AI/rocm-systems
2
0
Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
3 545 коммитов 3 Ветки 0 Теги
d0252dfa79cdc1127dda008aa386702fb6fecf16
Граф коммитов

46 Коммитов

Автор SHA1 Сообщение Дата
Siu Chi Chan d0252dfa79 migrate program_state logic from header into shared library (phase I) (#1077) 
* Revert "Revert "Use COMgr to read Kernel Args Metadata (#1006)""

This reverts commit 62e96cb4cf.

* Revert "Use COMgr to read Kernel Args Metadata (#1006)"

This reverts commit 882006555b.

* Revert "improve program state commentary"

This reverts commit fb2beb0c88.

* Revert "load program state once per agent"

This reverts commit 21f5e142f5.

* start moving function_names() into the hip shared lib

* start moving code_object_blobs to a new "state" object

* Consolidate various program state related static objects into a
single program_state object

* minor clean up

* move more stuffs from functional_grid_launch into program_state

* debug make_kernarg

* moving lookup for kernargs size_align into program_state

* clean up old code for kernarg size and alignment

* update hip_module to use newer api in program_state

* Create public member functions for program_state

* move most program state functions into shared library

* Pass the data buffer size to load_executable
Otherwise, it can't figure what the data size is
just from the char* (since the data is not really a string)

* turning free functions in program state into members of program_state_impl

* change the free function globals() into a member of program_state_impl

* replace the static mutex used for populating globals

* moving associate_code_object_symbols_with_host_allocation into
program_state_impl

* move load_code_object_and_freeze_executable into program_state_impl

* moving executables and functions_names into program_state_impl

* moving kernels() into program_state_impl

* moving functions() into program_state_impl

* move get_kernargs into program_state_impl

* moving kernel_descriptor into program_state_impl

* moving kernargs_size_align calculation into program_state_impl

* Changing the handle to program_state_impl to a pointer

* moving program_state_impl into a separate inline source file

* fixing/cleaning up some header file includes

* moving member function for kernargs_size_align into program_state.cpp

* moving Kernel_descriptor into program_state.inl

* add a new class to manage agent globals

* moving all agent globals processing functions into agent_globals_impl

* load program state once per agent

re-merging PR991 against other program state changes

* fix per-agent program state member initialization

* cache executables based on elf name, isa, and agent.

This avoids program state reloading executables after a shared library is dlopened.

re-merging PR1057 against other program state changes

* protect executables cache by a global mutex

* return ref to executables cache

* adapt PR#981 Make hipModuleGetGlobal be in HIP runtime


[ROCm/hip commit: f5eb91d53d]
 2019-05-12 19:24:03 +05:30
Alex Voicu 0c16497abd dlopen() fixes (#929) 
* Initial attempt to switch over to internally linked state.

* Add missing CMake update.

* hipLaunchKernelGGLImpl must be inline as well. Ensure internal linkage.

* Ensure global retrieval uses internally linked state.

* Hide HC in the implementation. Minimise ADL woes.

* Strange software exists, and must be catered to.

* Use a less spammy mechanism for ensuring internal linkage / non-export.

* Remove leftover internal detail.


[ROCm/hip commit: ea0fcf3e61]
 2019-03-06 17:31:44 +05:30
Alex Voicu e2911291dd Ensure that static structures are populated 
[ROCm/hip commit: 0b57f50855]
 2019-01-09 17:21:53 +00:00
Alex Voicu 587745b841 Hook into the creaky lazy-reinit machinery. Try to minimise race-risk. 
[ROCm/hip commit: ec14daa7ce]
 2019-01-01 11:01:16 +05:30
Alex Voicu e127990e23 More blobs, more problems. 
[ROCm/hip commit: 340674ceb6]
 2019-01-01 11:01:07 +05:30
Alex Voicu 7bcb83a05f Start re-working 731 for 2.0. 
[ROCm/hip commit: 25c7e5d609]
 2019-01-01 11:00:57 +05:30
Siu Chi Chan bca8022aa0 Revert "Rely on code object metadat for kernarg arguments alignof and sizeof." 
This reverts commit 6d64f5e112.


[ROCm/hip commit: 1fbf639962]
 2018-11-29 11:38:37 -05:00
Siu Chi Chan a72a54996e Revert "Handle the very confusing dual encoding of the symbol name." 
This reverts commit 2a69dd1fb6.


[ROCm/hip commit: 71189c10c1]
 2018-11-29 11:38:36 -05:00
Siu Chi Chan 8bf51361e4 Revert "If we've already seen a __global__ function we do not need to re-parse" 
This reverts commit d3beba42d3.


[ROCm/hip commit: 09f87e41d9]
 2018-11-29 11:38:35 -05:00
Siu Chi Chan a715dea79c Revert "Missing handling nullary __global__ functions for mixed arity cases." 
This reverts commit 51c47fcc2e.


