-07 12:46:29 -05:00
0459f3db72
Add hipdbPrintMem - wrapper for hcc memory tracker.
2017-07-03 15:05:30 -05:00
34fcaa23bb
Fixed build error in hipDeviceGetByPCIBusId
...
Change-Id: I33be362910c4c5dca7435fb9c41f427b54f0e9a7
2017-07-01 07:56:30 +05:30
9c229f7530
Refactor hip_hcc.
...
Don't require setting __HIP_PLATFORM_HCC__ ; Instead check if compiler is HCC.
The functions here use HCC-specific functionality so only work with HCC.
ANd they work regardless of the __HIP_PLATFORM_HCC__ setting so don't
require that.
Also remove the "hcc_detail" extra hierarchy level for hip_hcc.h as
it is not necessary. Remove hcc_detail/hip_hcc.h.
2017-06-30 08:26:15 -05:00
1e1654c225
Remove some warning debug info and add weak attribute back to GGL __global__ define
...
Change-Id: I2021b107dda697b1262d44fa1506465e94a3916b
2017-06-27 14:15:16 -05:00
522e059a79
fixed default args for symbol memcpy apis
...
Change-Id: Ie0b63f8b9c5535eb3946bd6af3f30fe71a015244
2017-06-23 19:05:44 -05:00
7912e61502
Clean up old USE_* and RELEASE.md notes.
2017-06-23 18:05:30 -05:00
3c73229916
Abort device function in HIP/HCC, need new HCC
...
Change-Id: I4195ab75e9b7b48c8b8128d6925ddc0fa5e9e009
2017-06-18 12:31:31 +05:30
64bb8d154a
removed bad copy constructor
...
Change-Id: I661991d9d43941a61848b0b8e9879c0bfa811b40
2017-06-16 09:02:26 -05:00
fd36303c24
Additional GGL make_kernel_functor_* macros, contributed by Alex
...
Change-Id: I01aabb7d2b5418fcefb1bbf78eb5d1888dbc5c96
2017-06-14 11:10:52 -05:00
43df5ba660
Fix error related to undefined reference of __get_dynamicgroupbaseptr().
...
Change-Id: I14951e1725e35dd5f5e53805f81cdb58661f59f2
2017-06-08 19:24:32 -05:00
06816fb68b
Add clang version guard so the hip_fp16.h header won't be picked up by gcc
...
Change-Id: Ia21335a455bc93210901b44bc8c76a7f4a385b55
2017-06-08 19:24:32 -05:00
a9808961bd
Improve HIP kernel names, attributes and codegen, contributed by Alex Voicu
...
Change-Id: I2cafbdc5a98e26c7f4fad84739c915e7dc09993c
2017-06-05 11:39:00 -05:00
39c18e5e5f
Fix HIP_SYNC_NULL_STREAM=0 mode.
...
- Fix null-stream sync
- hipStreamDestroy of null stream returns hipErrorInvalidResourceHandle
- Update documentation.
- Add tests for null stream sync, hipEventElapsedTime.
- Rename internal enum hipEventStatusRecorded to hipEventStatusComplete
- refactor hipStreamWaitEvent to streamline control-flow
2017-06-05 08:50:22 -05:00
cb7c4c423c
added half data type and vector destructors
...
1. Added half data types to hip_fp16.h
2. Added destructor to vector data types
Change-Id: Id5ae76a663bb90a4bde2839ec79c58fbaee5072f
2017-06-02 11:19:33 -05:00
6e99e388ea
[HIP] [HIPIFY] CUDA Driver API 8.0.44 JIT options support.
2017-05-31 18:55:29 +03:00
ec7102f461
Add event controls for release fences.
...
Env var : HIP_EVENT_SYS_RELEASE
Event allocation flags : hipEventReleaseToDevice, hipEventReleaseToSystem
(remove hipEventDisableSystemRelease)
Update test for new functionality.
2017-05-27 16:02:34 -05:00
be8d0ba644
Updates so hip compiles on CUDA.
2017-05-27 15:55:07 -05:00
75f691ec2f
Add hipHostMallocCoherent, hipHostMallocNonCoherent
...
Provide per-allocation control over coherent/non-coherent mem.
These overrid the default HIP_COHERENT_HOST_ALLOC setting.
2017-05-24 00:48:10 -05:00
6d0f58b939
fix GGL helper header file, reorder for C++17
...
