Commit Graph

591 Commits

Author SHA1 Message Date
Alex Voicu dfa532db98 Remove leftover comment. 2017-11-22 19:37:03 +00:00
Alex Voicu f8c1c1b38e Refactor the __device__ versions of memset and memcpy to be less awkward i.e. not return nullptr as opposed to the destination pointer (it can only be assumed it was done for maximum confusion) and actually unroll as they claim to. Change all of the {to, from}Symbol functions to use hipModuleGetGlobal, as opposed to hc::accelerator::get_symbol_address which is no longer valid with module based dispatch. 2017-11-21 02:40:34 +00:00
Alex Voicu 27bc487635 Correct ill-formed merge in earlier commit and adjust for differences with the new CUDA natural indexing mechanism. 2017-11-20 16:33:52 +00:00
Alex Voicu 30d90dab38 Re-sync with upstream. 2017-11-20 15:34:50 +00:00
Alex Voicu 0cc921f103 This implements the trivial change needed to move back from the hip{Something}_{x, y, z} macros to the natural CUDA syntax of Something.{x, y, z}. This is contained in lines 384-404 in hip_runtime.h. All of the other changes have to do with changing unit tests to use this syntax. The macros are retained for backwards compatibility. 2017-11-19 01:54:12 +00:00
Alex Voicu 0ad1308efd Clean up trailing whitespace so as to reduce noise in #246. 2017-11-08 00:08:55 +00:00
Alex Voicu 28f87f7d2e 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
Ben Sander 7e8b39fc96 Merge pull request #222 from bensander/fix_device_prop
Fix device prop
2017-10-30 17:58:48 +01:00
Siu Chi Chan cf98d0e37d Merge remote-tracking branch 'origin/master' into HEAD 2017-10-27 01:18:28 -04:00
Siu Chi Chan 36c2795dd4 add a printf device function 2017-10-23 18:30:08 -04:00
Ben Sander ed85b15c3e 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
Chris Kitching 939fa02ade Add [[nodiscard]] attribute to hipError_t in C++17 mode
This will yield a compiler warning any time you discard an error
return value from an API call.
2017-10-19 13:34:02 +01:00
Maneesh Gupta 132316fecf Merge pull request #194 from bensander/fix_genco_math_path
Fix math ordering for --genco mode.
2017-10-03 16:17:34 +05:30
Ben Sander 2e9b78c274 Fix math ordering for --genco mode. 2017-10-02 21:52:16 +00:00
Rahul Garg 71a5a0cb42 Fixed review comment 2017-10-02 17:29:08 +05:30
Rahul Garg 79a943e654 Fixed review comments 2017-10-02 10:57:25 +05:30
Rahul Garg d92cfa44d2 Fixed build issue 2017-10-02 10:40:01 +05:30
Rahul Garg e6725e2b7a Fix texture support on HIP/NVCC path 2017-10-02 10:40:01 +05:30
Siu Chi Chan bf6a3f4294 ensure the condition is evaluated before applying the negation operator 2017-09-20 01:38:28 -04:00
Maneesh Gupta 01163d327b Merge pull request #155 from wsttiger/master
Modify hip headers such that they are more compatible with strict C compiler
2017-09-15 10:49:55 +05:30
Maneesh Gupta 846b0555b9 Fix typo in nvcc_detail/hip_runtime_api.h 2017-09-14 16:19:57 +05:30
Maneesh Gupta 096caca840 Merge pull request #175 from gargrahul/assert_support
Device side assert support
2017-09-14 16:08:00 +05:30
sriharikarnam f6fda276ce Add hipDevice[Get/Set]SharedMemConfig API on nvcc details 2017-09-14 16:03:19 +05:30
Rahul Garg 9dcf2ad751 Device side assert support 2017-09-07 20:45:27 +05:30
Ben Sander a6d1778fff Update docs.
- Review unsupported comments and refresh.
- Review experimental tag in API.
