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
e127990e23
More blobs, more problems.
...
[ROCm/hip commit: 340674ceb6
2019-01-01 11:01:07 +05:30
7bcb83a05f
Start re-working 731 for 2.0.
...
[ROCm/hip commit: 25c7e5d609
2019-01-01 11:00:57 +05:30
bca8022aa0
Revert "Rely on code object metadat for kernarg arguments alignof and sizeof."
...
This reverts commit 6d64f5e1121fbf639962
2018-11-29 11:38:37 -05:00
a72a54996e
Revert "Handle the very confusing dual encoding of the symbol name."
...
This reverts commit 2a69dd1fb671189c10c1
2018-11-29 11:38:36 -05:00
8bf51361e4
Revert "If we've already seen a __global__ function we do not need to re-parse"
...
This reverts commit d3beba42d309f87e41d9
2018-11-29 11:38:35 -05:00
a715dea79c
Revert "Missing handling nullary __global__ functions for mixed arity cases."
...
This reverts commit 51c47fcc2e8eb9b38e76
2018-11-29 11:38:31 -05:00
954535e0b5
Revert "Fix issue in kernarg metadata parsing due to early finalization"
...
This reverts commit 48c2d69d32909609773c
2018-11-29 11:35:00 -05:00
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
51c47fcc2e
Missing handling nullary __global__ functions for mixed arity cases.
...
[ROCm/hip commit: 4ebc229b9a
2018-11-12 01:51:59 +00:00
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
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
2a69dd1fb6
Handle the very confusing dual encoding of the symbol name.
...
[ROCm/hip commit: bce3de8162
2018-10-30 01:55:09 +00:00
6d64f5e112
Rely on code object metadat for kernarg arguments alignof and sizeof.
...
[ROCm/hip commit: fe1e963299
2018-10-28 17:01:00 +00:00
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
63a075fc96
Keep the map which tracks GPU kernel symbols to grow monotonically
...
[ROCm/hip commit: dd56942335
2018-09-26 19:49:02 +00:00
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
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
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
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
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
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
38b6402860
Revert "HIP program state re-initialization logic"
...
This reverts commit e5ca9eb0812604f33930
2018-08-03 17:03:04 -05:00
48406c881c
Revert "Improve performance of re-initialization logic"
...
This reverts commit c6b975bf133426f15171
2018-08-03 17:02:58 -05:00
22e4ddf301
Revert "Keep the map which tracks GPU kernel symbols to grow monotonically"
...
This reverts commit d214b045c3136bcc2981
2018-08-03 17:02:50 -05:00
d214b045c3
Keep the map which tracks GPU kernel symbols to grow monotonically
...
[ROCm/hip commit: 32789a8b7d
2018-06-18 16:54:18 -05:00
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
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
d5f965c44a
Add support for the hipFuncGetAttributes interface.
...
[ROCm/hip commit: 13274ce559
2018-05-11 03:35:10 +01:00
4f42ee762d
Apply .clangformat to all repo source files
...
Change-Id: I7e79c6058f0303f9a98911e3b7dd2e8596079344
[ROCm/hip commit: 1ba06f63c4
2018-03-12 11:29:03 +05:30
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
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
3afca75a71
Re-sync with upstream.
...
[ROCm/hip commit: baf50a5311
2018-02-12 20:20:24 +00:00
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
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
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
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
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
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
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
e8ca14848e
Clean-up some remaining noise in program_state.cpp.
...
[ROCm/hip commit: 1824fb7698
2017-11-20 22:41:46 +00:00
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
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
Alex Voicu
Siu Chi Chan
Wen-Heng (Jack) Chung
Maneesh Gupta
sunway513
Rahul Garg