[ROCm/hip commit: 8eb9b38e76]
 2018-11-29 11:38:31 -05:00
Siu Chi Chan 954535e0b5 Revert "Fix issue in kernarg metadata parsing due to early finalization" 
This reverts commit 48c2d69d32.


[ROCm/hip commit: 909609773c]
 2018-11-29 11:35:00 -05:00
Siu Chi Chan 48c2d69d32 Fix issue in kernarg metadata parsing due to early finalization 
The logic to parse the kernel metadata is unaware that enabling
of early finalization could result in multiple code blobs in a
single .kernel section.  This teaches the HIP runtime to handle
that.

Change-Id: I1581b42f0da8b30233d7898014f7468728c1d489


[ROCm/hip commit: 19acf86cef]
 2018-11-21 12:09:46 -05:00
Alex Voicu 51c47fcc2e Missing handling nullary __global__ functions for mixed arity cases. 
[ROCm/hip commit: 4ebc229b9a]
 2018-11-12 01:51:59 +00:00
Alex Voicu 9cd4a9dbb1 Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_get_alignment_and_size_from_metadata 
[ROCm/hip commit: f28cde3f98]
 2018-11-01 23:17:27 +00:00
Alex Voicu d3beba42d3 If we've already seen a __global__ function we do not need to re-parse 
[ROCm/hip commit: f7ba987038]
 2018-10-30 23:34:27 +00:00
Alex Voicu 2a69dd1fb6 Handle the very confusing dual encoding of the symbol name. 
[ROCm/hip commit: bce3de8162]
 2018-10-30 01:55:09 +00:00
Alex Voicu 6d64f5e112 Rely on code object metadat for kernarg arguments alignof and sizeof. 
[ROCm/hip commit: fe1e963299]
 2018-10-28 17:01:00 +00:00
Siu Chi Chan 7ce37f3a08 Support more than one bundles in a single .kernel section 
When compiling with Early Finalization enabled in HCC,
the resulting .kernel section of the host object now may
contain more than one device code bundles.  This is to
teach the HIP runtime to correctly extract all the
bundles from the .kernel section.


[ROCm/hip commit: 30ce25e627]
 2018-10-18 17:00:27 -04:00
Wen-Heng (Jack) Chung 63a075fc96 Keep the map which tracks GPU kernel symbols to grow monotonically 
[ROCm/hip commit: dd56942335]
 2018-09-26 19:49:02 +00:00
Wen-Heng (Jack) Chung 70dd826abf Improve performance of re-initialization logic 
Keep track of shared libaries already discovered. Do not build HSA executables
for them.


[ROCm/hip commit: 35c542b70f]
 2018-09-26 19:48:56 +00:00
Wen-Heng (Jack) Chung 4e04cf3d2a HIP program state re-initialization logic 
This commit is to support kernels dynamically loaded thru means such as
dlopen() after HIP runtime initializes.


[ROCm/hip commit: dab1a0f9db]
 2018-09-26 19:48:47 +00:00
Maneesh Gupta b5940c7969 Merge pull request #621 from ROCm-Developer-Tools/disable_startup_loader 
Disable startup loader by default and guard with env var

[ROCm/hip commit: 4cf851f416]
 2018-08-10 10:18:25 +05:30
sunway513 cfe96a2db0 resolve a segfault bug when env var not set; remove startup_kernel_loader class 
[ROCm/hip commit: 17f38937e0]
 2018-08-09 16:40:26 +00:00
sunway513 09a4ad1dcf Add more check to ensure the startup loader only be enabled with the env var set to 1 
[ROCm/hip commit: 30dfa6f129]
 2018-08-04 01:52:27 +00:00
sunway513 653a04fe98 Add startup loader under HIP_STARTUP_LOADER env var, disable by default 
[ROCm/hip commit: 3a68ab4919]
 2018-08-04 01:48:06 +00:00
Wen-Heng (Jack) Chung 38b6402860 Revert "HIP program state re-initialization logic" 
This reverts commit e5ca9eb081.


[ROCm/hip commit: 2604f33930]
 2018-08-03 17:03:04 -05:00
Wen-Heng (Jack) Chung 48406c881c Revert "Improve performance of re-initialization logic" 
This reverts commit c6b975bf13.


[ROCm/hip commit: 3426f15171]
 2018-08-03 17:02:58 -05:00
Wen-Heng (Jack) Chung 22e4ddf301 Revert "Keep the map which tracks GPU kernel symbols to grow monotonically" 
This reverts commit d214b045c3.


[ROCm/hip commit: 136bcc2981]
 2018-08-03 17:02:50 -05:00
Wen-Heng (Jack) Chung d214b045c3 Keep the map which tracks GPU kernel symbols to grow monotonically 
[ROCm/hip commit: 32789a8b7d]
 2018-06-18 16:54:18 -05:00
Wen-Heng (Jack) Chung c6b975bf13 Improve performance of re-initialization logic 
Keep track of shared libaries already discovered. Do not build HSA executables
for them.