Change-Id: I3d9ddfe670bf7e3e8e7bd85e52cc61f48c19c213
2017-05-22 08:52:43 -05:00
270f643c9c
[HIP] [HIPIFY] [FIX] cuModuleLoadDataEx -> hipModuleLoadDataEx
...
https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/issues/81
1. Do not use JIT options on HCC path, call hipModuleLoadData instead.
2. NVCC path is unchanged, to call cuModuleLoadDataEx with all options.
3. Get rid of manual hipification, based on #ifdef #else for NVCC/HIP.
4. Update documentation accordingly.
2017-05-19 17:22:14 +03:00
bdc08fcf10
fixed vector type issues by reverting to old code, changed __half2 to map to vector types in llvm
...
Change-Id: I7317408c25e8c1a0c02a346042c9137e160c8bbd
2017-05-18 10:51:07 -05:00
9dceccf136
changed vector types to make sure it generate proper llvm vector types
...
Change-Id: I6c4616dae137dc4eac35e5827dc5b7f3251e0247
2017-05-16 21:35:40 -05:00
27877f8854
Add initial HIP_SYNC_NULL_STREAM=0 mode.
...
This eliminates host-synchronization for null stream. Instead, the
null-stream uses GPU-side events to wait for other streams.
Default is OFF pending additional testing.
Add enhanced null-stream test.
Also refine HIP_TRACE_API.
2017-05-16 19:04:25 -05:00
b306095ac2
Add hipEventDisableSystemRelease flag.
2017-05-12 16:06:03 -05:00
a38e36ec2f
added guard against hip_runtime.h so that non-hcc compilers can use it
...
Change-Id: I3d68deda9ce8a5956e21e15a69e549d6c21e3e39
2017-05-09 10:14:16 -05:00
ec27c695c4
Added support for hipMemcpy2DAsync in HIP/HCC
...
Change-Id: Ia4a8306f2dc1e33a81a7195ec29aef652fcccc4b
2017-05-03 22:29:12 +05:30
a5cb2d40ec
fixed hipFuncSetCacheConfig on rocm path
...
Change-Id: I937a3afbf115edc94a753a0beb2230ed60a6f021
2017-04-28 11:53:11 -05:00
59df70662a
Fix hipMalloc to return error code if allocation fails.
2017-04-24 22:30:54 -05:00
72bcfa438b
changed arguments for hipPointerGetAttributes
...
Change-Id: Ia7a7c4722c1f7d0a23f0e5cc3dd6dea6c01c1fd8
2017-04-24 15:24:16 -05:00
22f3b91cad
Add integer abs (initial implementation, can be optimized with OCML)
...
Change-Id: I1f568c8c0e2333af1fda4c313dc48ea0c5b6ab00
2017-04-11 01:16:28 +00:00
2848d7a222
add math.h to cover sqrtf function
...
Change-Id: Ia37752710cea4ca77e0a4e61f8e69a0355d9488d
2017-04-10 08:53:12 -05:00
a9fd0d4e0d
Update the define of __global__ for GGL
...
Change-Id: I563bb2a132403bcbe9e9f279b55406cf0255af7d
2017-04-07 16:39:33 -05:00
a5ca430e5c
Add more operator overloading for float2 type, contributed by Aditya
...
Change-Id: If1ab7fb24d64bb5304142aed0951c9bd5ad47d20
2017-04-07 14:17:41 -05:00
6d4af1ab1f
update GGL to log launched kernel information
...
Change-Id: Ied0aa6055673c687071b4a579aecd17f0f3f09ce
2017-04-07 14:06:31 -05:00
6656d33f75
Finish adding start/stop event support to hipHccModuleLaunchKernel.
...
Change interface to use hipEvent_t rather than hipEvent_t*
Change-Id: I259062dc087a13d51dc27f84e1e8861f332a104d
2017-04-06 21:02:50 -05:00
5995965558
Improve documentation for hipModuleLaunch functions.
...
Change-Id: I0e22621e499775740c3301347b7416d5f98c2414
2017-04-06 21:02:50 -05:00
0a07382d92
fixed header structure for complex data types
...
Change-Id: I16bf19005d933f42e8c8603c5d0b2df8ea3ad04f
2017-04-06 16:43:26 -05:00
Alex Voicu
Ben Sander
Siu Chi Chan
Rahul Garg
Maneesh Gupta
Weixing Zhang
Wen-Heng (Jack) Chung
Sun, Peng
Aditya Atluri
Evgeny Mankov