2017-08-28 15:44:38 -05:00
wsttiger 8302138d57 Modify header such that it's compatible with strict C compiler 2017-08-15 13:23:09 -05:00
wsttiger 7933b3292d Add missing CUDA tags 2017-08-15 13:22:20 -05:00
Siu Chi Chan b6e22b5c93 implement __threadfence_system 2017-08-02 08:50:18 +00:00
Ben Sander 702651fc85 Merge pull request #100 from weixingzhang/texture
HIP Texture Support
2017-07-26 19:28:15 -05:00
Maneesh Gupta 1bd1c6bea8 Renable frexp(f) device math function
Change-Id: I53c022b8ddf38cd17ddb42eba457b9020db66395
2017-07-20 14:41:30 +05:30
Weixing Zhang ccbd3b13fc HIP Texture Support 2017-07-17 15:16:12 -04:00
Wen-Heng (Jack) Chung 0237aeab06 Remove explicit address spaces declarations 2017-07-07 12:46:29 -05:00
Ben Sander 18660be8ce Add hipdbPrintMem - wrapper for hcc memory tracker. 2017-07-03 15:05:30 -05:00
Rahul Garg cbc98cc098 Fixed build error in hipDeviceGetByPCIBusId
Change-Id: I33be362910c4c5dca7435fb9c41f427b54f0e9a7
2017-07-01 07:56:30 +05:30
Ben Sander 5e5b017b0d 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
Rahul Garg 467a2ba014 Fixed hipDeviceGetByPCIBusId
Change-Id: Ia36bb9425671ef7659541c9aeedae4098456a31b
2017-06-30 10:11:41 +05:30
Rahul Garg 38d48b5cf0 Fixed hipDeviceGetPCIBusId for HIP/NVCC
Change-Id: I662efa148257a710f09002850b41d57bef00dff3
2017-06-29 00:13:02 +05:30
Rahul Garg a7c727f352 Fixed hipDeviceGetPCIBusId for HIP/HCC
Change-Id: I3688fa2476e1baada2d3c5fc3735cec3f15a1e21
2017-06-28 23:48:27 +05:30
Sun, Peng 3d2a729580 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
Aditya Atluri 3043766899 fixed default args for symbol memcpy apis
Change-Id: Ie0b63f8b9c5535eb3946bd6af3f30fe71a015244
2017-06-23 19:05:44 -05:00
Ben Sander 42882ddf9c Clean up old USE_* and RELEASE.md notes. 2017-06-23 18:05:30 -05:00
Rahul Garg 0fd6b59e22 Added device side abort function in HIP/NVCC
Change-Id: I6ae35a72a8b9c34852619f02da1a046c8d3b2ed3
2017-06-20 09:38:56 +05:30
Rahul Garg d9935cd089 Abort device function in HIP/HCC, need new HCC
Change-Id: I4195ab75e9b7b48c8b8128d6925ddc0fa5e9e009
2017-06-18 12:31:31 +05:30
Aditya Atluri 34e14bb02d removed bad copy constructor
Change-Id: I661991d9d43941a61848b0b8e9879c0bfa811b40
2017-06-16 09:02:26 -05:00
Sun, Peng 9bce2af76f Additional GGL make_kernel_functor_* macros, contributed by Alex
Change-Id: I01aabb7d2b5418fcefb1bbf78eb5d1888dbc5c96
2017-06-14 11:10:52 -05:00
Sun, Peng 682dda4418 Fix error related to undefined reference of __get_dynamicgroupbaseptr().
Change-Id: I14951e1725e35dd5f5e53805f81cdb58661f59f2
2017-06-08 19:24:32 -05:00
Sun, Peng 5450021f93 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
Sun, Peng 3b6a863eef Improve HIP kernel names, attributes and codegen, contributed by Alex Voicu
Change-Id: I2cafbdc5a98e26c7f4fad84739c915e7dc09993c
2017-06-05 11:39:00 -05:00
Ben Sander 823281dcba 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
Aditya Atluri fdcc223842 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