[ROCm/hip commit: ece4539c1d]
 2018-06-15 18:07:33 -05:00
Wen-Heng (Jack) Chung e5ca9eb081 HIP program state re-initialization logic 
This commit is to support kernels dynamically loaded thru means such as
dlopen() after HIP runtime initializes.


[ROCm/hip commit: 379b7a2241]
 2018-06-14 15:46:49 +00:00
Alex Voicu d5f965c44a Add support for the hipFuncGetAttributes interface. 
[ROCm/hip commit: 13274ce559]
 2018-05-11 03:35:10 +01:00
Maneesh Gupta 4f42ee762d Apply .clangformat to all repo source files 
Change-Id: I7e79c6058f0303f9a98911e3b7dd2e8596079344


[ROCm/hip commit: 1ba06f63c4]
 2018-03-12 11:29:03 +05:30
Alex Voicu 7f9c1eab10 Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_purge_genco 
[ROCm/hip commit: 49ef24c042]
 2018-02-22 12:08:52 +00:00
Siu Chi Chan afc71e3bad make HIP to load the GPU objects and to setup the function symbol map on startup 
[ROCm/hip commit: ebc92e5975]
 2018-02-18 14:26:44 -05:00
Alex Voicu 3afca75a71 Re-sync with upstream. 
[ROCm/hip commit: baf50a5311]
 2018-02-12 20:20:24 +00:00
Rahul Garg e2ade308cf Fixed host allocated globals address lookup for host usage 
Fixed texture driver APIs failure


[ROCm/hip commit: 24ab820a11]
 2018-01-30 18:06:31 +05:30
Alex Voicu 56fd7f129a This introduces LipoProteinLipase (lpl), a simple tool for creating fat binaries. It represents a direct replacement of the creaky hccgenco.sh script, which had various issues. The format it uses is that of a code object bundle, generated by the Clang Offload Bundler. The output is always suffixed with the ".adipose" extension. It is shared with HCC. The hipcc script and associated tests are modified to use lpl. Help can be obtained by invoking lpl --help. A more computer-sciency / corporate friendly name is likely to be beneficial, which is a reason for choosing easily searchable/replaceable names such as lpl or adipose. 
[ROCm/hip commit: b842394957]
 2017-12-08 04:22:57 +00:00
Alex Voicu abe3c22cf1 This is primarily intended as an additional cleanup of the module functionality, in the aftermath of adopting module based dispatch. The main effort was associated with refactoring the questionable ihipModuleGetSymbol. It was quaintly written and misleading, in that it had little to do with getting symbols, and was exactly retrieving a kernel object. Error handling is modified so as to reduce branching depth. Functions which serve as interfaces to the HSA RT are moved in a separate helper header. Code object readers are properly deleted. Some leftover dead functionality pertaining to associating namespace scope variables with their allocated memory is removed. Executable loading is changed to use a string which holds the ELF image of the code object being loaded, thus avoiding some corner cases where using a istream would fail. 
[ROCm/hip commit: 5127ce67e8]
 2017-12-03 23:09:06 +00:00
Alex Voicu 08a0d96448 Fix legacy mode detection of the address of an agent allocated variable. In this mode, there exist two executables per each code object, one created by HCC and one created by HIP. Since we dispatch through HCC in legacy mode, we should obtain the address for an agent allocated variable from the latter's executable. Also add two omitted validity checks, whose absence could lead to segfaults when the current process had no .kernel section and / or when an invalid or empty blob was extracted from the latter. 
[ROCm/hip commit: 7c0b9a005b]
 2017-11-30 03:29:04 +00:00
Alex Voicu aef26d3477 Re-sync with upstream and re-factor platform global management for texture references. 
[ROCm/hip commit: 02c2bfc7ef]
 2017-11-28 19:15:29 +00:00
Alex Voicu d71132de7c This corrects how addresses are formed for symbols which reside in shared objects. For this case, the .value component of an ELF symbol holds the offset from the base VA where the shared object was loaded. Thus, to correctly obtain the VA of the object refered by the symbol, we must add the offset to the VA where the shared object is loaded. We were already doing this correctly for symbols denoting functions, but we were incorrect for those denoting objects. 
[ROCm/hip commit: 5e16ee0d1f]
 2017-11-21 13:15:13 +00:00
Alex Voicu 45ff3c31c4 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. 
[ROCm/hip commit: 9d088d2283]
 2017-11-21 02:40:34 +00:00
Alex Voicu e8ca14848e Clean-up some remaining noise in program_state.cpp. 
[ROCm/hip commit: 1824fb7698]
 2017-11-20 22:41:46 +00:00
Alex Voicu dab971370e Correctly deal with functions from shared objects, wherein the program visible VA == so_base_va + st_value(function_symbol). Remove quaint usage of pfe for hipMemset (which is actually fill_n). 
[ROCm/hip commit: 2cacda91bb]
 2017-11-01 22:33:13 +00:00
Alex Voicu 70a41e7dac 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. 
[ROCm/hip commit: c2482d1255]
 2017-11-01 15:09:59 +00:00